FIELD OF THE INVENTION
The present invention generally relates to the field of education. In particular, the present invention is directed to systems and methods for artificial intelligence-mediated multiparty electronic communication.
BACKGROUND
Currently, attempts at automated evaluation of students are largely limited to situations where data is easily available and clear, such as detection of which bubble a student filled in on a multiple choice test. However, little work has been done on automatically assessing student understanding based on data from a relatively free form discussion. Such data is not as clear as that of the multiple choice example, and a conversation may not reliably produce sufficient data on every subject of interest or every student of interest. This makes it difficult to reliably evaluate students based on discussions without needing to go back and re-evaluate students, which may cause hassle and take valuable class time.
In addition, current automated systems for communicating with users do not allow for, or struggle with, situations in which multiple users share a communication channel. This is particularly true where user communication is done by speech. Problems that may arise in these situations include differentiating between the data provided by each user and determining how to intelligently respond to differing situations presented by multiple users. Evaluation of users in such a format poses additional problems. It may be desirable to evaluate users based on the content of their speech, but this data is mixed with other audio data such as their accent, volume, and tone.
SUMMARY OF THE DISCLOSURE
In an aspect, an apparatus for synchronous learning may include at least a processor; and a memory communicatively connected to the at least processor, the memory containing instructions configuring the at least processor to receive a discussion topic; generate a first prompt as a function of the discussion topic; present to a user the first prompt; receive a discussion datum, wherein the discussion datum comprises a user response to the first prompt; and generate a user understanding score as a function of the discussion datum and a grading threshold.
In another aspect, a method for synchronous learning may include using at least a processor, receiving a discussion topic; using at least a processor, generating a first prompt as a function of the discussion topic; using at least a processor, presenting to a user the first prompt; using at least a processor, receiving a discussion datum, wherein the discussion datum comprises a user response to the first prompt; and using at least a processor, generating a user understanding score as a function of the discussion datum and a grading threshold.
These and other aspects and features of non-limiting embodiments of the present invention will become apparent to those skilled in the art upon review of the following description of specific non-limiting embodiments of the invention in conjunction with the accompanying drawings.
BRIEF DESCRIPTION OF THE DRAWINGS
For the purpose of illustrating the invention, the drawings show aspects of one or more embodiments of the invention. However, it should be understood that the present invention is not limited to the precise arrangements and instrumentalities shown in the drawings, wherein:
FIG. 1 is a diagram depicting an exemplary apparatus for synchronous learning;
FIG. 2 is a diagram depicting an exemplary immutable sequence listing;
FIG. 3 is a diagram depicting an exemplary machine learning model;
FIG. 4 is a diagram depicting an exemplary neural network;
FIG. 5 is a diagram depicting an exemplary neural network node;
FIG. 6 is a diagram depicting an exemplary chatbot system;
FIG. 7 is a diagram depicting an exemplary method of synchronous learning;
FIG. 8 is a depiction of an exemplary interface;
FIG. 9 is a depiction of an exemplary interface; and
FIG. 10 is a block diagram of a computing system that can be used to implement any one or more of the methodologies disclosed herein and any one or more portions thereof.
The drawings are not necessarily to scale and may be illustrated by phantom lines, diagrammatic representations and fragmentary views. In certain instances, details that are not necessary for an understanding of the embodiments or that render other details difficult to perceive may have been omitted.
DETAILED DESCRIPTION
At a high level, aspects of the present disclosure are directed to systems and methods for synchronous learning. An apparatus may receive a discussion topic, such as a discussion topic for students to discuss in a classroom environment. Discussion topic may be provided by an instructor. Apparatus may generate a prompt as a function of discussion topic. Prompt may be communicated to one or more users, such as students. Prompt may be communicated to students while they are in breakout rooms in an online class environment. Prompt may direct students to discuss a particular topic, such as a topic students have been studying. Apparatus may collect discussion datum from student discussion of prompt. Discussion datum may include an audio recording of student conversation. Apparatus may interpret such audio data using machine learning techniques, such as through use of a speech recognition model and/or a language model. Apparatus may score student understanding of relevant topics, such as discussion topic, based on the output of such machine learning models. Apparatus may detect situations in which data is likely to be insufficient to score student understanding, such as when a particular student is silent; in such a situation, apparatus may generate and communicate to students a follow up prompt, directing the student in question to speak. Apparatus may communicate student understanding scores to instructor.
Referring now to FIG. 1, an exemplary embodiment of an apparatus 100 for synchronous learning is illustrated. Apparatus 100 may include a computing device. Apparatus 100 may include a processor. Processor may include, without limitation, any processor described in this disclosure. Processor may be included in a computing device. Computing device may include any computing device as described in this disclosure, including without limitation a microcontroller, microprocessor, digital signal processor (DSP) and/or system on a chip (SoC) as described in this disclosure. Computing device may include, be included in, and/or communicate with a mobile device such as a mobile telephone or smartphone. Computing device may include a single computing device operating independently, or may include two or more computing device operating in concert, in parallel, sequentially or the like; two or more computing devices may be included together in a single computing device or in two or more computing devices. Computing device may interface or communicate with one or more additional devices as described below in further detail via a network interface device. Network interface device may be utilized for connecting computing device to one or more of a variety of networks, and one or more devices. Examples of a network interface device include, but are not limited to, a network interface card (e.g., a mobile network interface card, a LAN card), a modem, and any combination thereof. Examples of a network include, but are not limited to, a wide area network (e.g., the Internet, an enterprise network), a local area network (e.g., a network associated with an office, a building, a campus or other relatively small geographic space), a telephone network, a data network associated with a telephone/voice provider (e.g., a mobile communications provider data and/or voice network), a direct connection between two computing devices, and any combinations thereof. A network may employ a wired and/or a wireless mode of communication. In general, any network topology may be used. Information (e.g., data, software etc.) may be communicated to and/or from a computer and/or a computing device. Computing device may include but is not limited to, for example, a computing device or cluster of computing devices in a first location and a second computing device or cluster of computing devices in a second location. Computing device may include one or more computing devices dedicated to data storage, security, distribution of traffic for load balancing, and the like. Computing device may distribute one or more computing tasks as described below across a plurality of computing devices of computing device, which may operate in parallel, in series, redundantly, or in any other manner used for distribution of tasks or memory between computing devices. Computing device may be implemented, as a non-limiting example, using a “shared nothing” architecture.
With continued reference to FIG. 1, computing device may be designed and/or configured to perform any method, method step, or sequence of method steps in any embodiment described in this disclosure, in any order and with any degree of repetition. For instance, computing device may be configured to perform a single step or sequence repeatedly until a desired or commanded outcome is achieved; repetition of a step or a sequence of steps may be performed iteratively and/or recursively using outputs of previous repetitions as inputs to subsequent repetitions, aggregating inputs and/or outputs of repetitions to produce an aggregate result, reduction or decrement of one or more variables such as global variables, and/or division of a larger processing task into a set of iteratively addressed smaller processing tasks. Computing device may perform any step or sequence of steps as described in this disclosure in parallel, such as simultaneously and/or substantially simultaneously performing a step two or more times using two or more parallel threads, processor cores, or the like; division of tasks between parallel threads and/or processes may be performed according to any protocol suitable for division of tasks between iterations. Persons skilled in the art, upon reviewing the entirety of this disclosure, will be aware of various ways in which steps, sequences of steps, processing tasks, and/or data may be subdivided, shared, or otherwise dealt with using iteration, recursion, and/or parallel processing.
Still referring to FIG. 1, in some embodiments, apparatus 100 may include at least a processor 104 and a memory 108 communicatively connected to the at least a processor 104, the memory 108 containing instructions 112 configuring the at least a processor 104 to perform one or more processes described herein. Computing devices including memory 108 and at least a processor 104 are described in further detail herein.
Still referring to FIG. 1, as used in this disclosure, “communicatively connected” means connected by way of a connection, attachment or linkage between two or more relata which allows for reception and/or transmittance of information therebetween. For example, and without limitation, this connection may be wired or wireless, direct or indirect, and between two or more components, circuits, devices, systems, and the like, which allows for reception and/or transmittance of data and/or signal(s) therebetween. Data and/or signals therebetween may include, without limitation, electrical, electromagnetic, magnetic, video, audio, radio and microwave data and/or signals, combinations thereof, and the like, among others. A communicative connection may be achieved, for example and without limitation, through wired or wireless electronic, digital or analog, communication, either directly or by way of one or more intervening devices or components. Further, communicative connection may include electrically coupling or connecting at least an output of one device, component, or circuit to at least an input of another device, component, or circuit. For example, and without limitation, via a bus or other facility for intercommunication between elements of a computing device. Communicative connecting may also include indirect connections via, for example and without limitation, wireless connection, radio communication, low power wide area network, optical communication, magnetic, capacitive, or optical coupling, and the like. In some instances, the terminology “communicatively coupled” may be used in place of communicatively connected in this disclosure.
Still referring to FIG. 1, in some embodiments, apparatus 100 may receive discussion topic 116. As used herein, a “discussion topic” is a subject for users to discuss and be evaluated on. For example, discussion topic 116 may include a particular chapter from a book, a particular mathematical concept, a particular historical figure, or the like. Apparatus 100 may receive discussion topic 116 from discussion topic database 120. For example, discussion topic database may include an academic syllabus, which apparatus 100 may retrieve and analyze in order to determine an appropriate discussion topic 116 for a particular class session.
Still referring to FIG. 1, a database such as discussion topic database 120 may be implemented, without limitation, as a relational database, a key-value retrieval database such as a NOSQL database, or any other format or structure for use as a database that a person skilled in the art would recognize as suitable upon review of the entirety of this disclosure. Database may alternatively or additionally be implemented using a distributed data storage protocol and/or data structure, such as a distributed hash table or the like. Database may include a plurality of data entries and/or records as described above. Data entries in a database may be flagged with or linked to one or more additional elements of information, which may be reflected in data entry cells and/or in linked tables such as tables related by one or more indices in a relational database. Persons skilled in the art, upon reviewing the entirety of this disclosure, will be aware of various ways in which data entries in a database may store, retrieve, organize, and/or reflect data and/or records as used herein, as well as categories and/or populations of data consistently with this disclosure.
Still referring to FIG. 1, in some embodiments, a file such as a syllabus may be analyzed in order to determine discussion topic 116 using machine learning techniques such as a language model as described further herein. In some embodiments, apparatus 100 may receive discussion topic 116 from instructor device 124. Instructor device 124 may include, for example, a smartphone, smartwatch, tablet, or computer. Instructor device 124 may include instructor interface 128. Instructor interface 128 may include an input interface and/or an output interface. Input interface of instructor interface 128 may include, for example, a mouse, keyboard, touchscreen, button, scroll wheel, controller, microphone, camera, and the like. Output interface of instructor interface 128 may include, for example, a screen, speaker, and the like. An interface may include a graphical user interface (GUI). In some embodiments. an interface may be configured to prompt a user for an input. In a non-limiting example, an interface may request that a user input discussion topic 116 and/or a syllabus. In some embodiments, apparatus 100 may obtain discussion topic 116 through a physical or digital form such as a form on a website. For example, an instructor may scan a physical syllabus, and the physical syllabus may be analyzed using optical character recognition techniques in order to convert the scanned syllabus into a machine readable format such as text; a language model may then be used to interpret the syllabus and determine a discussion topic. In another example, an instructor may input discussion topic 116 into a form on a website. In another example, an instructor may verbally express that tomorrow's class will be about a certain historical figure, and apparatus 100 may detect this speech using a microphone, transcribe the speech using an automatic speech recognition system, then use a language model to interpret the speech and determine discussion datum 116. In another example, an instructor may write on a whiteboard that tomorrow's class will be about a certain chemical process, and apparatus 100 may use a camera to detect the writing, use an optical character recognition system to transcribe the writing, and use a language model to interpret the writing and determine discussion datum 116.
Still referring to FIG. 1, in some embodiments, instructor may approve, reject, modify and/or replace discussion datum 116. For example, apparatus 100 may suggest to instructor discussion datum 116 based on what instructor wrote on a whiteboard, and instructor may approve the suggested discussion datum 116. In another example, apparatus 100 may suggest to instructor discussion datum 116 and instructor may reject it and input a substitute.
Still referring to FIG. 1, in some embodiments, variables described herein may be converted into different forms. Data formats may be converted in a variety of ways, such as without limitation, using a speech to text function or using optical character recognition. In some embodiments, a variable such as discussion topic 116 may be converted into a different form such that it is in a form appropriate for input into a function. As a non-limiting example, a machine learning model that accepts discussion topic 116 as an input may only accept inputs in a particular format, and discussion topic 116 may be converted into that format such that it may be effectively input into the machine learning model. For example, discussion topic 116 may be on a physical syllabus scanned by an instructor. Apparatus 100 may use optical character recognition techniques to read the syllabus, and may use another machine learning model, such as a language model, to interpret the syllabus and identify discussion topic 116.
Still referring to FIG. 1, data may also be altered such that it retains the same format but is more likely to produce successful or relevant results. As a non-limiting example, a machine learning model may be used to replace obscure words in a text file with more common words that have similar or identical meanings. In this example, this may be done by training a machine learning model on samples of text using unsupervised learning such that the machine learning model learns associations between words (such as based on how frequently they are used together). In this example, words may be represented as vectors with dimensions indicating their relationship to other words, and whether words are synonyms may be determined based on how similar their vectors are (as in, if vectors representing 2 words point in the same direction, those words may be synonyms). In this example, a first word determined to be similar to or a synonym of a second word, may be replaced by the second word.
Still referring to FIG. 1, in some embodiments, discussion datum 116 may be determined using OCR. For example, discussion datum 116 may be determined from a syllabus in image format, and OCR may be used to identify text from the image. In another example, discussion datum 116 may be determined from writing on a whiteboard or chalkboard, or slides an instructor presents to a class. In these examples, OCR may also be used to identify text from the image, and further techniques such as language models may be used to interpret the text and determine discussion datum 116.
Still referring to FIG. 1, in some embodiments, optical character recognition or optical character reader (OCR) includes automatic conversion of images of written (e.g., typed, handwritten or printed text) into machine-encoded text. In some cases, recognition of at least a keyword from image data may include one or more processes, including without limitation optical character recognition (OCR), optical word recognition, intelligent character recognition, intelligent word recognition, and the like. In some cases, OCR may recognize written text, one glyph or character at a time. In some cases, optical word recognition may recognize written text, one word at a time, for example, for languages that use a space as a word divider. In some cases, intelligent character recognition (ICR) may recognize written text one glyph or character at a time, for instance by employing machine-learning processes. In some cases, intelligent word recognition (IWR) may recognize written text, one word at a time, for instance by employing machine-learning processes.
Still referring to FIG. 1, in some cases OCR may be an “offline” process, which analyses a static document or image frame. In some cases, handwriting movement analysis can be used as input to handwriting recognition. For example, instead of merely using shapes of glyphs and words, this technique may capture motions, such as the order in which segments are drawn, the direction, and the pattern of putting the pen down and lifting it. This additional information may make handwriting recognition more accurate. In some cases, this technology may be referred to as “online” character recognition, dynamic character recognition, real-time character recognition, and intelligent character recognition.
Still referring to FIG. 1, in some cases, OCR processes may employ pre-processing of image data. Pre-processing process may include without limitation de-skew, de-speckle, binarization, line removal, layout analysis or “zoning,” line and word detection, script recognition, character isolation or “segmentation,” and normalization. In some cases, a de-skew process may include applying a transform (e.g., homography or affine transform) to image data to align text. In some cases, a de-speckle process may include removing positive and negative spots and/or smoothing edges. In some cases, a binarization process may include converting an image from color or greyscale to black-and-white (i.e., a binary image). Binarization may be performed as a simple way of separating text (or any other desired image component) from a background of image data. In some cases, binarization may be required for example if an employed OCR algorithm only works on binary images. In some cases, a line removal process may include removal of non-glyph or non-character imagery (e.g., boxes and lines). In some cases, a layout analysis or “zoning” process may identify columns, paragraphs, captions, and the like as distinct blocks. In some cases, a line and word detection process may establish a baseline for word and character shapes and separate words, if necessary. In some cases, a script recognition process may, for example in multilingual documents, identify script allowing an appropriate OCR algorithm to be selected. In some cases, a character isolation or “segmentation” process may separate signal characters, for example character-based OCR algorithms. In some cases, a normalization process may normalize aspect ratio and/or scale of image data.
Still referring to FIG. 1, in some embodiments an OCR process may include an OCR algorithm. Exemplary OCR algorithms include matrix matching process and/or feature extraction processes. Matrix matching may involve comparing an image to a stored glyph on a pixel-by-pixel basis. In some case, matrix matching may also be known as “pattern matching,” “pattern recognition,” and/or “image correlation.” Matrix matching may rely on an input glyph being correctly isolated from the rest of image data. Matrix matching may also rely on a stored glyph being in a similar font and at a same scale as input glyph. Matrix matching may work best with typewritten text.
Still referring to FIG. 1, in some embodiments, an OCR process may include a feature extraction process. In some cases, feature extraction may decompose a glyph into at least a feature. Exemplary non-limiting features may include corners, edges, lines, closed loops, line direction, line intersections, and the like. In some cases, feature extraction may reduce dimensionality of representation and may make the recognition process computationally more efficient. In some cases, extracted feature may be compared with an abstract vector-like representation of a character, which might reduce to one or more glyph prototypes. General techniques of feature detection in computer vision are applicable to this type of OCR. In some embodiments, machine-learning processes like nearest neighbor classifiers (e.g., k-nearest neighbors algorithm) may be used to compare image features with stored glyph features and choose a nearest match. OCR may employ any machine-learning process described in this disclosure, for example machine-learning processes described with reference to FIGS. 3-5. Exemplary non-limiting OCR software includes Cuneiform and Tesseract. Cuneiform is a multi-language, open-source optical character recognition system originally developed by Cognitive Technologies of Moscow, Russia. Tesseract is free OCR software originally developed by Hewlett-Packard of Palo Alto, California, United States.
Still referring to FIG. 1, in some cases, OCR may employ a two-pass approach to character recognition. A first pass may try to recognize a character. Each character that is satisfactory is passed to an adaptive classifier as training data. The adaptive classifier then gets a chance to recognize characters more accurately as it further analyzes image data. Since the adaptive classifier may have learned something useful a little too late to recognize characters on the first pass, a second pass is run over the image data. Second pass may include adaptive recognition and use characters recognized with high confidence on the first pass to recognize better remaining characters on the second pass. In some cases, two-pass approach may be advantageous for unusual fonts or low-quality image data. Another exemplary OCR software tool include OCRopus. OCRopus development is led by German Research Centre for Artificial Intelligence in Kaiserslautern, Germany. In some cases, OCR software may employ neural networks.
Still referring to FIG. 1, in some cases, OCR may include post-processing. For example, OCR accuracy may be increased, in some cases, if output is constrained by a lexicon. A lexicon may include a list or set of words that are allowed to occur in a document. In some cases, a lexicon May include, for instance, all the words in the English language, or a more technical lexicon for a specific field. In some cases, an output stream may be a plain text stream or file of characters. In some cases, an OCR process may preserve an original layout of image data. In some cases, near-neighbor analysis can make use of co-occurrence frequencies to correct errors, by noting that certain words are often seen together. For example, “Washington, D.C.” is generally far more common in English than “Washington DOC.” In some cases, an OCR process may make us of a priori knowledge of grammar for a language being recognized. For example, grammar rules may be used to help determine if a word is likely to be a verb or a noun. Distance conceptualization may be employed for recognition and classification. For example, a Levenshtein distance algorithm may be used in OCR post-processing to further optimize results.
Still referring to FIG. 1, in some embodiments, discussion datum 116 may be determined using an automatic speech recognition system. For example, an instructor may verbally express to a class that the next subject will be a particular topic in physics and related equations. Apparatus 100 may detect such speech using a microphone, transcribe the speech using an automatic speech recognition system, and interpret the speech and determine discussion datum 116 using a language model.
Still referring to FIG. 1, in some embodiments, speech data may be processed using automatic speech recognition. In some embodiments, automatic speech recognition may require training (i.e., enrollment). In some cases, training an automatic speech recognition model may require an individual speaker to read text or isolated vocabulary. In some cases, training data may include an audio component having an audible verbal content, the contents of which are known a priori by a computing device. Computing device may then train an automatic speech recognition model according to training data which includes audible verbal content correlated to known content. In this way, computing device may analyze a person's specific voice and train an automatic speech recognition model to the person's speech, resulting in increased accuracy. Alternatively, or additionally, in some cases, computing device may include an automatic speech recognition model that is speaker independent. As used in this disclosure, a “speaker independent” automatic speech recognition process does not require training for each individual speaker. Conversely, as used in this disclosure, automatic speech recognition processes that employ individual speaker specific training are “speaker dependent.”
Still referring to FIG. 1, in some embodiments, an automatic speech recognition process may perform voice recognition or speaker identification. As used in this disclosure, “voice recognition” refers to identifying a speaker, from audio content, rather than what the speaker is saying. In some cases, computing device may first recognize a speaker of verbal audio content and then automatically recognize speech of the speaker, for example by way of a speaker dependent automatic speech recognition model or process. In some embodiments, an automatic speech recognition process can be used to authenticate or verify an identity of a speaker. In some cases, a speaker may or may not include subject. For example, subject may speak within speech data, but others may speak as well.
Still referring to FIG. 1, in some embodiments, an automatic speech recognition process may include one or all of acoustic modeling, language modeling, and statistically based speech recognition algorithms. In some cases, an automatic speech recognition process may employ hidden Markov models (HMMs). As discussed in greater detail below, language modeling such as that employed in natural language processing applications like document classification or statistical machine translation, may also be employed by an automatic speech recognition process.
Still referring to FIG. 1, an exemplary algorithm employed in automatic speech recognition may include or even be based upon hidden Markov models. Hidden Markov models (HMMs) may include statistical models that output a sequence of symbols or quantities. HMMs can be used in speech recognition because a speech signal can be viewed as a piecewise stationary signal or a short-time stationary signal. For example, over a short time scale (e.g., 10 milliseconds), speech can be approximated as a stationary process. Speech (i.e., audible verbal content) can be understood as a Markov model for many stochastic purposes.
Still referring to FIG. 1, in some embodiments HMMs can be trained automatically and may be relatively simple and computationally feasible to use. In an exemplary automatic speech recognition process, a hidden Markov model may output a sequence of n-dimensional real-valued vectors (with n being a small integer, such as 10), at a rate of about one vector every 10 milliseconds. Vectors may consist of cepstral coefficients. A cepstral coefficient requires using a spectral domain. Cepstral coefficients may be obtained by taking a Fourier transform of a short time window of speech yielding a spectrum, decorrelating the spectrum using a cosine transform, and taking first (i.e., most significant) coefficients. In some cases, an HMM may have in each state a statistical distribution that is a mixture of diagonal covariance Gaussians, yielding a likelihood for each observed vector. In some cases, each word, or phoneme, may have a different output distribution; an HMM for a sequence of words or phonemes may be made by concatenating an HMMs for separate words and phonemes.
Still referring to FIG. 1, in some embodiments, an automatic speech recognition process may use various combinations of a number of techniques in order to improve results. In some cases, a large-vocabulary automatic speech recognition process may include context dependency for phonemes. For example, in some cases, phonemes with different left and right context may have different realizations as HMM states. In some cases, an automatic speech recognition process may use cepstral normalization to normalize for different speakers and recording conditions. In some cases, an automatic speech recognition process may use vocal tract length normalization (VTLN) for male-female normalization and maximum likelihood linear regression (MLLR) for more general speaker adaptation. In some cases, an automatic speech recognition process may determine so-called delta and delta-delta coefficients to capture speech dynamics and might use heteroscedastic linear discriminant analysis (HLDA). In some cases, an automatic speech recognition process may use splicing and a linear discriminate analysis (LDA)-based projection, which may include heteroscedastic linear discriminant analysis or a global semi-tied covariance transform (also known as maximum likelihood linear transform [MLLT]). In some cases, an automatic speech recognition process may use discriminative training techniques, which may dispense with a purely statistical approach to HMM parameter estimation and instead optimize some classification-related measure of training data; examples may include maximum mutual information (MMI), minimum classification error (MCE), and minimum phone error (MPE).
Still referring to FIG. 1, in some embodiments, an automatic speech recognition process may be said to decode speech (i.e., audible verbal content). Decoding of speech may occur when an automatic speech recognition system is presented with a new utterance and must compute a most likely sentence. In some cases, speech decoding may include a Viterbi algorithm. A Viterbi algorithm may include a dynamic programming algorithm for obtaining a maximum a posteriori probability estimate of a most likely sequence of hidden states (i.e., Viterbi path) that results in a sequence of observed events. Viterbi algorithms may be employed in context of Markov information sources and hidden Markov models. A Viterbi algorithm may be used to find a best path, for example using a dynamically created combination hidden Markov model, having both acoustic and language model information, using a statically created combination hidden Markov model (e.g., finite state transducer [FST] approach).
Still referring to FIG. 1, in some embodiments, speech (i.e., audible verbal content) decoding may include considering a set of good candidates and not only a best candidate, when presented with a new utterance. In some cases, a better scoring function (i.e., re-scoring) may be used to rate each of a set of good candidates, allowing selection of a best candidate according to this refined score. In some cases, a set of candidates can be kept either as a list (i.e., N-best list approach) or as a subset of models (i.e., a lattice). In some cases, re-scoring may be performed by optimizing Bayes risk (or an approximation thereof). In some cases, re-scoring may include optimizing for sentence (including keywords) that minimizes an expectancy of a given loss function with regards to all possible transcriptions. For example, re-scoring may allow selection of a sentence that minimizes an average distance to other possible sentences weighted by their estimated probability. In some cases, an employed loss function may include Levenshtein distance, although different distance calculations may be performed, for instance for specific tasks. In some cases, a set of candidates may be pruned to maintain tractability.
Still referring to FIG. 1, in some embodiments, an automatic speech recognition process may employ dynamic time warping (DTW)-based approaches. Dynamic time warping may include algorithms for measuring similarity between two sequences, which may vary in time or speed. For instance, similarities in walking patterns would be detected, even if in one video the person was walking slowly and if in another he or she were walking more quickly, or even if there were accelerations and deceleration during the course of one observation. DTW has been applied to video, audio, and graphics-indeed, any data that can be turned into a linear representation can be analyzed with DTW. In some cases, DTW may be used by an automatic speech recognition process to cope with different speaking (i.e., audible verbal content) speeds. In some cases, DTW may allow computing device to find an optimal match between two given sequences (e.g., time series) with certain restrictions. That is, in some cases, sequences can be “warped” non-linearly to match each other. In some cases, a DTW-based sequence alignment method may be used in context of hidden Markov models.
Still referring to FIG. 1, in some embodiments, an automatic speech recognition process may include a neural network. Neural network may include any neural network, for example those disclosed with reference to FIGS. 3-5. In some cases, neural networks may be used for automatic speech recognition, including phoneme classification, phoneme classification through multi-objective evolutionary algorithms, isolated word recognition, audiovisual speech recognition, audiovisual speaker recognition and speaker adaptation. In some cases, neural networks employed in automatic speech recognition may make fewer explicit assumptions about feature statistical properties than HMMs and therefore may have several qualities making them attractive recognition models for speech recognition. When used to estimate the probabilities of a speech feature segment, neural networks may allow discriminative training in a natural and efficient manner. In some cases, neural networks may be used to effectively classify audible verbal content over short-time interval, for instance such as individual phonemes and isolated words. In some embodiments, a neural network may be employed by automatic speech recognition processes for pre-processing, feature transformation and/or dimensionality reduction, for example prior to HMM-based recognition. In some embodiments, long short-term memory (LSTM) and related recurrent neural networks (RNNs) and Time Delay Neural Networks (TDNN's) may be used for automatic speech recognition, for example over longer time intervals for continuous speech recognition.
Still referring to FIG. 1, in some embodiments, a language model may be used to process language, such as language extracted from a syllabus, transcribed from speech by an instructor, or transcribed from handwriting of an instructor. In some embodiments, a language model may be used to determine discussion datum 116. As used herein, a “language model” is a program capable of interpreting natural language, generating natural language, or both. In some embodiments, a language model may be configured to interpret the output of an automatic speech recognition function and/or an OCR function. A language model may include a neural network. A language model may be trained using a dataset that includes natural language.
Still referring to FIG. 1, generating language model may include generating a vector space, which may be a collection of vectors, defined as a set of mathematical objects that can be added together under an operation of addition following properties of associativity, commutativity, existence of an identity element, and existence of an inverse element for each vector, and can be multiplied by scalar values under an operation of scalar multiplication compatible with field multiplication, and that has an identity element is distributive with respect to vector addition, and is distributive with respect to field addition. Each vector in an n-dimensional vector space may be represented by an n-tuple of numerical values. Each unique extracted word and/or language element as described above may be represented by a vector of the vector space. In an embodiment, each unique extracted and/or other language element may be represented by a dimension of vector space; as a non-limiting example, each element of a vector may include a number representing an enumeration of co-occurrences of the word and/or language element represented by the vector with another word and/or language element. Vectors may be normalized, scaled according to relative frequencies of appearance and/or file sizes. In an embodiment associating language elements to one another as described above may include computing a degree of vector similarity between a vector representing each language element and a vector representing another language element; vector similarity may be measured according to any norm for proximity and/or similarity of two vectors, including without limitation cosine similarity, which measures the similarity of two vectors by evaluating the cosine of the angle between the vectors, which can be computed using a dot product of the two vectors divided by the lengths of the two vectors. Degree of similarity may include any other geometric measure of distance between vectors.
Still referring to FIG. 1, processor 104 may determine one or more language elements in language data by identifying and/or detecting associations between one or more language elements (including phonemes or phonological elements, morphemes or morphological elements, syntax or syntactic elements, semantics or semantic elements, and pragmatic elements) extracted from at least user data and/or response, including without limitation mathematical associations, between such words. Associations between language elements and relationships of such categories to other such term may include, without limitation, mathematical associations, including without limitation statistical correlations between any language element and any other language element and/or Language elements. Processor 104 may compare an input such as a sentence from language data with a list of keywords or a dictionary to identify language elements. For example, processor 104 may identify whitespace and punctuation in a sentence and extract elements comprising a string of letters, numbers or characters occurring adjacent to the whitespace and punctuation. Processor 104 may then compare each of these with a list of keywords or a dictionary. Based on the determined keywords or meanings associated with each of the strings, processor 104 may determine an association between one or more of the extracted strings and a feature of an element of language, such as an association between a short sequence of text containing a date, a colon, and a topic as an indication that the topic is to be discussed on the date. Associations may take the form of statistical correlations and/or mathematical associations, which may include probabilistic formulas or relationships indicating, for instance, a likelihood that a given extracted word indicates a given category of semantic meaning. As a further example, statistical correlations and/or mathematical associations may include probabilistic formulas or relationships indicating a positive and/or negative association between at least an extracted word and/or a given semantic meaning; positive or negative indication may include an indication that a given document is or is not indicating a category semantic meaning. Whether a phrase, sentence, word, or other textual element in a document or corpus of documents constitutes a positive or negative indicator may be determined, in an embodiment, by mathematical associations between detected words, comparisons to phrases and/or words indicating positive and/or negative indicators that are stored in memory.
Still referring to FIG. 1, processor 104 may be configured to determine one or more language elements in language data using machine learning. For example, processor 104 may generate the language processing model by any suitable method, including without limitation a natural language processing classification algorithm; language processing model may include a natural language process classification model that enumerates and/or derives statistical relationships between input terms and output terms. An algorithm to generate language processing model May include a stochastic gradient descent algorithm, which may include a method that iteratively optimizes an objective function, such as an objective function representing a statistical estimation of relationships between terms, including relationships between input language elements and output patterns or conversational styles in the form of a sum of relationships to be estimated. In an alternative or additional approach, sequential tokens may be modeled as chains, serving as the observations in a Hidden Markov Model (HMM). HMMs as used herein are statistical models with inference algorithms that that may be applied to the models. In such models, a hidden state to be estimated may include an association between an extracted word, phrase, and/or other semantic unit. There may be a finite number of categories to which an extracted word may pertain; an HMM inference algorithm, such as the forward-backward algorithm or the Viterbi algorithm, may be used to estimate the most likely discrete state given a word or sequence of words. Language processing module may combine two or more approaches. For instance, and without limitation, machine-learning program may use a combination of Naive-Bayes (NB), Stochastic Gradient Descent (SGD), and parameter grid-searching classification techniques; the result may include a classification algorithm that returns ranked associations.
Still referring to FIG. 1, processor 104 may be configured to determine one or more language elements in language data using machine learning by first creating or receiving language classification training data. Training data may include data containing correlations that a machine-learning process may use to model relationships between two or more categories of data elements. For instance, and without limitation, training data may include a plurality of data entries, each entry representing a set of data elements that were recorded, received, and/or generated together; data elements may be correlated by shared existence in a given data entry, by proximity in a given data entry, or the like. Multiple data entries in training data may evince one or more trends in correlations between categories of data elements; for instance, and without limitation, a higher value of a first data element belonging to a first category of data element may tend to correlate to a higher value of a second data element belonging to a second category of data element, indicating a possible proportional or other mathematical relationship linking values belonging to the two categories. Multiple categories of data elements may be related in training data according to various correlations; correlations may indicate causative and/or predictive links between categories of data elements, which may be modeled as relationships such as mathematical relationships by machine-learning processes as described in further detail below. Training data may be formatted and/or organized by categories of data elements, for instance by associating data elements with one or more descriptors corresponding to categories of data elements. As a non-limiting example, training data may include data entered in standardized forms by persons or processes, such that entry of a given data element in a given field in a form may be mapped to one or more descriptors of categories. Elements in training data may be linked to descriptors of categories by tags, tokens, or other data elements; for instance, and without limitation, training data may be provided in fixed-length formats, formats linking positions of data to categories such as comma-separated value (CSV) formats and/or self-describing formats such as extensible markup language (XML), JavaScript Object Notation (JSON), or the like, enabling processes or devices to detect categories of data.
Still referring to FIG. 1, training data may include one or more elements that are not categorized; that is, training data may not be formatted or contain descriptors for some elements of data. Machine-learning algorithms and/or other processes may sort training data according to one or more categorizations using, for instance, natural language processing algorithms, tokenization, detection of correlated values in raw data and the like; categories may be generated using correlation and/or other processing algorithms. As a non-limiting example, in a corpus of text, phrases making up a number “n” of compound words, such as nouns modified by other nouns, may be identified according to a statistically significant prevalence of n-grams containing such words in a particular order; such an n-gram may be categorized as an element of language such as a “word” to be tracked similarly to single words, generating a new category as a result of statistical analysis. Similarly, in a data entry including some textual data, a person's name may be identified by reference to a list, dictionary, or other compendium of terms, permitting ad-hoc categorization by machine-learning algorithms, and/or automated association of data in the data entry with descriptors or into a given format. The ability to categorize data entries automatedly may enable the same training data to be made applicable for two or more distinct machine-learning algorithms as described in further detail below.
Still referring to FIG. 1, language classification training data may be a training data set containing associations between language element inputs and associated language element outputs. Language element inputs and outputs may be categorized by communication form such as written language elements, spoken language elements, typed language elements, or language elements communicated in any suitable manner. Language elements may be categorized by component type, such as phonemes or phonological elements, morphemes or morphological elements, syntax or syntactic elements, semantics or semantic elements, and pragmatic elements. Associations may be made between similar communication types of language elements (e.g. associating one written language element with another written language element) or different language elements (e.g. associating a spoken language element with a written representation of the same language element).
Associations may be identified between similar communication types of two different language elements, for example written input consisting of the syntactic element “that” may be associated with written phonemes /th/, /ă/, and /t/. Associations may be identified between different communication forms of different language elements. For example, the spoken form of the syntactic element “that” and the associated written phonemes above. Language classification training data may be created using a classifier such as a language classifier. An exemplary classifier may be created, instantiated, and/or run using processor 104, or another computing device. Language classification training data may create associations between any type of language element in any format and other type of language element in any format. Additionally, or alternatively, language classification training data may associate language element input data to a feature related to a class. For example, language classification training data may associate occurrences of the syntactic elements “read,” “Hamlet” and “act 1” in a single sentence with the feature of Hamlet act 1 being a discussion topic option.
Still referring to FIG. 1, processor 104 may be configured to generate a classifier using a Naïve Bayes classification algorithm. Naïve Bayes classification algorithm generates classifiers by assigning class labels to problem instances, represented as vectors of element values. Class labels are drawn from a finite set. Naïve Bayes classification algorithm may include generating a family of algorithms that assume that the value of a particular element is independent of the value of any other element, given a class variable. Naïve Bayes classification algorithm may be based on Bayes Theorem expressed as P(A/B)=P(B/A) P(A)÷P(B), where P(A/B) is the probability of hypothesis A given data B also known as posterior probability; P(B/A) is the probability of data B given that the hypothesis A was true; P(A) is the probability of hypothesis A being true regardless of data also known as prior probability of A; and P(B) is the probability of the data regardless of the hypothesis. A naïve Bayes algorithm may be generated by first transforming training data into a frequency table. Processor 104 may then calculate a likelihood table by calculating probabilities of different data entries and classification labels. Processor 104 may utilize a naïve Bayes equation to calculate a posterior probability for each class. A class containing the highest posterior probability is the outcome of prediction. Naïve Bayes classification algorithm may include a gaussian model that follows a normal distribution. Naïve Bayes classification algorithm may include a multinomial model that is used for discrete counts. Naïve Bayes classification algorithm may include a Bernoulli model that may be utilized when vectors are binary.
Still referring to FIG. 1, processor 104 may be configured to generate a classifier using a K-nearest neighbors (KNN) algorithm. A “K-nearest neighbors algorithm” as used in this disclosure, includes a classification method that utilizes feature similarity to analyze how closely out-of-sample-features resemble training data to classify input data to one or more clusters and/or categories of features as represented in training data; this may be performed by representing both training data and input data in vector forms, and using one or more measures of vector similarity to identify classifications within training data, and to determine a classification of input data. K-nearest neighbors algorithm may include specifying a K-value, or a number directing the classifier to select the k most similar entries training data to a given sample, determining the most common classifier of the entries in the database, and classifying the known sample; this may be performed recursively and/or iteratively to generate a classifier that may be used to classify input data as further samples. For instance, an initial set of samples may be performed to cover an initial heuristic and/or “first guess” at an output and/or relationship, which may be seeded, without limitation, using expert input received according to any process as described herein. As a non-limiting example, an initial heuristic may include a ranking of associations between inputs and elements of training data. Heuristic may include selecting some number of highest-ranking associations and/or training data elements.
Still referring to FIG. 1, generating k-nearest neighbors algorithm may generate a first vector output containing a data entry cluster, generating a second vector output containing an input data, and calculate the distance between the first vector output and the second vector output using any suitable norm such as cosine similarity, Euclidean distance measurement, or the like. Each vector output may be represented, without limitation, as an n-tuple of values, where n is at least two values. Each value of n-tuple of values may represent a measurement or other quantitative value associated with a given category of data, or attribute, examples of which are provided in further detail below; a vector may be represented, without limitation, in n-dimensional space using an axis per category of value represented in n-tuple of values, such that a vector has a geometric direction characterizing the relative quantities of attributes in the n-tuple as compared to each other. Two vectors may be considered equivalent where their directions, and/or the relative quantities of values within each vector as compared to each other, are the same; thus, as a non-limiting example, a vector represented as [5, 10, 15] may be treated as equivalent, for purposes of this disclosure, as a vector represented as [1, 2, 3]. Vectors may be more similar where their directions are more similar, and more different where their directions are more divergent; however, vector similarity may alternatively or additionally be determined using averages of similarities between like attributes, or any other measure of similarity suitable for any n-tuple of values, or aggregation of numerical similarity measures for the purposes of loss functions as described in further detail below. Any vectors as described herein may be scaled, such that each vector represents each attribute along an equivalent scale of values. Each vector may be “normalized,” or divided by a “length” attribute, such as a length attribute l as derived using a Pythagorean norm: l=√{square root over (Σi=0nai2)}, where ai is attribute number i of the vector. Scaling and/or normalization may function to make vector comparison independent of absolute quantities of attributes, while preserving any dependency on similarity of attributes; this may, for instance, be advantageous where cases represented in training data are represented by different quantities of samples, which may result in proportionally equivalent vectors with divergent values.
Still referring to FIG. 1, in some embodiments, processor 104 may identify certain aspects of data to input into a language model in order to determine discussion topic 116. For example, a syllabus may include a table with columns for date and assigned reading; in this example, processor may determine discussion topic 116 for a particular date by inputting the description of the assigned reading for the relevant date into a language model and receiving an output.
Still referring to FIG. 1, in some embodiments, apparatus 100 may generate prompt 132 as a function of discussion topic 116. In some embodiments, apparatus 100 may generate prompt 132 by looking up a list of prompts associated with a particular discussion topic from a database. Databases are described above. Prompts may be ranked in order of priority, categorized as being appropriate in certain situations, and the like. For example, if discussion topic 116 is how to calculate the resulting velocity of each object after multiple objects collide, then a first prompt may be designated as a prompt to open a discussion with and may direct users, such as students, to solve a particular problem, and a second prompt may be designated as a prompt to be used if the users are stuck and may direct the users to identify certain values to be used in a relevant equation and plug them in.
Still referring to FIG. 1, in some embodiments, apparatus 100 may generate prompt 132 using a machine learning model such as prompt generation machine learning model 136. Prompt generation machine learning model 136 may use a machine learning algorithm described herein, such as a supervised learning algorithm, an unsupervised learning algorithm, a reinforcement learning algorithm, and the like. In some embodiments, prompt generation machine learning model 136 may include a neural network model. In some embodiments, prompt generation machine learning model 136 may include a language model. In some embodiments, a supervised learning algorithm and a training dataset are used to train prompt generation machine learning model 136; such training dataset may include model discussion topics, associated with model prompts. Such training data may be gathered by, for example, reviewing historical teaching documents such as assigned readings and homework questions based on those readings; in this example, a historical assigned reading and/or the core subject matter of a historical assigned reading may be used as a model discussion topic, and a historical question asked based on the assigned reading, such as a homework question or an in class essay question, may be used as a model prompt. Training data may also be generated by gathering questions from sources such as academic exams or standardized tests and matching them to related subject matter. Training data may also be generated by gathering questions from textbooks and determining topics to be associated with those questions based on the content of the section of the book that the question is focused on (for example, by inputting such content into a language model). Once prompt generation machine learning model 136 has been trained, it may be used to generate prompt 132. This may be done by inputting discussion topic 116 into prompt generation machine learning model 136 and receiving, as an output, prompt 132.
Still referring to FIG. 1, in some embodiments, prompt generation machine learning model 136 may accept as an additional input a context datum. In some embodiments, a context datum include an amount of time in a discussion session and/or the amount of time remaining in a discussion session. In some embodiments, a context datum may include a datum indicating whether a particular user, such as a student, has spoken up yet and/or generated sufficient data to be evaluated. In some embodiments, a context datum may include a datum indicating how difficult the prompt should be. For example, a first input into prompt generation machine learning model 136 may include discussion topic 116 and a context datum indicating the need for a general question on discussion topic 116, then during a discussion section, if a particular user has not yet spoken, a second input into prompt generation machine learning model 136 may include discussion topic 116 and an indication that the question should be directed at a particular user. In this example, a second prompt may be based on the output from prompt generation machine learning model 136 and may be directed at the silent user in order to get them to speak. In another example, a first input into prompt generation machine learning model 136 may include discussion topic 116 and a context datum indicating the need for a general question on discussion topic 116, then during a discussion section, if the users appear to have a solid understanding of the subject matter and/or have solved a question posed to them, then a second input into prompt generation machine learning model 136 may include discussion topic 116 and an indication that a question with a particular difficulty is needed. In this example, a second prompt may be based on the output from prompt generation machine learning model 136 and may be more challenging than the first prompt.
Still referring to FIG. 1, prompt generation machine learning model 136 that accepts as an input a context datum may be trained on a training dataset that includes model context data. For example, such training data may include discussion topic 116 based on historical syllabus and context datum based on the grade of the users for which that syllabus was designed, and this may be associated with homework questions asked of those users based on the relevant section of the syllabus.
Still referring to FIG. 1, follow up prompts may be generated based on analysis of an ongoing discussion responding to a prompt. Methods of detecting and analyzing discussion are described in more detail herein and include detecting discussion using a microphone, using an automatic speech recognition system to identify speakers and/or transcribe speech, and using a score generation machine learning model to identify a user understanding score and/or a certainty score. In some embodiments, a follow up prompt may be generated in order to improve the data available to apparatus 100 for evaluating users. For example, if apparatus 100 has enough data to evaluate 4 of 5 users in a group based on discussion in response to an initial prompt, then apparatus 100 may generate a second prompt directed at the remaining user in order to gather more data on that user. Whether apparatus 100 has enough data to properly evaluate a user may be based on a certainty score, which may be evaluated during a discussion between users based on the first part of the discussion. For example, apparatus 100 may generate a follow up prompt based on a comparison between a certainty score and a certainty score threshold. Certainty scores are discussed in further detail below.
Still referring to FIG. 1, in some embodiments, prompt generation machine learning model 136 may be trained using a reinforcement learning algorithm. For example, prompt generation machine learning model 136 may be used to generate a prompt, and an instructor may approve or deny the prompt. Apparatus 100 may use the instructor's approval or denial of the prompt to train prompt generation machine learning model 136. For example, prompt generation machine learning model 136 may be trained using a reinforcement learning mechanism in which prompt generation machine learning model 136 receives discussion topic 116 as an input, generates a prompt as an output, and receives feedback in the form of a cost function, where high cost function values dissuade prompt generation machine learning model 136 from producing similar outputs in the future and low cost function values encourage prompt generation machine learning model 136 to produce similar outputs in the future. Instructor approval of a prompt may cause apparatus 100 to determine a low cost, whereas instructor denial of a prompt may cause apparatus 100 to determine a high cost in this context. In some embodiments, costs are determined based on a resulting certainty score. For example, outputs that result in low certainty scores may be assigned high costs, while outputs that result in high certainty scores may be assigned low costs.
Still referring to FIG. 1, in some embodiments, apparatus 100 may present to a user prompt 132. In some embodiments, apparatus 100 may present to a user (such as a student) prompt 132 by sending a signal to user device 140, where the signal configures user device 140 to communicate prompt 132 to the user. In some embodiments, user device 140 may communicate prompt 132 to a user through user interface 144. User device 140 and/or user interface 144 may have one or more properties described with reference to instructor device 124 and instructor interface 128. For example, user device 140 may include a smartphone, tablet, smartwatch, computer, and the like. For example, user interface 144 may include a screen, speaker, and the like.
Still referring to FIG. 1, in some embodiments, apparatus 100 may present the same prompt 132 to multiple users, such as all users in a class. In some embodiments, apparatus 100 may organize users into groups and present prompt 132 to members of a group. This may be done, for example, to facilitate discussion in small groups where each user has sufficient opportunity to speak. In some embodiments, this may aid in generating sufficient data for evaluating each user. Organizing users into groups may include, for example, dividing them into breakout rooms in an online class environment using online meeting software. Groups may be determined, for example, randomly, based on instructor assignments, based on user behavior (such as to avoid creating disruptive user combinations), based on user scores in previous sessions, or based on which users talk more on average across multiple sessions.
Still referring to FIG. 1, in some embodiments, apparatus 100 may allow users to discuss prompt 132. This discussion may be allowed to proceed for a set period of time, such as the duration of a class, or half the duration of a class. A set period of time may be input by an instructor, determined from a syllabus, or the like. An instructor may be able to observe user discussion based on prompts. For example, instructor may be able to select a user group to observe and may listen in on their conversation and/or discuss prompt 132 with members of the group.
Still referring to FIG. 1, in some embodiments, apparatus 100 may receive discussion datum 148. In some embodiments, discussion datum 148 may comprise a user response to prompt 132. As used herein, a “discussion datum” is an audio recording of user discussion in response to a prompt, a datum derived from an audio recording of user discussion in response to a prompt, or both. Apparatus 100 may record discussion datum 148 using a microphone, such as a microphone that is part of user device 140. In some embodiments, apparatus 100 may record discussion datum 148 by receiving or recording conversation transmitted through a meeting app.
Still referring to FIG. 1, discussion datum 148 may be transcribed using an automatic speech recognition system as described above. Apparatus 100 may attribute statements within discussion datum 148 to individual speakers using an automatic speech recognition system as described above. Apparatus 100 may interpret discussion datum 148 using a machine learning model such as a language model as described above. In some embodiments, apparatus 100 may first transcribe discussion datum 148 and attribute statements to speakers using an automatic speech recognition system, then interpret statements within discussion datum 148 using a machine learning model such as a language model.
Still referring to FIG. 1, in some embodiments, apparatus 100 may also record visual information relating to user discussion, such as a video of user discussion. This may be used alongside a machine vision system to, for example, identify speakers. For example, a machine vision system may detect which user appears to be speaking at a variety of time points in a video of a discussion between users, and apparatus 100 may use this information to attribute statements within an audio recording to specific users. A machine vision system may utilize data gathered through a camera, such as a camera within user device 140.
Still referring to FIG. 1, in some embodiments, apparatus 100 may include at least a camera. As used in this disclosure, a “camera” is a device that is configured to sense electromagnetic radiation, such as without limitation visible light, and generate an image representing the electromagnetic radiation. In some cases, a camera may include one or more optics. Exemplary non-limiting optics include spherical lenses, aspherical lenses, reflectors, polarizers, filters, windows, aperture stops, and the like. In some cases, at least a camera may include an image sensor. Exemplary non-limiting image sensors include digital image sensors, such as without limitation charge-coupled device (CCD) sensors and complimentary metal-oxide-semiconductor (CMOS) sensors, chemical image sensors, and analog image sensors, such as without limitation film. In some cases, a camera may be sensitive within a non-visible range of electromagnetic radiation, such as without limitation infrared. As used in this disclosure, “image data” is information representing at least a physical scene, space, and/or object. In some cases, image data may be generated by a camera. “Image data” may be used interchangeably through this disclosure with “image,” where image is used as a noun. An image may be optical, such as without limitation where at least an optic is used to generate an image of an object. An image may be material, such as without limitation when film is used to capture an image. An image may be digital, such as without limitation when represented as a bitmap. Alternatively, an image may be comprised of any media capable of representing a physical scene, space, and/or object. Alternatively, where “image” is used as a verb, in this disclosure, it refers to generation and/or formation of an image.
Still referring to FIG. 1, in some embodiments, apparatus 100 may include a machine vision system. In some embodiments, a machine vision system may include at least a camera. A machine vision system may use images, such as images from at least a camera, to make a determination about a scene, space, and/or object. For example, in some cases a machine vision system may be used for world modeling or registration of objects within a space. In some cases, registration may include image processing, such as without limitation object recognition, feature detection, edge/corner detection, and the like. Non-limiting example of feature detection may include scale invariant feature transform (SIFT), Canny edge detection, Shi Tomasi corner detection, and the like. In some cases, registration may include one or more transformations to orient a camera frame (or an image or video stream) relative a three-dimensional coordinate system; exemplary transformations include without limitation homography transforms and affine transforms. In an embodiment, registration of first frame to a coordinate system may be verified and/or corrected using object identification and/or computer vision, as described above. For instance, and without limitation, an initial registration to two dimensions, represented for instance as registration to the x and y coordinates, may be performed using a two-dimensional projection of points in three dimensions onto a first frame, however. A third dimension of registration, representing depth and/or a z axis, may be detected by comparison of two frames; for instance, where first frame includes a pair of frames captured using a pair of cameras (e.g., stereoscopic camera also referred to in this disclosure as stereo-camera), image recognition and/or edge detection software may be used to detect a pair of stereoscopic views of images of an object; two stereoscopic views may be compared to derive z-axis values of points on object permitting, for instance, derivation of further z-axis points within and/or around the object using interpolation. This may be repeated with multiple objects in field of view, including without limitation environmental features of interest identified by object classifier and/or indicated by an operator. In an embodiment, x and y axes may be chosen to span a plane common to two cameras used for stereoscopic image capturing and/or an xy plane of a first frame; a result, x and y translational components and ϕ may be pre-populated in translational and rotational matrices, for affine transformation of coordinates of object, also as described above. Initial x and y coordinates and/or guesses at transformational matrices may alternatively or additionally be performed between first frame and second frame, as described above. For each point of a plurality of points on object and/or edge and/or edges of object as described above, x and y coordinates of a first stereoscopic frame may be populated, with an initial estimate of z coordinates based, for instance, on assumptions about object, such as an assumption that ground is substantially parallel to an xy plane as selected above. Z coordinates, and/or x, y, and z coordinates, registered using image capturing and/or object identification processes as described above may then be compared to coordinates predicted using initial guess at transformation matrices; an error function may be computed using by comparing the two sets of points, and new x, y, and/or z coordinates, may be iteratively estimated and compared until the error function drops below a threshold level. In some cases, a machine vision system may use a classifier, such as any classifier described throughout this disclosure.
Still referring to FIG. 1, an exemplary machine vision camera is an OpenMV Cam H7 from OpenMV, LLC of Atlanta, Georgia, U.S.A. OpenMV Cam comprises a small, low power, microcontroller which allows execution of machine vision applications. OpenMV Cam comprises an ARM Cortex M7 processor and a 640×480 image sensor operating at a frame rate up to 150 fps. OpenMV Cam may be programmed with Python using a Remote Python/Procedure Call (RPC) library. OpenMV CAM may be used to operate image classification and segmentation models, such as without limitation by way of TensorFlow Lite; detection motion, for example by way of frame differencing algorithms; marker detection, for example blob detection; object detection, for example face detection; eye tracking; person detection, for example by way of a trained machine learning model; camera motion detection, for example by way of optical flow detection; code (barcode) detection and decoding; image capture; and video recording.
Still referring to FIG. 1, in some embodiments, apparatus 100 may generate user understanding score 152. In some embodiments, apparatus 100 may generate user understanding score 152 as a function of discussion datum 148, prompt 132, discussion topic 116 and/or a grading threshold. As used herein, a “user understanding score” is an evaluation of a specific user's understanding of a discussion topic.
Still referring to FIG. 1, in some embodiments, apparatus 100 may generate user understanding score 152 using score generation machine learning model 156. Score generation machine learning model 156 may use a machine learning algorithm described herein, such as a supervised learning algorithm, an unsupervised learning algorithm, a reinforcement learning algorithm, and the like. In some embodiments, score generation machine learning model 156 may include a neural network model. In some embodiments, score generation machine learning model 156 may include a language model. In some embodiments, a supervised learning algorithm and a training dataset are used to train score generation machine learning model 156; such training dataset may include model discussion data and model prompts, associated with model user understanding scores. Such training data may be gathered by, for example, gathering historical academic essay questions, historical answers to those essay questions, and the grades those answers received. In this example, the historical academic essay questions may be used as model prompts, the historical answers may be used as model discussion data, and the grades may be used as model user understanding data. In another example, training data may be gathered by posing prompts to users, receiving responses, and having instructors grade those responses. Similarly, score generation machine learning model 156 may be trained using a training data set including model discussion data and model discussion topics, associated with model user understanding scores. Such training data may be gathered by, for example, gathering historical academic essay topics, historical answers to essay questions on those topics, and historical grades those answers received. Once score generation machine learning model 156 is trained, it may be used to generate user understanding score 152. In some embodiments, apparatus 100 may input into score generation machine learning model 156 prompt 132 and discussion datum 148 and may receive user understanding score 152 or a datum used to determine user understanding score 152 as an output. In some embodiments, apparatus 100 may input into score generation machine learning model 156 discussion topic 116 and discussion datum 148 and may receive user understanding score 152 or a datum used to determine user understanding score 152 as an output.
Still referring to FIG. 1, in some embodiments, apparatus 100 may modify an output of score generation machine learning model 156 in order to determine user understanding score 152. For example, score generation machine learning model 156 may receive as an input discussion topic 116 and discussion datum 148 and may output a datum evaluating a user's understanding of discussion topic 116. However, expectations for users may differ such that further data may be needed in order to determine an appropriate user understanding score 152. For example, a 7th grader, a high school junior, and a college senior may all discuss a particular historical figure, but the expectations of the college senior's understanding may be higher than the expectations of the high school junior, and much higher than the expectations of the 7th grader. If each of these users receive the same output from score generation machine learning model 156, then their user understanding scores 152 may differ according to their expectations. Apparatus 100 may apply one or more grading thresholds to the output of score generation machine learning model 156 in order to determine user understanding score 152. In some embodiments, a grading threshold may be set by an instructor. In some embodiments, a grading threshold may be set by an institution such as an academic institution. In some embodiments, a grading threshold may be recommended to an instructor by apparatus 100 and the instructor may have the option to accept the recommended threshold or set their own. In some embodiments, a grading threshold may be determined based on a syllabus or other data input by an instructor and/or institution. For example, a grading threshold may be determined based on the grade of the user being evaluated.
Still referring to FIG. 1, in some embodiments, a user understanding score 152 and/or a grading threshold may be determined based on outputs from score generation machine learning model 156 for a plurality of users, such as a class, group, or multiple classes. For example, user understanding score 152 may be determined as a percentile rank among users in the class, based on the output of score generation machine learning model 156 for each user in the class. In another example, user understanding score 152 may be determined using a scaled grade based on a percentile rank among users in the class, based on the output of score generation machine learning model 156 for each user in the class. In another example, user understanding score may be determined based on the output of score generation machine learning model 156 for all users taking a class in a school district, all users who have taken a class within the past 5 years, and the like. In some embodiments, user understanding scores 152 are stored for future retrieval in order to create such metrics in the future. User understanding scores may be stored, for example, in a database or an immutable sequence listing. Immutable sequence listings are described below.
Still referring to FIG. 1, in some embodiments, data may be prepared for score generation machine learning model 156 using an automatic speech recognition system. Automatic speech recognition systems are described above. Automatic speech recognition system may be used to transcribe audio discussion datum 148 into a machine readable format such as a text format. Automatic speech recognition system may be used to attribute elements of speech to particular users. In some embodiments, preparing discussion datum in this way may have the benefit of removing problematic data from an analysis. For example, if audio data were to be directly used, then factors such as tone of voice, speaking volume, a user's accent, and the like may affect user understanding score 152. However, this data may be more likely to create improper biases than to be useful in accurately evaluating user understanding. In some embodiments, transcribing the audio first may remove this data from consideration, preventing it from being considered by score generation machine learning model 156. This may prevent biases from being introduced into the output and/or scenarios where users learn to game the system by, for example, speaking in a confident tone regardless of whether they know the answer (which may detract from learning the substance of a lesson).
Still referring to FIG. 1, in some embodiments, apparatus 100 may determine a certainty score. In some embodiments, score generation machine learning model 156 may output a certainty score in addition to user understanding score 152. As used herein, a “certainty score” is a degree of confidence in a measure of user understanding. Certainty score may indicate low confidence when, for example, a user has not spoken in a particular discussion session. Additional examples of scenarios where certainty scores may indicate low confidence include situations in which user responses are off topic, short, or incomprehensible. A certainty score may indicate high confidence where, for example, a user has given a thorough response to a question and/or discussion datum 148 produced by that user fits well into a training data pattern indicating a particular user understanding score 152. For example, score generation machine learning model 156 may include a classifier designed to categorize users according to their degree of understanding of a particular topic, and score generation machine learning model 156 may be designed to output a low certainty score where it is less clear which category to assign discussion datum 148 to. In some embodiments, score generation machine learning model 156 may assign certainty scores based on, for example, how closely discussion datum 148 matches a pattern in training data or an evaluation of a percent chance of a particular result (as may be calculated in certain classification algorithms for example).
Still referring to FIG. 1, in some embodiments, score generation machine learning model 156 may be used to generate follow up prompts. For example, score generation machine learning model 156 may be used to periodically calculate certainty scores for users participating in a discussion. If, after a certain period of time, a certainty score for a particular user remains low, apparatus 100 may generate a new prompt 132 directed at the user with the low certainty score and may communicate the new prompt 132 to the user and/or a group that the user is in. In some embodiments, this may minimize the occurrence of scenarios in which there is not enough data to evaluate the understanding of certain users with a high degree of confidence. In some embodiments, this may get around problems in which a system does not consistently have enough data to evaluate each user with high confidence, and it is not clear that this will be a problem for any particular user before the discussion.
Still referring to FIG. 1, in some embodiments, apparatus 100 may break down user understanding score 152 into evaluations of sub-topics and/or may evaluate user understanding of additional topics. For example, if discussion topic 116 is a particular book, then apparatus 100 may use several score generation machine learning models 156 and/or several inputs into score generation machine learning model 156 to evaluate a user's understanding of certain parts of the book. For example, score generation machine learning model 156 may be trained using training data differentiating between different chapters of the book, and score generation machine learning model 156 may be used to generate a breakdown of a user's understanding of each chapter. In some embodiments, apparatus 100 may break down user understanding score 152 based on a user's performance in response to different prompts. For example, a user may not have contributed to a conversation about a first prompt, but may have produced a thorough answer in response to a second prompt. In this situation, score generation machine learning model 156 may be used to separately evaluate responses to each prompt, and a breakdown of user understanding by prompt may be generated based on the outputs.
Still referring to FIG. 1, in some embodiments, apparatus 100 may generate a user understanding score as a function of content received in a non-audio format. For example, a user may type an answer in a chat window, and this may be evaluated as a transcribed discussion datum.
Still referring to FIG. 1, in some embodiments, a datum, such as user understanding score 152, may be protected by one or more security measures, such as immutable sequence listing 160. Security measures may include, in non-limiting examples, storage in a database, password protection, multi factor authentication, hashing, encryption, digital signatures, inclusion in a blockchain, and the like. Cryptographic systems and blockchain are described further herein.
Still referring to FIG. 1, in some embodiments, apparatus 100 may communicate user understanding score 152 to an instructor. In some embodiments, apparatus 100 may transmit a signal including user understanding score 152 to instructor device 124, and the signal may configure instructor device 124 to communicate user understanding score 152 to instructor. Instructor device 124 may communicate user understanding score 152 to instructor using, for example, a visual or audio format. Apparatus 100 may communicate a visual element and/or visual element data structure including user understanding score 152 to instructor device 124. This may configure instructor device 124 to display a visual element. As used herein, a device “displays” a datum if the device outputs the datum in a format suitable for communication to a user. For example, a device may display a datum by outputting text or an image on a screen, or outputting a sound using a speaker.
Still referring to FIG. 1, in some embodiments, a visual element data structure may include a visual element. As used herein, a “visual element” is a datum that is displayed visually to a user. In some embodiments, a visual element data structure may include a rule for displaying visual element. In some embodiments, a visual element data structure may be determined as a function of user understanding score 152. In some embodiments, a visual element data structure may be determined as a function of an item from the list consisting of discussion topic 116, prompt 132, and user understanding score 152. In a non-limiting example, a visual element data structure may be generated such that visual element describing or highlighting user understanding score 152 is displayed to a user. For example, an instructor may select a particular user and a particular discussion session, and a visual element depicting user understanding score 152 for that discussion session may be displayed. In another example, an instructor may select a particular user and a visual element including a chart showing that user's user understanding scores 152 over time may be displayed.
Still referring to FIG. 1, in some embodiments, visual element may include one or more elements of text, images, shapes, charts, particle effects, interactable features, and the like. For example, if a user had a particularly high user understanding score, then that score may be highlighted and a check mark may be displayed next to it.
Still referring to FIG. 1, a visual element data structure may include rules governing if or when visual element is displayed. In a non-limiting example, a visual element data structure may include a rule causing a visual element describing user understanding score 152 to be displayed when a user selects user understanding score 152 using a GUI.
Still referring to FIG. 1, a visual element data structure may include rules for presenting more than one visual element, or more than one visual element at a time. In an embodiment, about 1, 2, 3, 4, 5, 10, 20, or 50 visual elements are displayed simultaneously.
Still referring to FIG. 1, a visual element data structure rule may apply to a single visual element or datum, or to more than one visual element or datum. A visual element data structure may categorize data into one or more categories and may apply a rule to all data in a category, to all data in an intersection of categories, or all data in a subsection of a category (such as all data in a first category and not in a second category). For example, all user understanding scores 152 below a certain threshold (such as a threshold required for a user to pass a class) may be displayed in red. A visual element data structure may rank data or assign numerical values to them. For example, greater weightings may be applied to user understanding scores 152 in which users had more time to discuss. In another example, greater weightings may be applied to user understanding scores 152 with a higher certainty score. A visual element data structure may apply rules based on a comparison between a ranking or numerical value and a threshold. For example, user understanding scores 152 may be organized in a table, with a column of the table indicating a degree of confidence in the relevant user understanding score; in this example, the text “high confidence” in blue may be displayed where a relevant certainty score is above a threshold, and the text “low confidence” in red may be displayed otherwise. Rankings, numerical values, categories, and the like may be used to set visual element data structure rules. Similarly, rankings, numerical values, categories, and the like may be applied to visual elements, and visual elements may be applied based on them. For example, certain visual elements may be designated as higher priority than others. For example, a visual element indicating that a user has a user understanding score 152 below a passing score threshold may take priority over a visual element indicating how frequently the user spoke in the last discussion session.
Still referring to FIG. 1, in some embodiments, visual element may be interacted with. For example, visual element may include an interface, such as a button or menu. In some embodiments, visual element may be interacted with using a user device such as a smartphone.
Still referring to FIG. 1, in some embodiments, apparatus 100 may determine visual element. In some embodiments, apparatus 100 may transmit visual element data structure to user device 140 and/or instructor device 124. In some embodiments, visual element data structure may configure user device 140 and/or instructor device 124 to display visual element. In some embodiments, visual element data structure may cause an event handler to be triggered in an application of user device 140 and/or instructor device 124 such as a web browser. In some embodiments, triggering of an event handler may cause a change in an application of user device 140 and/or instructor device 124 such as display of visual element.
Still referring to FIG. 1, in some embodiments, apparatus 100 may transmit visual element to a display. A display may communicate visual element to user and/or instructor. A display may include, for example, a smartphone screen, a computer screen, or a tablet screen. A display may be configured to provide a visual interface. A visual interface may include one or more virtual interactive elements such as, without limitation, buttons, menus, and the like. A display may include one or more physical interactive elements, such as buttons, a computer mouse, or a touchscreen, that allow user to input data into the display. Interactive elements may be configured to enable interaction between a user and a computing device. In some embodiments, a visual element data structure is determined as a function of data input by user into a display.
Still referring to FIG. 1, a variable and/or datum described herein may be represented as a data structure. In some embodiments, a data structure may include one or more functions and/or variables, as a class might in object-oriented programming. In some embodiments, a data structure may include data in the form of a Boolean, integer, float, string, date, and the like. In a non-limiting example, a user understanding score data structure may include an int value representing the value of the score. In some embodiments, data in a data structure may be organized in a linked list, tree, array, matrix, tenser, and the like. In a non-limiting example, a plurality of user understanding scores for a particular user may be organized in an array. In some embodiments, a data structure may include or be associated with one or more elements of metadata. A data structure may include one or more self-referencing data elements, which processor 104 may use in interpreting the data structure. In a non-limiting example, a data structure may include “<date>” and “</date>,” tags, indicating that the content between the tags is a date. In some embodiments, a data structure may be stored in, for example, memory 108 or a database.
Still referring to FIG. 1, in some embodiments, a data structure may be read and/or manipulated by processor 104. In a non-limiting example, a prompt data structure may be read and accepted or rejected by an instructor device 124.
Still referring to FIG. 1, in some embodiments, a data structure may be calibrated. In some embodiments, a data structure may be trained using a machine learning algorithm. In a non-limiting example, a data structure may include an array of data representing the biases of connections of a neural network. In this example, the neural network may be trained on a set of training data, and a back propagation algorithm may be used to modify the data in the array. Machine learning models and neural networks are described further herein.
Still referring to FIG. 1, in some embodiments, an instructor viewing user understanding scores 152 may be able to edit a user understanding score 152. For example, score generation machine learning model 156 output may lead to apparatus assigning a particular user a first user understanding score for a particular topic, and an instructor listening in on that user's discussion may believe the correct value to be higher and may edit the user's score.
Still referring to FIG. 1, in some embodiments, apparatus 100 may display a transcript of a user discussion to an instructor. For example, apparatus 100 may store a transcript generated from discussion datum 148 by an automatic speech recognition system. Apparatus 100 may then determine user understanding score 152 based on discussion datum and display user understanding score 152 to instructor. In some embodiments, apparatus 100 may display a transcript of the relevant user discussion alongside user understanding score 152. In some embodiments, apparatus 100 may identify sections of a transcript of particular importance to user understanding score 152. Apparatus 100 may do this by, for example, analyzing user understanding score 152 as normal, and also without each response by the user in question. In this way, alternate user understanding scores may be determined as though the relevant user had not given a particular response. In some embodiments, apparatus 100 may identify one or more responses within discussion datum 148 that impacted the relevant user's user understanding score. For example, if a user spoke 5 times during a discussion, and 1 of them showed that he had a very good understanding, but the other 4 were not particularly insightful, then when apparatus 100 re-analyzes his understanding without each response, apparatus 100 may determine that his score would have been much lower without that response; apparatus 100 may then highlight that response as important to the score when an instructor views the user's user understanding score 152.
Still referring to FIG. 1, in some embodiments, apparatus 100 may alter variables based on instructor input. For example, an instructor may be able to view and/or edit discussion topics 116, proposed prompts 132, user understanding scores 152, discussion datum 148 audio and/or transcripts, and the like. In some embodiments, an instructor may be able to make suggestions for future discussion sections. For example, an instructor may be able to speak a suggestion to alter a proposed prompt 132 aloud, and this may be recorded using a microphone, transcribed using an automatic speech recognition system, interpreted using a language model, and apparatus 100 may respond to the request by modifying the proposed prompt 132, such as by replacing it with an instructor suggestion.
Still referring to FIG. 1, in some embodiments, apparatus 100 may assign study materials ahead of a discussion session. For example, apparatus 100 may determine discussion topic 116 as described above and may refer to a database including grade appropriate readings associated with discussion topic 116. In some embodiments, apparatus 100 may communicate such study materials to a user and/or instructor, such as by transmitting signals to user device 140 and/or instructor device 124.
Now referring to FIG. 2, in an embodiment, methods and systems described herein may perform or implement one or more aspects of a cryptographic system. In one embodiment, a cryptographic system is a system that converts data from a first form, known as “plaintext,” which is intelligible when viewed in its intended format, into a second form, known as “ciphertext,” which is not intelligible when viewed in the same way. Ciphertext may be unintelligible in any format unless first converted back to plaintext. In one embodiment, a process of converting plaintext into ciphertext is known as “encryption.” Encryption process may involve the use of a datum, known as an “encryption key,” to alter plaintext. Cryptographic system may also convert ciphertext back into plaintext, which is a process known as “decryption.” Decryption process may involve the use of a datum, known as a “decryption key,” to return the ciphertext to its original plaintext form. In embodiments of cryptographic systems that are “symmetric,” decryption key is essentially the same as encryption key: possession of either key makes it possible to deduce the other key quickly without further secret knowledge. Encryption and decryption keys in symmetric cryptographic systems may be kept secret and shared only with persons or entities that the user of the cryptographic system wishes to be able to decrypt the ciphertext. One example of a symmetric cryptographic system is the Advanced Encryption Standard (“AES”), which arranges plaintext into matrices and then modifies the matrices through repeated permutations and arithmetic operations with an encryption key.
Still referring to FIG. 2, in embodiments of cryptographic systems that are “asymmetric,” either encryption or decryption key cannot be readily deduced without additional secret knowledge, even given the possession of a corresponding decryption or encryption key, respectively; a common example is a “public key cryptographic system,” in which possession of the encryption key does not make it practically feasible to deduce the decryption key, so that the encryption key may safely be made available to the public. An example of a public key cryptographic system is RSA, in which an encryption key involves the use of numbers that are products of very large prime numbers, but a decryption key involves the use of those very large prime numbers, such that deducing the decryption key from the encryption key requires the practically infeasible task of computing the prime factors of a number which is the product of two very large prime numbers. Another example is elliptic curve cryptography, which relies on the fact that given two points P and Q on an elliptic curve over a finite field, and a definition for addition where A+B=−R, the point where a line connecting point A and point B intersects the elliptic curve, where “0,” the identity, is a point at infinity in a projective plane containing the elliptic curve, finding a number k such that adding P to itself k times results in Q is computationally impractical, given correctly selected elliptic curve, finite field, and P and Q.
Still referring to FIG. 2, in some embodiments, systems and methods described herein produce cryptographic hashes, also referred to by the equivalent shorthand term “hashes.” A cryptographic hash, as used herein, is a mathematical representation of a lot of data, such as files or blocks in a block chain as described in further detail below; the mathematical representation is produced by a lossy “one-way” algorithm known as a “hashing algorithm.” Hashing algorithm may be a repeatable process; that is, identical lots of data may produce identical hashes each time they are subjected to a particular hashing algorithm. Because hashing algorithm is a one-way function, it may be impossible to reconstruct a lot of data from a hash produced from the lot of data using the hashing algorithm. In the case of some hashing algorithms, reconstructing the full lot of data from the corresponding hash using a partial set of data from the full lot of data may be possible only by repeatedly guessing at the remaining data and repeating the hashing algorithm; it is thus computationally difficult if not infeasible for a single computer to produce the lot of data, as the statistical likelihood of correctly guessing the missing data may be extremely low. However, the statistical likelihood of a computer of a set of computers simultaneously attempting to guess the missing data within a useful timeframe may be higher, permitting mining protocols as described in further detail below.
Still referring to FIG. 2, in an embodiment, hashing algorithm may demonstrate an “avalanche effect,” whereby even extremely small changes to lot of data produce drastically different hashes. This may thwart attempts to avoid the computational work necessary to recreate a hash by simply inserting a fraudulent datum in data lot, enabling the use of hashing algorithms for “tamper-proofing” data such as data contained in an immutable ledger as described in further detail below. This avalanche or “cascade” effect may be evinced by various hashing processes; persons skilled in the art, upon reading the entirety of this disclosure, will be aware of various suitable hashing algorithms for purposes described herein. Verification of a hash corresponding to a lot of data may be performed by running the lot of data through a hashing algorithm used to produce the hash. Such verification may be computationally expensive, albeit feasible, potentially adding up to significant processing delays where repeated hashing, or hashing of large quantities of data, is required, for instance as described in further detail below. Examples of hashing programs include, without limitation, SHA256, a NIST standard; further current and past hashing algorithms include Winternitz hashing algorithms, various generations of Secure Hash Algorithm (including “SHA-1,” “SHA-2,” and “SHA-3”), “Message Digest” family hashes such as “MD4,” “MD5,” “MD6,” and “RIPEMD,” Keccak, “BLAKE” hashes and progeny (e.g., “BLAKE2,” “BLAKE-256,” “BLAKE-512,” and the like), Message Authentication Code (“MAC”)-family hash functions such as PMAC, OMAC, VMAC, HMAC, and UMAC, Polyl305-AES, Elliptic Curve Only Hash (“ECOH”) and similar hash functions, Fast-Syndrome-based (FSB) hash functions, GOST hash functions, the Grøstl hash function, the HAS-160 hash function, the JH hash function, the RadioGatun hash function, the Skein hash function, the Streebog hash function, the SWIFFT hash function, the Tiger hash function, the Whirlpool hash function, or any hash function that satisfies, at the time of implementation, the requirements that a cryptographic hash be deterministic, infeasible to reverse-hash, infeasible to find collisions, and have the property that small changes to an original message to be hashed will change the resulting hash so extensively that the original hash and the new hash appear uncorrelated to each other. A degree of security of a hash function in practice may depend both on the hash function itself and on characteristics of the message and/or digest used in the hash function. For example, where a message is random, for a hash function that fulfills collision-resistance requirements, a brute-force or “birthday attack” may to detect collision may be on the order of O(2n/2) for n output bits; thus, it may take on the order of 2256 operations to locate a collision in a 512 bit output “Dictionary” attacks on hashes likely to have been generated from a non-random original text can have a lower computational complexity, because the space of entries they are guessing is far smaller than the space containing all random permutations of bits. However, the space of possible messages may be augmented by increasing the length or potential length of a possible message, or by implementing a protocol whereby one or more randomly selected strings or sets of data are added to the message, rendering a dictionary attack significantly less effective.
Still referring to FIG. 2, a “secure proof,” as used in this disclosure, is a protocol whereby an output is generated that demonstrates possession of a secret, such as device-specific secret, without demonstrating the entirety of the device-specific secret; in other words, a secure proof by itself, is insufficient to reconstruct the entire device-specific secret, enabling the production of at least another secure proof using at least a device-specific secret. A secure proof may be referred to as a “proof of possession” or “proof of knowledge” of a secret. Where at least a device-specific secret is a plurality of secrets, such as a plurality of challenge-response pairs, a secure proof may include an output that reveals the entirety of one of the plurality of secrets, but not all of the plurality of secrets; for instance, secure proof may be a response contained in one challenge-response pair. In an embodiment, proof may not be secure; in other words, proof may include a one-time revelation of at least a device-specific secret, for instance as used in a single challenge-response exchange.
Still referring to FIG. 2, secure proof may include a zero-knowledge proof, which may provide an output demonstrating possession of a secret while revealing none of the secret to a recipient of the output; zero-knowledge proof may be information-theoretically secure, meaning that an entity with infinite computing power would be unable to determine secret from output. Alternatively, zero-knowledge proof may be computationally secure, meaning that determination of secret from output is computationally infeasible, for instance to the same extent that determination of a private key from a public key in a public key cryptographic system is computationally infeasible. Zero-knowledge proof algorithms may generally include a set of two algorithms, a prover algorithm, or “P,” which is used to prove computational integrity and/or possession of a secret, and a verifier algorithm, or “V” whereby a party may check the validity of P. Zero-knowledge proof may include an interactive zero-knowledge proof, wherein a party verifying the proof must directly interact with the proving party; for instance, the verifying and proving parties may be required to be online, or connected to the same network as each other, at the same time. Interactive zero-knowledge proof may include a “proof of knowledge” proof, such as a Schnorr algorithm for proof on knowledge of a discrete logarithm. in a Schnorr algorithm, a prover commits to a randomness r, generates a message based on r, and generates a message adding r to a challenge c multiplied by a discrete logarithm that the prover is able to calculate; verification is performed by the verifier who produced c by exponentiation, thus checking the validity of the discrete logarithm. Interactive zero-knowledge proofs may alternatively or additionally include sigma protocols. Persons skilled in the art, upon reviewing the entirety of this disclosure, will be aware of various alternative interactive zero-knowledge proofs that may be implemented consistently with this disclosure.
Still referring to FIG. 2, alternatively, zero-knowledge proof may include a non-interactive zero-knowledge, proof, or a proof wherein neither party to the proof interacts with the other party to the proof; for instance, each of a party receiving the proof and a party providing the proof may receive a reference datum which the party providing the proof may modify or otherwise use to perform the proof. As a non-limiting example, zero-knowledge proof may include a succinct non-interactive arguments of knowledge (ZK-SNARKS) proof, wherein a “trusted setup” process creates proof and verification keys using secret (and subsequently discarded) information encoded using a public key cryptographic system, a prover runs a proving algorithm using the proving key and secret information available to the prover, and a verifier checks the proof using the verification key; public key cryptographic system may include RSA, elliptic curve cryptography, ElGamal, or any other suitable public key cryptographic system. Generation of trusted setup may be performed using a secure multiparty computation so that no one party has control of the totality of the secret information used in the trusted setup; as a result, if any one party generating the trusted setup is trustworthy, the secret information may be unrecoverable by malicious parties. As another non-limiting example, non-interactive zero-knowledge proof may include a Succinct Transparent Arguments of Knowledge (ZK-STARKS) zero-knowledge proof. In an embodiment, a ZK-STARKS proof includes a Merkle root of a Merkle tree representing evaluation of a secret computation at some number of points, which may be 1 billion points, plus Merkle branches representing evaluations at a set of randomly selected points of the number of points; verification may include determining that Merkle branches provided match the Merkle root, and that point verifications at those branches represent valid values, where validity is shown by demonstrating that all values belong to the same polynomial created by transforming the secret computation. In an embodiment, ZK-STARKS does not require a trusted setup.
Still referring to FIG. 2, zero-knowledge proof may include any other suitable zero-knowledge proof. Zero-knowledge proof may include, without limitation bulletproofs. Zero-knowledge proof may include a homomorphic public-key cryptography (hPKC)-based proof. Zero-knowledge proof may include a discrete logarithmic problem (DLP) proof. Zero-knowledge proof may include a secure multi-party computation (MPC) proof. Zero-knowledge proof may include, without limitation, an incrementally verifiable computation (IVC). Zero-knowledge proof may include an interactive oracle proof (IOP). Zero-knowledge proof may include a proof based on the probabilistically checkable proof (PCP) theorem, including a linear PCP (LPCP) proof. Persons skilled in the art, upon reviewing the entirety of this disclosure, will be aware of various forms of zero-knowledge proofs that may be used, singly or in combination, consistently with this disclosure.
Still referring to FIG. 2, in an embodiment, secure proof is implemented using a challenge-response protocol. In an embodiment, this may function as a one-time pad implementation; for instance, a manufacturer or other trusted party may record a series of outputs (“responses”) produced by a device possessing secret information, given a series of corresponding inputs (“challenges”), and store them securely. In an embodiment, a challenge-response protocol may be combined with key generation. A single key may be used in one or more digital signatures as described in further detail below, such as signatures used to receive and/or transfer possession of crypto-currency assets; the key may be discarded for future use after a set period of time. In an embodiment, varied inputs include variations in local physical parameters, such as fluctuations in local electromagnetic fields, radiation, temperature, and the like, such that an almost limitless variety of private keys may be so generated. Secure proof may include encryption of a challenge to produce the response, indicating possession of a secret key. Encryption may be performed using a private key of a public key cryptographic system, or using a private key of a symmetric cryptographic system; for instance, trusted party may verify response by decrypting an encryption of challenge or of another datum using either a symmetric or public-key cryptographic system, verifying that a stored key matches the key used for encryption as a function of at least a device-specific secret. Keys may be generated by random variation in selection of prime numbers, for instance for the purposes of a cryptographic system such as RSA that relies prime factoring difficulty. Keys may be generated by randomized selection of parameters for a seed in a cryptographic system, such as elliptic curve cryptography, which is generated from a seed. Keys may be used to generate exponents for a cryptographic system such as Diffie-Helman or ElGamal that are based on the discrete logarithm problem.
Still referring to FIG. 2, keys may be generated by random variation in selection of prime numbers, for instance for the purposes of a cryptographic system such as secret that relies prime factoring difficulty. Keys may be generated by randomized selection of parameters for a seed in a cryptographic system, such as elliptic curve cryptography, which is generated from a seed. Keys may be used to generate exponents for a cryptographic system such as Diffie-Helman or ElGamal that are based on the discrete logarithm problem.
Still referring to FIG. 2, cryptographic system may be configured to generate a session-specific secret. Session-specific secret may include a secret, which may be generated according to any process as described above, that uniquely identifies a particular instance of an attested boot and/or loading of software monitor. Session-specific secret may include without limitation a random number. Session-specific secret may be converted to and/or added to a secure proof, verification datum, and/or key according to any process as described above for generation of a secure proof, verification datum, and/or key from a secret or “seed”; session-specific secret, a key produced therewith, verification datum produced therewith, and/or a secure proof produced therewith may be combined with module-specific secret, a key produced therewith, a verification datum produced therewith, and/or a secure proof produced therewith, such that, for instance, a software monitor and/or other signed element of attested boot and/or attested computing may include secure proof both of session-specific secret and of module-specific secret. In an embodiment, session-specific secret may be usable to identify that a given computation has been performed during a particular attested session, just as device-specific secret may be used to demonstrate that a particular computation has been produced by a particular device. This may be used, e.g., where secure computing module and/or any component thereof is stateless, such as where any such element has no memory that may be overwritten and/or corrupted.
Still referring to FIG. 2, a “digital signature,” as used herein, includes a secure proof of possession of a secret by a signing device, as performed on provided element of data, known as a “message.” A message may include an encrypted mathematical representation of a file or other set of data using the private key of a public key cryptographic system. Secure proof may include any form of secure proof as described above, including without limitation encryption using a private key of a public key cryptographic system as described above. Signature may be verified using a verification datum suitable for verification of a secure proof; for instance, where secure proof is enacted by encrypting message using a private key of a public key cryptographic system, verification may include decrypting the encrypted message using the corresponding public key and comparing the decrypted representation to a purported match that was not encrypted; if the signature protocol is well-designed and implemented correctly, this means the ability to create the digital signature is equivalent to possession of the private decryption key and/or device-specific secret. Likewise, if a message making up a mathematical representation of file is well-designed and implemented correctly, any alteration of the file may result in a mismatch with the digital signature; the mathematical representation may be produced using an alteration-sensitive, reliably reproducible algorithm, such as a hashing algorithm as described above. A mathematical representation to which the signature may be compared may be included with signature, for verification purposes; in other embodiments, the algorithm used to produce the mathematical representation may be publicly available, permitting the easy reproduction of the mathematical representation corresponding to any file.
Still referring to FIG. 2, in some embodiments, digital signatures may be combined with or incorporated in digital certificates. In one embodiment, a digital certificate is a file that conveys information and links the conveyed information to a “certificate authority” that is the issuer of a public key in a public key cryptographic system. Certificate authority in some embodiments contains data conveying the certificate authority's authorization for the recipient to perform a task. The authorization may be the authorization to access a given datum. The authorization may be the authorization to access a given process. In some embodiments, the certificate may identify the certificate authority. The digital certificate may include a digital signature.
Still referring to FIG. 2, in some embodiments, a third party such as a certificate authority (CA) is available to verify that the possessor of the private key is a particular entity; thus, if the certificate authority may be trusted, and the private key has not been stolen, the ability of an entity to produce a digital signature confirms the identity of the entity and links the file to the entity in a verifiable way. Digital signature may be incorporated in a digital certificate, which is a document authenticating the entity possessing the private key by authority of the issuing certificate authority and signed with a digital signature created with that private key and a mathematical representation of the remainder of the certificate. In other embodiments, digital signature is verified by comparing the digital signature to one known to have been created by the entity that purportedly signed the digital signature; for instance, if the public key that decrypts the known signature also decrypts the digital signature, the digital signature may be considered verified. Digital signature may also be used to verify that the file has not been altered since the formation of the digital signature.
Still referring to FIG. 2, a secure element may include a time-varying secure element, which may have a time limit after which time-varying secure element is no longer valid. Time limit may be calculated from an initial time, which may be a datum linked to a particular timestamp or other value representing a fixed moment in time, associated with time-varying secure element; initial time may be a time of creation, a time of verification, or other significant time relating to validity of time-varying token. Initial time may include, without limitation, a timestamp, which may include a secure timestamp, and/or a datum linked to a secure timestamp, such as a cryptographic hash of the secure timestamp or the like. As used herein, a “secure timestamp” is an element of data that immutably and verifiably records a particular time, for instance by incorporating a secure proof, cryptographic hash, or other process whereby a party that attempts to modify the time and/or date of the secure timestamp will be unable to do so without the alteration being detected as fraudulent.
Still referring to FIG. 2, a process may include performing a trusted time evaluation of a variable. As a non-limiting example, secure proof may be generated using a secure timestamp. Generating the secure timestamp may include digitally signing the secure timestamp using any digital signature protocol as described above. In one embodiment authenticity of received data signals is established by utilizing a chain of attestation via one or more attestation schemes (in nonlimiting example, via direct anonymous attestation (DAA)) to verify that a secure element is an authentic secure element that has the property of attested time. Generating a secure timestamp may be used to weed out spoofers or “man in the middle attacks.”
Still referring to FIG. 2, secure timestamp may record the current time in a hash chain. In an embodiment, a hash chain includes a series of hashes, each produced from a message containing a current time stamp (i.e., current at the moment the hash is created) and the previously created hash, which may be combined with one or more additional data; additional data may include a random number. Additional data may be hashed into a Merkle tree or other hash tree, such that a root of the hash tree may be incorporated in an entry in hash chain. It may be computationally infeasible to reverse hash any one entry, particularly in the amount of time during which its currency is important; it may be astronomically difficult to reverse hash the entire chain, rendering illegitimate or fraudulent timestamps referring to the hash chain all but impossible. A purported entry may be evaluated by hashing its corresponding message. In an embodiment, the trusted timestamping procedure utilized is substantially similar to the RFC 3161 standard. In this scenario, the received data signals are locally processed at the listener device by a one-way function, e.g. a hash function, and this hashed output data is sent to a timestamping authority (TSA). The use of secure timestamps as described herein may enable systems and methods as described herein to instantiate attested time. Attested time is the property that a device incorporating a local reference clock may hash data, e.g. [data], along with the local timestamp of the device. Attested time may additionally incorporate attested identity, attested device architecture and other pieces of information identifying properties of the attesting device. In one embodiment, secure timestamp is generated by a trusted third party (TTP) that appends a timestamp to the hashed output data, applies the TSA private key to sign the hashed output data concatenated to the timestamp, and returns this signed, a.k.a. trusted timestamped data back to the listener device. Alternatively, or additionally, one or more additional participants, such as other verifying nodes, may evaluate secure timestamp, or other party generating secure timestamp and/or perform threshold cryptography with a plurality of such parties, each of which may have performed an embodiment of method to produce a secure timestamp. In an embodiment, a data store or other parties authenticating digitally signed assertions, devices, and/or user credentials may perform authentication at least in part by evaluating timeliness of entry and/or generation data as assessed against secure timestamp. In an embodiment, secure proof is generated using an attested computing protocol; this may be performed, as a non-limiting example, using any protocol for attested computing as described above.
Still referring to FIG. 2, “immutable sequential listing,” as used in this disclosure, is a data structure that places data entries in a fixed sequential arrangement, such as a temporal sequence of entries and/or blocks thereof, where the sequential arrangement, once established, cannot be altered or reordered. An immutable sequential listing may be, include and/or implement an immutable ledger, where data entries that have been posted to the immutable sequential listing cannot be altered.
Still referring to FIG. 2, an exemplary embodiment of an immutable sequential listing 160 is illustrated. Data elements may be listed in immutable sequential listing 160; data elements may include any form of data, including textual data, image data, encrypted data, cryptographically hashed data, and the like. Data elements may include, without limitation, one or more at least a digitally signed assertion. In one embodiment, a digitally signed assertion 204 is a collection of textual data signed using a secure proof as described in further detail below; secure proof may include, without limitation, a digital signature as described above. Collection of textual data may contain any textual data, including without limitation American Standard Code for Information Interchange (ASCII), Unicode, or similar computer-encoded textual data, any alphanumeric data, punctuation, diacritical mark, or any character or other marking used in any writing system to convey information, in any form, including any plaintext or cyphertext data; in an embodiment, collection of textual data may be encrypted, or may be a hash of other data, such as a root or node of a Merkle tree or hash tree, or a hash of any other information desired to be recorded in some fashion using a digitally signed assertion 204. In an embodiment, collection of textual data states that the owner of a certain transferable item represented in a digitally signed assertion 204 register is transferring that item to the owner of an address. A digitally signed assertion 204 may be signed by a digital signature created using the private key associated with the owner's public key, as described above.
Still referring to FIG. 2, a digitally signed assertion 204 may describe a transfer of virtual currency, such as crypto-currency as described below. The virtual currency may be a digital currency. Item of value may be a transfer of trust, for instance represented by a statement vouching for the identity or trustworthiness of the first entity. Item of value may be an interest in a fungible negotiable financial instrument representing ownership in a public or private corporation, a creditor relationship with a governmental body or a corporation, rights to ownership represented by an option, derivative financial instrument, commodity, debt-backed security such as a bond or debenture or other security as described in further detail below. A resource may be a physical machine e.g. a ride share vehicle or any other asset. A digitally signed assertion 204 may describe the transfer of a physical good; for instance, a digitally signed assertion 204 may describe the sale of a product. In some embodiments, a transfer nominally of one item may be used to represent a transfer of another item; for instance, a transfer of virtual currency may be interpreted as representing a transfer of an access right; conversely, where the item nominally transferred is something other than virtual currency, the transfer itself may still be treated as a transfer of virtual currency, having value that depends on many potential factors including the value of the item nominally transferred and the monetary value attendant to having the output of the transfer moved into a particular user's control. The item of value may be associated with a digitally signed assertion 204 by means of an exterior protocol, such as the COLORED COINS created according to protocols developed by The Colored Coins Foundation, the MASTERCOIN protocol developed by the Mastercoin Foundation, or the ETHEREUM platform offered by the Stiftung Ethereum Foundation of Baar, Switzerland, the Thunder protocol developed by Thunder Consensus, or any other protocol.
Still referring to FIG. 2, in one embodiment, an address is a textual datum identifying the recipient of virtual currency or another item of value in a digitally signed assertion 204. In some embodiments, address is linked to a public key, the corresponding private key of which is owned by the recipient of a digitally signed assertion 204. For instance, address may be the public key. Address may be a representation, such as a hash, of the public key. Address may be linked to the public key in memory of a computing device, for instance via a “wallet shortener” protocol. Where address is linked to a public key, a transferee in a digitally signed assertion 204 may record a subsequent a digitally signed assertion 204 transferring some or all of the value transferred in the first a digitally signed assertion 204 to a new address in the same manner. A digitally signed assertion 204 may contain textual information that is not a transfer of some item of value in addition to, or as an alternative to, such a transfer. For instance, as described in further detail below, a digitally signed assertion 204 may indicate a confidence level associated with a distributed storage node as described in further detail below.
Still referring to FIG. 2, in an embodiment, immutable sequential listing 160 records a series of at least a posted content in a way that preserves the order in which the at least a posted content took place. Temporally sequential listing may be accessible at any of various security settings; for instance, and without limitation, temporally sequential listing may be readable and modifiable publicly, may be publicly readable but writable only by entities and/or devices having access privileges established by password protection, confidence level, or any device authentication procedure or facilities described herein, or may be readable and/or writable only by entities and/or devices having such access privileges. Access privileges may exist in more than one level, including, without limitation, a first access level or community of permitted entities and/or devices having ability to read, and a second access level or community of permitted entities and/or devices having ability to write; first and second community may be overlapping or non-overlapping. In an embodiment, posted content and/or immutable sequential listing 160 may be stored as one or more zero knowledge sets (ZKS), Private Information Retrieval (PIR) structure, or any other structure that allows checking of membership in a set by querying with specific properties. Such database may incorporate protective measures to ensure that malicious actors may not query the database repeatedly in an effort to narrow the members of a set to reveal uniquely identifying information of a given posted content.
Still referring to FIG. 2, immutable sequential listing 160 may preserve the order in which the at least a posted content took place by listing them in chronological order; alternatively or additionally, immutable sequential listing 160 may organize digitally signed assertions 204 into sub-listings 208 such as “blocks” in a blockchain, which may be themselves collected in a temporally sequential order; digitally signed assertions 204 within a sub-listing 208 may or may not be temporally sequential. The ledger may preserve the order in which at least a posted content took place by listing them in sub-listings 208 and placing the sub-listings 208 in chronological order. The immutable sequential listing 160 may be a distributed, consensus-based ledger, such as those operated according to the protocols promulgated by Ripple Labs, Inc., of San Francisco, Calif., or the Stellar Development Foundation, of San Francisco, Calif, or of Thunder Consensus. In some embodiments, the ledger is a secured ledger; in one embodiment, a secured ledger is a ledger having safeguards against alteration by unauthorized parties. The ledger may be maintained by a proprietor, such as a system administrator on a server, that controls access to the ledger; for instance, the user account controls may allow contributors to the ledger to add at least a posted content to the ledger, but may not allow any users to alter at least a posted content that have been added to the ledger. In some embodiments, ledger is cryptographically secured; in one embodiment, a ledger is cryptographically secured where each link in the chain contains encrypted or hashed information that makes it practically infeasible to alter the ledger without betraying that alteration has taken place, for instance by requiring that an administrator or other party sign new additions to the chain with a digital signature. Immutable sequential listing 160 may be incorporated in, stored in, or incorporate, any suitable data structure, including without limitation any database, datastore, file structure, distributed hash table, directed acyclic graph or the like. In some embodiments, the timestamp of an entry is cryptographically secured and validated via trusted time, either directly on the chain or indirectly by utilizing a separate chain. In one embodiment the validity of timestamp is provided using a time stamping authority as described in the RFC 3161 standard for trusted timestamps, or in the ANSI ASC x9.95 standard. In another embodiment, the trusted time ordering is provided by a group of entities collectively acting as the time stamping authority with a requirement that a threshold number of the group of authorities sign the timestamp.
Still referring to FIG. 2, in some embodiments, immutable sequential listing 160, once formed, may be inalterable by any party, no matter what access rights that party possesses. For instance, immutable sequential listing 160 may include a hash chain, in which data is added during a successive hashing process to ensure non-repudiation. Immutable sequential listing 160 may include a block chain. In one embodiment, a block chain is immutable sequential listing 160 that records one or more new at least a posted content in a data item known as a sub-listing 208 or “block.” An example of a block chain is the BITCOIN block chain used to record BITCOIN transactions and values. Sub-listings 208 may be created in a way that places the sub-listings 208 in chronological order and link each sub-listing 208 to a previous sub-listing 208 in the chronological order so that any computing device may traverse the sub-listings 208 in reverse chronological order to verify any at least a posted content listed in the block chain. Each new sub-listing 208 may be required to contain a cryptographic hash describing the previous sub-listing 208. In some embodiments, the block chain contains a single first sub-listing 208 sometimes known as a “genesis block.”
Still referring to FIG. 2, the creation of a new sub-listing 208 may be computationally expensive; for instance, the creation of a new sub-listing 208 may be designed by a “proof of work” protocol accepted by all participants in forming the immutable sequential listing 160 to take a powerful set of computing devices a certain period of time to produce. Where one sub-listing 208 takes less time for a given set of computing devices to produce the sub-listing 208 protocol may adjust the algorithm to produce the next sub-listing 208 so that it will require more steps; where one sub-listing 208 takes more time for a given set of computing devices to produce the sub-listing 208 protocol may adjust the algorithm to produce the next sub-listing 208 so that it will require fewer steps. As an example, protocol may require a new sub-listing 208 to contain a cryptographic hash describing its contents; the cryptographic hash may be required to satisfy a mathematical condition, achieved by having the sub-listing 208 contain a number, called a nonce, whose value is determined after the fact by the discovery of the hash that satisfies the mathematical condition. Continuing the example, the protocol may be able to adjust the mathematical condition so that the discovery of the hash describing a sub-listing 208 and satisfying the mathematical condition requires more or less steps, depending on the outcome of the previous hashing attempt. Mathematical condition, as an example, might be that the hash contains a certain number of leading zeros and a hashing algorithm that requires more steps to find a hash containing a greater number of leading zeros, and fewer steps to find a hash containing a lesser number of leading zeros. In some embodiments, production of a new sub-listing 208 according to the protocol is known as “mining.” The creation of a new sub-listing 208 may be designed by a “proof of stake” protocol as will be apparent to those skilled in the art upon reviewing the entirety of this disclosure.
Still referring to FIG. 2, in some embodiments, protocol also creates an incentive to mine new sub-listings 208. The incentive may be financial; for instance, successfully mining a new sub-listing 208 may result in the person or entity that mines the sub-listing 208 receiving a predetermined amount of currency. The currency may be fiat currency. Currency may be cryptocurrency as defined below. In other embodiments, incentive may be redeemed for particular products or services; the incentive may be a gift certificate with a particular business, for instance. In some embodiments, incentive is sufficiently attractive to cause participants to compete for the incentive by trying to race each other to the creation of sub-listings 208 Each sub-listing 208 created in immutable sequential listing 160 may contain a record or at least a posted content describing one or more addresses that receive an incentive, such as virtual currency, as the result of successfully mining the sub-listing 208.
Still referring to FIG. 2, where two entities simultaneously create new sub-listings 208, immutable sequential listing 160 may develop a fork; protocol may determine which of the two alternate branches in the fork is the valid new portion of the immutable sequential listing 160 by evaluating, after a certain amount of time has passed, which branch is longer. “Length” may be measured according to the number of sub-listings 208 in the branch. Length may be measured according to the total computational cost of producing the branch. Protocol may treat only at least a posted content contained the valid branch as valid at least a posted content. When a branch is found invalid according to this protocol, at least a posted content registered in that branch may be recreated in a new sub-listing 208 in the valid branch; the protocol may reject “double spending” at least a posted content that transfer the same virtual currency that another at least a posted content in the valid branch has already transferred. As a result, in some embodiments the creation of fraudulent at least a posted content requires the creation of a longer immutable sequential listing 160 branch by the entity attempting the fraudulent at least a posted content than the branch being produced by the rest of the participants; as long as the entity creating the fraudulent at least a posted content is likely the only one with the incentive to create the branch containing the fraudulent at least a posted content, the computational cost of the creation of that branch may be practically infeasible, guaranteeing the validity of all at least a posted content in the immutable sequential listing 160.
Still referring to FIG. 2, additional data linked to at least a posted content may be incorporated in sub-listings 208 in the immutable sequential listing 160; for instance, data may be incorporated in one or more fields recognized by block chain protocols that permit a person or computer forming a at least a posted content to insert additional data in the immutable sequential listing 160. In some embodiments, additional data is incorporated in an unspendable at least a posted content field. For instance, the data may be incorporated in an OP_RETURN within the BITCOIN block chain. In other embodiments, additional data is incorporated in one signature of a multi-signature at least a posted content. In an embodiment, a multi-signature at least a posted content is at least a posted content to two or more addresses. In some embodiments, the two or more addresses are hashed together to form a single address, which is signed in the digital signature of the at least a posted content. In other embodiments, the two or more addresses are concatenated. In some embodiments, two or more addresses may be combined by a more complicated process, such as the creation of a Merkle tree or the like. In some embodiments, one or more addresses incorporated in the multi-signature at least a posted content are typical crypto-currency addresses, such as addresses linked to public keys as described above, while one or more additional addresses in the multi-signature at least a posted content contain additional data related to the at least a posted content; for instance, the additional data may indicate the purpose of the at least a posted content, aside from an exchange of virtual currency, such as the item for which the virtual currency was exchanged. In some embodiments, additional information may include network statistics for a given node of network, such as a distributed storage node, e.g. the latencies to nearest neighbors in a network graph, the identities or identifying information of neighboring nodes in the network graph, the trust level and/or mechanisms of trust (e.g. certificates of physical encryption keys, certificates of software encryption keys, (in non-limiting example certificates of software encryption may indicate the firmware version, manufacturer, hardware version and the like), certificates from a trusted third party, certificates from a decentralized anonymous authentication procedure, and other information quantifying the trusted status of the distributed storage node) of neighboring nodes in the network graph, IP addresses, GPS coordinates, and other information informing location of the node and/or neighboring nodes, geographically and/or within the network graph. In some embodiments, additional information may include history and/or statistics of neighboring nodes with which the node has interacted. In some embodiments, this additional information may be encoded directly, via a hash, hash tree or other encoding.
Still referring to FIG. 2, in some embodiments, virtual currency is traded as a crypto-currency. In one embodiment, a crypto-currency is a digital, currency such as Bitcoins, Peercoins, Namecoins, and Litecoins. Crypto-currency may be a clone of another crypto-currency. The crypto-currency may be an “alt-coin.” Crypto-currency may be decentralized, with no particular entity controlling it; the integrity of the crypto-currency may be maintained by adherence by its participants to established protocols for exchange and for production of new currency, which may be enforced by software implementing the crypto-currency. Crypto-currency may be centralized, with its protocols enforced or hosted by a particular entity. For instance, crypto-currency may be maintained in a centralized ledger, as in the case of the XRP currency of Ripple Labs, Inc., of San Francisco, Calif. In lieu of a centrally controlling authority, such as a national bank, to manage currency values, the number of units of a particular crypto-currency may be limited; the rate at which units of crypto-currency enter the market may be managed by a mutually agreed-upon process, such as creating new units of currency when mathematical puzzles are solved, the degree of difficulty of the puzzles being adjustable to control the rate at which new units enter the market. Mathematical puzzles may be the same as the algorithms used to make productions of sub-listings 208 in a block chain computationally challenging; the incentive for producing sub-listings 208 may include the grant of new crypto-currency to the miners. Quantities of crypto-currency may be exchanged using at least a posted content as described above.
Referring now to FIG. 3, an exemplary embodiment of a machine-learning module 300 that may perform one or more machine-learning processes as described in this disclosure is illustrated. Machine-learning module may perform determinations, classification, and/or analysis steps, methods, processes, or the like as described in this disclosure using machine learning processes. A “machine learning process,” as used in this disclosure, is a process that automatedly uses training data 304 to generate an algorithm instantiated in hardware or software logic, data structures, and/or functions that will be performed by a computing device/module to produce outputs 308 given data provided as inputs 312; this is in contrast to a non-machine learning software program where the commands to be executed are determined in advance by a user and written in a programming language.
Still referring to FIG. 3, “training data,” as used herein, is data containing correlations that a machine-learning process may use to model relationships between two or more categories of data elements. For instance, and without limitation, training data 304 may include a plurality of data entries, also known as “training examples,” each entry representing a set of data elements that were recorded, received, and/or generated together; data elements may be correlated by shared existence in a given data entry, by proximity in a given data entry, or the like. Multiple data entries in training data 304 may evince one or more trends in correlations between categories of data elements; for instance, and without limitation, a higher value of a first data element belonging to a first category of data element may tend to correlate to a higher value of a second data element belonging to a second category of data element, indicating a possible proportional or other mathematical relationship linking values belonging to the two categories. Multiple categories of data elements may be related in training data 304 according to various correlations; correlations may indicate causative and/or predictive links between categories of data elements, which may be modeled as relationships such as mathematical relationships by machine-learning processes as described in further detail below. Training data 304 may be formatted and/or organized by categories of data elements, for instance by associating data elements with one or more descriptors corresponding to categories of data elements. As a non-limiting example, training data 304 may include data entered in standardized forms by persons or processes, such that entry of a given data element in a given field in a form may be mapped to one or more descriptors of categories. Elements in training data 304 may be linked to descriptors of categories by tags, tokens, or other data elements; for instance, and without limitation, training data 304 may be provided in fixed-length formats, formats linking positions of data to categories such as comma-separated value (CSV) formats and/or self-describing formats such as extensible markup language (XML), JavaScript Object Notation (JSON), or the like, enabling processes or devices to detect categories of data.
Alternatively or additionally, and continuing to refer to FIG. 3, training data 304 may include one or more elements that are not categorized; that is, training data 304 may not be formatted or contain descriptors for some elements of data. Machine-learning algorithms and/or other processes may sort training data 304 according to one or more categorizations using, for instance, natural language processing algorithms, tokenization, detection of correlated values in raw data and the like; categories may be generated using correlation and/or other processing algorithms. As a non-limiting example, in a corpus of text, phrases making up a number “n” of compound words, such as nouns modified by other nouns, may be identified according to a statistically significant prevalence of n-grams containing such words in a particular order; such an n-gram may be categorized as an element of language such as a “word” to be tracked similarly to single words, generating a new category as a result of statistical analysis. Similarly, in a data entry including some textual data, a person's name may be identified by reference to a list, dictionary, or other compendium of terms, permitting ad-hoc categorization by machine-learning algorithms, and/or automated association of data in the data entry with descriptors or into a given format. The ability to categorize data entries automatedly may enable the same training data 304 to be made applicable for two or more distinct machine-learning algorithms as described in further detail below. Training data 304 used by machine-learning module 300 may correlate any input data as described in this disclosure to any output data as described in this disclosure. As a non-limiting illustrative example, a training dataset may include model discussion data and model prompts, associated with model user understanding scores.
Further referring to FIG. 3, training data may be filtered, sorted, and/or selected using one or more supervised and/or unsupervised machine-learning processes and/or models as described in further detail below; such models may include without limitation a training data classifier 316. Training data classifier 316 may include a “classifier,” which as used in this disclosure is a machine-learning model as defined below, such as a data structure representing and/or using a mathematical model, neural net, or program generated by a machine learning algorithm known as a “classification algorithm,” as described in further detail below, that sorts inputs into categories or bins of data, outputting the categories or bins of data and/or labels associated therewith. A classifier may be configured to output at least a datum that labels or otherwise identifies a set of data that are clustered together, found to be close under a distance metric as described below, or the like. A distance metric may include any norm, such as, without limitation, a Pythagorean norm. Machine-learning module 300 may generate a classifier using a classification algorithm, defined as a processes whereby a computing device and/or any module and/or component operating thereon derives a classifier from training data 304. Classification may be performed using, without limitation, linear classifiers such as without limitation logistic regression and/or naive Bayes classifiers, nearest neighbor classifiers such as k-nearest neighbors classifiers, support vector machines, least squares support vector machines, fisher's linear discriminant, quadratic classifiers, decision trees, boosted trees, random forest classifiers, learning vector quantization, and/or neural network-based classifiers. As a non-limiting example, training data classifier 316 may classify elements of training data to particular grades (such as high school freshman, sophomore, junior, or senior), or particular subject matter (such as history, English, biology, math, or a particular sub-category of those subjects).
With further reference to FIG. 3, training examples for use as training data may be selected from a population of potential examples according to cohorts relevant to an analytical problem to be solved, a classification task, or the like. Alternatively or additionally, training data may be selected to span a set of likely circumstances or inputs for a machine-learning model and/or process to encounter when deployed. For instance, and without limitation, for each category of input data to a machine-learning process or model that may exist in a range of values in a population of phenomena such as images, user data, process data, physical data, or the like, a computing device, processor, and/or machine-learning model may select training examples representing each possible value on such a range and/or a representative sample of values on such a range. Selection of a representative sample may include selection of training examples in proportions matching a statistically determined and/or predicted distribution of such values according to relative frequency, such that, for instance, values encountered more frequently in a population of data so analyzed are represented by more training examples than values that are encountered less frequently. Alternatively or additionally, a set of training examples may be compared to a collection of representative values in a database and/or presented to a user, so that a process can detect, automatically or via user input, one or more values that are not included in the set of training examples. Computing device, processor, and/or module may automatically generate a missing training example; this may be done by receiving and/or retrieving a missing input and/or output value and correlating the missing input and/or output value with a corresponding output and/or input value collocated in a data record with the retrieved value, provided by a user and/or other device, or the like.
Still referring to FIG. 3, computer, processor, and/or module may be configured to sanitize training data. “Sanitizing” training data, as used in this disclosure, is a process whereby training examples are removed that interfere with convergence of a machine-learning model and/or process to a useful result. For instance, and without limitation, a training example may include an input and/or output value that is an outlier from typically encountered values, such that a machine-learning algorithm using the training example will be adapted to an unlikely amount as an input and/or output; a value that is more than a threshold number of standard deviations away from an average, mean, or expected value, for instance, may be eliminated. Alternatively or additionally, one or more training examples may be identified as having poor quality data, where “poor quality” is defined as having a signal to noise ratio below a threshold value.
As a non-limiting example, and with further reference to FIG. 3, images used to train an image classifier or other machine-learning model and/or process that takes images as inputs or generates images as outputs may be rejected if image quality is below a threshold value. For instance, and without limitation, computing device, processor, and/or module may perform blur detection, and eliminate one or more Blur detection may be performed, as a non-limiting example, by taking Fourier transform, or an approximation such as a Fast Fourier Transform (FFT) of the image and analyzing a distribution of low and high frequencies in the resulting frequency-domain depiction of the image; numbers of high-frequency values below a threshold level may indicate blurriness. As a further non-limiting example, detection of blurriness may be performed by convolving an image, a channel of an image, or the like with a Laplacian kernel; this may generate a numerical score reflecting a number of rapid changes in intensity shown in the image, such that a high score indicates clarity and a low score indicates blurriness. Blurriness detection may be performed using a gradient-based operator, which measures operators based on the gradient or first derivative of an image, based on the hypothesis that rapid changes indicate sharp edges in the image, and thus are indicative of a lower degree of blurriness. Blur detection may be performed using Wavelet-based operator, which takes advantage of the capability of coefficients of the discrete wavelet transform to describe the frequency and spatial content of images. Blur detection may be performed using statistics-based operators take advantage of several image statistics as texture descriptors in order to compute a focus level. Blur detection may be performed by using discrete cosine transform (DCT) coefficients in order to compute a focus level of an image from its frequency content.
Continuing to refer to FIG. 3, computing device, processor, and/or module may be configured to precondition one or more training examples. For instance, and without limitation, where a machine learning model and/or process has one or more inputs and/or outputs requiring, transmitting, or receiving a certain number of bits, samples, or other units of data, one or more training examples' elements to be used as or compared to inputs and/or outputs may be modified to have such a number of units of data. For instance, a computing device, processor, and/or module may convert a smaller number of units, such as in a low pixel count image, into a desired number of units, for instance by upsampling and interpolating. As a non-limiting example, a low pixel count image may have 100 pixels, however a desired number of pixels may be 128. Processor may interpolate the low pixel count image to convert the 100 pixels into 128 pixels. It should also be noted that one of ordinary skill in the art, upon reading this disclosure, would know the various methods to interpolate a smaller number of data units such as samples, pixels, bits, or the like to a desired number of such units. In some instances, a set of interpolation rules may be trained by sets of highly detailed inputs and/or outputs and corresponding inputs and/or outputs downsampled to smaller numbers of units, and a neural network or other machine learning model that is trained to predict interpolated pixel values using the training data. As a non-limiting example, a sample input and/or output, such as a sample picture, with sample-expanded data units (e.g., pixels added between the original pixels) may be input to a neural network or machine-learning model and output a pseudo replica sample-picture with dummy values assigned to pixels between the original pixels based on a set of interpolation rules. As a non-limiting example, in the context of an image classifier, a machine-learning model may have a set of interpolation rules trained by sets of highly detailed images and images that have been downsampled to smaller numbers of pixels, and a neural network or other machine learning model that is trained using those examples to predict interpolated pixel values in a facial picture context. As a result, an input with sample-expanded data units (the ones added between the original data units, with dummy values) may be run through a trained neural network and/or model, which may fill in values to replace the dummy values. Alternatively or additionally, processor, computing device, and/or module may utilize sample expander methods, a low-pass filter, or both. As used in this disclosure, a “low-pass filter” is a filter that passes signals with a frequency lower than a selected cutoff frequency and attenuates signals with frequencies higher than the cutoff frequency. The exact frequency response of the filter depends on the filter design. Computing device, processor, and/or module may use averaging, such as luma or chroma averaging in images, to fill in data units in between original data units.
In some embodiments, and with continued reference to FIG. 3, computing device, processor, and/or module may down-sample elements of a training example to a desired lower number of data elements. As a non-limiting example, a high pixel count image may have 256 pixels, however a desired number of pixels may be 128. Processor may down-sample the high pixel count image to convert the 256 pixels into 128 pixels. In some embodiments, processor may be configured to perform downsampling on data. Downsampling, also known as decimation, may include removing every Nth entry in a sequence of samples, all but every Nth entry, or the like, which is a process known as “compression,” and may be performed, for instance by an N-sample compressor implemented using hardware or software. Anti-aliasing and/or anti-imaging filters, and/or low-pass filters, may be used to clean up side-effects of compression.
Still referring to FIG. 3, machine-learning module 300 may be configured to perform a lazy-learning process 320 and/or protocol, which may alternatively be referred to as a “lazy loading” or “call-when-needed” process and/or protocol, may be a process whereby machine learning is conducted upon receipt of an input to be converted to an output, by combining the input and training set to derive the algorithm to be used to produce the output on demand. For instance, an initial set of simulations may be performed to cover an initial heuristic and/or “first guess” at an output and/or relationship. As a non-limiting example, an initial heuristic may include a ranking of associations between inputs and elements of training data 304. Heuristic may include selecting some number of highest-ranking associations and/or training data 304 elements. Lazy learning may implement any suitable lazy learning algorithm, including without limitation a K-nearest neighbors algorithm, a lazy naïve Bayes algorithm, or the like; persons skilled in the art, upon reviewing the entirety of this disclosure, will be aware of various lazy-learning algorithms that may be applied to generate outputs as described in this disclosure, including without limitation lazy learning applications of machine-learning algorithms as described in further detail below.
Alternatively or additionally, and with continued reference to FIG. 3, machine-learning processes as described in this disclosure may be used to generate machine-learning models 324. A “machine-learning model,” as used in this disclosure, is a data structure representing and/or instantiating a mathematical and/or algorithmic representation of a relationship between inputs and outputs, as generated using any machine-learning process including without limitation any process as described above, and stored in memory; an input is submitted to a machine-learning model 324 once created, which generates an output based on the relationship that was derived. For instance, and without limitation, a linear regression model, generated using a linear regression algorithm, may compute a linear combination of input data using coefficients derived during machine-learning processes to calculate an output datum. As a further non-limiting example, a machine-learning model 324 may be generated by creating an artificial neural network, such as a convolutional neural network comprising an input layer of nodes, one or more intermediate layers, and an output layer of nodes. Connections between nodes may be created via the process of “training” the network, in which elements from a training data 304 set are applied to the input nodes, a suitable training algorithm (such as Levenberg-Marquardt, conjugate gradient, simulated annealing, or other algorithms) is then used to adjust the connections and weights between nodes in adjacent layers of the neural network to produce the desired values at the output nodes. This process is sometimes referred to as deep learning.
Still referring to FIG. 3, machine-learning algorithms may include at least a supervised machine-learning process 328. At least a supervised machine-learning process 328, as defined herein, include algorithms that receive a training set relating a number of inputs to a number of outputs, and seek to generate one or more data structures representing and/or instantiating one or more mathematical relations relating inputs to outputs, where each of the one or more mathematical relations is optimal according to some criterion specified to the algorithm using some scoring function. For instance, a supervised learning algorithm may include discussion datum 148 and prompt 132 as described above as inputs, user understanding score 152 as an output, and a scoring function representing a desired form of relationship to be detected between inputs and outputs; scoring function may, for instance, seek to maximize the probability that a given input and/or combination of elements inputs is associated with a given output to minimize the probability that a given input is not associated with a given output. Scoring function may be expressed as a risk function representing an “expected loss” of an algorithm relating inputs to outputs, where loss is computed as an error function representing a degree to which a prediction generated by the relation is incorrect when compared to a given input-output pair provided in training data 304. Persons skilled in the art, upon reviewing the entirety of this disclosure, will be aware of various possible variations of at least a supervised machine-learning process 328 that may be used to determine relation between inputs and outputs. Supervised machine-learning processes may include classification algorithms as defined above.
With further reference to FIG. 3, training a supervised machine-learning process may include, without limitation, iteratively updating coefficients, biases, weights based on an error function, expected loss, and/or risk function. For instance, an output generated by a supervised machine-learning model using an input example in a training example may be compared to an output example from the training example; an error function may be generated based on the comparison, which may include any error function suitable for use with any machine-learning algorithm described in this disclosure, including a square of a difference between one or more sets of compared values or the like. Such an error function may be used in turn to update one or more weights, biases, coefficients, or other parameters of a machine-learning model through any suitable process including without limitation gradient descent processes, least-squares processes, and/or other processes described in this disclosure. This may be done iteratively and/or recursively to gradually tune such weights, biases, coefficients, or other parameters. Updating may be performed, in neural networks, using one or more back-propagation algorithms. Iterative and/or recursive updates to weights, biases, coefficients, or other parameters as described above may be performed until currently available training data is exhausted and/or until a convergence test is passed, where a “convergence test” is a test for a condition selected as indicating that a model and/or weights, biases, coefficients, or other parameters thereof has reached a degree of accuracy. A convergence test may, for instance, compare a difference between two or more successive errors or error function values, where differences below a threshold amount may be taken to indicate convergence. Alternatively or additionally, one or more errors and/or error function values evaluated in training iterations may be compared to a threshold.
Still referring to FIG. 3, a computing device, processor, and/or module may be configured to perform method, method step, sequence of method steps and/or algorithm described in reference to this figure, in any order and with any degree of repetition. For instance, a computing device, processor, and/or module may be configured to perform a single step, sequence and/or algorithm repeatedly until a desired or commanded outcome is achieved; repetition of a step or a sequence of steps may be performed iteratively and/or recursively using outputs of previous repetitions as inputs to subsequent repetitions, aggregating inputs and/or outputs of repetitions to produce an aggregate result, reduction or decrement of one or more variables such as global variables, and/or division of a larger processing task into a set of iteratively addressed smaller processing tasks. A computing device, processor, and/or module may perform any step, sequence of steps, or algorithm in parallel, such as simultaneously and/or substantially simultaneously performing a step two or more times using two or more parallel threads, processor cores, or the like; division of tasks between parallel threads and/or processes may be performed according to any protocol suitable for division of tasks between iterations. Persons skilled in the art, upon reviewing the entirety of this disclosure, will be aware of various ways in which steps, sequences of steps, processing tasks, and/or data may be subdivided, shared, or otherwise dealt with using iteration, recursion, and/or parallel processing.
Further referring to FIG. 3, machine learning processes may include at least an unsupervised machine-learning processes 332. An unsupervised machine-learning process, as used herein, is a process that derives inferences in datasets without regard to labels; as a result, an unsupervised machine-learning process may be free to discover any structure, relationship, and/or correlation provided in the data. Unsupervised processes 332 may not require a response variable; unsupervised processes 332 may be used to find interesting patterns and/or inferences between variables, to determine a degree of correlation between two or more variables, or the like.
Still referring to FIG. 3, machine-learning module 300 may be designed and configured to create a machine-learning model 324 using techniques for development of linear regression models. Linear regression models may include ordinary least squares regression, which aims to minimize the square of the difference between predicted outcomes and actual outcomes according to an appropriate norm for measuring such a difference (e.g. a vector-space distance norm); coefficients of the resulting linear equation may be modified to improve minimization. Linear regression models may include ridge regression methods, where the function to be minimized includes the least-squares function plus term multiplying the square of each coefficient by a scalar amount to penalize large coefficients. Linear regression models may include least absolute shrinkage and selection operator (LASSO) models, in which ridge regression is combined with multiplying the least-squares term by a factor of 1 divided by double the number of samples. Linear regression models may include a multi-task lasso model wherein the norm applied in the least-squares term of the lasso model is the Frobenius norm amounting to the square root of the sum of squares of all terms. Linear regression models may include the elastic net model, a multi-task elastic net model, a least angle regression model, a LARS lasso model, an orthogonal matching pursuit model, a Bayesian regression model, a logistic regression model, a stochastic gradient descent model, a perceptron model, a passive aggressive algorithm, a robustness regression model, a Huber regression model, or any other suitable model that may occur to persons skilled in the art upon reviewing the entirety of this disclosure. Linear regression models may be generalized in an embodiment to polynomial regression models, whereby a polynomial equation (e.g. a quadratic, cubic or higher-order equation) providing a best predicted output/actual output fit is sought; similar methods to those described above may be applied to minimize error functions, as will be apparent to persons skilled in the art upon reviewing the entirety of this disclosure.
Continuing to refer to FIG. 3, machine-learning algorithms may include, without limitation, linear discriminant analysis. Machine-learning algorithm may include quadratic discriminant analysis. Machine-learning algorithms may include kernel ridge regression. Machine-learning algorithms may include support vector machines, including without limitation support vector classification-based regression processes. Machine-learning algorithms may include stochastic gradient descent algorithms, including classification and regression algorithms based on stochastic gradient descent. Machine-learning algorithms may include nearest neighbors algorithms. Machine-learning algorithms may include various forms of latent space regularization such as variational regularization. Machine-learning algorithms may include Gaussian processes such as Gaussian Process Regression. Machine-learning algorithms may include cross-decomposition algorithms, including partial least squares and/or canonical correlation analysis. Machine-learning algorithms may include naïve Bayes methods. Machine-learning algorithms may include algorithms based on decision trees, such as decision tree classification or regression algorithms. Machine-learning algorithms may include ensemble methods such as bagging meta-estimator, forest of randomized trees, AdaBoost, gradient tree boosting, and/or voting classifier methods. Machine-learning algorithms may include neural net algorithms, including convolutional neural net processes.
Still referring to FIG. 3, a machine-learning model and/or process may be deployed or instantiated by incorporation into a program, apparatus, system and/or module. For instance, and without limitation, a machine-learning model, neural network, and/or some or all parameters thereof may be stored and/or deployed in any memory or circuitry. Parameters such as coefficients, weights, and/or biases may be stored as circuit-based constants, such as arrays of wires and/or binary inputs and/or outputs set at logic “1” and “0” voltage levels in a logic circuit to represent a number according to any suitable encoding system including twos complement or the like or may be stored in any volatile and/or non-volatile memory. Similarly, mathematical operations and input and/or output of data to or from models, neural network layers, or the like may be instantiated in hardware circuitry and/or in the form of instructions in firmware, machine-code such as binary operation code instructions, assembly language, or any higher-order programming language. Any technology for hardware and/or software instantiation of memory, instructions, data structures, and/or algorithms may be used to instantiate a machine-learning process and/or model, including without limitation any combination of production and/or configuration of non-reconfigurable hardware elements, circuits, and/or modules such as without limitation ASICs, production and/or configuration of reconfigurable hardware elements, circuits, and/or modules such as without limitation FPGAs, production and/or of non-reconfigurable and/or configuration non-rewritable memory elements, circuits, and/or modules such as without limitation non-rewritable ROM, production and/or configuration of reconfigurable and/or rewritable memory elements, circuits, and/or modules such as without limitation rewritable ROM or other memory technology described in this disclosure, and/or production and/or configuration of any computing device and/or component thereof as described in this disclosure. Such deployed and/or instantiated machine-learning model and/or algorithm may receive inputs from any other process, module, and/or component described in this disclosure, and produce outputs to any other process, module, and/or component described in this disclosure.
Continuing to refer to FIG. 3, any process of training, retraining, deployment, and/or instantiation of any machine-learning model and/or algorithm may be performed and/or repeated after an initial deployment and/or instantiation to correct, refine, and/or improve the machine-learning model and/or algorithm. Such retraining, deployment, and/or instantiation may be performed as a periodic or regular process, such as retraining, deployment, and/or instantiation at regular elapsed time periods, after some measure of volume such as a number of bytes or other measures of data processed, a number of uses or performances of processes described in this disclosure, or the like, and/or according to a software, firmware, or other update schedule. Alternatively or additionally, retraining, deployment, and/or instantiation may be event-based, and may be triggered, without limitation, by user inputs indicating sub-optimal or otherwise problematic performance and/or by automated field testing and/or auditing processes, which may compare outputs of machine-learning models and/or algorithms, and/or errors and/or error functions thereof, to any thresholds, convergence tests, or the like, and/or may compare outputs of processes described herein to similar thresholds, convergence tests or the like. Event-based retraining, deployment, and/or instantiation may alternatively or additionally be triggered by receipt and/or generation of one or more new training examples; a number of new training examples may be compared to a preconfigured threshold, where exceeding the preconfigured threshold may trigger retraining, deployment, and/or instantiation.
Still referring to FIG. 3, retraining and/or additional training may be performed using any process for training described above, using any currently or previously deployed version of a machine-learning model and/or algorithm as a starting point. Training data for retraining may be collected, preconditioned, sorted, classified, sanitized or otherwise processed according to any process described in this disclosure. Training data may include, without limitation, training examples including inputs and correlated outputs used, received, and/or generated from any version of any system, module, machine-learning model or algorithm, apparatus, and/or method described in this disclosure; such examples may be modified and/or labeled according to user feedback or other processes to indicate desired results, and/or may have actual or measured results from a process being modeled and/or predicted by system, module, machine-learning model or algorithm, apparatus, and/or method as “desired” results to be compared to outputs for training processes as described above.
Redeployment may be performed using any reconfiguring and/or rewriting of reconfigurable and/or rewritable circuit and/or memory elements; alternatively, redeployment may be performed by production of new hardware and/or software components, circuits, instructions, or the like, which may be added to and/or may replace existing hardware and/or software components, circuits, instructions, or the like.
Further referring to FIG. 3, one or more processes or algorithms described above may be performed by at least a dedicated hardware unit 336. A “dedicated hardware unit,” for the purposes of this figure, is a hardware component, circuit, or the like, aside from a principal control circuit and/or processor performing method steps as described in this disclosure, that is specifically designated or selected to perform one or more specific tasks and/or processes described in reference to this figure, such as without limitation preconditioning and/or sanitization of training data and/or training a machine-learning algorithm and/or model. A dedicated hardware unit 336 may include, without limitation, a hardware unit that can perform iterative or massed calculations, such as matrix-based calculations to update or tune parameters, weights, coefficients, and/or biases of machine-learning models and/or neural networks, efficiently using pipelining, parallel processing, or the like; such a hardware unit may be optimized for such processes by, for instance, including dedicated circuitry for matrix and/or signal processing operations that includes, e.g., multiple arithmetic and/or logical circuit units such as multipliers and/or adders that can act simultaneously and/or in parallel or the like. Such dedicated hardware units 336 may include, without limitation, graphical processing units (GPUs), dedicated signal processing modules, FPGA or other reconfigurable hardware that has been configured to instantiate parallel processing units for one or more specific tasks, or the like, A computing device, processor, apparatus, or module may be configured to instruct one or more dedicated hardware units 336 to perform one or more operations described herein, such as evaluation of model and/or algorithm outputs, one-time or iterative updates to parameters, coefficients, weights, and/or biases, and/or any other operations such as vector and/or matrix operations as described in this disclosure.
With continued reference to FIG. 3, apparatus 100 may use user and/or instructor feedback to train the machine-learning models and/or classifiers described above. For example, classifier may be trained using past inputs and outputs of classifier. In some embodiments, if user and/or instructor feedback indicates that an output of classifier was “bad,” then that output and the corresponding input may be removed from training data used to train classifier, and/or may be replaced with a value entered by, e.g., another user that represents an ideal output given the input the classifier originally received, permitting use in retraining, and adding to training data; in either case, classifier may be retrained with modified training data as described in further detail below. In some embodiments, training data of classifier may include user feedback.
With continued reference to FIG. 3, in some embodiments, an accuracy score may be calculated for classifier using user feedback. For the purposes of this disclosure, “accuracy score,” is a numerical value concerning the accuracy of a machine-learning model. For example, a plurality of user feedback scores may be averaged to determine an accuracy score. In some embodiments, a cohort accuracy score may be determined for particular cohorts of persons. For example, user and/or instructor feedback for users and/or instructors belonging to a particular cohort of persons may be averaged together to determine the cohort accuracy score for that particular cohort of persons and used as described above. Accuracy score or another score as described above may indicate a degree of retraining needed for a machine-learning model such as a classifier; apparatus 100 may perform a larger number of retraining cycles for a higher number (or lower number, depending on a numerical interpretation used), and/or may collect more training data for such retraining, perform more training cycles, apply a more stringent convergence test such as a test requiring a lower mean squared error, and/or indicate that additional training data is needed.
Referring now to FIG. 4, an exemplary embodiment of neural network 400 is illustrated. A neural network 400 also known as an artificial neural network, is a network of “nodes,” or data structures having one or more inputs, one or more outputs, and a function determining outputs based on inputs. Such nodes may be organized in a network, such as without limitation a convolutional neural network, including an input layer of nodes 404, one or more intermediate layers 408, and an output layer of nodes 412. Connections between nodes may be created via the process of “training” the network, in which elements from a training dataset are applied to the input nodes, a suitable training algorithm (such as Levenberg-Marquardt, conjugate gradient, simulated annealing, or other algorithms) is then used to adjust the connections and weights between nodes in adjacent layers of the neural network to produce the desired values at the output nodes. This process is sometimes referred to as deep learning. Connections may run solely from input nodes toward output nodes in a “feed-forward” network, or may feed outputs of one layer back to inputs of the same or a different layer in a “recurrent network.” As a further non-limiting example, a neural network may include a convolutional neural network comprising an input layer of nodes, one or more intermediate layers, and an output layer of nodes. A “convolutional neural network,” as used in this disclosure, is a neural network in which at least one hidden layer is a convolutional layer that convolves inputs to that layer with a subset of inputs known as a “kernel,” along with one or more additional layers such as pooling layers, fully connected layers, and the like.
Referring now to FIG. 5, an exemplary embodiment of a node 500 of a neural network is illustrated. A node may include, without limitation a plurality of inputs xi that may receive numerical values from inputs to a neural network containing the node and/or from other nodes. Node may perform one or more activation functions to produce its output given one or more inputs, such as without limitation computing a binary step function comparing an input to a threshold value and outputting either a logic 1 or logic 0 output or something equivalent, a linear activation function whereby an output is directly proportional to the input, and/or a non-linear activation function, wherein the output is not proportional to the input. Non-linear activation functions may include, without limitation, a sigmoid function of the form
given input x, a tanh (hyperbolic tangent) function, of the form
a tanh derivative function such as ƒ(x)=tanh2(x), a rectified linear unit function such as ƒ(x)=max (0, x), a “leaky” and/or “parametric” rectified linear unit function such as ƒ(x)=max (ax, x) for some a, an exponential linear units function such as
for some value of α (this function may be replaced and/or weighted by its own derivative in some embodiments), a softmax function such as
where the inputs to an instant layer are xi, a swish function such as ƒ(x)=x*sigmoid(x), a Gaussian error linear unit function such as ƒ(x)=a(1+tanh(√{square root over (2/π)}(x+bxr))) for some values of a, b, and r, and/or a scaled exponential linear unit function such as
Fundamentally, there is no limit to the nature of functions of inputs xi that may be used as activation functions. As a non-limiting and illustrative example, node may perform a weighted sum of inputs using weights wi that are multiplied by respective inputs xi. Additionally or alternatively, a bias b may be added to the weighted sum of the inputs such that an offset is added to each unit in the neural network layer that is independent of the input to the layer. The weighted sum may then be input into a function φ, which may generate one or more outputs y. Weight wi applied to an input xi may indicate whether the input is “excitatory,” indicating that it has strong influence on the one or more outputs y, for instance by the corresponding weight having a large numerical value, and/or a “inhibitory,” indicating it has a weak effect influence on the one more inputs y, for instance by the corresponding weight having a small numerical value. The values of weights wi may be determined by training a neural network using training data, which may be performed using any suitable process as described above.
Still referring to FIG. 5, a “convolutional neural network,” as used in this disclosure, is a neural network in which at least one hidden layer is a convolutional layer that convolves inputs to that layer with a subset of inputs known as a “kernel,” along with one or more additional layers such as pooling layers, fully connected layers, and the like. CNN may include, without limitation, a deep neural network (DNN) extension, where a DNN is defined as a neural network with two or more hidden layers.
Still referring to FIG. 5, in some embodiments, a convolutional neural network may learn from images. In non-limiting examples, a convolutional neural network may perform tasks such as classifying images, detecting objects depicted in an image, segmenting an image, and/or processing an image. In some embodiments, a convolutional neural network may operate such that each node in an input layer is only connected to a region of nodes in a hidden layer. In some embodiments, the regions in aggregate may create a feature map from an input layer to the hidden layer. In some embodiments, a convolutional neural network may include a layer in which the weights and biases for all nodes are the same. In some embodiments, this may allow a convolutional neural network to detect a feature, such as an edge, across different locations in an image.
Now referring to FIG. 6, in some embodiments, apparatus 100 may communicate with user and/or instructor using a chatbot. According to some embodiments, one or more user interfaces including first user interface 604a and second user interface 604b on one or more user devices including first user device 632a and second user device 632b may be communicative with a computing device 608 that is configured to operate a chatbot. In some embodiments, one or more user devices may be communicative in this way, such as 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 20, 30, 40, 50, 60, 70, 80, 90, 100, or more user devices. In some embodiments, first user interface 604a may be local to first user device 632a. In some embodiments, additional user interfaces such as second user interface 604b may be local to their respective user devices. In some embodiments, first user interface 604a may be local to computing device 608. In some embodiments, additional user interfaces such as second user interface 604b may be local to computing device 608. Alternatively or additionally, in some cases, first user interface 604a may remote to first user device 632a and communicative with first user device 632a, by way of one or more networks, such as without limitation the internet. Alternatively or additionally, one or more user interfaces may communicate with computing device 608 using telephonic devices and networks, such as without limitation fax machines, short message service (SMS), or multimedia message service (MMS). Commonly, user interfaces such as first user interface 604a communicate with computing device 608 using text-based communication, for example without limitation using a character encoding protocol, such as American Standard for Information Interchange (ASCII). Typically, user interfaces conversationally interface with a chatbot, by way of at least a submission, from a user interface to the chatbot, and a response, from the chatbot to the user interface. For example, first user interface 604a may interface with a chatbot using first submission 612a and first response 616a. In another example, second user interface 604b may interface with a chatbot using second submission 612b and second response 616b. In some embodiments, submissions such as first submission 612a and/or responses such as first response 616a may use text-based communication. In some embodiments, submissions such as first submission 612a and/or responses such as first response 616a may use audio communication.
Still referring to FIG. 6, a submission such as first submission 612a once received by computing device 608 operating a chatbot, may be processed by a processor 620. In some embodiments, processor 620 processes a submission such as first submission 612a using one or more of keyword recognition, pattern matching, and natural language processing. In some embodiments, processor employs real-time learning with evolutionary algorithms. In some cases, processor 620 may retrieve a pre-prepared response from at least a storage component 624, based upon submission such as first submission 612a. Alternatively or additionally, in some embodiments, processor 620 communicates a response such as first response 616a without first receiving a submission, thereby initiating conversation. In some cases, processor 620 communicates an inquiry to a user interface such as first user interface 604a; and processor 620 is configured to process an answer to the inquiry in a following submission from the user interface. In some cases, an answer to an inquiry present within a submission from a user device may be used by computing device 608 as an input to another function. In some embodiments, computing device 608 may include machine learning module 628. Machine learning module 628 may include any machine learning models described herein. In some embodiments, a submission such as first submission 612a may be input into a trained machine learning model within machine learning module 628. In some embodiments, a submission such as first submission 612a may undergo one or more processing steps before being input into a machine learning model. In some embodiments, a submission such as first submission 612a may be used to train a machine learning model within machine learning module 628.
Referring now to FIG. 7, an exemplary embodiment of a method 700 of synchronous learning is illustrated. One or more steps of method 700 may be implemented, without limitation, as described above in reference to FIG. 1. One or more steps of method 700 may be implemented, without limitation, using at least a processor.
Still referring to FIG. 7, method 700 may include receiving a discussion topic 705. In some embodiments, receiving a discussion topic includes receiving from an instructor device speech data; transcribing the speech data using an automatic speech recognition system to create transcribed speech data; and interpreting the transcribed speech data using a language model to determine the discussion topic.
Still referring to FIG. 7, method 700 may include generating a first prompt as a function of the discussion topic 710. In some embodiments, generating a first prompt as a function of the discussion topic includes training a prompt generation machine learning model on a training dataset including model discussion topics associated with model prompts; inputting the discussion topic into the prompt generation machine learning model; and receiving as an output from the prompt generation machine learning model the first prompt.
Still referring to FIG. 7, method 700 may include presenting to a user the first prompt 715. In some embodiments, presenting the first prompt to the user includes sending a signal to a user device, wherein the signal includes the first prompt and configures the user device to display the first prompt, wherein receiving the discussion datum includes receiving the discussion datum from the user device. In some embodiments, presenting to the user the first prompt is done using a chatbot.
Still referring to FIG. 7, method 700 may include receiving a discussion datum, wherein the discussion datum includes a user response to the first prompt 720.
Still referring to FIG. 7, method 700 may include generating a user understanding score as a function of the discussion datum and a grading threshold 725. In some embodiments, generating a user understanding score includes recording audio of a user response to the first prompt to create an audio discussion datum; transcribing the audio discussion datum using an automatic speech recognition system to create a transcribed discussion datum; training a score generation machine learning model on a training dataset including model discussion data associated with model user understanding scores; inputting the transcribed discussion datum into the score generation machine learning model; and receiving as an output from the score generation machine learning model the user understanding score. In some embodiments, generating a user understanding score includes recording audio of a user response to the first prompt to create an audio discussion datum; and transcribing the audio discussion datum using an automatic speech recognition system to create a transcribed discussion datum; further including displaying the transcribed discussion datum to the instructor alongside the user understanding score.
Still referring to FIG. 7, in some embodiments, method 700 may further include communicating the user understanding score to an instructor. In some embodiments, method 700 may further include generating a certainty score as a function of the discussion datum. In some embodiments, method 700 may further include generating a second prompt as a function of the discussion topic and the certainty score; and presenting to the user the second prompt; wherein the discussion datum further includes a user response to the second prompt.
Now referring to FIG. 8, an exemplary interface 800 is depicted. In some embodiments, apparatus 100 and/or an associated device such as instructor device 124 and/or user device 140 may display interface 800. Interface 800 may be used, for example, on user device 140 during a discussion session. Interface 800 may include representations of one or more users 804, such as video feeds of those users. Interface 800 may include chat window 808 into which users may input messages. In some embodiments, chat window 808 may include one or more additional tabs containing additional resources. For example, formulas useful for solving a problem posed by a prompt may be included in such additional resources. In some embodiments, interface 800 may include prompt field 812 which may display a prompt generated as described herein. As described above, prompts may change during a discussion, such as in order to generate additional data on a user that has not spoken yet. Such a change may be reflected in prompt field 812.
Now referring to FIG. 9, an exemplary interface 900 is depicted. In some embodiments, apparatus 100 and/or an associated device such as instructor device 124 and/or user device 140 may display interface 900. Interface 800 may be used, for example, on instructor device 124 while instructor is viewing user understanding scores 152. Interface 900 may include a field identifying one or more users 904. Interface 900 may include a field identifying which group the one or more users are in 908. Interface 900 may include a field indicating user understanding scores 912. Interface 900 may include a field including contributions users made to a discussion 916. In some embodiments, certain contributions may be highlighted or otherwise emphasized as described above.
It is to be noted that any one or more of the aspects and embodiments described herein may be conveniently implemented using one or more machines (e.g., one or more computing devices that are utilized as a user computing device for an electronic document, one or more server devices, such as a document server, etc.) programmed according to the teachings of the present specification, as will be apparent to those of ordinary skill in the computer art. Appropriate software coding can readily be prepared by skilled programmers based on the teachings of the present disclosure, as will be apparent to those of ordinary skill in the software art. Aspects and implementations discussed above employing software and/or software modules may also include appropriate hardware for assisting in the implementation of the machine executable instructions of the software and/or software module.
Such software may be a computer program product that employs a machine-readable storage medium. A machine-readable storage medium may be any medium that is capable of storing and/or encoding a sequence of instructions for execution by a machine (e.g., a computing device) and that causes the machine to perform any one of the methodologies and/or embodiments described herein. Examples of a machine-readable storage medium include, but are not limited to, a magnetic disk, an optical disc (e.g., CD, CD-R, DVD, DVD-R, etc.), a magneto-optical disk, a read-only memory “ROM” device, a random access memory “RAM” device, a magnetic card, an optical card, a solid-state memory device, an EPROM, an EEPROM, and any combinations thereof. A machine-readable medium, as used herein, is intended to include a single medium as well as a collection of physically separate media, such as, for example, a collection of compact discs or one or more hard disk drives in combination with a computer memory. As used herein, a machine-readable storage medium does not include transitory forms of signal transmission.
Such software may also include information (e.g., data) carried as a data signal on a data carrier, such as a carrier wave. For example, machine-executable information may be included as a data-carrying signal embodied in a data carrier in which the signal encodes a sequence of instruction, or portion thereof, for execution by a machine (e.g., a computing device) and any related information (e.g., data structures and data) that causes the machine to perform any one of the methodologies and/or embodiments described herein.
Examples of a computing device include, but are not limited to, an electronic book reading device, a computer workstation, a terminal computer, a server computer, a handheld device (e.g., a tablet computer, a smartphone, etc.), a web appliance, a network router, a network switch, a network bridge, any machine capable of executing a sequence of instructions that specify an action to be taken by that machine, and any combinations thereof. In one example, a computing device may include and/or be included in a kiosk.
FIG. 10 shows a diagrammatic representation of one embodiment of a computing device in the exemplary form of a computer system 1000 within which a set of instructions for causing a control system to perform any one or more of the aspects and/or methodologies of the present disclosure may be executed. It is also contemplated that multiple computing devices may be utilized to implement a specially configured set of instructions for causing one or more of the devices to perform any one or more of the aspects and/or methodologies of the present disclosure. Computer system 1000 includes a processor 1004 and a memory 1008 that communicate with each other, and with other components, via a bus 1012. Bus 1012 may include any of several types of bus structures including, but not limited to, a memory bus, a memory controller, a peripheral bus, a local bus, and any combinations thereof, using any of a variety of bus architectures.
Processor 1004 may include any suitable processor, such as without limitation a processor incorporating logical circuitry for performing arithmetic and logical operations, such as an arithmetic and logic unit (ALU), which may be regulated with a state machine and directed by operational inputs from memory and/or sensors; processor 1004 may be organized according to Von Neumann and/or Harvard architecture as a non-limiting example. Processor 1004 may include, incorporate, and/or be incorporated in, without limitation, a microcontroller, microprocessor, digital signal processor (DSP), Field Programmable Gate Array (FPGA), Complex Programmable Logic Device (CPLD), Graphical Processing Unit (GPU), general purpose GPU, Tensor Processing Unit (TPU), analog or mixed signal processor, Trusted Platform Module (TPM), a floating point unit (FPU), and/or system on a chip (SoC).
Memory 1008 may include various components (e.g., machine-readable media) including, but not limited to, a random-access memory component, a read only component, and any combinations thereof. In one example, a basic input/output system 1016 (BIOS), including basic routines that help to transfer information between elements within computer system 1000, such as during start-up, may be stored in memory 1008. Memory 1008 may also include (e.g., stored on one or more machine-readable media) instructions (e.g., software) 1020 embodying any one or more of the aspects and/or methodologies of the present disclosure. In another example, memory 1008 may further include any number of program modules including, but not limited to, an operating system, one or more application programs, other program modules, program data, and any combinations thereof.
Computer system 1000 may also include a storage device 1024. Examples of a storage device (e.g., storage device 1024) include, but are not limited to, a hard disk drive, a magnetic disk drive, an optical disc drive in combination with an optical medium, a solid-state memory device, and any combinations thereof. Storage device 1024 may be connected to bus 1012 by an appropriate interface (not shown). Example interfaces include, but are not limited to, SCSI, advanced technology attachment (ATA), serial ATA, universal serial bus (USB), IEEE 1394 (FIREWIRE), and any combinations thereof. In one example, storage device 1024 (or one or more components thereof) may be removably interfaced with computer system 1000 (e.g., via an external port connector (not shown)). Particularly, storage device 1024 and an associated machine-readable medium 1028 may provide nonvolatile and/or volatile storage of machine-readable instructions, data structures, program modules, and/or other data for computer system 1000. In one example, software 1020 may reside, completely or partially, within machine-readable medium 1028. In another example, software 1020 may reside, completely or partially, within processor 1004.
Computer system 1000 may also include an input device 1032. In one example, a user of computer system 1000 may enter commands and/or other information into computer system 1000 via input device 1032. Examples of an input device 1032 include, but are not limited to, an alpha-numeric input device (e.g., a keyboard), a pointing device, a joystick, a gamepad, an audio input device (e.g., a microphone, a voice response system, etc.), a cursor control device (e.g., a mouse), a touchpad, an optical scanner, a video capture device (e.g., a still camera, a video camera), a touchscreen, and any combinations thereof. Input device 1032 may be interfaced to bus 1012 via any of a variety of interfaces (not shown) including, but not limited to, a serial interface, a parallel interface, a game port, a USB interface, a FIREWIRE interface, a direct interface to bus 1012, and any combinations thereof. Input device 1032 may include a touch screen interface that may be a part of or separate from display 1036, discussed further below. Input device 1032 may be utilized as a user selection device for selecting one or more graphical representations in a graphical interface as described above.
A user may also input commands and/or other information to computer system 1000 via storage device 1024 (e.g., a removable disk drive, a flash drive, etc.) and/or network interface device 1040. A network interface device, such as network interface device 1040, may be utilized for connecting computer system 1000 to one or more of a variety of networks, such as network 1044, and one or more remote devices 1048 connected thereto. Examples of a network interface device include, but are not limited to, a network interface card (e.g., a mobile network interface card, a LAN card), a modem, and any combination thereof. Examples of a network include, but are not limited to, a wide area network (e.g., the Internet, an enterprise network), a local area network (e.g., a network associated with an office, a building, a campus or other relatively small geographic space), a telephone network, a data network associated with a telephone/voice provider (e.g., a mobile communications provider data and/or voice network), a direct connection between two computing devices, and any combinations thereof. A network, such as network 1044, may employ a wired and/or a wireless mode of communication. In general, any network topology may be used. Information (e.g., data, software 1020, etc.) may be communicated to and/or from computer system 1000 via network interface device 1040.
Computer system 1000 may further include a video display adapter 1052 for communicating a displayable image to a display device, such as display device 1036. Examples of a display device include, but are not limited to, a liquid crystal display (LCD), a cathode ray tube (CRT), a plasma display, a light emitting diode (LED) display, and any combinations thereof. Display adapter 1052 and display device 1036 may be utilized in combination with processor 1004 to provide graphical representations of aspects of the present disclosure. In addition to a display device, computer system 1000 may include one or more other peripheral output devices including, but not limited to, an audio speaker, a printer, and any combinations thereof. Such peripheral output devices may be connected to bus 1012 via a peripheral interface 1056. Examples of a peripheral interface include, but are not limited to, a serial port, a USB connection, a FIREWIRE connection, a parallel connection, and any combinations thereof.
The foregoing has been a detailed description of illustrative embodiments of the invention. Various modifications and additions can be made without departing from the spirit and scope of this invention. Features of each of the various embodiments described above may be combined with features of other described embodiments as appropriate in order to provide a multiplicity of feature combinations in associated new embodiments. Furthermore, while the foregoing describes a number of separate embodiments, what has been described herein is merely illustrative of the application of the principles of the present invention. Additionally, although particular methods herein may be illustrated and/or described as being performed in a specific order, the ordering is highly variable within ordinary skill to achieve methods, systems, and software according to the present disclosure. Accordingly, this description is meant to be taken only by way of example, and not to otherwise limit the scope of this invention.
Exemplary embodiments have been disclosed above and illustrated in the accompanying drawings. It will be understood by those skilled in the art that various changes, omissions and additions may be made to that which is specifically disclosed herein without departing from the spirit and scope of the present invention.
Patent Application
20250201139
