Patent Application
20210166267
This invention relates generally to the field of electronic communications and the transmittance of such communications. More specifically, the invention discloses a new and useful method for self-rating and autonomously rating a therapeutic value to digital content. Further, tracking a digital diet of a user based on consumption of the labeled content for targeted delivery of an advertisement. Further, the invention discloses a new and useful method for aggregating the therapeutic values of collections of individual pieces of digital content.
In the past few decades, the availability and use of electronic computing devices, such as desktop computers, laptop computers, handheld computer systems, tablet computer systems, and cellular phones have grown tremendously, which provide users with a variety of new and interactive applications, business utilities, communication abilities, and entertainment possibilities.
One such communication ability is electronic messaging, such as text-based, user-to-user messages. Electronic messaging has grown to include a number of different forms, including, but not limited to, short message service (SMS), multimedia messaging service (MMS), electronic mail (e-mail), social media posts and direct messages, and enterprise software messages. Electronic messaging has proliferated to such a degree that it has become the primary mode of communication for many people.
While electronic messaging can be a particularly efficient mode of communication for a variety of reasons—instant delivery, limitless distance connectivity, recorded history of the communication—electronic messaging does not benefit from the advantages of in-person communication and telecommunication. For example, when communicating via telecommunication, a person can adjust, alter, or augment the content of their message to an intended recipient through tone, volume, intonation, and cadence. When communicating in-person, or face-to-face, a person can further enhance or enrich their spoken words with eye contact and shift of focus, facial expressions, hand gestures, body language, and the like. In electronic messaging, users lack these critically important signals, clues, and cues, making it difficult for people to convey the subtler aspects of communication and deeper intent. As a result, issues of meaning, substance, and sentiment are often lost or confused in electronic messages, which can, and very often does, result in harmful or damaging misunderstandings. Miscommunications can be particularly damaging in interpersonal and business relationships.
Another unintended effect of our overreliance on electronic communication is the impairment of emotional and mental health. In a recent article published in the American Journal of Psychiatry, Dr. Jerald Block wrote “technology addiction is now so common that it merits inclusion in the Diagnostic and Statistical Manual of Mental Disorders, the profession's primary resource to categorize and diagnose mental illnesses.” He went on to further state that the disorder leads to anger and depression when the tech isn't available, as well as lying, social isolation and fatigue. Our devices and experiences from said devices (receiving likes, comments and shares on social media) are in essence a drug dealer and drugs, respectively: Having the capability of doling out the same kind of dopamine hit as a tiny bump of cocaine. In effect, creating the typical addiction/dependency vicious cycle and all of the attendant consequences.
According to psychotherapist, Nancy Colier, author of “The Power of Life”, “We are spending far too much of our time doing things that don't really matter to us . . . [and become] disconnected from what really matters, from what makes us feel nourished and grounded as human beings.” Based on her findings, the average person checks their smartphones 150 times per day, or every six minutes. Furthermore, the average young adult sends on average 110 texts per day and 46% of respondents checked that their devices are something that they couldn't live without.
With this kind of digital ubiquity, it is becoming readily apparent that any solution to the problem involving curtailing or augmenting user behavior is not a realistic approach. Current approaches espoused by experts involve any one of, or combination of, the following: Downloading an app (Moment, Alter, etc.) that locks or limits phone usage upon reaching a pre-specified limit; disabling notifications from your phone settings; keeping the blue-hued light of your smartphone away from your place of rest; and even buying and carrying around a dummy phone.
There is a void for a solution that takes into account ubiquitous usage and provides delivery of pro-mental and emotional health content—personalized to the user, much like the way therapeutics have become narrowly tailored—to counter all of the digital-mediated ill effects plaguing our society. These effects will only logarithmically grow as we transition into the IoT era—where we will be exposed to thousands of internet-enabled objects (each capable of delivering contextualized analytics and provisioning) as part of our day-to-day living.
Moreover, there is a void for a solution that allows for a self-generated or system-generated rating for therapeutic value of digital content. In other words, currently, there is no technological solution for a standardized rating of digital content based on its psycho-emotional effects on the targeted user or a general user. Furthermore, there is currently no solution with downstream provisioning of digital/interactive content based on the rated content. Furthermore, there lacks a means for tracking a user's consumption of labeled digital content (indicator of intended psycho-emotional effect) for a more targeted and personalized advertisement delivery/experience.
Disclosed is a method and system for imposing a dynamic sentiment vector to an electronic message. In one embodiment of the invention, the method comprises: receiving a text input comprising message content from an electronic computing device associated with a user; parsing the message content comprised in the text input for emotionally-charged language; assigning a sentiment value, based on the emotionally-charged language, from a dynamic sentiment value spectrum to the text input; and, based on the sentiment value, imposing a sentiment vector, corresponding to the assigned sentiment value, to the text input, the imposed sentiment vector rendering a sensory effect on the message content designed to convey a corresponding sentiment.
In another embodiment of the invention, the method comprises: receiving a text input comprising message content from an electronic computing device associated with a user; converting the message content comprised in the text input received from the electronic computing device into converted text in a standardized lexicon; parsing the converted text for emotionally-charged language; generating a sentiment value for the text input from a dynamic sentiment value spectrum by referencing the emotionally-charged language with a dynamic library of emotionally-charged language; and, based on the sentiment value, imposing a sentiment vector to the text input, the imposed sentiment vector rendering a sensory effect on the message content designed to convey a corresponding sentiment.
For example, in one application of the invention, a user can write and submit a text message on the user's cellular phone for delivery to the user's best friend. After receiving the text message, the invention can analyze the message content of the text message and determine, based on the verbiage, syntax, and punctuation within the message content, that the user is attempting to convey excitement through the text message. The invention can then apply a visual filter of red exclamation points or other illustrative, performative, or kinetic attributes to the text message, indicating the excitement of the user, before the text message is delivered to the user's best friend.
In another example of one application of the invention, a user can write and submit a direct message through a social media application (e.g., Instagram, Facebook, SnapChat) on the user's mobile phone for delivery to a second user. After receiving the direct message, the invention can use a camera built into the user's mobile phone to capture an image of the user's face and analyze aspects of the user's face (e.g., curvature of the lips, motion of the eyes, etc.) to determine the user's mood or expression. Based on the user's mood or expression, the invention can then apply a vibration pattern to the direct message before the direct message is delivered to the second user.
In another object of the invention, sentiment and cues of the users emotional or mental state is not gleamed by referencing a parsed user input against a dynamic library of emotionally-charged language to generate a sentiment value and vector for overlaying the said input. Rather, the emotional and mental state (EMS) of the user is chosen by the user or determined by the system based on user engagement with the interface or content. Once the EMS of the user is defined, carefully curated and efficacious content is delivered to the user to combat the defined EMS.
In another aspect, a method is provided for delivering a digital therapeutic, specific to a user-chosen emotional or mental state (EMS), the method comprising the steps of: recognizing at least one EMS selected by the user from a plurality of EMS, the selected EMS indicating at least one of a feeling, sensation, type of discomfort, mood, mental state, emotional condition, or physical status of the user. Once the EMS is defined, the method then calls for pushing a primary-level message personalized to the user based on at least one stored message coupled to the selected EMS. Finally, pushing at least a secondary-level message personalized to the user based on a threshold-grade match of the user response to the pushed primary-level message with at least one stored response coupled to a stored primary-level message, whereby the user and stored response is a measure of at least one of a reaction, compliance, engagement, or interactivity with the pushed and, or stored primary-level message. The primary and secondary-level messages may contain at least one of a text, image, sound, video, art asset, suggested action or recommended behavior. The efficaciousness or therapeutic value of the primary or secondary messages are validated by at least one—and typically two—independent sources of clinical research or peer-reviewed science, as verified by a credentialed EMS expert.
In another aspect, once the EMS is defined, the method may call for pushing at least a single-level message. The at least single message may contain at least one of a text, image, sound, video, art asset, suggested action or recommended behavior. Again, the efficaciousness or therapeutic value of the primary or secondary messages are validated by at least one—and typically two—independent sources of clinical research or peer-reviewed science, as verified by a credentialed EMS expert.
In yet another aspect, a system is described and claimed for delivering the digital content of validated therapeutic efficacy. The system may comprise an EMS store; at least a primary message prescriber; a processor coupled to a memory element with instructions, the processor when executing said memory-stored instructions, configure the system to cause: at least one EMS from a plurality of EMS in the EMS store to be selected by the user, said selected EMS indicating at least one of a feeling, sensation, type of discomfort, mood, mental state, emotional condition, or physical status of the user; and the at least primary message prescriber pushing a primary-level message personalized to the user based on at least one stored message coupled to the selected EMS.
In yet other aspect, at least a secondary message prescriber is included, wherein the at least secondary message prescriber pushes at least a secondary-level message personalized to the user based on a threshold-grade match of the user response to the pushed primary-level message with at least one stored response coupled to a stored primary-level message, whereby the user and stored response is a measure of at least one of a reaction, compliance, engagement, or interactivity with the pushed and, or stored primary-level message.
In both aspects (primary or at least secondary message prescribers), the messages or content may contain at least one of a text, image, sound, video, art asset, suggested action or recommended behavior. Much like in the method aspects, the therapeutic value of the messages or content are validated by at least one—and typically two—independent sources of clinical research or peer reviewed published science and selected by a credentialed EMS expert.
Whether the sentiment or cues are generated by the system or defined by the user, content is being overlaid or delivered to enhance intonation, heighten digital communication, obviate ambiguity, boost mood, support self-esteem, inspire wellness, and aid in the longitudinal and non-interventional care for people in distress or need—leveraging a familiar and known modality (digital devices). According to the claimed invention, a whole ecosystem of receiving and delivering modalities are provided for a host of digital therapeutics. The digital therapeutic offerings—with the aid of Artificial Intelligence (AI), machine learning, and, or predictive EMS assessment tools—may deliver increasingly personalized solutions uniquely tailored to aid each subscriber. Such non-interventional, anonymous, and device-centric solutions are far more appropriate to combat the rising ill-effects of device dependency—rather than pharmaceutical dosing, in-patient treatment, and altering device behavior.
In another aspect of the invention, the user or system may generate a rating for a therapeutic value of digital content. The claimed invention claims and discloses a technological solution for a standardized rating of digital content based on its psycho-emotional effects on the targeted user or a general user. The user may then engage with the content accordingly. Forms of engagement may be suggested, prompted, or pushed based on the uploaded and rated content. It is one object to enable a system and method for labeling a therapeutic value to digital content, said method comprising the steps of uploading a digital content by a user; selecting at least one condition from a plurality of conditions that the uploaded digital content is intended to cure, said selected condition indicating at least one of a feeling, sensation, mood, mental state, physical state, emotional condition, physical status; and overlaying a therapeutic label to the digital content corresponding to the selected condition.
It is another object to disclose and claim a method and system, wherein said system comprises of a condition selector, a therapeutic labeler, a non-transitory storage element coupled to the processor wherein the encoded instructions when implemented by the processor, configure the digital therapeutic value pipeline to: upload a digital content by a user; select at least one condition from a plurality of conditions that the uploaded digital content is intended to cure by the condition selector, said selected condition indicating at least one of a feeling, sensation, mood, mental state, physical state, emotional condition, physical status; and overlay a therapeutic label to the digital content corresponding to the selected condition by the therapeutic labeler.
In another aspect of the invention, the digital content, labeled in terms of its determined intended psycho-emotional effect on the user, is further tracked by a Digital Nutrition (DN) tracker to assess a DN diet score for the user. The score may be an at-the-moment score or more longitudinal, reflecting the users media consumption habits for a more targeted delivery of an advertisement.
In another aspect of the disclosed invention, systems and methods are described for accessing a collection of individual pieces of digital content (also referred to as a “digital content channel”), autonomously determining a therapeutic value for each of the individual pieces of digital content (also referred to as “individual content pieces” (ICPs)), and aggregating the therapeutic values of the individual pieces of digital content to generate a digital nutrition footprint for the collection. A graphical representation of the digital nutrition fingerprint may also be provided. The digital nutrition footprint may provide users with a holistic snapshot of the digital nutrition value of the collection of individual pieces of digital content.
Numerous embodiments of the invention will now be described in detail with reference to the accompanying figures. The following description of the embodiments of the invention is not intended to limit the invention to these embodiments but rather to enable a person skilled in the art to make and use this invention. Variations, configurations, implementations, and applications described herein are optional and not exclusive to the variations, configurations, implementations, and applications they describe. The invention described herein can include any and all permutations of these variations, configurations, implementations, and applications.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the invention. It will be apparent, however, to one skilled in the art that the invention can be practiced without these specific details.
Reference in this specification to “one embodiment” or “an embodiment” means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the invention. The appearances of the phrase “in one embodiment” in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Moreover, various features are described which may be exhibited by some embodiments and not by others. Similarly, various requirements are described which may be requirements for some embodiments but no other embodiments.
The electronic computing device 140 may be any electronic device capable of sending, receiving, and processing information. Examples of the computing device include, but are not limited to, a smartphone, a mobile device/phone, a Personal Digital Assistant (PDA), a computer, a workstation, a notebook, a mainframe computer, a laptop, a tablet, a smart watch, an internet appliance and any equivalent device capable of processing, sending and receiving data. The electronic computing device 140 can include any number of sensors or components configured to intake or gather data from a user of the electronic computing device 140 including, but not limited to, a camera, a heart rate monitor, a temperature sensor, an accelerometer, a microphone, and a gyroscope. The electronic computing device 140 can also include an input device (e.g., a touchscreen or a keyboard) through which a user may input text and commands.
As further described below, the sentiment vector generator 110 is configured to receive an electronic message 160 (e.g., a text input) from the particular user 130 associated with the electronic computing device 140 and run a program 116 executed by the processor 120 to analyze contents of the electronic message, determine a tone or a sentiment that the particular user 130 is expressing through the electronic message 160, and apply a sentiment vector to the electronic message 160, the sentiment vector designed to convey the tone or sentiment determined by the sentiment vector generator 110. The electronic message 160 can be in the form of a SMS message, a text message, an e-mail, a social media post, an enterprise-level workflow automation tool message, or any other form of electronic, text-based communication. The electronic message 160 may also be a transcription of a voice message generated by the particular user 130. For example, in one embodiment, from a messaging application installed on the electronic computing device 140, the user 130 may select to input a voice (i.e., audio) message through a microphone coupled to the electronic computing device 140 or initiate a voice message through a lift-to-talk feature (e.g., the user lifts a mobile phone to the user's ear and the messaging application automatically begins recording a voice message). In this example, the system 100 can generate a transcription of the voice message or receive a transcription of the voice message from the messaging application. After receiving or generating the transcription (i.e., an electronic message), the sentiment vector generator 110 can then analyze the message content within the electronic message, determine the mood or sentiment of the message content, and apply a corresponding sentiment vector to the electronic message, as further described below.
In one embodiment, the system 100 may receive an electronic message 160 in the form of an electroencephalograph (EEG) output. For example, in this embodiment, a user can generate a message using an electronic device communicatively coupled to the user and capable of performing an electroencephalograph to measure and record the electrochemical activity in the user's brain. In this example, the system 100 can transcribe the EEG output into an electronic message 160 or receive a transcription of the EEG output from the electronic device communicatively coupled to the user. After receiving or generating the electronic message 160 from the EEG, the sentiment vector generator 110 can then analyze the message content within the electronic message 160, determine the mood or sentiment of the message content, and apply a corresponding sentiment vector to the electronic message. In one example of this embodiment, a user is connected to an augmented reality (AR) or virtual reality (VR) headset capable of performing an EEG or an equivalent brain mapping technique. The user can generate a message simply by thinking of what the user is feeling or would like to say. The headset can monitor and record these thoughts and feelings using the EEG and transcribe the thoughts and feelings into an electronic message or send the EEG output signals directly to the system 100. The system 100 can then analyze the message content included within the electronic message 160, determine the mood or sentiment of the message content, and apply a corresponding sentiment vector to the electronic message 160, creating a vectorized message. The system 100 can then send the vectorized message to the user's intended recipient (e.g., a recipient that the user thought of).
In one embodiment, the particular user 130 may submit an electronic message 160 through a mobile application (e.g., a native or destination app, or a mobile web application) installed on the particular user's mobile phone or accessed through a web browser installed on the user's phone. In one example of this embodiment, the user accesses the mobile application, submits the electronic message 160 in the form of a text input. The sentiment vector generator 110 can then analyze the message content included within the electronic message 160, determine the mood or sentiment of the message content, and apply a corresponding sentiment vector to the electronic message 160, creating a vectorized message. In this example, the user can then send the vectorized message to the user's intended recipient(s) 131 (e.g., by copying and pasting the vectorized message into a separate messaging application or selecting to export the vectorized message to a separate application, as further described below). In one variation of this embodiment, the user may send the vectorized message to the intended recipient 131 directly through the mobile application. In one embodiment, the user may submit an electronic message 160, or a component of an electronic message (e.g., a single word or phrase within the message content of an electronic message) using a touch input gesture. In one example of this embodiment, the user may submit the electronic message 160 through an electronic computing device by swiping a finger on a touch screen coupled to the electronic computing device 140 in a U-shaped gesture on the electronic message.
In another embodiment, the user may input an electronic message 160 into an entry field of a third-party application such as an email client (e.g., Gmail, Yahoo Mail) or a social media application (e.g., Facebook, Twitter, Instagram). For example, the user may input a message into the body of an email, or into a status update on Facebook. In this embodiment, the system 100 can detect the input of the electronic message 160 into the third-party application and upload the electronic message 160 to the sentiment vector generator 110. The sentiment vector generator 110 can then analyze the message content contained within the electronic message 160, determine the mood or sentiment of the message content, and apply a corresponding sentiment vector to the electronic message 160, creating a vectorized message. The sentiment vector 110 can then replace the electronic message 160 within the third-party application with the vectorized message. Alternatively, the user may select to replace the electronic message 160 with the vectorized message (e.g., by copying and pasting the vectorized message into the entry field).
The semantic layer 112b is configured to recognize, within the message content contained within the electronic message 160, natural language syntax. For example, in the message “is it ok if we text on WhatsApp ?” the construction of the phrases “is it ok” and “WhatsApp ?” reflect natural language syntax that can express particular sentiments. “is it ok[?]” can express tentativeness in addition to the objective question that the phrase asks. For reference, inverting and contracting the first two words to create the phrase “it's okay[?]” results in a phrase that can express more confidence. Likewise, the space inserted between “WhatsApp” and “?” can have the effect of “softening” the question mark in comparison to “WhatsApp?” The semantic layer 112b is configured to recognize the use of natural language syntax such as “is it ok” and “WhatsApp ?” and can be further configured to translate the recognized natural language syntax into a standardized lexicon. The standardized lexicon can be a standard set of words and terms (e.g., an Oxford dictionary) that the parsing module 112 is able to parse for emotionally-charged language. In one embodiment, the standardized lexicon is a standard set of words and terms with predefined attributes. For example, again referring to the previous example, the semantic layer 112b can translate the entire message from “is it ok if we text on WhatsApp ?” to “can[soft] we text on WhatsApp?[soft]” in order to compare the sentiments expressed within different messages in a more objective manner and determine the nature of the emotionally-charged language contained within the message of content of the electronic message 160.
In one embodiment, the parsing module 112 can include a library of emotionally-charged language 112c. In this embodiment, after parsing the message content contained within the electronic message 160, the parsing module 112 can cross-reference the words and terms contained with the message content to the library of emotionally-charged language 112c. The words and terms contained within the library of emotionally-charged language 112c may be tagged with attributes according to the sentiments they most commonly express. For example, the library of emotionally-charged language 112c may include the terms “disastrous,” “splendid,” “terrible,” and “awesome.” Within the library of emotionally-charged language 112c, “disastrous” may be tagged with the attribute [bad] or [negative]; “splendid” may be tagged with the attribute [good] or [positive]. In one embodiment, the terms contained within the library of emotionally-charged language 112c may additionally or alternatively be tagged with a numeric value. For example, “disastrous” may be tagged with the attributes [negative; 7], and “terrible” may be tagged with the attributes [negative; 5], indicating that while “disastrous” and “terrible” may express similar “negative” sentiments, “disastrous” is more negative than “terrible.” In one embodiment, the parsing module 112 (or, alternatively, any component of the system 100) can dynamically add or remove words or terms to and from the library of emotionally-charged language 112c. The parsing module 112 may use any technique to tag or evaluate the sentiments of emotionally-charged language.
In one embodiment, the library of emotionally-charged language 112c is specific to the particular user 130. In this embodiment, each particular user 130 of the system 100 access a unique library of emotionally-charged language 112c associated only with that particular user. In one variation of this embodiment, the particular user 130 may manually add or remove words and terms to and from the library of emotionally-charged language 112c. In one embodiment of the system 100, the system 100 can be accessed by multiple users. In one variation of this embodiment, the library of emotionally-charged language 112c employed by the parsing module 112 is the same for each user.
In one embodiment of the system 100, the parsing module additionally includes a neural network 150 and a library of inputs 151. In this embodiment, after parsing the message content of an electronic message 160 received by the sentiment vector generator 110, the parsing module 112 can store the electronic message 160 in the library of inputs 151, along with the emotionally-charged language found within the message content and any accompanying attributes, creating a database of messages and their accompanying emotionally-charged language. In this embodiment, the neural network 150 can employ machine learning techniques to analyze this database for patterns and trends in order to dynamically improve the performance of the sentiment vector generator 110. For example, the neural network 150 may determine through the application of an algorithm that the particular user 130 uses the term “disastrous” ten times more often than the particular user 130 uses the term “terrible.” Thus, even though “disastrous” may be a more negative term than “terrible” for the average user or person, the neural network can determine that, for the particular user 130, “disastrous” generally carries less emotional weight than “terrible.” In this example, the neural network 150 can then update the parsing module 112 and the library of emotionally-charged language accordingly. For example, in the example in which the terms “disastrous” and “terrible” begin as tagged within the library of emotionally-charged language 112c as [negative; 7] and [negative; 5], respectively, the neural network 150 can update the attributes to read [negative; 5] and [negative 7], respectively. In one embodiment, the parsing module 112 can store electronic messages into the library of inputs 151 along with their standardized lexicon conversions.
In one embodiment, as discussed above, after parsing the message content contained within the electronic message 160, the parsing module 112 can cross-reference the words and terms contained with the message content to a library of emotionally-charged language 112c, as depicted in
In one embodiment, as discussed above, after parsing message content contained within an electronic message 160 for emotionally-charged language, the parsing module 112 can assign attributes to the emotionally-charged language found in the message content of the electronic message 160. In one embodiment, the sentiment vector generator 110 can analyze the emotionally-language and their accompanying attributes to generate a sentiment value from the dynamic sentiment value spectrum 114, as depicted in
In one embodiment, the sentiment vector generator 110 can generate a sentiment value for an electronic message 160 by determining which of the emotionally-charged terms found in the message content of the electronic message carries the most emotional weight. For example, in one embodiment, the parsing module 112 can parse the message content of an electronic message 160 for emotionally-charged language and assign each emotionally-charged term with a positivity scale value, an activity scale value, and an emotional weight value. In this embodiment, the sentiment vector generator 110 can then determine a sentiment value for the electronic message by determining which of the emotionally-charged terms has the highest emotional weight value, and then determining the sentiment value on the dynamic sentiment value spectrum 114 closest to the position of emotionally-charged term with the highest emotional weight value.
In one embodiment, the library of emotionally-charged language 112c associates each emotionally-charged term contained within the library with a sentiment value from the dynamic sentiment value spectrum 114. For example, the library of emotionally-charged language 112c may associate the words “gleeful,” “splendid,” and “terrific” with a “happy” sentiment value. In this example, if the message content of an electronic message 160 includes any of the terms “gleeful,” “splendid,” or “terrific,” the sentiment vector generator 110 can generate a “happy” sentiment value for the electronic message 160. However, the sentiment vector generator can generate a sentiment value for an electronic message 160 using any other methodology.
In one embodiment, the particular user 130 may select a sentiment value from the dynamic sentiment value spectrum for an electronic message 160. In one variation of this embodiment, after the parsing module 112 parses the message content of an electronic message 160 submitted by the particular user 130, the sentiment vector generator 110 can generate multiple sentiment values for the electronic message 160 and present the multiple sentiment values for the electronic message 160 to the particular user 130 for selection. For example, after receiving electronic message 160a (depicted in
In one embodiment, as discussed above, the system 100 includes a neural network 150 and a library of inputs 151 communicatively coupled to the sentiment vector generator 110. In one variation of this embodiment, after generating a sentiment value for an electronic message 160, the sentiment vector generator 110 store the electronic message 160 and its accompanying sentiment value in the library of inputs 151 creating a database of messages and their accompanying sentiment values. In this embodiment, the neural network 150 can employ machine learning techniques to analyze this database for patterns and trends in order to dynamically improve the performance of the sentiment vector generator 110. In one variation of this embodiment, the neural network 150 can dynamically edit or rearrange the dynamic sentiment value spectrum 114. For example, In the rearranged version, the sentiment values have adjusted and coalesced into more discrete sections (115c-115e). This may reflect that a particular user 130 associated with the rearranged sentiment value spectrum 117 generates messages most of their messages with a similar tone, making the difference between similar sentiments subtler than that of the average person.
In one embodiment, the sentiment vector generator 110 can generate a sentiment value for an electronic message 160 at least in part by utilizing information about a particular user 130. For example, in one embodiment, the system 100 can generate sender context associated with a particular user 130. The sender context can include, but is not limited to: social media data associated with the particular user, data obtained from IoT (internet of things) devices associated with the particular user, data obtained from wearable devices associated with the particular user, genetic profile data associated with the particular user, and stress data of the particular user. In one variation of this embodiment, the system 100 can leverage sensors and inputs coupled to an electronic computing device 140 associated with the particular user 130 to generate sender context associated with the particular user 130, as depicted by step S160 in
In another variation of the previous embodiment, the sentiment vector generator 110 can generate a sentiment value for an electronic message 160 at least in part by utilizing information about an intended recipient of the electronic message 160. In this embodiment, after receiving an electronic message 160, the system 100 can determine an intended recipient 131 of the electronic message 160. The system 100 can then generate recipient context associated with the intended recipient 131. The recipient context can include but is not limited to: social media data associated with the intended recipient, data obtained from IoT (internet of things, e.g., a smart home assistant such the Amazon Echo) devices associated with the intended recipient, data obtained from wearable devices associated with the intended recipient, genetic profile data associated with the intended recipient, and stress data associated with the intended recipient. For example, in one embodiment, the system 100 can leverage sensors built into an electronic device 141 associated with the intended recipient to determine a mood of the intended recipient 131 at the time that the electronic message 160 is generated. The sentiment vector generator 110 can then generate a sentiment value for the electronic message 160 based at least in part on the determined mood of the intended recipient 131.
After generating a sentiment value for an electronic message 160, the sentiment vector generator 110 can then select a sentiment vector from a library of sentiment vectors 118, the selected sentiment vector designed to convey a sentiment corresponding to the generated sentiment value, and impose the selected sentiment vector to the electronic message 160, as depicted in
In one embodiment, for example, after generating an “inquisitive” sentiment value for an electronic message 160, the sentiment vector generator 110 may impose a graphic onto the electronic message 160, as depicted by step 141b in
In one embodiment, for another example, after generating a “judgmental” sentiment value for an electronic message 160, the sentiment vector generator 110 can edit the font of a key word in the message content, as depicted by step S141c in
In one embodiment, the sentiment vector generator 110 can impose an animated character or personality to the electronic message 160, or transpose the electronic message 160 into a graphic of an animated character or personality. For example, in one variation of this embodiment, the library of sentiment vectors 118 may include a series of the same animated character (take, for example, an animated llama or chicken) performing various actions associated with various corresponding sentiments. For example, the library of sentiment vectors 118 may include a static or dynamic graphic of an animated chicken stomping with red eyes (expressing anger), another graphic of the animated chicken laying in a hammock and basking in the sun (expressing contentedness), and another graphic of the animated chicken blowing a kiss (expressing affection). In this example, after generating an “anger” sentiment value for an electronic message 160, the sentiment vector generator 110 can transpose the electronic message into the graphic of the animated chicken stomping and saying the message content of the electronic message 160.
In one embodiment, the sentiment vector generator 110 can impose a haptic effect onto an electronic message 160. For example, after generating an “anger” sentiment value for an electronic message 160, the sentiment vector generator 110 can impose a vibration or vibration pattern onto the electronic message 160, as depicted by step S141d in
In one embodiment, the sentiment vector generator 110 can impose an audio effect onto an electronic message 160. For example, after generating an “unhappy” sentiment value for an electronic message 160, the sentiment vector generator 110 can impose an audio accompaniment onto the electronic message 160, as depicted by step S142 in
In one embodiment, after generating a sentiment value for an electronic message 160, the sentiment vector generator 110 can impose a vector onto the electronic message 160 that adjusts the position of the words contained with the message content of the electronic message, as depicted by step S141e in
In one embodiment, a user may submit sentiment vectors to the sentiment vector generator 110. For example, in one embodiment, a user may submit a picture or graphic design to impose onto the background of an electronic message and select a sentiment value for the picture or graphic design to be associated with. In this example, after generating a sentiment value for an electronic message 160 corresponding to the sentiment value that the user has selected to associate with the picture or graphic design, the sentiment vector generator 110 can impose the picture or graphic design to the background of the electronic message 160 to convey the corresponding sentiment. In another example, in one variation of this embodiment, a user can select a sentiment vector previously included in the library of sentiment vectors 118 and previously associated with a sentiment value and disassociate the sentiment vector from the associated sentiment value, or re-associate the sentiment vector with a different sentiment value. In yet another example, in one variation of this embodiment, a user can select one or more elements from existing sentiment vectors contained within the library of sentiment vectors 118 and combine them to create a new sentiment vector. In this example, the user can also choose a sentiment value to associate with the new sentiment vector. In another example, in one variation of this embodiment, a user can select a sentiment vector by scrolling through a list of sentiment vectors (e.g., a list including options to adjust text weight, height, font, color, highlight, or content animation) using a flicking gesture, within a mobile application, on a touch screen coupled to an electronic computing device.
The sentiment vector generator can include or generate, but is not limited to, sentiment vectors using any combination of the elements of the sentiment vectors described herein. Additionally, environmental conditions and factors for example, but not limited to, wind, heat, humidity, cold may also play a role in generating the sentiment vector.
In one embodiment of the system 100, a user can submit an electronic message 160 to the sentiment vector generator 110 through a mobile application (e.g., a native application), as discussed above. In one variation of this embodiment, the mobile application can store vectorized messages generated by the sentiment vector generator and allow the user to search through the vectorized messages. In this embodiment, the user can search through the vectorized messages using different filters or queries including, but not limited to: mood, color, content, and sentiment. For example, in one embodiment, the user can enter a sentiment as “anger” as a search query, and a graphical user interface of the mobile application can display a list of all of the vectorized messages that the user has created through the sentiment vector generator 110 with a sentiment value corresponding to an “anger” sentiment. In one embodiment, the sentiment vector generator 110 can impose a hyperlink onto an electronic message 160.
In an embodiment of the invention, the sentiment vector generator 110 can impose a hyperlink onto an electronic message 160. An imperative function of the sentiment vector is GEEQ (genetics, emotion and electroencephalography) and its capacity to integrate messages and messaging with movement and thought as well as the ability to pair information with form and performative elements. In a nutshell, our technology will introduce, integrate, account for, and actively utilize GEEQ (Genetics, Emotion, and Electroencephalography). GEEQ, by its very design, integrates and intermingles the beliefs and postulates of Darwin, Mendel, Mendelssohn, Morgan, and Martha Graham.
As will be discussed, often a plurality of different user devices may be used, but for simplicity this plurality of devices will often be spoken of in the singular form. This use of the singular form is not intended to be limiting, and in general the claims and invention should be understood as operating with a plurality of devices. Although for simplicity, often mobile client computerized devices such as Internet connected versions of the popular Android, iOS, or Windows smartphones and tablets will be used as specific examples of devices, these specific examples are not intended to be limiting. The electronic computing device may include any number of sensors or components configured to intake or gather data from a user of the electronic computing device including, but not limited to, a camera, a heart rate monitor, a temperature sensor, an accelerometer, a microphone, and a gyroscope. The electronic computing device can also include an input device (e.g., a touchscreen or a keyboard) through which a user may input text and commands.
While not shown, note that server, Internet connected storage device and database memory may all be hosted on a cloud computing system. This is intended to both designate and remind the reader that the server, Internet connected storage device and database memory are in fact operating according to scalable Internet cloud-based methods that in turn operate according to automated service provisioning and automated virtual machine migration methods. As previously discussed, examples of such scalable methods include, but are not limited to, Amazon EC2, Microsoft Windows Azure platform, and the Google App Engine. Thus, for example, server and Internet connected storage device will often be implemented as automatically provisioned virtual machines under a cloud service system that can create a greater or lesser number of copies of server and Internet connected video storage device and associated database memory according to the underlying demands on the system at any given time.
Preferred embodiments may include the addition of a remote server 204 or cloud server to further provide for back-end functionality and support. Any one of the storage or processing may be done on-board the device or be situated adjacent or remotely from the system and connected to each system via a communication network 206. In one embodiment, the server 204 may be used to support user behavior profiling; user history function; predictive learning/analytics; alert function; network sharing function; digital footprint tracking, etc. The remote server 204 may be further configured to authenticate the user and retrieve data of the user, device, and, or network and applies the data against a library of messages, content, validated user information, etc.
Now in reference to
As shown in
The at least primary message prescriber 305 may push a message or interactively therapeutic content personalized to the user based on at least one stored message matched to the selected EMS. For example, within the EMS store 403, if EMS 1 (lethargic) is selected as defined by the user or the system, any one of message 1, 2 . . . n may be selected by the prescriber 305. The pre-defined messages validated by the accredited expert may all be messages with documented utility in elevating mood and energy (rubric). The mood and energy documented for each message may be on a scale. For instance, EMS 1 message 1 may be low-moderate; EMS 1/message 2 may be moderate; and EMS 1/message n may be high-severe, etc. Any variant of the scale may be featured without departing from the scope of the invention. In other embodiments, the messages, while falling under the same rubric and un-scaled, can vary along design cues. For instance, the prescriber 305 may choose EMS 1/message 2, over other available messages, due to the fact that the message is comprised of traditionally feminine cues (pink-colored bauhaus typeface) for a female user. Other user profile or demographic information may further inform the prescribers 305 choice of message type, such as age, education level, voting preference, etc. User profile or demographic information may be user inputted or digitally crawled.
Still in reference to
In some embodiments, the full list of message types is not grouped by EMS type or along any design categories, but rather simply listed arbitrarily and mapped or matched to an appropriate EMS type. In this arbitrarily listed manner, the prescriber 305 may match to more than one EMS type. Likewise, a user may be defined by more than one EMS type and be prescribed the same message type.
In some embodiments, the system or method may call for pushing at least a secondary-level message personalized to the user based on a threshold-grade match of the user response to the pushed primary-level message with at least one stored response coupled to a stored primary-level message, whereby the user and stored response is a measure of at least one of a reaction, compliance, engagement, or interactivity with the pushed and, or stored primary-level message. Much like the primary message or primary-level message, the secondary-level messages may also contain at least one of a text, image, sound, video, art asset, suggested action or recommended behavior. Again, the efficaciousness or therapeutic value of the primary or secondary messages are validated by at least one—and typically two—independent sources of clinical research or peer-reviewed science, as verified by a credentialed EMS expert.
In order to facilitate the at least secondary message or secondary-level message, the primary prescriber 305 may be used: Assigning a second message to the same user in the same session for the first defined EMS type. As is with the assignment of the first message, the assignment of the second may arbitrarily choose among EMS-grouped messages or from the full arbitrary list of messages in the EMS store. Moreover, the primary prescriber 305 may perform the secondary assignment in a logic-defined manner, wherein gathered, contextualized, or profiled data informs the assignment. In yet other aspects, second-level assignment may be performed by at least a secondary message prescriber 307, wherein the at least secondary message prescriber 307 pushes at least a secondary-level message personalized to the user based on a threshold-grade match of the user response to the pushed primary-level message with at least one stored response coupled to a stored primary-level message, whereby the user and stored response is a measure of at least one of a reaction, compliance, engagement, or interactivity with the pushed and, or stored primary-level message.
For instance, when a user-generated or system-generated EMS is defined as ‘unfulfilled’ for user A, a primary prescriber 305 assigns message 2 (uplifting; inspiring message) from EMS 1 (unfulfilled). In one embodiment, a secondary prescriber 307 prescribes a pro-social behavior, such as a local community service, immediately upon a touch interaction with the first inspiring message pushed. In other embodiments, a level of engagement, interaction or compliance may be tracked by the system to infer severity of the EMS. For instance, if user A does not comply with the touch-interaction requests from the first inspiring message or pro-social behavior recommendation of the second message, then the secondary prescriber 307 may push a less physically strenuous pro-social recommendation, such as suggesting to call an in-network licensed expert or simply make a cash donation to a charitable organization of the users choosing via a linked micro-payment method. For the purposes of inferring severity of EMS, any number of diagnostics that leverage any one of the on-device tools may be used, such as gyroscopic sensors or cameras. Secondary assignment may also be based on learned history, such as a past positive reaction (compliance) to a receiving a message from a loved one that a donation was made in user A's name to a charitable organization. Based on such history, a secondary prescriber 307 may assign a primary or secondary message recommending to make a donation in the name of a loved one during an ‘unfulfilled’ EMS experienced by user A.
The processing unit may further be communicatively coupled to at least one of an interface module, display module, input module, logic module, a context module, timeline module, tracking module, notification module, and a payment/gifting module. In accordance with one aspect, the notification module may be configured to generate reports at regular intervals (such as daily at 12:00 PM, weekly and monthly), on-demand (when the user requests for a report corresponding to the user), when triggered by an event, or upon a detected severe EMS. In an embodiment of the present invention, the notification module may also be configured to send a notification to the user or to a chosen loved one of the user. The notification may be a message, a phone call or any other communication means.
In an embodiment of the present invention, a timeline module may push already pushed messages in at least one of a static, dynamic, and, or scheduled fashion based on at least one of the user's scheduler criteria. The line of static, dynamic, and, or scheduled messages may be curated by the user, pre-set, or dynamically pushed based on any one of a user parameter. In some embodiments, the timeline module enables the displayed line of static, dynamic, and, or scheduled messages to be further replicated on at least one of a social media timelines or stories. In other words, the timeline module enables the displayed messages to be further shared with social media outlets.
In an embodiment of the present invention, a payment or gifting module may enable purchasing and gifting donations, physical objects, or digital assets. The gifting module may further be coupled to a distributive digital ledger, wherein each transaction among any user is represented as a unique node in the digital ledger. Each node tagged with meta data facilitating at least one of a transaction, validation and, or registration for each transaction.
The focal point of the card (window) is the actual EMS-defined message (treatment), and in the case of this window, is a suggested action—jump for 5 seconds. Jumping for 5 seconds is a suggested action to restore the oxytocin neurotransmitter, which is documented for building happiness and confidence—the initially chosen EMS or behavioral intervention by the user (
While not shown in
The uploaded content (digital content) may be at least one of an application-selected content and user-selected content. Additionally, the uploaded content may be at least one of a created content and curated content. Created content is any type of material in print or digital form that is at least one of selected, sorted, parsed, edited, and processed by at least one of the application and uploaded user. On the other hand, curated content is any type of material in print or digital form that is at least one of built, engineered, designed, and created by at least one of the application and uploaded user. Furthermore, the uploaded content may further contain an animation, infographic, meme, GIF, chat, post, augmented reality/virtual reality expressions, and audio. The digital content uploaded by the user is originated from at least one of a stored, received, visited, curated, and created source.
The selected condition may be an EMS (emotional mental state indicator) indicating at least one of a feeling, sensation, type of discomfort, mood, mental state, emotional condition, or physical status of the user 508. Once the EMS is defined and labeled, the method may then call for pushing at least a subsequent or battery of messages/content personalized to the user based on the initially labeled EMS 509. In some embodiments, the system or method may call for pushing at least a subsequent message or battery of messages personalized to the user based on a user response or interaction to the uploaded digital content and, or to the pushed primary/initial/level message. User response or interaction may be based on a threshold-grade match of the user response to the uploaded digital content and, or to the pushed primary-level message with at least one stored response coupled to a stored uploaded content/primary-level message, whereby the user and stored response is a measure of at least one of a reaction, compliance, engagement, or interactivity with the uploaded digital content and, or pushed primary-level message. Much like the uploaded digital content—whether simply uploaded, created, or curated—the primary message or primary-level message and the subsequent/battery messages may also contain at least one of a text, image, sound, video, art asset, suggested action or recommended behavior. The digital content may further contain an animation, infographic, meme, GIF, chat, post, and audio. The digital content uploaded by the user is originated from at least one of a stored, received, visited, curated, and created source.
In continuing reference to
Now in reference to
In continuing reference to
While not shown in
At least one of content review, condition selection, and therapeutic labeling may be achieved by analyzing at least one of computed pixel values derived from at least one of a parameter from a threshold-grade event or object by referencing against at least one of a pre-defined, user-defined, and, or learned reference table of recognized object/event-computed pixel values. Any number of may employ machine learning to update any one of a threshold of computed pixel values for object/event detection and, or update any one of a reference analysis of computed pixel values for condition selection/therapeutic labeling. Examples of machine learning may be at least one of a convolution neural network, associated model, training data set, feed-forward neural network, and, or back-propagated neural network.
Still in reference to
In other embodiments, the primary prescriber 305 may be used to do at least one of a content review, condition/EMS selection, and overlay of a therapeutic label to a digital content. Assigning a second message to the same user in the same session for the first defined EMS type. The primary prescriber 305 may perform at least one of a content review, condition/EMS selection, and therapeutic label overlay in a logic-defined or rule-based manner, wherein gathered, contextualized, or profiled data may further inform at least one of the content review, condition/EMS selection, and overlay.
For instance, when a system-generated EMS is selected as ‘Love’ for user A, a primary prescriber 305 or therapeutic labeler 1008c assigns a therapeutic label (Serotonin: uplifting and inspiring message to stabilize mood and provide stability for happiness to flourish). In a preferred embodiment, the therapeutic label may also be tapped for providing additional information, such as drug/neurotransmitter information, benefits, and citations (
In one embodiment, therapeutic labeling of uploaded digital content may be based on learned user history, such as previous labeling history and, or engagement/reaction (compliance/non-compliance) to receiving a message/content. Based on such history of labeling and, or engagement, a prescriber 307 or therapeutic labeler 1008c may assign a therapeutic label for uploaded content by user A that is consistent or departed from the previous labeling.
In an embodiment of the invention, the inputs 1101 may be motion characteristics corresponding to at least one of, physical activity, physiological and sleep related characteristics of a user quantified from a body worn or user device. Additionally, inputs 1101 may account for environmental conditions, such as wind velocity, temperature, humidity, aridness, light, darkness, noise pollution, exposure to UV, airborne pollution and radioactivity quantified from a body-worn/user device and, or remote stations. Further yet, data generated from a periodic survey pushed to a body worn/user device may be used to generate a behavioral profile of the user, which may serve as an input 1101 or inform an input 1101. The system may flag a threshold discrepancy between a composite behavioral profile and a reference behavioral profile to detect or select an appropriate condition/EMS, in addition to the parsed digital content by the content reviewer 1102, condition selector 1102, therapeutic labeler 1102, whereby the appropriate condition/EMS is determined by machine learning algorithms to trigger a number of downstream provisionings 1104.
Further yet, in another embodiment, the system may further comprise integration with any one of a third-party application via an Application Program Interface (API) 1104. This allows for 3rd party database integration, such as Electronic Medical Records (EMR), health monitoring, proxy health provisioning, remote server and, or a cloud based server for other downstream analytics and provisioning. Additionally, the completed automated responses may be saved onto a remote cloud based server for easy access for data acquisition and archival analytics for future use.
In another embodiment of the invention, the system may allow for easy saving, searching, printing, and sharing of completed automated response information with authorized participants. Additionally, the system may allow for non-API applications, for example, building reports and updates, create dashboard alerts as well as sign in/verifications 1104. Alternatively, sharing may be possible with less discrimination based on select privacy filters. Moreover, the system may be integrated with certain workflow automation tools, prompting the system to perform a task command, provided a trigger is activated based on the threshold discrepancy. In an embodiment of the invention, at least one conditional event triggers at least one action controlled by a “if this, then that” 1104 script manager. Further yet, the “if this, then that” 1104 script manager is embedded with an “and, or” trigger or action operators, allowing increased triggers or actions in a command set.
In another instance, the script manager may be embedded with a “if, this, then that” as well as a “and, or” trigger or action operator for increased triggers either downstream or upstream of a command set. While not shown in
In yet another embodiment of the invention, “OR” operators may be used instead of the “AND” operator. Further, any number of “AND” and, or “OR” operator may be used in a command function. Such an automation layer may add further efficiencies. An ecosystem of apps may provide for a API-mediated link to the system for enhanced co-interactivity among users network, diagnostics, and other measurables.
The processer system 1102 may further be communicatively coupled to at least one of a provisioning module 1103, interface module, display module, input module, logic module, a context module, timeline module, tracking module, notification module, payment/gifting module, and marketplace module in order to effectuate any number of remote provisioning. In accordance with one aspect, the notification module may be configured to generate reports at regular intervals (such as daily at 12:00 PM, weekly and monthly), on-demand (when the user requests for a report corresponding to the user), when triggered by an event, or upon a detected severe EMS. In an embodiment of the present invention, the notification module may also be configured to send a notification to the user or to a chosen loved one of the user. The notification may be a message, a phone call or any other communication means.
In an embodiment of the present invention, a timeline module may push already pushed messages in at least one of a static, dynamic, and, or scheduled fashion based on at least one of the user's scheduler criteria. The line of static, dynamic, and, or scheduled messages may be curated by the user, pre-set, or dynamically pushed based on any one of a user parameter. In some embodiments, the timeline module enables the displayed line of static, dynamic, and, or scheduled messages to be further replicated on at least one of a social media timelines or stories. In other words, the timeline module enables the displayed messages to be further shared with social media outlets.
In an embodiment of the present invention, a payment or gifting module may enable purchasing and gifting donations, physical objects, or digital assets. In an embodiment of the present invention, a marketplace module may enable purchasing digital assets. The gifting and marketplace module may further be coupled to a distributive digital ledger, wherein each transaction among any user is represented as a unique node in the digital ledger. Each node tagged with meta data facilitating at least one of a transaction, validation and, or registration for each transaction.
Digital Nutrition is proactive, and constitutes the underpinning of any approach to comprehensive wellness.
Alternatively, the first step in the flow may be: uploading a digital content by a user; secondly, assigning a digital nutrition (DN) label to the uploaded digital content, wherein said label is an indication of the intended psycho-emotional effect of said content; and lastly, triggering delivery of a targeted advertisement from a store, wherein the targeted advertisement is triggered based on a counter threshold being reached and is matched to the last viewed labeled content based on a match of label types or group.
The uploaded content (digital content) may be at least one of an application-selected content and user-selected content. Additionally, the uploaded content may be at least one of a created content and curated content. Created content is any type of material in print or digital form that is at least one of selected, sorted, parsed, edited, and processed by at least one of the application and uploaded user. On the other hand, curated content is any type of material in print or digital form that is at least one of built, engineered, designed, and created by at least one of the application and uploaded user. Furthermore, the uploaded content may further contain an animation, infographic, meme, GIF, chat, post, augmented reality/virtual reality expressions, image, video, text, and audio. The digital content uploaded by the user is originated from at least one of a stored, received, visited, curated, and created source.
The method or system may comprise an option to upload a digital content by a user; parse the uploaded digital content into frames for object/event identification. In some embodiments, object/event identification comprises isolating individual frame into cropped defined structures by the content reviewer. In some embodiments, processing the cropped frames through at least one of a convolutional classifier network or convolutional semantic segmentation network. In other embodiments, object/event identification does not require processing using a convolutional classifier network or convolutional segmentation network. Once identified (i) or identified/processed (i-p), match at least one (i/i-p) frame against a library of stored content indicating at least one selected emotional/mental state (EMS cue) or intended psycho-emotional effect by the condition selector, said condition/effect being at least one of a feeling, sensation, mood, mental state, physical state, emotional condition, physical status. Finally, overlay a therapeutic label or Digital Nutrition (DN) label to the uploaded digital content corresponding to the stored content with selected condition/effect above a matched threshold by the therapeutic or DN labeler 1408a.
At least one of content review, condition selection, and DN labeling may be achieved by analyzing at least one of computed pixel values derived from at least one of a parameter from a threshold-grade event or object by referencing against at least one of a pre-defined, user-defined, and, or learned reference table of recognized object/event-computed pixel values. Any number of machine learning techniques may be employed to update any one of a threshold of computed pixel values for object/event detection and, or update any one of a reference analysis of computed pixel values for condition selection/therapeutic labeling. Examples of machine learning may be at least one of a convolution neural network, associated model, training data set, feed-forward neural network, and, or back-propagated neural network. Alternatively, content review, condition/EMS selection, and DN labeling may be performed in a logic-defined or rule-based manner. Furthermore, gathered, contextualized, or profiled data may further inform at least one of the content review, condition/EMS selection, and DN label overlay.
For example, Zeeshan may be come across a video on-line and prior to viewing it, upload it into the Moodrise DN loader or labeler for DN labeling. After review/parsing, the labeler may label the content—rich with D.I.Y home improvement tips—with a score of 63, which corresponds to a contemplative, focus-centric psycho-emotional effect potential. In other embodiments, Zeeshan's D.I.Y. video may be labeled textually with “contemplative, focus-centric psycho-emotional effect potentially elicited”. This psycho-emotional effect may be labelled as seen in
Labeling by the labeler 1408a, may further be informed by the original source or publisher of the content. For instance, since the D.I.Y. millwork video was downloaded for the Moodrise (MR) uploader from the Home Depot website, this meta or contextual data may further inform the labeler 1408a in assessing the ‘focus-centric’, ‘63’, ‘ACh+++’ label. In some embodiments, Zeeshan may directly stream the video content from the Home Depot site for the MR labeler 1408a to review/parse/label prior to the content being viewable or concomitantly. Once the content is labeled for immediate or future playback, the content may be saved in the EMS store, indexed by EMS/PEE, for future requested playback, MR provisioned, and/or more efficient tracking of viewed content for targeted ad delivery.
The user may be assigned a DN diet score, which is generated by the DN diet score tracker (tracker) 1408b based on at least one of an aggregation, moving average, or last viewed labeled content. In one scenario, Yitzhak having just viewed three distinct clips—two of which are generally action/thrilling and one of which is largely dramatic/politically conscious—the tracker may calculate a score of 76 reflecting the overall emotion/mental state cue (overall intended psycho-emotional effect of the content in the aggregate) and deliver an advertisement clip with a diet score range of 72-78, which corresponds to an ad clip featuring a thrill-seeking element (Red Bull ad featuring a freestyling sports-biker, for instance).
In another embodiment, ad retrieval from the DN Ad store 1408d for triggered delivery by the DN Ad player 1408c is not score or range specific, but rather, just based on broad EMS/PEE grouping. For instance, returning to the scenario of Zeeshan, his ACh+++ labeled content was not off-set by the following short-clip of Luca Doncic crossing over an opponent—rated by the labeler several weeks ago with a ‘Dopamine’ or ‘DA’. As a result, the tracker 1408b has tracked Zeeshan over the past two views with a psyho-emotional effect evoked (EMS/PEE) of a ACh+. With this slightly revised down ‘ACh+’ EMS/PEE rating, the DN tracker 1408b or DN Player 1408c retrieves an Ethan Allen spot for a patio set rated ACh-ACh++. In other embodiments, Zeeshan's tracked ACh+ rating will retrieve a “Cool Grey” Jumpman retro 4 ad based on the fact that one of the two views prominently featured Luka Doncic wearing grey basketball sneakers. This type of object detection and matching similar objects from an ad may obviate the need of score matching.
The DN labeling for targeted ad delivery may not require label tracking of viewed content, but rather just assign a digital nutrition (DN) label to the uploaded digital content, wherein said label is an indication of the intended psycho-emotional effect of said content; and trigger delivery of a targeted advertisement from a store, wherein the targeted advertisement is labeled with a digital diet score range covering for a score corresponding to the last viewed labeled content prior to an advertisement delivery trigger point. Tracking is obviated by simply relying on a ‘last content viewed’ approach. For instance, in the scenario above, since the millwork clip rated with a ACh+++ was the last seen clip by Zeeshan prior to the DN trigger recognizing a counter threshold (max limit of number of clips/content or duration) being reached, the DN Player 1408c will play the Ethan Allen patio spot or any other ad with a comparable ACh-ACh++ rating from the DN Ad Store 1408d.
To further clarify, in continuing reference to Yitzhak, though his last viewed content was action/thrill-seeking/DA++ rated (man swimming to train for an upcoming triathalon), a Serotonin/5-HT3 rated ad featuring an elderly man fishing against a soothing backdrop for an Acid-Reflux over-the-counter generic may be pushed by the Ad Player, rather than the Red Bull spot, for its countering effect or value. Though countering the DA++ rating of the viewed content, the Ad Player decision to choose a 5-HT3 rated ad with a common water feature truly reflects the level of nuance that may be incorporated in the delivery of targeted advertising. In addition to labeling, retrieval and delivery of targeted advertising may further take advantage of profile data or contextual data (geo-location, date/time, temperature, sensor-captured data, etc.) to further personalize for maximal branding impact.
In an embodiment, delivery of the ad precedes content viewing. For example, in case of Jen, who is an avid runner, vegan and a pet lover. Jen viewed a documentary on blind people competing on an iron man and was highly inspired to run an ironman releasing a rush of adrenaline. Next morning Jen came across a video—, but prior to viewing she uploaded it on the Moodrise App DN loader or labeler for DN labeling. After review/parsing, the labeler may label the content—bungee jumping of a man into a river gorge, a score of 89 which corresponds to thrill seeking and fun—increase in adrenaline. Based on Jen's last viewed content of the ironman, the DN Ad store would push content for adrenaline the FitBit commercial video before viewing the content of—bungee jumping of a man into a river. Additionally, the match maybe based on labels meaning the Fitbit commercial labels are a match to the labels on the content video.
In an alternative embodiment, the match may not be based on matched content labels. The user has the discretion to choose an ad based on a completely different labelled content. For example, Jen who normally is trilled watching content that would increase adrenalin, may choose to view a soothing content—cascading waterfalls with chirping birds—Calm Inc. ad before she views the adrenaline rich high-octane skydiving content.
Additionally, the content labels may be labelled independent of the EMS/neurotransmitters. For example, in a Sherwin William commercial with a room painted yellow would match a content video—girl in a sunflower field. Both of these would have the color yellow in common thus, similar content label. The color yellow creates an uplifting effect on the mood making one feel happy and optimistic and thus, an increase in dopamine.
In another embodiment, content labelling and delivery of ad decisions may be based on an ad experience which the user may choose to play. For example, Jen wants to experience buying/selling a car from a seller's perspective. She would choose to watch a Carvana—buying and selling cars—ad before she views her content.
In an alternate embodiment, content labelling and the delivery of ads may not be based on the EMS/neurotransmitters. For example, a color wheel may be used to create content labeling—Blue-yellow color wheel may represent a pleasure and reward thus, a release of dopamine. Additionally, consider a scenario of raindrops on leaves with soothing music would depict a blue-green color on the color wheel and would score an 89 on a scoring system depicting calmness thus releasing GABA. Consider a scenario where Jen was listening to soothing music last night before going to bed—blue on the color wheel to destress. Following morning before her morning meditation—blue on the color wheel—an ad of Calm Inc. would be pushed based on the soothing content viewed last night. Alternatively, in an emergency situation in case of a landslide a deep red color on the color wheel and would score a 94 on the scoring system depicting a rush of adrenaline.
Any one of the content labeling, ad labeling, ad scoring, ad retrieval decisions may be backed by peer-reviewed research for scientific support. Additionally, the content labeling may further comprise options for accessing additional information regarding the label, condition, EMS, EMS/PEE, neurotransmitter, treatment, therapeutic, cure, rational, etc. The platform/App may have an extension for advertisers to preview or sneak peek into the most saved content across the Moodrise community and their corresponding rating, thereby allowing for advertisers to tailor their spots to fit within a particular content silo and target demo.
The claimed invention leverages existing clinical research and proven science (already published in peer-reviewed journals) and repackages insights as content modules or behavioral interventions that are simpler, more seductive, and profoundly more fun than traditional analogue therapies or digital treatment regimen. Described more simply, the system and platform curates existing digital content, and creates entirely new content programs, informed by and centered around techniques proven to boost mood, alleviate anxiety, reduce stress, and improve psychological health or mental fitness by directing users to follow procedures proven to increase the production of beneficial molecules and neurotransmitters like Dopamine, Oxytocin, Acetylcholine, Serotonin, and GABA to deliver positive mood and mind-altering effects. This is, in essence, a purely digital, transorbital drug delivery system. No pills. No powders. Purely digital experiences to positively impact mood, mind and personal sense of well-being.
Digital Nutrition Database System (DNDS)
In various embodiments, disclosed herein is a Digital Nutrition Database System (DNDS) for creating, storing, applying, and sharing digital nutrition values (DNVs) and digital nutrition fingerprints (DNFs). As described in further detail below, a digital nutrition value (DNV) is a characterization of the therapeutic values (as described above) of a plurality of individual pieces of digital content (hereinafter, “individual content pieces” (ICP)). As described below, a DNV may be quantitative or qualitative in nature, and may be expressed numerically, verbally, or graphically. In some embodiments, a graphical representation of a DNV is referred to as a digital nutrition fingerprint (DNF). As described below, a DNV (or an associated DNF) may be created for a digital content channel (also referred to as a “content channel” or a “channel”) or for an individual. Once a DNV has been created (e.g., for a channel or for an individual), the DNV may be stored within a database (e.g., a digital nutrition database, as described below), exported and shared to various third party systems, or used for various applications, as described below. In some embodiments, a DNV (or an associated DNF) may be used to display or express the digital nutrition of a digital content channel at a glance, as described below.
In some embodiments, a method for providing a digital nutrition database (DND) comprises: a) accessing a plurality of content channels, each content channel within the plurality of content channels having a plurality of individual content pieces (ICPs); b) for each content channel within the plurality of content channels: i) determining a therapeutic value for each ICP within the plurality of ICPs based on attributes of the ICPs; and ii) aggregating the therapeutic values of each ICP within the plurality of ICPs to generate a digital nutrition valuue (DNV) for the content channel; and c) compiling the DNV generated for each content channel within the plurality of content channels into a digital nutrition database (DND). In some embodiments, the method further comprises exporting a first DNV associated with a first content channel from the DND to a third party system. In some embodiments, the first DNV is exported from the DND to the third party system via an application programming interface (API). In some embodiments, the method further comprises: a) providing a graphical user interface (GUI) for the digital nutrition database; b) receiving a selection of a first content channel from within the GUI for the digital nutrition database; c) retrieving a first DNV associated with the first content channel from the digital nutrition database; and d) displaying a first digital nutrition fingerprint (DNF) graphically representing the first DNV within the GUI for the digital nutrition database. In some embodiments, the GUI for the digital nutrition database is accessed through a website or a web application. In some embodiments, the graphical representation of the first DNF is a radar chart. In some embodiments, the method further comprises displaying additional information associated with the first content channel. In some embodiments, the method further comprises: a) determining a second content channel recommended based on the first DNV associated with the first content channel; and displaying the second content channel within the GUI for the digital nutrition database. In some embodiments, displaying the second content channel within the GUI for the digital nutrition database comprises displaying a second DNF associated with the second content channel. In some embodiments, determining the second content channel recommended based on the first DNV associated with the first content channel comprises: a) referencing the digital nutrition database with the first DNV; and b) identifying one or more content channels associated with respective DNVs similar to the first DNV. In some embodiments, the method further comprises: a) determining a suitable advertisement based on the first DNV; and b) presenting the suitable advertisement within the GUI for the digital nutrition database. In some embodiments, the method further comprises: a) providing a graphical user interface (GUI) for the digital nutrition database; b) generating a digital nutrition value (DNV) for a user accessing the GUI for the digital nutrition database; c) determining one or more recommended content channels based on the DNV generated for the user; and d) displaying the one or more recommended content channels within the GUI for the digital nutrition database. In some embodiments, generating a DNV for the user accessing the GUI for the digital nutrition database comprises: a) tracking the user's consumption of a plurality of individual content pieces (ICPs); b) determining a therapeutic value for each ICP within the plurality of ICPs based on attributes of the ICPs; and c) aggregating the therapeutic values of each ICP within the plurality of ICPs to generate the DNV for the user.
As will be described in more detail below, once a digital nutrition value (DNV) has been created for a channel (or for a user, as described below), the DNV may be stored in a digital nutrition database (DND) 2802, as depicted in
As mentioned above, in some embodiments, a digital nutrition database system (DNDS) accesses one or more digital content channels to create one or more respective digital nutrition values (DNVs) for the one or more digital content channels.
In some embodiments, an individual content piece (ICP) has one or more attributes. For example, as illustrated in
Digital Nutrition Value (DNV)
As mentioned above, in some embodiments, a digital nutrition database system (DNDS) accesses one or more digital content channels to create one or more respective digital nutrition values (DNVs) for the one or more digital content channels. In some embodiments, a method for creating a digital nutrition value (DNV) comprises: a) accessing a content channel having a plurality of individual content pieces (ICPs); b) determining a therapeutic value for each ICP within the plurality of ICPs based on attributes of the ICPs; and c) aggregating the therapeutic values of each ICP within the plurality of ICPs to generate a digital nutrition value (DNV) for the content channel. In some embodiments, the plurality of ICPs is a subset of the total ICPs comprised by the content channel. In some embodiments, determining a therapeutic value for each ICP within the plurality of ICPs comprises identifying one or more tags associated with one or more ICPs. In some embodiments, determining a therapeutic value for each ICP within the plurality of ICPs comprises analyzing text associated with one or more ICPs for emotionally-charged language. In some embodiments, determining a therapeutic value for each ICP within the plurality of ICPs comprises analyzing audio or video associated with one or more ICPs. In some embodiments, aggregating the therapeutic values of each ICP within the plurality of ICPs to generate a DNV for the content channel comprises assigning the content channel a score for each of a plurality of therapeutic value categories. In some embodiments, the plurality of therapeutic value categories comprises one of oxytocin, dopamine, serotonin, endorphins, testosterone, and acetylcholine. In some embodiments, the plurality of therapeutic value categories comprises at least three of oxytocin, dopamine, serotonin, endorphins, testosterone, and acetylcholine. In some embodiments, the method further comprises presenting a digital nutrition fingerprint (DNF) graphically representing the DNV generated for the content channel within a graphical user interface (GUI). In some embodiments, the graphical representation of the DNF is a radar chart.
As described above, it has been proven that digital content consumed by a person can various psychochemical reactions in the brain, which can have various therapeutic values. For example, as mentioned above, the content depicted in the representative screenshots of
As mentioned above, in some embodiments, the DNDS determines one or more therapeutic values for an individual content piece (ICP) using one or more attributes associated with the ICP. For example, in some embodiments, the DNDS uses tags associated with an ICP to determine one or more therapeutic values for the ICP. For example, considering the steak dinner video example from above, tagged with the hashtags #cooking, #steak, #meat, #meatandpotatoes, and #delicious, the DNDS can identify all five tags as associated with food, and determine that a video ostensibly about food might have a gabapentin (GABA) therapeutic value (which can make a person feel excited). The DNDS can then assign a gabapentin therapeutic value to the steak dinner video. As mentioned above, the DNDS may use multiple types of attributes associated with an ICP when determining a therapeutic value for the ICP. For example, in addition to using the tags associated with the steak dinner video, the DNDS may also process the sounds and images of the video file itself and determine that it does indeed include images of food. Or, the DNDS may process the sounds and images of the steak dinner video and determine that while the video is of two chefs cooking a steak dinner, the two chefs get into a lengthy and heated verbal altercation. In this case, although the five tags associated with the video are associated with food, the DNDS may determine that the steak dinner video has more testosterone value than gabapentin value, and assign the video a testosterone therapeutic value instead of a gabapentin therapeutic value. Or, in some embodiments, the DNDS assigns the steak dinner video both a testosterone therapeutic value and a gabapentin therapeutic value.
As mentioned above, when the digital nutrition database system (DNDS) accesses a digital content channel having a plurality of individual content pieces (ICPs), the DNDS can determine a therapeutic value for each of the ICPs included in the plurality of ICPs. For example, if a YouTube channel includes 50 individual YouTube videos, the DNDS can determine a therapeutic value for each of the 50 individual YouTube videos. Or for example, if an Instagram page has 30 individual videos and 70 individual images, the DNDS can determine a therapeutic value for each of the 30 individual videos and each of the 70 individual images. In some embodiments, the DNDS may determine therapeutic values on a “post” basis. For example, an Instagram “post” may include multiple videos, multiple images, or a combination thereof. In such an embodiment, additionally or alternatively to determining a therapeutic value for each individual video and image included in the post, the DNDS may determine a therapeutic value for the post itself, wherein the post represents the individual content piece. Once the DNDS has determined a therapeutic value for each of the ICPs included in a digital content channel, the DNDS can aggregate the therapeutic values of the ICPs to generate a digital nutrition fingerprint (DNF) for the digital content channel. In some embodiments, the DNDS accesses a digital content channel and its ICPs through an application programming interface (API).
In some embodiments, after generating a digital nutrition value (DNV) 3003 for a digital content channel (such as Example Channel #1, as illustrated in
Digital Nutrition Database (DND) and Graphical User Interface (GUI)
As described above, in some embodiments, a digital nutrition database system (DNDS) can access a digital content channel having a plurality of individual content pieces (ICPs), analyze each of the ICPs included in the plurality of ICPs for their therapeutic value, and aggregate the therapeutic values of the plurality of ICPs to generate a digital nutrition fingerprint (DNV) for the digital content channel. The DNDS can also create a graphical representation of the DNV, referred to as a digital nutrition fingerprint (DNF). In some embodiments, the DNDS can be used to access and generate DNVs and DNFs for individual digital content channels. For example, the DNDS may be a desktop application or a web application that a user can access and submit a digital content channel (e.g., a photo or music album) into, and the DNDS can return a DNV (and a DNF) of the digital content channel to the user. However, in some embodiments, the DNDS can access and generate DNVs (and DNFs) for a plurality of digital content channels and store the DNVs (and their associated DNFs) in a digital nutrition database (DND), where they can be maintained and later used for various purposes and applications. In some embodiments, the DNDS regularly updates the DNV (and its associated DNF) of a digital content channel over time, as ICPs are added or removed the from the channel.
For example,
As mentioned above, once one or more digital nutrition values (DNVs) have been generated for one or more respective digital content channels by the digital nutrition database system (DNDS) and stored within a digital nutrition database (DND), the DNVs may be used for various purposes.
In some embodiments, the digital nutrition database system (DNDS) can recommend digital content channels to users through the GUI 3220. For example, in some embodiments, after generating digital nutrition values (DNVs) for a plurality of digital contents channels and storing the DNVs in a digital nutrition database (DND), the DNDS can compare the DNVs to identify potentially similar channels. The DNDS can use DNVs to identify similar channels in various ways. In some embodiments, the DNDS identifies two channels as similar if their DNVs have similar scores for two or more therapeutic value categories. In some embodiments, the DNDS identifies to channels as similar if their DNVs have the highest score for the same therapeutic value category (e.g., both DNVs are scored highest in endorphins). In some embodiments, the DNDS performs a regression analysis on two DNVs to determine their similarity. However, the DNDS may identify two DNVs as similar in any other way. In some embodiments, when a user navigates to the Channel Insights & Analytics (CIA) page 3222 for a particular digital content channel, the GUI 3220 displays recommended channels based on the DNV of the particular digital content channel (e.g., channels that the DNDS has identified as having DNV similar to that of the particular digital content channel). In the example, illustrated by
As mentioned above, in some embodiments, the digital nutrition database system (DNDS) can generate a digital nutrition value (DNV) and a digital nutrition fingerprint (DNF) for a user, as opposed to a digital content channel, based on individual content pieces (ICPs) consumed or uploaded by the user. For example, in some embodiments, the DNDS provides a plugin, an extension, or an application programming interface (API) that a user can install in their Internet browser or other application to track their consumption of ICPs. Or for example, in some embodiments, a user can inform the DNDS of their content preferences, such as by selecting or listing preferred ICPs within the GUI. In some embodiments, after tracking the user's consumption or uploading of ICPs (or after receiving the user's content preferences), the DNDS can generate a DNV for the user (e.g., by analyzing the ICPs that the user has consumed/uploaded or analyzing the user's content preferences), much in the same way that the DNDS generates a DNV for a digital content channel. In some embodiments, the DNDS can additionally or alternatively generate a DNV for a user based on the digital content channels that the user accesses or frequents.
In some embodiments, a method for creating a digital nutrition fingerprint (DNF) comprises: a) tracking a user's consumption of a plurality of individual content pieces (ICPs); b) determining a therapeutic value for each ICP within the plurality of ICPs based on attributes of the ICPs; and c) aggregating the therapeutic values of each ICP within the plurality of ICPs to create a DNF for the user. In some embodiments, the therapeutic value of an ICP is weighted based on how recently the ICP was consumed by the user. In some embodiments, determining a therapeutic value for each ICP within the plurality of ICPs comprises identifying one or more tags associated with one or more ICPs. In some embodiments, determining a therapeutic value for each ICP within the plurality of ICPs comprises analyzing text associated with one or more ICPs for emotionally-charged language. In some embodiments, determining a therapeutic value for each ICP within the plurality of ICPs comprises analyzing audio or video associated with one or more ICPs. In some embodiments, aggregating the therapeutic values of each ICP within the plurality of ICPs to create a DNF for the user comprises assigning the user a score for each of a plurality of therapeutic value categories. In some embodiments, the plurality of therapeutic value categories comprises one of oxytocin, dopamine, serotonin, endorphins, testosterone, and acetylcholine. In some embodiments, the plurality of therapeutic value categories comprises at least three of oxytocin, dopamine, serotonin, endorphins, testosterone, and acetylcholine. In some embodiments, the method further comprises presenting a graphical representation of the DNF created for the user within a graphical user interface (GUI). In some embodiments, the graphical representation of the DNF is a radar chart.
As mentioned above, in some embodiments, the digital nutrition database system (DNDS) includes or is communicatively coupled to one or more advertisement systems. In some embodiments, the one or more advertisement systems include collections of advertisements that can be accessed, retrieved, and deployed by the DNDS. In some embodiments, the DNDS can use the digital nutrition database (DND; as described above), which stores a plurality of digital nutrition values (DNVs; as described above), to target advertisements (also referred to as “ads”) at users. For example, in some embodiments, the DNDS determines which advertisements from the one or more advertisement systems align best with which therapeutic values or DNVs. Then, in some embodiments, when a user accesses a Channel Insights & Analytics (CIA) page for a channel having a particular DNV, for example, the GUI can display an advertisement aligned with the particular DNV of the channel. Similarly, in some embodiments, if a user accesses a Me page 3324, the GUI can display an advertisement 3325 aligned with the DNV generated for the user, as illustrated by
Embodiments are described at least in part herein with reference to flowchart illustrations and/or block diagrams of methods, systems, and computer program products and data structures according to embodiments of the disclosure. It will be understood that each block of the illustrations, and combinations of blocks, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general-purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function/act specified in the block or blocks.
The computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus, to produce a computer implemented process such that, the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions/acts specified in the block or blocks. In general, the word “module” as used herein, refers to logic embodied in hardware or firmware, or to a collection of software instructions, written in a programming language, such as, Java, C, etc. One or more software instructions in the unit may be embedded in firmware. The modules described herein may be implemented as either software and/or hardware modules and may be stored in any type of non-transitory computer-readable medium or other non-transitory storage elements. Some non-limiting examples of non-transitory computer-readable media include CDs, DVDs, BLU-RAY, flash memory, mobile device, remote device, and hard disk drives.
| Number | Date | Country | |
|---|---|---|---|
| Parent | 16990702 | Aug 2020 | US |
| Child | 17143742 | US | |
| Parent | 16159119 | Oct 2018 | US |
| Child | 16990702 | US | |
| Parent | 15702555 | Sep 2017 | US |
| Child | 16159119 | US | |
| Parent | 15959075 | Apr 2018 | US |
| Child | 16990702 | US | |
| Parent | 15702555 | Sep 2017 | US |
| Child | 15959075 | US | |
| Parent | 16655265 | Oct 2019 | US |
| Child | 15702555 | US | |
| Parent | 16570770 | Sep 2019 | US |
| Child | 16655265 | US | |
| Parent | 16403841 | May 2019 | US |
| Child | 16570770 | US | |
| Parent | 16282262 | Feb 2019 | US |
| Child | 16403841 | US | |
| Parent | 16239138 | Jan 2019 | US |
| Child | 16282262 | US | |
| Parent | 16159119 | Oct 2018 | US |
| Child | 16239138 | US | |
| Parent | 15959075 | Apr 2018 | US |
| Child | 16159119 | US | |
| Parent | 15702555 | Sep 2017 | US |
| Child | 15959075 | US |
