Patent Issued for Valence profiling of virtual interactive objects (USPTO 11521719): Verily Life Sciences LLC
2022 DEC 27 (NewsRx) -- By a
The patent’s inventors are
This patent was filed on
From the background information supplied by the inventors, news correspondents obtained the following quote: “Contemporary research has begun exploring how media content affects the emotional health state. Such research has considered emotion as a predictor of media selection, an outcome of media exposure, a mediator of other psychological/behavioral outcomes resulting from media exposure, etc.
“For example, several studies have examined the emotional consequences of using social media (e.g., Facebook® or Twitter®). These studies have shown that the use of social media can cause both positive feelings and negative feelings, which can facilitate or hinder the development of social capital and social connectedness. However, these studies often fail to account for how the emotional health state impacts which media content is consumed by an individual.
“The drawings depict various embodiments for the purpose of illustration only. Those skilled in the art will recognize that alternative embodiments may be employed without departing from the principles of the technology. Accordingly, while specific embodiments are shown in the drawings, the technology is amenable to various modifications.”
Supplementing the background information on this patent, NewsRx reporters also obtained the inventors’ summary information for this patent: “Clinical interactions with individuals (also referred to as “patients” or “subjects”) are often infrequent, so it can be difficult for a clinician to follow transitions in the health state of a subject at an optimal temporal resolution. This is particularly true for at-risk subjects and subjects that have recently been prescribed new medications, treatments, etc.
“Entities have begun developing healthcare-focused computer programs that can automatically identify, monitor, and promote different aspects of physical, mental, and emotional well-being. Some computer programs expressly solicit feedback directly from subjects (e.g., via manually populated forms), while other computer programs continually track subject behaviors along multiple dimensions without requiring user input. For example, a computer program may monitor user interactions with a social media application that resides on a mobile phone. As another example, a computer program may monitor user interactions with a calling application or a messaging application that resides on a mobile phone.
“Classification algorithms can then be applied by the computer program to detect deviations from routine patterns. By applying the classification algorithms, the computer program can automatically assess the health state based on health characteristics inferred from these subject behaviors. Health characteristics can include, for example, estimated sleep duration, physical activities, communication activities, and social interactions.
“However, these computer programs cannot capture much of the contextual resolution necessary to fully understand the health implications of various activities. For example, conventional technologies simply consider whether these activities occurred, rather than the nature of the objects involved in these activities. Said another way, conventional technologies are often unable to accurately estimate the health state in a non-invasive manner because limited information is considered. Having an accurate understanding of most, if not all, activities affecting the health state can be critical in providing diagnoses, monitoring disease or risk progression, suggesting treatment options, etc.
“Introduced here, therefore, are health management platforms able to monitor changes in the health state of a subject based on the context of digital activities performed by, or involving, the subject. More specifically, the health management platforms can examine contextual data associated with digital activities to determine whether the objects involved in the digital activities are indicative of positive or negative valence. The term “digital activity” can refer to actions completed using an electronic medium (e.g., calling, messaging, or browsing activities) and actions capable of being virtually represented (e.g., movement activities from location data, physical activities from activity data, or medication activities from healthcare data).”
The claims supplied by the inventors are:
“1. A method comprising: acquiring, by a processor, data pertaining to an activity performed by a first individual using a social media application executing on a computing device; analyzing, by the processor, the data to identify a social network identifier that is representative of a second individual involved in the activity; generating, by the processor, an electronic record of the activity that programmatically links the social network identifier with the activity performed by the first individual; calculating, by the processor, a valence measure to associate with the electronic record based on (i) the social network identifier and (ii) textual analysis of the activity; comparing, by the processor, the electronic record to entries of a personalized valence index associated with the first individual; configuring, by the processor, a profile associated with the first individual to include (i) an association between the valence measure and the electronic record of the activity and (ii) an indication whether a matching entry was found in the personalized valence index for the electronic record; establishing, by the processor, there has been a change in a health state of the individual based on a count of new entries generated in the personalized valence index over a preceding interval of time exceeding a threshold.
“2. The method of claim 1, wherein the valence measure is based on paralinguistic analysis of the activity.
“3. The method of claim 1, wherein the valence measure is based on non-linguistic analysis of the activity.
“4. The method of claim 1, wherein the valence measure is based on linguistic analysis of the activity.
“5. The method of claim 1, further comprising: estimating, by the processor, the health state of the first individual by applying a personalized valence model to the profile.
“6. The method of claim 5, wherein the personalized valence model is configured to produce an output indicative of the health state based on an analysis of valence measures associated with electronic records corresponding to another preceding interval of time.
“7. The method of claim 1, wherein the valence measure characterizes how the first individual feels emotionally about the second individual, as inferred from the analysis of the activity.
“8. The method of claim 1, further comprising: establishing, by the processor, communication with a social media platform responsible for managing the social media application via an application programming interface (API); wherein the data is acquired by the processor via the API.
“9. The method of claim 1, wherein the processor is communicatively connected to the computing device across a network.
“10. A non-transitory computer-readable medium with instructions stored thereon that, when executed by a processor, cause the processor to perform operations comprising: acquiring contextual data pertaining to a digital activity performed by an individual; parsing the contextual data to identify a target that is representative of an object of interest involved in the digital activity; generating an electronic record of the digital activity by associating the digital activity and the target; calculating, based on the target, a valence measure to associate with the electronic record by- accessing a personalized valence index that includes entries representing past digital activities performed by the individual, and comparing the electronic record to the personalized valence index; configuring a profile to include an association between the valence measure and the electronic record; and monitoring the personalized valence index to infer changes in a health state of the individual by- generating a count of new entries in the personalized valence index that were created over a preceding interval of time, comparing the count of new entries to a threshold, and inferring that the health state of the individual has changed responsive to determining that the count of new entries exceeds the threshold.
“11. The non-transitory computer-readable medium of claim 10, wherein the operations further comprise: indicating in the profile whether a matching entry was found in the personalized valence index for the electronic record.
“12. The non-transitory computer-readable medium of claim 10, wherein said calculating and said configuring are continually performed as contextual data pertaining to digital activities performed by the individual is received.
“13. The non-transitory computer-readable medium of claim 12, wherein the operations further comprise: monitoring valence measures included in the profile in such a manner that a trend in the valence measures can be identified in real time.
“14. The non-transitory computer-readable medium of claim 10, wherein the operations further comprise: determining that the electronic record does not match any entries in the personalized valence index; and updating the personalized valence index by adding a new entry corresponding to the electronic record.
“15. A method comprising: acquiring, by a health management platform, contextual data pertaining to a digital activity performed by an individual; analyzing, by the health management platform, the contextual data to identify a target that is representative of an object of interest involved in the digital activity; generating, by the health management platform, an electronic record of the digital activity by associating the digital activity and the target; calculating, by the health management platform, a valence measure to associate with the electronic record by- comparing the electronic record to a personalized valence index that includes entries representing past digital activities performed by the individual, and producing, based on an outcome of said comparing, the valence measure that is indicative of an emotional feeling of the individual with respect to the object of interest; configuring, by the health management platform, a profile associated with the individual to include (i) an association between the valence measure and the electronic record of the digital activity and (ii) an indication whether a matching entry was found in the personalized valence index for the electronic record; and monitoring, by the health management platform, the personalized valence index to detect changes in a health state of the individual by- generating a count of new entries created for the personalized valence index over a preceding interval of time, and inferring that the health state has changed responsive to determining that the count of new entries exceeds a threshold.
“16. The method of claim 15, further comprising: determining, by the health management platform, that the electronic record does not match any entries in the personalized valence index; and updating, by the health management platform, the personalized valence index to include a new entry corresponding to the electronic record.
“17. The method of claim 15, further comprising: generating, by the health management platform, a notification that specifies the individual is likely to have experienced a change in health responsive to said inferring.
“18. The method of claim 15, further comprising: determining, by the health management platform, that the contextual data is associated with the individual based on the individual having previously logged into a source from which the contextual data is acquired.
“19. The method of claim 15, further comprising: identifying, by the health management platform, a first valence measure in the profile that is associated with a first point in time; identifying, by the health management platform, a second valence measure in the profile that is associated with a second point of time following the first point in time; and determining, by the health management platform, a rate at which valence is changing over time by comparing the first and second valence measures, wherein the rate is indicative of a health trend of the individual.
“20. The method of claim 15, wherein the object of interest is a person, an item, or a location involved in the digital activity.”
For the URL and additional information on this patent, see:
(Our reports deliver fact-based news of research and discoveries from around the world.)
Studies from University of Cape Town Update Current Data on Health Policy and Planning (How does power shape District Health Management Team responsiveness to public feedback in Low-and-Middle Income Countries? An interpretive synthesis): Health and Medicine – Health Policy and Planning
Patent Issued for Secure content sharing (USPTO 11520911): Imprivata Inc.
Advisor News
- Social cultivation: How to talk with wealthy prospects
- How important is a written financial plan?
- Coalition wants to advise people impacted by policy changes in new administration
- Diagnosing miscommunication in retirement planning
- Election creates an opportunity for advisor/client dialogue
More Advisor NewsAnnuity News
Health/Employee Benefits News
- ‘Especially disgusting’: Former workers, patients, level accusations at addiction treatment empire
- Doctor’s bills often come with sticker shock
- Covering weight loss drugs driving Virginia Medicaid costs higher
- Generations
- Vermont Dept. of Financial Regulation warns of potential health insurance scams
More Health/Employee Benefits NewsLife Insurance News