Patent Application
20240221524
The present invention is generally related to educational data analytics and machine learning. The present invention is particularly related to student engagement and analytics systems and methods with machine learning. The present invention is more particularly related to a system and method for assessing student engagement and to enhance a student's understanding in a subject.
Academic institutions and other learning entities increasingly provide electronic learning materials, either to replace or to supplement traditional, classroom pedagogical methods. While electronic learning materials are often convenient, effective, and efficient, their use can limit personal interactions between teachers and students. This lack of personal contact can make it difficult for academic institutions to determine whether students using electronic learning materials are engaged by the material, whether students are likely to succeed academically, or the like. Hence, student evaluation is critical in any mode of education.
Evaluating students is an important aspect in any mode of learning because the presenter has a better understanding of the students in a subject. As opposed to passive learning where the students just absorb like a sponge, active learning based on asking questions enhances understanding and helps them to remember. However, if a student is learning from a computer system, the student does not have the luxury of having a question-and-answer dialog with the computer.
Asking questions not only focuses student's attention on the subject, it also fills gaps in their understanding. When the students are learning through online mode, typically they cannot comprehend everything. As their misunderstanding grows, very soon the students begin to lose track of the subject, and their interest in the subject wanes. Similarly, they lose interest in reading a book with many individuals if they confuse their names. During those instances, asking questions to fill the gaps of misunderstanding might rekindle their interest in the subject or the book.
Furthermore, real-time quizzing of students who view a broadcast of live or recorded events can be a fun and interactive experience. Events may occur in games, sports, political events, news, or any other occurrence. A quiz may include one or more questions and may test the knowledge of or poll the audience member.
Hence there is a need for developing a system and method for conducting real-time quizzing and testing the students, to evaluate them. Furthermore, there is a need to track participant engagement or understanding of a certain topic when they are part of a session either in-person or remote.
The above-mentioned shortcomings, disadvantages and problems are addressed herein, and which will be understood by reading and studying the following specification.
The principal object of the embodiments herein is to provide a method and system for intelligent interpretation of information to autonomously design in-class/hybrid/remote assessment.
Another object of the embodiments herein is to track participant engagement or understanding of a certain topic when they are part of a session in-person or remote or hybrid.
Yet another object of this embodiment here in is to provide a system and method to generate real-time questions during a session based on the content being discussed.
Yet another object of the embodiments herein is to utilize an AI-based system and method to categorize the course content and automatically generate questions from the interaction and publish the questions to all the participants during the session.
Yet another object of the embodiments herein is to provide a system and method, that enables the participants to respond to the questions in real-time, thereby the host gets the opportunity to track the participants engagement during the session.
Yet another object of the embodiments herein is to provide a system and method, that enables the presenter to track the student, who persistently answering incorrectly during the session.
Yet another object of the embodiments herein is to provide a system and method, which provides detailed classroom analytics, including the questions being asked during the session, class reports, lesson reports and student reports.
Yet another object of the embodiments herein is to provide a system and method, that helps the presenter to generate classroom performance and attention level reports for each individual student which can then be shared with the student and their parents.
These and other objects and advantages of the present invention will become readily apparent from the following detailed description taken in conjunction with the accompanying drawings.
The following details present a simplified summary of the embodiments herein to provide a basic understanding of the several aspects of the embodiments herein. This summary is not an extensive overview of the embodiments herein. It is not intended to identify key/critical elements of the embodiments herein or to delineate the scope of the embodiments herein. Its sole purpose is to present the concepts of the embodiments herein in a simplified form as a prelude to the more detailed description that is presented later.
The other objects and advantages of the embodiments herein will become readily apparent from the following description taken in conjunction with the accompanying drawings. It should be understood, however, that the following descriptions, while indicating preferred embodiments and numerous specific details thereof, are given by way of illustration and not of limitation. Many changes and modifications may be made within the scope of the embodiments herein without departing from the spirit thereof, and the embodiments herein include all such modifications.
This Summary is provided to introduce a selection of concepts in a simplified form that is further described below in the Detailed Description. This Summary is not intended to identify key or essential features of the claimed subject matter, nor is it intended to be used as an aid in determining the scope of the claimed subject matter.
The various embodiments herein provide a system and method for intelligent interpretation of information to autonomously design in-class/hybrid/remote assessment. The method involves picking up audio of the presenter from an audio input device such as microphone during an interaction. The interaction includes both either audio or video interaction. Further, the method involves extracting the key information present in the captured audio interaction and then use the extracted key information to intelligently generate assessments such as quiz questions, multiple-choice questions and mathematical questions.
According to one embodiment herein, a method for intelligent interpretation of information to autonomously design in-class/hybrid/remote assessment is provided. The method includes receiving audio interaction of a presenter through an audio input device and uploading course content into a knowledge database. The method allows the presenter to optionally flag the significant keywords of the audio interaction while speaking into the audio input device through a plurality of means. The plurality of means comprises a specific key on a keyboard, a clicker device including mouse or a verbal que spoken into the microphone. Furthermore, the plurality of means is used in real-time, when the presenter wants to forcefully publish the question to the plurality of participants based on an important information just communicated. For instance, if the presenter is talking about the history of the world and mentions an important detail while talking, they may click on the clicker, press a designated key on the keyboard, a click on the interface or say out a verbal que such as “flag this” and the system will be able to generate a question or quiz from the recently communicated information to send to the participants. Moreover, the audio interaction comprises an audio or a video interaction and the audio input device include a microphone. The method further comprises capturing the audio interaction of the presenter by an audio capturing module. Then, transcribing the audio interaction along with the optionally flagged significant keywords by the presenter into a plurality of text by an audio-text conversion module and saving the transcribed plurality of text and course content in the knowledge database. The method further comprises analyzing the transcribed plurality of text by a text analyzation module. The text analyzation module, further separates the last phrase or sentence or piece of information of the transcribed plurality of text comprising the flagged significant keywords received from the presenter. Furthermore, the method includes generating question by a question generation module based on the course content presented by the presenter. Followed by reviewing and seeking approval of the presenter for the question generated by the question generation module. On reviewing the question, the presenter either approves or disapproves the question and publishes the question to a plurality of participants the approved questions. In addition, if the presenter disapproves the question generated, then the question generation module, generates another question, seeks approval from the presenter and publishes to the plurality of participants. The method further involves saving the published question in the knowledge database. Once saved, the question is displayed to the plurality of participants to respond. Furthermore, the method involves generating analytics, auto-checking the responses of the plurality of participants, and displaying the analytics to the presenter by a response generation module. Following this, the presenter receives an alert if the plurality of participants persistently responds incorrectly to the published question. Finally, the method involves displaying the precise response to the plurality of participants, generating, and storing detailed classroom analytics in the knowledge database.
According to one embodiment herein, the transcribing the audio interaction into the plurality of text by the audio-text conversion module, employs an automatic speech recognition system (ASR). The ASR is made up of statistical models that reflect the mapping of continuous phonetic sound sequences (spoken utterances or speech waveforms) to the plurality of text outputs that is recognized as being in human language. The ASR model, further comprises a Language Model, a Pronunciation Model (Lexicon/Dictionary), and an Acoustic Model. In addition, the accuracy of the transcription improves whenever the models are consistently trained with fresh voice data from multiple speakers and a wider vocabulary (Language Model). Thus, the accuracy is quantified statistically by the Word Error Rate (WER). Ideally, the WER equates to less than 11% for very accurate models. Quality of the dataset, audio, and lexicon are ultimately the most crucial factors while training a speech recognition model. Furthermore, the presenter can make audio information accessible with the aid of speech recognition. The audio has a lot of essential information that is hidden away, but it is difficult to look through. By using voice to text, audio is converted into text and made searchable on a word-by-word basis. As a result, the output can be utilized to index content archives in addition to existing metadata to improve the searchability of big archives and serve as automatic subtitles for those who have hearing loss. Imagine a journalist searching for video to use in a piece they are writing. The journalist can easily seek for the footage based on terms regarding the incident instead of attempting to determine the exact date that an event occurred.
According to one embodiment herein, the question generated by the question generation module includes empirical or theoretical depending on the subject taught by the presenter. The empirical questions include mathematical questions or those that can be measured or calculated. For instance, when the presenter/teacher asks the plurality of participants/student to solve a mathematical question which has a unique or limited unique answers such as square root of 81. The response can be + or −9. Such questions when asked by the presenter/teacher would send out the question as fill in the blank, type short or long answer etc. Thus, the system will input information from the presenter and generate a question. The result of the question will also be automatically calculated using a separate system which may involve use of external tools, software, service. Once the question has been generated and approved, the question will be shared with the presenter and then once the presenter approves the question, the students will be able to solve the question. The student's response will be compared with the saved correct result. The theoretical questions include those questions that contains an important piece of information, including significant keywords. Furthermore, the method for generating question is provided. The method includes breaking the statement of the presenter, into sentence structures, identifying intelligently the important piece of information in the respective sentence, applying english grammar rules and machine learning NLP (Natural Language Processing) models, selecting the topic that matches the subject being taught by the presenter and creating the question. Moreover, while applying grammar rules and machine learning NLP models for generating questions, the following method is observed. The method includes finding and marking a verb in a sentence, checking the type of verb in the sentence. The type of verb includes action verb and state of being verb or linking verb. The method further involves, finding the subject and complement. Finding the complement includes finding the object of the action verb and finding the subject complement. The object of the action verb includes direct object and indirect object, and the subject complement includes predictive nominative and predictive adjective. The predictive nominative comprises renaming the subject and predictive adjective comprises describing the subject. The method further involves saving the object of the action verb and subject complement in the knowledge database, finding the object of the action verb and subject in the course contents uploaded by the presenter in the knowledge database and getting the type of sentence. The type of sentence includes simple and complex sentences. Finally, the method involves generating questions using english grammar rules for simple sentences and generating questions using machine learning NLP (Natural Language Processing) models for complex sentences. For instance, during a lesson the presenter communicates the following information: “Mount Everest is the tallest peak in the world.” In this sentence the important piece of information is “Mount Everest” and “tallest.” The method will pick up subject, object, verb, adjective. The method will then lock down to one piece of information for instance in this case it may be “Mount Everest.” Now the method will use a third-party system to find reasonable alternates of this and generate a multiple-choice question. The alternates may be “Black mountain,” “K2” or “Kangchenjunga”. Further, the method will then send a question as follows to the presenter for approval: ______ is the tallest mountain in the world:
According to one embodiment herein, the type of question generated by the question generation modules includes a multiple-choice question, an information-based question, true/false questions, fill in the blank's questions or short answer questions. Furthermore, the method provides the presenter to either set the time for the question being published, by having limited time for the plurality of participants to respond to the question or the presenter may choose not to time the question.
According to one embodiment herein, the plurality of participants attending the session comprises various modes including in-class, hybrid or remotely. The method allows the plurality of participants to respond to the questions by typing, clicking or by dictating if attending remotely. Furthermore, the plurality of participants after responding to the question, an automatic report is generated, saved, and displayed to the presenter. The automatic report is then displayed to the presenter in graphical format based on the percentage of the plurality of participants choosing to submit a certain response during the session. In addition, the presenter also has the option to track the effectiveness of the session while conducting the session. Furthermore, the auto-checking the responses of the plurality of participants by the response generation module is carried out using an external tools, software, or service.
According to one embodiment herein, the detailed classroom analytics comprises a detailed report of the questions published, class reports, course content reports and student reports. The detailed classroom analytics is stored in the knowledge database and the detailed classroom analytics is populated after every session and an aggregate; the detailed classroom analytics is available to the presenter as the session continues to happen. Furthermore, the detailed classroom analytics generated by the response generator module enables the presenter to identify the poor student performance and helps to build a better future content. The detailed classroom analytics further enables the presenter to generate classroom performance and attention level reports for each of the plurality of participants and the attention level reports are shared with the parents of the plurality of the participants or students.
According to one embodiment herein, a computer implemented system comprising instructions stored on a non-transitory computer readable storage medium and executed on a hardware processor for intelligent interpretation of information to autonomously design in-class/hybrid/remote assessment is provided. The system comprises an audio input device configured to receive an audio interaction of a presenter. The audio interaction comprises of significant keywords that is optionally flagged by the presenter through a plurality of means. The audio interaction includes an audio or a video interaction. The audio input device includes a microphone. Furthermore, the plurality of means comprises a specific key on a keyboard, a clicker device including mouse or a verbal que spoken into the microphone. The plurality of means is used in real-time, when the presenter wants to forcefully publish the question to the plurality of participants based on an important information just communicated. For instance, if the presenter is talking about the history of the world and mentions an important detail while talking, they may click on the clicker, press a designated key on the keyboard, a click on the interface or say out a verbal que such as “flag this” and the system will be able to generate a question or quiz from the recently communicated information to send to the participants. The system further includes an audio capturing module configured to capture the audio interaction of the presenter; an audio-text conversion module configured to transcribe the audio interaction and the optionally flagged significant keywords by the presenter, into a plurality of text. In addition, the system further comprises a knowledge database configured to maintain the transcribed plurality of text and course content uploaded by the presenter. Furthermore, the system comprises a text analyzation module configured to analyze the transcribed plurality of text, and separate the last phrase or sentence or piece of information of the flagged significant keywords received from the presenter. The system also includes a question generation module configured to generate question based on the course content presented by the presenter. The question generated is further subjected to review and approval from the presenter. The question approved by the presenter is then, published by the question generation module to a plurality of participants for responding. Furthermore, the question generation module is configured to generate another question, seek approval from the presenter and publish the question to the plurality of participants for responding, on disapproval of previous question by the presenter. Furthermore, the system comprises a response generation module configured to generate analytics, auto-check the responses of the plurality of participants and display the analytics to the presenter. The response generation module is further configured to send an alert to the presenter, if the plurality of participants persistently responds incorrectly, display the precise response to the plurality of participants, generate and store detailed classroom analytics in the knowledge database.
According to one embodiment herein, the audio-text conversion module configured to transcribe the audio interaction into the plurality of text, employs an automatic speech recognition system (ASR). The ASR is made up of statistical models that reflect the mapping of continuous phonetic sound sequences (spoken utterances or speech waveforms) to the plurality of text outputs that is recognized as being in human language. The ASR model comprises a Language Model, a Pronunciation Model (Lexicon/Dictionary), and an Acoustic Model. In addition, the accuracy of the transcription improves whenever the models are consistently trained with fresh voice data from multiple speakers and a wider vocabulary (Language Model). Thus, the accuracy is quantified statistically by the Word Error Rate (WER). Ideally, the WER equates to less than 11% for very accurate models. Quality of the dataset, audio, and lexicon are ultimately the most crucial factors while training a speech recognition model. Furthermore, the presenter can make audio information accessible with the aid of speech recognition. The audio has a lot of essential information that is hidden away, but it is difficult to look through. By using voice to text, audio is converted into text and made searchable on a word-by-word basis. As a result, the output can be utilized to index content archives in addition to existing metadata to improve the searchability of big archives and serve as automatic subtitles for those who have hearing loss. Imagine a journalist searching for video to use in a piece they are writing. The journalist can easily seek for the footage based on terms regarding the incident instead of attempting to determine the exact date that an event occurred.
According to one embodiment herein, the question generated by the question generation module includes empirical or theoretical depending on the subject taught by the presenter. The empirical questions include mathematical questions or those that can be measured or calculated. For instance, when the presenter/teacher asks the plurality of participants/student to solve a mathematical question which has a unique or limited unique answers such as square root of 81. The response can be + or −9. Such questions when asked by the presenter/teacher would send out the question as fill in the blank, type short or long answer etc. Thus, the system will input information from the presenter and generate a question. The result of the question will also be automatically calculated using a separate system which may involve use of external tools, software, service. Once the question has been generated and approved, the question will be shared with the presenter and then once the presenter approves the question, the students will be able to solve the question. The student's response will be compared with the saved correct result. The theoretical questions include those questions that contains an important piece of information, including significant keywords.
According to one embodiment herein, the type of question generated by the question generation modules includes a multiple-choice question, an information-based question, true/false questions, fill in the blank's questions or short answer questions. Furthermore, the system provides the presenter to either set the time for the question being published, by having limited time for the plurality of participants to respond to the question or the presenter may choose not to time the question.
According to one embodiment herein, the plurality of participants attending the session comprises various modes including in-class, hybrid or remotely. The system further provides the plurality of participants to respond to the questions by typing, clicking or by dictating if attending remotely. Furthermore, the plurality of participants after responding to the question, an automatic report is generated, saved, and displayed to the presenter. The automatic report is then displayed to the presenter in graphical format based on the percentage of the plurality of participants choosing to submit a certain response during the session. In addition, the presenter also has the option to track the effectiveness of the session while conducting the session. Furthermore, the response generation module is configured to auto-check the responses of the plurality of participants using an external tools, software, or service.
According to one embodiment herein, the response generation module is configured to generate detailed classroom analytics comprising a detailed report of the questions published, class reports, course content reports and student reports. The detailed classroom analytics is stored in the knowledge database and the detailed classroom analytics is populated after every session and, is available to the presenter as the session continues to happen. Furthermore, the detailed classroom analytics generated by the response generator module enables the presenter to identify the poor student performance and helps to build a better future content. The detailed classroom analytics, also enables the presenter to generate classroom performance and attention level reports for each of the plurality of participants and the attention level reports are shared with the parents of the plurality of the participants.
According to one embodiment herein, the system further enables the presenter to evaluate his/her own performance by generating aggregate engagement score of the plurality of participants. The aggregate engagement score is high for the plurality of participant, then the presenter is doing a good job and if the aggregate engagement score of the plurality of participants is below par, then the presenter is notified about the overall below par lesson delivery.
The foregoing summary is illustrative only and is not intended to be in any way limiting. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features will become apparent by reference to the drawings and the following detailed description.
These and other aspects of the embodiments herein will be better appreciated and understood when considered in conjunction with the following description and the accompanying drawings. It should be understood, however, that the following descriptions, while indicating preferred embodiments and numerous specific details thereof, are given by way of illustration and not of limitation. Many changes and modifications may be made within the scope of the embodiments herein without departing from the spirit thereof, and the embodiments herein include all such modifications.
The other objects, features and advantages will occur to those skilled in the art from the following description of the preferred embodiment and the accompanying drawings in which:
Although the specific features of the present invention are shown in some drawings and not in others. This is done for convenience only as each feature may be combined with any or all of the other features in accordance with the present invention.
In the following detailed description, reference is made to the accompanying drawings that form a part hereof, and in which the specific embodiments that may be practiced is shown by way of illustration. These embodiments are described in sufficient detail to enable those skilled in the art to practice the embodiments and it is to be understood that the logical, mechanical, and other changes may be made without departing from the scope of the embodiments. The following detailed description is therefore not to be taken in a limiting sense.
The foregoing of the specific embodiments will so fully reveal the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and/or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments.
The accompanying drawings are used to help easily understand various technical features and it should be understood that the embodiments presented herein are not limited by the accompanying drawings. As such, the present disclosure should be construed to extend to any alterations, equivalents and substitutes in addition to those which are particularly set out in the accompanying drawings. Although the terms first, second, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are generally only used to distinguish one element from another.
The various embodiments herein provide a system and method for intelligent interpretation of information to autonomously design in-class/hybrid/remote assessment. The method involves picking up audio of the presenter from an audio input device such as microphone during an interaction. The interaction includes both either audio or video interaction. Further, the method involves extracting the key information present in the captured audio interaction and then use the extracted key information to intelligently generate assessments such as quiz questions, multiple-choice questions and mathematical questions.
According to one embodiment herein, a method for intelligent interpretation of information to autonomously design in-class/hybrid/remote assessment is provided. The method includes receiving audio interaction of a presenter through an audio input device and uploading course content into a knowledge database. The method allows the presenter to optionally flag the significant keywords of the audio interaction while speaking into the audio input device through a plurality of means. The plurality of means comprises a specific key on a keyboard, a clicker device including mouse or a verbal que spoken into the microphone. Furthermore, the plurality of means is used in real-time, when the presenter wants to forcefully publish the question to the plurality of participants based on an important information just communicated. For instance, if the presenter is talking about the history of the world and mentions an important detail while talking, they may click on the clicker, press a designated key on the keyboard, a click on the interface or say out a verbal que such as “flag this” and the system will be able to generate a question or quiz from the recently communicated information to send to the participants. Moreover, the audio interaction comprises an audio or a video interaction and the audio input device includes a microphone. The method further comprises capturing the audio interaction of the presenter by an audio capturing module. Then, transcribing the audio interaction along with the optionally flagged significant keywords by the presenter into a plurality of text by an audio-text conversion module and saving the transcribed plurality of text and course content in the knowledge database. The method further comprises analyzing the transcribed plurality of text by a text analyzation module. The text analyzation module, further separates the last phrase or sentence or piece of information of the transcribed plurality of text comprising the flagged significant keywords received from the presenter. Furthermore, the method includes generating question by a question generation module based on the course content presented by the presenter. Followed by reviewing and seeking approval of the presenter for the question generated by the question generation module. On reviewing the question, the presenter either approves or disapproves the question and publishes the question to a plurality of participants the approved questions. In addition, if the presenter disapproves the question generated, then the question generation module, generates another question, seeks approval from the presenter and publishes to the plurality of participants. The method further involves saving the published question in the knowledge database. Once saved, the question is displayed to the plurality of participants to respond. Furthermore, the method involves generating analytics, auto-checking the responses of the plurality of participants and displaying the analytics to the presenter by a response generation module. Following this, the presenter receives an alert if the plurality of participants persistently responds incorrectly to the published question. Finally, the method involves displaying the precise response to the plurality of participants, generating and storing detailed classroom analytics in the knowledge database.
According to one embodiment herein, the transcribing the audio interaction into the plurality of text by the audio-text conversion module, employs an automatic speech recognition system (ASR). The ASR is made up of statistical models that reflect the mapping of continuous phonetic sound sequences (spoken utterances or speech waveforms) to the plurality of text outputs that is recognized as being in human language. The ASR model, further comprises a Language Model, a Pronunciation Model (Lexicon/Dictionary), and an Acoustic Model. In addition, the accuracy of the transcription improves whenever the models are consistently trained with fresh voice data from multiple speakers and a wider vocabulary (Language Model). Thus, the accuracy is quantified statistically by the Word Error Rate (WER). Ideally, the WER equates to less than 11% for very accurate models. Quality of the dataset, audio, and lexicon are ultimately the most crucial factors while training a speech recognition model. Furthermore, the presenter can make audio information accessible with the aid of speech recognition. The audio has a lot of essential information that is hidden away, but it is difficult to look through. By using voice to text, audio is converted into text and made searchable on a word-by-word basis. As a result, the output can be utilized to index content archives in addition to existing metadata to improve the searchability of big archives and serve as automatic subtitles for those who have hearing loss. Imagine a journalist searching for video to use in a piece they are writing. The journalist can easily seek for the footage based on terms regarding the incident instead of attempting to determine the exact date that an event occurred.
According to one embodiment herein, the question generated by the question generation module includes empirical or theoretical depending on the subject taught by the presenter. The empirical questions includes mathematical questions or those that can be measured or calculated. For instance, when the presenter/teacher asks the plurality of participants/student to solve a mathematical question which has a unique or limited unique answers such as square root of 81. The response can be + or −9. Such questions when asked by the presenter/teacher would send out the question as fill in the blank, type short or long answer etc. Thus, the system will input information from the presenter and generate a question. The result of the question will also be automatically calculated using a separate system which may involve use of external tools, software, service. Once the question has been generated and approved, the question will be shared with the presenter and then once the presenter approves the question, the students will be able to solve the question. The student's response will be compared with the saved correct result. The theoretical questions include those questions that contains an important piece of information, including significant keywords. Furthermore, the method for generating question is provided. The method includes breaking the statement of the presenter, into sentence structures, identifying intelligently the important piece of information in the respective sentence, applying english grammar rules and machine learning NLP (Natural Language Processing) models, selecting the topic that matches the subject being taught by the presenter and creating the question. Moreover, while applying grammar rules and machine learning NLP models for generating questions, the following method is observed. The method includes finding and marking a verb in a sentence, checking the type of verb in the sentence. The type of verb includes action verb and state of being verb or linking verb. The method further involves, finding the subject and complement. Finding the complement includes finding the object of the action verb and finding the subject complement. The object of the action verb includes direct object and indirect object, and the subject complement includes predictive nominative and predictive adjective. The predictive nominative comprises renaming the subject and predictive adjective comprises describing the subject. The method further involves saving the object of the action verb and subject complement in the knowledge database, finding the object of the action verb and subject in the course contents uploaded by the presenter in the knowledge database and getting the type of sentence. The type of sentence includes simple and complex sentences. Finally, the method involves generating questions using english grammar rules for simple sentences and generating questions using machine learning NLP (Natural Language Processing) models for complex sentences. For instance, during a lesson the presenter communicates the following information: “Mount Everest is the tallest peak in the world”. In this sentence the important piece of information is “Mount Everest” and “tallest”. The method will pick up subject, object, verb, adjective. The method will then lock down to one piece of information for instance in this case it may be “Mount Everest”. Now the method will use a third-party system to find reasonable alternates of this and generate a multiple-choice question. The alternates may be “Black mountain,” “K2” or “Kangchenjunga”. Further, the method will then send a question as follows to the presenter for approval: ______ is the tallest mountain in the world:
For instance, if the presenter is teaching a topic relating to physics subject and the presenter mentions the following detail. “Sir Isaac Newton discovered gravity” and flags this detail as important. Then the method will highlight the elements such as: Sir Isaac Newton; Discovered and Gravity. Then the method uses AI to generate the following question:
Sir Isaac Newton discovered ______.
There are a total of 7 national parks in California.
According to one embodiment herein, the type of question generated by the question generation modules includes a multiple-choice question, an information-based question, true/false questions, fill in the blank's questions or short answer questions. Furthermore, the method provides the presenter to either set the time for the question being published, by having limited time for the plurality of participants to respond to the question or the presenter may choose not to time the question.
According to one embodiment herein, the plurality of participants attending the session comprises various modes including in-class, hybrid or remotely. The method allows the plurality of participants to respond to the questions by typing, clicking or by dictating if attending remotely. Furthermore, the plurality of participants after responding to the question, an automatic report is generated, saved and displayed to the presenter. The automatic report is then displayed to the presenter in graphical format based on the percentage of the plurality of participants choosing to submit a certain response during the course of session. In addition, the presenter also has the option to track the effectiveness of the session while conducting the session. Furthermore, the auto-checking the responses of the plurality of participants by the response generation module is carried out using an external tools, software or service.
According to one embodiment herein, the detailed classroom analytics comprises a detailed report of the questions published, class reports, course content reports and student reports. The detailed classroom analytics is stored in the knowledge database and the detailed classroom analytics is populated after every session and an aggregate; the detailed classroom analytics is available to the presenter as the session continues to happen. Furthermore, the detailed classroom analytics generated by the response generator module enables the presenter to identify the poor student performance and helps to build a better future content. The detailed classroom analytics further enables the presenter to generate classroom performance and attention level reports for each of the plurality of participants and the attention level reports are shared with the parents of the plurality of the participants or students.
According to one embodiment herein, a computer implemented system comprising instructions stored on a non-transitory computer readable storage medium and executed on a hardware processor for intelligent interpretation of information to autonomously design in-class/hybrid/remote assessment is provided. The system comprises an audio input device configured to receive an audio interaction of a presenter. The audio interaction comprises of significant keywords that is optionally flagged by the presenter through a plurality of means. The audio interaction includes an audio or a video interaction. The audio input device includes a microphone. Furthermore, the plurality of means comprises a specific key on a keyboard, a clicker device including mouse or a verbal que spoken into the microphone. The plurality of means is used in real-time, when the presenter wants to forcefully publish the question to the plurality of participants based on an important information just communicated. For instance, if the presenter is talking about the history of the world and mentions an important detail while talking, they may click on the clicker, press a designated key on the keyboard, a click on the interface or say out a verbal que such as “flag this” and the system will be able to generate a question or quiz from the recently communicated information to send to the participants. The system further includes an audio capturing module configured to capture the audio interaction of the presenter; an audio-text conversion module configured to transcribe the audio interaction and the optionally flagged significant keywords by the presenter, into a plurality of text. In addition, the system further comprises a knowledge database configured to maintain the transcribed plurality of text and course content uploaded by the presenter. Furthermore, the system comprises a text analyzation module configured to analyze the transcribed plurality of text, and separate the last phrase or sentence or piece of information of the flagged significant keywords received from the presenter. The system also includes a question generation module configured to generate question based on the course content presented by the presenter. The question generated is further subjected to review and approval from the presenter. The question approved by the presenter is then, published by the question generation module to a plurality of participants for responding. Furthermore, the question generation module is configured to generate another question, seek approval from the presenter and publish the question to the plurality of participants for responding, on disapproval of previous question by the presenter. Furthermore, the system comprises a response generation module configured to generate analytics, auto-check the responses of the plurality of participants and display the analytics to the presenter. The response generation module is further configured to send an alert to the presenter, if the plurality of participants persistently responds incorrectly, display the precise response to the plurality of participants, generate and store detailed classroom analytics in the knowledge database.
According to one embodiment herein, the audio-text conversion module configured to transcribe the audio interaction into the plurality of text, employs an automatic speech recognition system (ASR). The ASR is made up of statistical models that reflect the mapping of continuous phonetic sound sequences (spoken utterances or speech waveforms) to the plurality of text outputs that is recognized as being in human language. The ASR model comprises a Language Model, a Pronunciation Model (Lexicon/Dictionary), and an Acoustic Model. In addition, the accuracy of the transcription improves whenever the models are consistently trained with fresh voice data from multiple speakers and a wider vocabulary (Language Model). Thus, the accuracy is quantified statistically by the Word Error Rate (WER). Ideally, the WER equates to less than 11% for very accurate models. Quality of the dataset, audio, and lexicon are ultimately the most crucial factors while training a speech recognition model. Furthermore, the presenter can make audio information accessible with the aid of speech recognition. The audio has a lot of essential information that is hidden away, but it is difficult to look through. By using voice to text, audio is converted into text and made searchable on a word-by-word basis. As a result, the output can be utilized to index content archives in addition to existing metadata to improve the searchability of big archives and serve as automatic subtitles for those who have hearing loss. Imagine a journalist searching for video to use in a piece they are writing. The journalist can easily seek for the footage based on terms regarding the incident instead of attempting to determine the exact date that an event occurred.
According to one embodiment herein, the question generated by the question generation module includes empirical or theoretical depending on the subject taught by the presenter. The empirical questions includes mathematical questions or those that can be measured or calculated. For instance, when the presenter/teacher asks the plurality of participants/student to solve a mathematical question which has a unique or limited unique answers such as square root of 81. The response can be + or −9. Such questions when asked by the presenter/teacher would send out the question as fill in the blank, type short or long answer etc. Thus, the system will input information from the presenter and generate a question. The result of the question will also be automatically calculated using a separate system which may involve use of external tools, software, service. Once the question has been generated and approved, the question will be shared with the presenter and then once the presenter approves the question, the students will be able to solve the question. The student's response will be compared with the saved correct result. The theoretical questions include those questions that contains an important piece of information, including significant keywords.
According to one embodiment herein, the type of question generated by the question generation modules includes a multiple-choice question, an information-based question, true/false questions, fill in the blank's questions or short answer questions. Furthermore, the system provides the presenter to either set the time for the question being published, by having limited time for the plurality of participants to respond to the question or the presenter may choose not to time the question.
According to one embodiment herein, the plurality of participants attending the session comprises various modes including in-class, hybrid or remotely. The system further provides the plurality of participants to respond to the questions by typing, clicking or by dictating if attending remotely. Furthermore, the plurality of participants after responding to the question, an automatic report is generated, saved and displayed to the presenter. The automatic report is then displayed to the presenter in graphical format based on the percentage of the plurality of participants choosing to submit a certain response during the course of session. In addition, the presenter also has the option to track the effectiveness of the session while conducting the session. Furthermore, the response generation module is configured to auto-check the responses of the plurality of participants using an external tools, software or service.
According to one embodiment herein, the response generation module is configured to generate detailed classroom analytics comprising a detailed report of the questions published, class reports, course content reports and student reports. The detailed classroom analytics is stored in the knowledge database and the detailed classroom analytics is populated after every session and, is available to the presenter as the session continues to happen. Furthermore, the detailed classroom analytics generated by the response generator module enables the presenter to identify the poor student performance and helps to build a better future content. The detailed classroom analytics, also enables the presenter to generate classroom performance and attention level reports for each of the plurality of participants and the attention level reports are shared with the parents of the plurality of the participants.
According to one embodiment herein, the system further enables the presenter to evaluate his/her own performance by generating aggregate engagement score of the plurality of participants. The aggregate engagement score is high for the plurality of participant, then the presenter is doing a good job and if the aggregate engagement score of the plurality of participants is below par, then the presenter is notified about the overall below par lesson delivery.
According to one embodiment herein, the
According to one embodiment herein,
______ is the tallest mountain in the world:
According to one embodiment herein,
It is also to be understood that various arrangements may be devised that, although not explicitly described or shown herein, embody the principles of the present disclosure. Moreover, all statements herein reciting principles, aspects, and embodiments of the present disclosure, as well as specific examples, are intended to encompass equivalents thereof.
While the disclosure is susceptible to various modifications and alternative forms, specific embodiment thereof has been shown by way of example in the drawings and will be described in detail above. It should be understood, however that it is not intended to limit the disclosure to the forms disclosed, but on the contrary, the disclosure is to cover all modifications, equivalents, and alternatives falling within the scope of the disclosure.
The embodiments herein disclose a system and method for intelligent interpretation of information to autonomously design in-class/hybrid/remote assessment in video and audio conferencing. The system includes a software platform to enable students to concentrate on an important piece of information and parallelly evaluate their attention level. The system enables the presenter/teacher to flag the sentence or line of importance while giving the session. Once a flag has been raised, the system will interpret and transcribe the information that the teacher is mentioning and save that line. Further, the system will identify main parts of the flagged line which includes at least one of a subject, object, or verb, and find alternates of a similar type of part of the line for at least one of the subject, object, or verbs, using any standard search systems. Furthermore, the system creates an assessment that includes one or more questions of, but not be limited to, multiple-choice question and push it out automatically to evaluate the student engagement.
Hence, the primary objective of the embodiment herein is to track the participant engagement or understanding of a certain topic when they are part of session (in-person or remote). The embodiment herein also helps to generate questions on the go during a session based on the content being discussed within the session. Furthermore, the system also employs AI or Artificial Intelligence to categorize the content into topics and to generate quiz-based questions from speech. The questions are then sent to all the participants of that session during the meeting. The participants respond to the question and the host gets to track the participants engagement during course of session.
Moreover, the embodiment herein disclosed also finds application beyond classroom such as during interviews, where a person is questioned based on what is being discussed. In criminal courts or interrogations, which enables the person to respond to auto-generated questions based on his/her own words or on what is being interrogated upon. The embodiment herein disclosed also finds in application in truth detection system or devices, where a person can be repeatedly posted questions out of his/her own words. Furthermore, the embodiment herein disclosed can also be used to generate questionnaire based on videos/movies, in MOOCs (massive open online courses) and related online courseware. Additionally, the embodiment disclosed herein is also used in integrating software/solutions to automatically capture audio and create quizzes/assessments.
Although the embodiments herein are described with various specific embodiments, it will be obvious for a person skilled in the art to practice the embodiments herein with modifications.
The foregoing description of the specific embodiments will so fully reveal the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and/or adapt for various applications such as specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments.
It is to be understood that the phrases or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practiced with modifications. However, all such modifications are deemed to be within the scope of the claims.
