JP2017538210A - System and method for providing health judgment services based on user knowledge and activities - Google Patents

Abstract

Examples are provided herein for providing services related to determining a user's health. A set of questions is stored for the user. Each question here is based on a documented claim about human health. Each question in the set of questions consists of (i) people in a control group with independent knowledge of the claims underlying the question, and (ii) values of predetermined health parameters for each person in the control group. The predetermined health parameter value for each person is associated with a correlated health parameter based at least in part on the health parameter value indicative of the person's health. Based on the data generated by the one or more activity monitoring devices, questions from the collection are selected for display to the user.
[Selection] Figure 1

Description

  The examples described herein relate to systems and methods for providing a health assessment service based on user knowledge and activity.

  There are online services that provide users with interactive gaming and social environments. These services generally exist for entertainment purposes only.

  There is also a questionnaire provided by the Insignia Health issued by Oregon (referred to as a positive rating scale (“PAM”)), which is based on knowledge and appears to be related to health. Contains a static set of questions.

FIG. 3 illustrates a system for predicting a user's physiological or mental health based on a user's level of knowledge about health, according to one or more embodiments. It is a figure which shows the analysis system which concerns on one Embodiment. FIG. 6 illustrates an example of a data structure that can be developed to link questions with health outcomes and topics, according to one or more embodiments. FIG. 5 illustrates an exemplary method for predicting a user's health outcome based in part on whether the user has independent knowledge of health claims. FIG. 4 illustrates an exemplary method for predicting a user's health outcome based on the user's knowledge profile. FIG. 3 illustrates an exemplary method for providing a user with health-related services based on health results that are knowledge predicted for the user. FIG. 7 illustrates a health service subsystem 680, according to one embodiment. FIG. 6 illustrates an exemplary method for providing a game-based environment in which user responses allow prediction of health outcomes for individual users. FIG. 3 illustrates a knowledge-based suggestion engine according to one or more embodiments. FIG. 6 illustrates an exemplary method for selecting a question to be provided to a user based on data obtained from an activity monitoring device. FIG. 6 illustrates an example interface for use with one or more embodiments described herein. FIG. 6 illustrates an example interface for use with one or more embodiments described herein. FIG. 6 illustrates an example interface for use with one or more embodiments described herein. FIG. 6 illustrates an example interface for use with one or more embodiments described herein. FIG. 6 illustrates an example interface for use with one or more embodiments described herein. FIG. 6 illustrates an example interface for use with one or more embodiments described herein. FIG. 6 illustrates an example interface for use with one or more embodiments described herein. FIG. 6 illustrates an example interface for use with one or more embodiments described herein. FIG. 11 is a block diagram that illustrates a computer system upon which embodiments described herein may be implemented.

  Some embodiments include systems and methods for predicting a user's health outcome based on a determination of the knowledge the user possesses regarding a physiological or mental health problem.

  Further, in some embodiments, systems and methods are provided for providing health service assistance to a user based on the user's predicted health determined from the user's knowledge of human health.

  In one embodiment, a set of claims is stored. Each claim in this set is about human health. For each individual in the control group, a value of a predetermined health parameter indicative of the person's health is determined. Correlation health parameters indicating the association between these individuals in the control group with independent knowledge of the claims and the values of the pre-determined health parameters for the control group for each set of claims Is determined. The set claims may be stored by associating each claim with a predetermined correlated health parameter for the claim. An interface is provided to the user to show the user's independent knowledge of each claim in at least a portion of the claims from the set. Health outcomes are predicted for the user based at least in part on the correlated health parameters of the individual claims in the subset of claims.

  In yet another embodiment, a user's health outcome is predicted based on the user's knowledge profile determination. In one embodiment, a knowledge profile for the user is determined. This knowledge profile reflects the user's independent knowledge of each claim in the set of claims. A correlation between a set of aspects of the user's knowledge profile and a corresponding set of aspects of the plurality of individual knowledge profiles is determined. A knowledge profile may be determined for at least one set of claims from the set claims. A health result is determined for each individual of the plurality of individuals. A user's health outcome may then be predicted based at least in part on the correlation and the health outcome of each individual of the plurality of individuals.

  In yet another embodiment, a knowledge profile is determined for the user that reflects the user's independent knowledge of individual claims in the set of claims. Each claim in a set may be non-specific to the user or to any person in the control group, but is differently related to human health. Are known. A determination is made regarding a first correlation value between the user's knowledge profile and the knowledge profile of a control group of people for whom one or more health outcomes are known. A first health result for the user is predicted based on the first correlation value. Health service assistance is provided to the user based at least in part on the predicted health outcome.

  Further, according to another embodiment, a human health knowledge profile is determined for each user in a group of users. This person's health knowledge profile reflects the user's independent knowledge of the claims in the set of claims. Each claim in the set of claims can relate to a person's health and is not limited to any user or to any person in the control group. At least a first correlation value between an aspect of the knowledge profile of the individual user in the group of users and a corresponding aspect of the knowledge profile of the control group of persons with known health outcome (s) Is determined. A subset of one or more users is selected based on a first correlation value for each user in the subset that exceeds the threshold specification. A service or designation for one set value is provided to the one or more users of the subset and not to other users of the subset. The service or designation is not equal to the set value, but is variable and increases over time when individual users in the subset experience undesirable health effects as a result of naturally progressing medical conditions Can be associated with a true per-user cost that is set to Further, some embodiments include systems and methods for providing health services or health assistance to users. For example, health services or health assistance may include health insurance (including primary or supplementary insurance), life insurance, admission to facilities for medical treatment, medical publications, discounts or May include service improvements. In one embodiment, a set of questions is stored. Each question is based on a written statement about human health. Each question in the first subset consists of (i) people in the control group with independent knowledge of the claims underlying the question, and (ii) values of predetermined health parameters for each person in the control group (A predetermined health parameter value for each person indicates the person's health) and a correlated health parameter based at least in part. In addition, the second subset of questions is associated with correlated health parameters that are none (ie non-existent) or neutral (ie do not indicate health). A corresponding set of questions is displayed to the user from the set so that each user in the set of users can respond. A response score for each user in a set of users is determined based on the correctness of each answer to the corresponding set of questions. A health parameter value for at least one health outcome is determined based at least in part on the health parameter value of at least some of the questions in the corresponding set of questions.

  Further, some embodiments include systems and methods for providing health suggestions to users. In one embodiment, multiple questions are provided to the user. The plurality of questions may include a plurality of questions relating to each of a plurality of health related topics. As a result, each individual question is associated with one or more of a plurality of topics. A score for the user is determined when answering each question in the plurality of questions. The score may include a topic score for one or more topics of the plurality of topics. A set of suggestions for the user may be identified based at least on the topic score of the first topic. This set of suggestions may include actions that the user can perform to improve the user's mental or physiological health with respect to the topic.

  According to some embodiments, status data is determined from user activity, and more particularly from health related activities recorded by the user device. The user device may correspond to, for example, a mobile device that can be carried on the body (eg, a mobile device in an arm holster) or a wearable electronic device. For example, a wearable electronic device may include a computerized device that records exercise, position, and / or a user's biometric output (eg, body temperature or heartbeat). Wearable electronic devices can have a variety of form factors (eg, bracelets, watches, armbands, glasses, hats, clothes, etc.). Depending on the design or implementation, such devices can operate independently or in communication with other computing devices (eg, via a Bluetooth connection or a wireless connection to other mobile computing devices).

  As used herein, an activity monitoring device includes any electronic device that can be carried by a user (e.g., a mobile computing device or a wearable electronic device) that can track and monitor user activity related to health. Record. The recorded activities may include data relating to daily activities (eg, sleeping, walking, eating, or working (eg, sitting at a desk)) in addition to data relating to user exercises. According to some embodiments, data generated by one or more activity monitoring devices is obtained and the questions displayed to the user are based on the obtained data.

  Although the examples described herein are implemented on a computer system, empirical data has been derived that indicates that health outcome prediction can be correlated to user knowledge. For example, in various examples, it has been found that good health outcome determinations made from evaluating user responses have a direct correlation to fewer hospital stays.

System Overview FIG. 1 illustrates a system for predicting a user's physiological or mental health based on the user's level of health knowledge, according to one or more embodiments. The system 100 illustrated by the example of FIG. 1 may be implemented using a combination of servers or other computers. When these servers or other computers are combined, network services operated by a user base are provided to client computers. While the example of FIG. 1 illustrates a system 100 implemented as a combination of logic components, alternative implementations readily provide that the functionality herein is integrated or discrete. Can do. Further, the particular combinations of functions and processes described herein may alternatively be implemented as sub-combination combinations or as alternative combinations. Similarly, the example of FIG. 1 illustrates the use of multiple data storage devices. These data storage devices may be implemented logically and / or physically as a combined or integrated data structure (eg, a database) or alternatively in a distributed manner as shown. .

  Among other implementations, the system 100 interactively communicates with individual users to determine an individual user's level of knowledge regarding various health topics, and further, based on the individual user's knowledge level regarding health, To predict a user's physiological or mental health, mobile computing devices (eg, feature phones, tablets, etc.), personal computers (eg, desktop computers, etc.) via the network 101 (eg, World Wide Web). Computers, laptops, etc.) and computing devices operated by other users are accessible to user 11. Among other advantages, the example of FIG. 1 allows one to determine physiological or mental health aspects of a person without having to obtain user-specific medical information or biological samples. For example, in one implementation, user health can be predicted without using user-specific medical questions. In one variation, the user's health can be predicted based on gender and age inputs. In other variations, the data collected through the activity monitoring device can be used alone or in combination with other inputs to predict a user's health.

  As will be described in more detail, the system 100 (i) obtains responses from the user and (ii) correlates some of these responses to a physiological or mental health determination. Generate fact-based questions on various health topics to correlate. One assumption underlying the system 100 is that people's lifestyle or habits generally have a tendency to have a measurable impact on people's physiological or mental health (especially this assumption is statistically A sample of significant people (when applied to hundreds or thousands of people, for example). In statistically significant samples, it is recognized that in the embodiments described herein, there may be a correlation between an individual's knowledge or perception and an individual's relative health outcome. More generally, in embodiments, health-conscious individuals are more generally knowledgeable about health and therefore less healthy (eg, those suffering from obesity, heart disease, etc.) In comparison, it was found to be healthier. In fact, in embodiments, healthy individuals are remarkably careful about maintaining healthy lifestyle habits and activities, and because of such a way of thinking, such individuals are much more familiar with health than others. It is recognized that

  Recognizing this, the embodiments described herein measure how careful a given user is about health based on the user's perception of specific and health driven information. Systems are provided, and various embodiments further recognize that point. Such information is often categorized as trivia, but nevertheless a mechanism for portraying these individuals in a population that is actually careful about healthy lifestyles. provide. In addition, the embodiments described herein programmatically correlate health knowledge with an individual's physiological health among statistically significant sample size users.

  To measure knowledge, the embodiment of FIG. 1 maintains a library of factual claims about various subjects of human health (eg, nutrition, exercise, medicine, etc.). In the example of FIG. 1, these claims are presented to the user in the form of questions. In response to these claims, the response may provide a correct or incorrect answer, and further allow assessment of knowledge based on whether the user gave the correct or incorrect answer To do. While various examples provide a claim that is presented to the user in the form of a question to confirm the user's knowledge, in other embodiments, to measure the user's perception or knowledge of a particular claim Alternative forms of interaction can be used. For example, a statement presented as an answer is provided to the user, and the interaction required for the user may be that the user generates a question that results in that particular answer. In this reversal, the user's ability to generate a question is combined with the statement as a presented question, whether the user has independent knowledge of the underlying claim from which the statement was originally presented It functions as a mechanism for determining.

  Furthermore, as will be described in more detail, in some embodiments a set of claims is utilized. It should be noted that only a few claims in this set are determined to have a correlation with physiological or mental health. The user may not know at all what questions have a correlation with health, or only some questions have a direct correlation with health, while others have alternatives It may also be provided for various purposes (eg entertainment purposes). In some cases, the user may not even know that some of the claims that the user is responding have no correlation with the user's actual physiological or mental health. Among other benefits, using a large number of questions in combination with questions that have been determined to correlate with physiological or mental health can make it difficult for several individuals to use their true knowledge. Prevent “fraud” from acting on questions in a way that conceals levels and perceptions.

  More particularly, the system 100 includes a user interface 110, question selection logic 120, response logic 130, and health score logic 140. The question selection 120 can receive or access the question 127 from the question library 152, and the user interface 110 can display content based on the selected question 127 individually in any of a variety of computing environments. To the user, thereby prompting these individuals to provide an intentional response that reflects the user's understanding and knowledge of the question topic. Question 127 may have various purposes. In one example, the question library 152 has a correlation between (i) a first set of questions 127a that correlate with physiological or mental health, and (ii) physiological or mental health. And a second set of questions 127b that may serve an alternative purpose of providing trivia, factual information and / or entertainment. In addition, the question library 152 can be assigned to topics and subtopics. Further, the question library 152 may be associated with a difficulty score based on, for example, the percentage of correct answers in the control group who answered the question.

  When a user launches a session, the user interface 110 may record a user ID 121 and session information 125. At runtime, the user interface 110 may authenticate the user and provide credentials 139 to the user profile store 138 to obtain profile data 137. Profile data 137 may include, for example, (i) a topic that the user has previously asked about it, (ii) a topic that the user is interested in, (iii) an identifier for a question that the user has previously answered, and / or (iv) ) Any one or more of the user's determined knowledge level 135 may be specified. Using profile data 137, user interface 110 may specify parameters or other information to assist in selecting questions for the user. In one example, the user interface 110 may use the profile information 137 to identify one or more topic parameters 123 and / or a user knowledge level 135. Question selection 120 can then select the question 127 based on the parameter 113. The parameter 113 may be based on, for example, topic parameters 123, knowledge level 135, or user interest and / or preferences.

  The profile data 137 may also include user-specific game data 119 (eg, user personal settings for a game, game history, current game play status, etc.). In addition, the profile data 137 may include user community or social network data 117 (user personal settings for social or social network applications, social network content, etc.). User-specific game data 119 and community or social network data 117 may be loaded, for example, through respective functional layers of the user interface 110 when the user initiates a session with a service of the system 100.

  In addition to creating parameter 113 using profile data 137, system 100 may use device data 193 alone or in combination with profile data 137 for parameter 113. The device data 193 may include an indication of the user's general health and fitness level generated by the activity monitoring device 191. The activity monitoring device 191 includes an electronic device (eg, a wearable electronic device) that can be worn or held by the user 11 to track data regarding the user's activity level and health parameters.

  In addition to recording and tracking the global positioning system (GPS), motion sensors, and / or user activity, the activity monitoring device 191 also records and tracks user biometric information when performing such activities. Resources such as sensors to perform (eg, a heart rate monitor) may be included. In addition, the activity monitoring device 191 measures an accelerometer or set of accelerometers, a gyroscope, a magnetometer, an ambient light sensor, a heart rate sensor, a temperature sensor, and / or a side of the user's body when performing the activity. Other sensors may be included. The activity monitoring device 191 records activity data 193. It should be noted that the activity data 193 may include statistical information such as pace, distance, elevation difference, path history, beats, body temperature, and / or other information regarding user activity. Activity data 193 may include both (i) raw or measured data, and (ii) derived or calculated data based on measured or raw data and / or user input. Additional examples of device data 193 include, among other things, heart rate and heart rate trends, steps, distance traveled, climbing rank, calories burned (eg, derived from distance, steps, user weight / gender), activity fractions, among others. , Sleep quality, blood sugar level, cholesterol level.

  In some aspects, activity monitoring device 191 may store activity monitoring device 191 data in device database 192. The device database 192 can be managed by a computing platform (for example, Apple's APPLE HEALTHKIT). Such a computing platform may allow a mobile application to read and write data to the device database 192 based on a set of permissions. For example, permissions allow a user to select which applications have access to device data 193 to protect privacy and prevent unauthorized access to potentially sensitive information. In some implementations, the system 100 may use only the device data 193 if the user is specifically opted in and authorized for data accessed by the system.

  User interface 110 may be used to record responses 129 from individual users. In one implementation, each question 127 may be communicated to the user interface using a sequence in which answers to the question are further packaged and presented to the user. For example, some conditional logic may be provided to the question 127 so that if the user's response is correct, the user is immediately notified and the next question is presented to the user. However, the conditional logic may provide alternative content (especially a panel or other information item that provides information about the actual answer to the presented question) in response to the user's incorrect response. In this way, the user becomes more familiar.

  The response 129 may correspond to, for example, an input that identifies a user's answer to a particular question. Response 129 may specify the user's answer, the answered question, and the user's identifier. In some implementations, each question 127 may be further associated with one or more subject topics. Response logic 130 can process responses 129 from various users. In one implementation, the initial determination of the response logic 130 determines whether the question specified in the response 129 is pre-associated with a physiological or mental health correlation, or such pre-associated physiological or Whether there is a mental health correlation for the question. In one implementation, the response logic 130 records a corresponding response entry 131 for each response, regardless of whether the response question is pre-associated with physiological or mental health. The response entry 131 may reflect whether the answer to the question is correct and the true answer. In some implementations, the response entry 131 further links the answered question to a topic specification for the question and to a calibration or difficulty score.

  Score logic 144 may process the response entry 131 response to determine a score value 145 for associating with a particular record entry. The score value 145 may be based in part on the difficulty level of the question. This difficulty level may be provided as a calibration factor pre-associated with the question in some implementations. Thus, the mathematical process for tabulating the score includes factors such as the number of questions that the user answered correctly, the number of questions that the user answered incorrectly, the difficulty parameter associated with each question, and so on. / Or secondary considerations (eg, the time it took a user to provide a response and / or whether the user answered the question correctly on the first challenge, etc.). The score value 145 can be stored using the response data store 118.

  In addition, the score logic 144 may also calculate one or more total or overall scores for the user based on the recorded history of responses. For example, the response data store 118 may also hold an overall score for the user in addition to one or more aggregate or ongoing subject topic scores (eg, weight lifting). As described in other examples, score logic 144 may be used to generate a comparative score between users based on the user's overall knowledge, session performance, and / or topic subject knowledge.

  The response logic 130 may include a knowledge level determination component 134 as desired. Knowledge level determination component 134 may determine a user's knowledge level 135 from response 129. Alternatively, knowledge determination component 134 may determine a user's level of knowledge from difficulty parameters associated with questions and / or score output provided by score component 144. Knowledge level determination component 134 may determine an overall knowledge level or a topic-specific knowledge level 135. The determined knowledge level (s) 135 may be stored as part of the user profile 138. Thereby, the user's knowledge level is communicated to the question selection logic 120 when the user initiates a session with the system 100.

  For those selected questions identified as having a pre-associated physiological or mental health correlation, the response logic 130 may provide a corresponding health question record 133. The health question record 133 identifies, for example, questions, provided answers, and / or whether the questions were answered correctly. The health question record 133 also specifies the topic (s) of the question.

  According to some embodiments, the questions identified in health question record 133 may be associated with health parameter values 151. As illustrated by other examples, the health parameter value 151 is one of the correlation models generated using the control group to provide a quantified correlation to physiological or mental health. It can be determined as a part. The health score data storage device 150 may maintain a set of health parameter values 151 for individual questions. In one implementation, the health parameter value 151 reflects a predetermined health outcome. Multiple health outcomes can be considered, and each question in the health question record 133 can be associated with a particular health outcome. For example, possible health outcomes that have a quantifiable correlation to health parameter value 151 include: (i) health care costs for an individual in a given period; (ii) number of medical facility visits by an individual in a given period , (Iii) the number of prescriptions the person has received in a given period, and / or (iv) the number of sick days experienced by the person. Other examples of health outcomes include propensity for cancer (including different types of cancer), heart disease, diabetes, hypertension, or other illnesses. Thus, health outcomes may be numerical or continuous in nature (eg, health care costs) or categorized (eg, number of medical visits, prescriptions, days of illness).

  Thus, in one implementation, health score component 140 utilizes health result logic 142 to generate a health result score 165 that is specific to a particular health result definition 155. The health outcome logic 142 may be implemented as a formula or model and may take into account parameters including health parameter values 151 determined from the answered questions, the number of answered questions, duration of participation, etc. In one implementation, the combined or tabulated health parameter value 151 may be determined from identifying the health question 141 and the user response 143. Based on the question and response, a health correlation parameter 151 is obtained.

  In one embodiment, the health score component 140 uses the question 141 and response 143 in addition to the health correlation parameter 151 to predict the user's health outcome 165. When determining the health outcome, the health score component 140 may determine the health output score 165 using a model or equation. For example, if the health score component 140 assigns the user's input to a health score output, the health score output can be predictive to the user. The model used by the score component 140 to predict the user's health outcome score 165 may be the same model that determines the correlation between the question and the particular health outcome definition. An example of such a model is provided in FIG.

  A health result score 165 may be generated and stored as part of the user health data store 160. In addition, the health result score 165 can be unique to a particular health result, and the type of value reflected by the health result score 165 can be unique to the health result type. For example, in one implementation, for health outcomes that reflect health care costs for an individual, the health outcome score 165 can be a numerical representation of a particular cost or cost range for that individual. On the other hand, the health result score 165 with respect to the number of visits to the medical facility can be reflected by classification or level (for example, 1 to 5 depending on the amount).

  In one implementation, the user health data store 160 is kept logically or physically separate from the question answering data store 118 to prevent viewability for users of the system 100. Each user may include a health outcome score profile in the user health data store 160. Each user profile 141 includes scores for a plurality of different health results. In some variations, a combined score or classification may also be given to individual users as part of the individual user's health profile.

  As described in other embodiments, the health result score (s) 165 for a user may be made available for a health service, such as a health insurance service. For example, the coverage provided as part of a premium, deduction, or health insurance package for a user may be determined from the health outcome score (s) 165. As another feature, the user's health outcome score (s) 165 is whether the user should receive a discount on health insurance, or alternatively, an additional provided (or provided) to the user. Can be used to determine whether to receive a good benefit from health-related services.

  According to one embodiment, the health service 190 subsystem can utilize the health result score 165 provided in the user health database 160 to determine a designation, qualification, or service level associated with the health related service. . Examples of health-related services 190 include health insurance, life insurance, health service plans, membership of health-related facilities (for example, health spas, clinics, etc.), information services (magazine or magazine magazine subscriptions, electronic news). Can be mentioned. The assistance provided to the user includes the service itself or, alternatively, a health designation for use with such service. For example, a user's predicted health level may be determined by a health outcome score (s) 165, thereby generating an overall health outcome determination (eg, grade or classification), and then an overall health outcome. Result determination can be used to receive discounts on health-related services (eg, discounts on health insurance or life insurance premiums, extended coverage, etc.). One example of a health service subsystem is provided in the example of FIG. 6B.

  In some implementations, the user interface 110 of the system 100 may include various layers or functional components to enhance the user interaction level. In one implementation, the user interface 110 includes a gamification layer 112 and a community social network layer 114. The gamification layer 112 includes logic, data, and content (generally “game data 103”) for implementing a competitive environment in which individuals provide answers to the questions 127. The game data 103 is generated from the game engine 115, which can further personalize the game environment for a particular user. For example, the user identifier 121 can be used by the game engine 115 to generate user-specific game data 103. The game data 103 may include, for example, a competitive environment based on the user's knowledge level and / or the user's topical interest. An implementation utilizing the gamification layer 112 is illustrated in FIG. 7A. The gamification layer 112 may determine rewards or credentials (eg, skill level badges) for the user based on the user's performance. For example, the question 127 presented through the user interface 110 is associated with a score value that describes the difficulty (which may be determined from the calibration process as detailed below), response time, handicap (eg, user age), etc. Can be.

  Community social network layer 114 is operable using community data 117. Community data 117 may be generated from community / social network service 116. The community / social network service 116 may provide user-specific community (or social network) data based on the user identifier 121, for example. Community data 117 may provide content that is provided as part of community social network layer 114 (eg, a user's health interests or knowledge expertise).

  The health parameter value 151 represents a correlation and quantified measure between human health and knowledge about a particular claim. While the granularity of the health parameter value 151 is applied to questions answered by individuals, the determination of the health parameter value 151 may be based on a correlation model applied to users in the control group. Control group users include, for example, individuals who voluntarily provide real information about themselves (more specifically, actual health results in a recent period).

  More particularly, the system 100 may include a question analysis subsystem 170. Question analysis subsystem 170 includes functionality to determine a correlation between knowledge of individual questions and actual health outcomes. Subsystem 170 may implement and develop one or more correlation models 172. Correlation model 172 may analyze input query 171 to determine completion of correlation for health outcome. In particular, the correlation model is the knowledge of individuals in the control group for a particular question (indicated by the control group data store 180) and for those individuals who answered the question (correctly or incorrectly, depending on the implementation) It may be implemented to determine health parameter values 149 that statistically reflect the correlation between each health outcome. The health correlation value 151 can be unique for an individual question or for a group of questions. In one implementation, different correlation models 172 may be used for different types of health outcomes. Different correlation models may compare the predicted values with the actual (or real) data provided to the individual (shown as verified input 175). One example of a question analysis subsystem is described in more detail in the example of FIG.

  While many examples provide for the use of health correlation scores, other embodiments also generate suggestions for users based on, for example, the user's overall knowledge level as determined by the user's score or topic-specific score. obtain. Response analysis 164 may, for example, obtain score 145 from response database 118 and generate suggestions, content, or other output based on the user score. One example of response analysis 164 is shown using FIG. 7B and its accompanying examples.

  Additionally or alternatively, the community social network layer 114 may provide a forum (eg, a message board, an expert talk, or a topical wall for sharing information and experiences). In one implementation, the credentials that the user obtains from the gamification layer 112 are continued into the social environment of the community social network layer 114. For example, an “expert level” user is qualified to respond to other users' questions, and can further request payment or other rewards for providing answers or information to other users. Even have.

  FIG. 2 shows an analysis system according to an embodiment. In particular, FIG. 2 asks a question (or other form of claim) for the purpose of determining whether knowledge of the underlying claim by the subject may be correlated with the subject's physiological or mental health. An analysis system 200 for analyzing is shown. According to some embodiments, an individual question, or alternatively a group of questions, is a quantification that statistically relates the subject's knowledge (or lack of knowledge) about the underlying claim to a particular health outcome potential It may have a correlation with the evaluated evaluation index. System 200 may be implemented, for example, as a subsystem of physiological / mental prediction system 100 illustrated using the example of FIG.

  More specifically, system 200 includes a query capture interface 210, a field 220, a calibration component 230, and a correlation model implementation component 250. The question interface receives the question 209 through, for example, a manual interface (eg, an expert generates a question based on health claims). Question 209 may be manually associated with one or more topics related to human health (eg, topics related to nutrition or exercise or specific medical conditions). The granularity of topic 211 may be determined by the implementation. Question store 215 may be used to store questions 209 for processing as questions are calibrated and / or correlated to human health.

  Field 220 includes the ability to distribute questions 209 to control group users through control group interface 222. For example, the field 220 may issue a question using the user interface 110 of the exemplary system of FIG. For example, with further reference to the example of FIG. 1, questions 209 may be issued through game play of the user interface 110 and responses from various users may be recorded. On the other hand, several users can be designated as belonging to the control group. The user may correspond to an individual for whom data corresponding to ground truth data exists. For example, many users may be given the opportunity to voluntarily provide real health information. Such a user may be asked a question such as “Tell me how many times I have been seen last year” or “Tell me how many days I have been ill.” Further, information such as the user's health insurance cost can be obtained from an information source such as an insurance company. Thus, in one example shown in FIG. 1, a control group member may provide a response 213 to the question 209 presented throughout the game. At another time (before or after question 209 is presented to the subject), the subject may be given a choice to provide actual data, shown as true user data 241. True user data 241 may represent the actual health outcome of the subject providing response 213. True user data 241 may include information provided by the subject's insurer, for example, in addition to information manually supplied by the subject. Each response 213 from one of a control group of subjects (e.g., a user of system 100 opt-in to provide information) may be linked to a question and subject identifier 205. In addition, the true user data 241 can be linked to the subject's user identifier 205 that provides a response.

  In addition, the true user data 241 can be supplemented or replaced with information collected by the activity monitoring device 225 to generate more accurate control data. Activity monitor 225 may provide health data 226 (eg, heart rate as well as heart rate trends, calories burned, fractions of activity, sleep quality, blood glucose level, or cholesterol level) from sensors. If the user is located based on GPS data, location data 227 may also be provided and included. The GPS data can be used in combination with other databases, for example, to determine if the user is in a restaurant, grocery store, or other location. In addition, time data 228 may be used to track the user's schedule. In addition, the user can select questions to send to friends through activity monitoring device 225 as friend data 229.

  In some embodiments, some or all of these data collected from the activity monitoring device 225 can be used by the field 220 to select which questions 209 are presented to the user. For example, if health data 226 indicates that the user's blood pressure is high, a question regarding how to lower the blood pressure may be selected. If the user's sleep quality is shown to be poor, questions about good sleep tips can be selected. If the user has just finished exercising, a question about post-exercise recovery may be selected. If the user decides to run a new run, questions about basic knowledge about running are selected, and if the user is an advanced runner, more advanced questions can be selected instead.

  Location data 227 and time data 228 may also be used by field 220 to interpret the user's schedule and select appropriate schedule related questions. For example, if these data indicate that the user has been commuting on the metro for a long time every weekday, questions about exercises for long-time commuters may be presented. If the user is found to be in a restaurant, questions about healthy food selection are presented, and if the user is in a grocery store, questions about vegetables, organic food, and nutrition are presented. Can be done.

  The calibration component 230 may analyze the question 209 being processed to determine the difficulty level 265 of the question. For example, the calibration component 230 can query the acquisition storage 215 to calculate 231 the number of correct or incorrect responses. The percentage of individuals who answered the question correctly can provide the basis for determining the difficulty level of the question. The difficulty level 265 may be stored with a question for the next use.

  Correlation model 250 operates to determine the correlation between the subject's knowledge of the assertion underlying the question and the subject's health. In one implementation, the correlation model 250 may have different health outcome definitions (eg, health care or health care costs required by an individual, number of visits to a medical facility, trends for heart disease, cancer, hypertension, or diabetes, etc. In order to determine different parameter values that are statistically correlated with), one or more models are implemented. Correlation model 250 includes, as model input 255, (i) question identifier 261, (ii) identification of the answers each person provided to question 209, and a set of individuals in the control group that answered question 209. Identification and (iii) true user data 241 for each person in the set of individuals who answered the question may be received. The particular model selected (i) assigns the person to the expected outcome corresponding to a particular health parameter value based on the answer to the question, and then (ii) uses the true user data 241 The expected result is then compared to the true result by comparing the true health result (which reflects the actual data of the individual supplying the answer) with the expected result.

  Expected results are initially hypothetical or neutral values that indicate that a person may or may not have a particular health outcome based on the answers that a given person has provided to the question Can start as. Expected results may further include different values depending on whether the user provided a correct answer or an incorrect answer, as well as which incorrect answer the user provided. This initial correlation is, for example, whether the underlying argument of the question is information indicating behavior that is highly health-oriented (eg, people who rub both eyes are more likely to catch a cold), or less health-oriented It may correspond to a coefficient (e.g. a value in the range of 0 to 1) set by an anticipation about whether it is information indicating behavior (e.g. specific nutritional information about a donut). From the initial value, the correlation can be positive, negative, or neutral based on expected / actual comparisons for a set of people. As more individuals are added to the set, the validity or certainty of the correlation becomes higher. The correlation determined from the correlation model 250 can be designated as the correlation health parameter 251. Correlated health parameter 251 may be specific to a particular health outcome 253. Correlated health parameter 251 may correspond to a parameter value such as weight or coefficient, for example. When this parameter value is aggregated, modeled, and / or combined with other parameter values, a health outcome determination is made.

  The particular model 255 embodied by the correlation model 250 may depend on the nature of the health outcome to which the claim applies. For health outcome definitions where health parameter values are continuous (eg, monetary cost, weight, or body mass index for health care in a given period), a linear regression model may be used. Some health outcome definitions may utilize stratified or categorical health parameter values. For example, the number of visits to a medical facility is 0 = the medical facility has not been visited 1 = the number of visits to the medical facility in one year is 1 to 2 times, 2 = the number of visits to the medical facility in one year is 3 It may be defined as a stratified value, such as -5 times, or 4 = more than 5 visits to a medical facility in a year. Similar stratified values can be used for health outcomes such as disease days. For such health outcomes, an order logistic regression model can be used. In a variation, a multinomial or multinomial model can be used for stratified categories, particularly for those health outcomes that define a hierarchy that is not naturally ordered. Each question may be assigned to a specific health outcome such that the health parameter value is unique to the health outcome determination.

  A number of other machine learning models can be used both in developing correlated health parameters and determining health outcomes based on the correlated health parameters. For example, such machine learning models may include models of random forests, neural networks, and / or gradient boosting.

  In some embodiments, the determination of health parameter value 251 may be adjusted to reflect a determination for use with a model for which user-specific information is unknown. In one implementation, the control group includes an age group (eg, greater than 50 years old, less than 50 years old), gender, weight, race, geographic location or setting, and / or presence or absence of specific medical conditions such as diabetes Can be associated with a classification parameter such as Each question is associated with a plurality of correlated health parameter values 251, including health parameter values that reflect the general control group, as well as health parameter values that are specific to a class or subclass (eg, women over 50). Can be attached.

  According to some embodiments, the combination of the query and the correlated health value 251 may be assigned to one health result of a plurality of possible health results. Thus, in one implementation, a query may have a correlated health value because it applies to a single health result.

  Other implementations are based on a model where a classification (eg, gender or age) or a set of classifications (eg, gender and age) for the person answering the question is known to the user's health. A determination of the correlated health parameter value 251 is provided. Depending on the implementation, the user's classification may be (i) an unknown user for whom no information is known, (ii) some basic health-related characteristics (eg, age, gender, or combinations thereof). (Iii) users with known health related aspects (eg, gender and age in addition to weight and / or height). One implementation is a correlation health parameter that is uniquely determined for different classes of users based on applying the model described herein to a portion of a control group that has an associated classification. Provide 251 verdicts. Thus, in some variations, the correlated health parameter value 251 may be unique for a particular class of people such that health for the user is assessed with reference to the user's class. For example, in some embodiments, questions can be categorized for individuals who categorize themselves by the presence of certain medical conditions such as gender, age, weight, and / or diabetes.

  The system 200 can be embodied on a dynamic control group (meaning that it is possible to add individuals to the control group continuously over time). As mentioned above, the larger the control group, the greater the validity of the results. In an interactive gaming environment such as that described in the example of FIG. 1, additional people can be added to the control group continuously through invitations or opt-in features. For example, the user interface 110 may prompt the individual to voluntarily provide questions that reflect actual medical related information. This mechanism may provide a way to expand the control group by adding users for whom true user data 241 can be provided. The control group can be further managed based on criteria such as gender and age so that the desired control group portion is accurately reflected.

  With the determination of the health parameter value 251, the question may be considered processed, in which case the question may be included in a library or set of questions and marked as having a correlation to health. In one implementation, the library construction process 260 links the processed question 259 with the question identifier 261, topic identifier, difficulty level 265, and correlation health parameter 251 (or values). The difficulty level 265 can be used to determine which individuals are asked questions based on the user level.

  The example of FIG. 2 provides for the processing of questions that appear to be correlated with health, while the classification and calibration process includes all questions that are considered to have no correlation with health. Can be used to determine the difficulty of a question. For example, every question is associated with topic 211 based on, for example, the percentage of individuals in the control group who answered the question correctly, classified into the control group described above, and further evaluated with respect to difficulty level 265. obtain.

  FIG. 3 illustrates one example of a data structure that can be developed to link questions with health outcomes and topics, according to one or more embodiments. Although the example of FIG. 3 shows the data structure 300 as being logically integrated, the variation provides a distributed data structure that associates or links the parameters described herein. obtain. Referring to the example of FIG. 1, the example data structure 300 of FIG. 3 may include information comprising, for example, a question library 152 and a health score.

  More specifically, in the data structure 300, individual questions are associated with one of a plurality of possible correlated health parameters 303 and one or more topics 305 by a question identifier 301. Other information or parameters that can be communicated in the data structure 300 include difficulty levels that can be determined, for example, through the output of the calibration component 230 (see, eg, FIG. 2). For a given implementation, the correlated health parameter may be related to a particular health outcome. Multiple health outcomes can be defined for future time intervals, including health care costs, medical facility visits, sick days, and prescriptions. Other examples of health outcomes include blood glucose levels, body weight or body fat (eg, BMI), cholesterol levels, depression or anxiety disorders, and / or longevity. In one embodiment, each question is associated with only one health outcome and is further assigned a correlation health parameter value that reflects a correlation index between the underlying claim knowledge and the corresponding health outcome. It is done. In one implementation, the system of FIG. 2 determines a health parameter value for each defined health outcome, and the health parameter value selected for the question is the health parameter value with the strongest correlation. . If a correlated health determination is not generated for a question, the health parameter value for such question may be shown as invalid.

  As further illustrated by the example of FIG. 3, each question may be linked to multiple topics based on, for example, manual input. The determined difficulty level can also be expressed as a parameter (for example, a numerical value in the range of 0 to 1). The difficulty level can be independent of the topic assignment for the question. This means that the difficulty level of the questions can be provided as the same regardless of the assigned topics considered.

Methodology FIG. 4 illustrates an exemplary method for predicting a user's health outcome based in part on whether the user has independent knowledge of health claims. FIG. 5 illustrates an exemplary method for predicting a user's health outcome based on the user's knowledge profile. In describing the exemplary methods of FIGS. 4 and 5, in order to illustrate suitable components for performing the steps or sub-steps described herein, FIG. 1, FIG. 2, or FIG. An element can be referenced.

  Referring to the example of FIG. 4, a set of human health claims may be stored and processed (410) for use to a population of users. In one implementation, these claims may be formatted (412) as questions that indicate whether the user's answer indicates whether the user has knowledge of the claims.

  For the control group, health parameter values are determined for the control group individuals (420). Health parameter values may refer to actual or actual data that serves as an indicator of a user's physiological or mental health. In one implementation, the determination of health parameter values may be based on user input. For example, in the interactive gaming environment of FIG. 1, several users may be opted in to provide input that is limited to the required health (eg, sick days in the previous month or year). In some embodiments, the health parameter value may be based on a defined health outcome (422) or a combination of health outcomes. For example, health results include estimated health care costs for individuals (424), medical center visits for individuals in a given period (425), prescription times for individuals in a given time frame (426), for a given period. It may correspond to the number of sick days (428) of the individual who occurred.

  For each claim, a correlated health parameter is determined (430). In general, a correlated health parameter corresponds to a parameter index that links claim knowledge to human health in a quantifiable manner. The health parameter values 151 (FIG. 1), 251 (FIG. 2) described in other examples provide an example based on the use of a control group (432).

  Establishing a question with an associated correlated health parameter can be done through model instantiation with ground truth data provided by a selected user from a larger user-based responder. Once the correlated health parameters are established for individual questions, the questions are provided to the user base. The response from the user may be used to determine the user's independent knowledge level for a particular claim (440).

  Correlated health parameters for individual questions answered by the user can be determined and modeled (450) into values for specific health outcomes. For each user, the correlated health parameters of the answered questions regarding a particular health outcome may serve as input to determine an expected health outcome for the user (460). Multiple health outcomes can be determined in this manner.

  Referring to FIG. 5, a user's knowledge profile for a particular health outcome may be determined (510). A knowledge profile may reflect answers to individual questions or answers to a group or group of questions. The knowledge profile can be determined based on the selected definition. In one implementation, the knowledge profile is unique to the question and reflects whether the user answers the question correctly. In the variation, the knowledge profile is specific to the question and reflects which question the user answered. Furthermore, the knowledge profile may reflect the user's answer in the form of a grand total (eg 3-10 questions, etc.). Here, aspects such as the number of questions correctly answered by the user in the group or the number of answers considered to be more incorrect than other answers are reflected.

  Aspects of the knowledge profile can be compared (520) with corresponding aspects of the knowledge profile from individuals in the control group. In one implementation, a user's answers to a particular set of questions can be individually compared to answers to the same set of questions from one or more people in the control group. In a variation, a user's answer to one group of questions may be compared to an answer provided by a subset of the control group to the same group of questions. Here, the comparison is made for one group of questions as a whole. In addition, the user's answer can be compared to the answer provided by a subset of the control group that provided the exact same answer for a group of questions.

  Health outcome may be determined for a control group of individuals (530). As described in other examples, health outcomes can be defined as healthy lifestyle characteristics indicative of a person's health. The health result determined for one person in the control group may reflect actual information about the person (532). In one implementation, individuals in the control group may voluntarily provide their health outcome information (534). For example, the information may be provided in exchange for some assistance to the control group. In another example, personal health outcome information for a control group person can be determined using data from an activity monitoring device. In a variation, health outcome information for a control group person may be determined from an information source, such as a health care or insurance provider (536).

  A user's health outcome may be predicted based at least in part on a correlation between an individual's health outcome in the control group and a compared aspect of the knowledge profile between the user and the control group of people. (540). Thus, for example, user responses to individual questions can be compared to responses provided by these members of the control group for the same question. Additionally or alternatively, the user's answer to a group of questions can be compared to the questions provided to the same group of questions for a control group of individuals. It should be noted here that the comparison is based on matching the user with a subset of people in the control group based on the percentage of correct or incorrect answers provided.

  Health service methodology and subsystems

  FIG. 6A illustrates an exemplary method for providing a user with health-related services based on health outcomes that are knowledge predicted for the user. In describing the exemplary method of FIG. 6A, reference may be made to the elements of FIG. 1, FIG. 2, or FIG. 3 to indicate suitable components for performing the described steps or sub-steps.

  Referring to FIG. 6A, a health knowledge profile is determined 610 from each of a plurality of users for claims regarding health (eg, physiological health or mental health). As described in other examples, a health knowledge profile may reflect individual answers to questions. Note that these questions may be answered correctly or incorrectly, specific answers provided for a specific question (eg, incorrect answers), and / or questions answered from a defined group of questions. Of percentage.

  In addition, as described in other examples, the value of a health correlation parameter between the user and a subset of people in the control group can be determined (620). With reference to the example of FIG. 1, the health value parameter 151 may be determined, for example, by the health score component 140. When determining the health correlation parameters, a given aspect of the user's knowledge profile may be compared (622) to the knowledge profile of the related person in the control group. For example, this comparison may be made on a question-by-question basis, or alternatively on a population-by-group basis (eg, comparing a set of five questions, etc.). The actual health outcome is known to the members of the control group, and the particular correlated health parameter may be based at least in part on the known health parameters of the individuals in the control group. Correlated health parameters are therefore predetermined for the control group and can be based on real-world information about the members of the control group.

  Based on the correlation value, a health outcome determination is provided to the user (630). As shown in the example of FIG. 3, the correlation value may be specific to a predetermined health outcome. Still referring to FIG. 1, given a set of health parameter values 151 for a particular health result, the health score component 140 can make a health result determination. The determination of health outcome may be in the form of a score so as to give a relative indication of a particular health outcome compared to other individuals in the general population. The health outcome determination may correspond to a health outcome score 165, or alternatively, a combination of health outcome scores. For example, a plurality of health result scores can be determined for a user, and combining these scores can form a total health result determination.

  Based on the health outcome determination, health service assistance may be provided to the user (640). While a service or designation can be made to a setting value, the service or designation is not equal to the setting value but is variable, and the result of a medical condition in which individual users in the subset progress naturally As a true per-user cost that is set to increase over time when suffering from undesirable health effects.

  Health service assistance may correspond to a variety of direct or indirect service-related assistance. In one implementation, a user with a health outcome determination that exceeds a certain threshold may receive a designation (642). This designation may correspond to, for example, a service or credential provided only to a selected user of a network service comprising the system 100 (644). For example, a user who receives a health outcome determination that places the user in the top 10 percent of all users can receive a certificate, which in turn provides the user with a health care provider, health insurance, or related health. Allow discounts on service activities (eg discounts on nutrition stores, athletic gym membership, life insurance, etc.). Alternatively, the designation may indicate that a subset of users have services such as primary health insurance, secondary accident insurance, life insurance, or other membership services (which may or may not be health related). Qualify to receive.

  In a variation, the health outcome determination provides a basis for predicting the user's health, which may then be used to determine health related services for the user (646). For example, health insurance, life insurance, and / or accident health insurance may be provided to the user at a range and cost determined by health outcome determination. For example, premium costs or deductions for individual users may be based on health outcome determination (648). For example, insurance services are provided to users of system 100, and users with better health outcome determinations are discounted or deducted compared to control users with lower health outcome assessments? Or alternatively, the scope of coverage will be greater.

  FIG. 6B illustrates a health service subsystem 680, according to one embodiment. The health service subsystem 680 may be implemented with the system 100, for example, or may be implemented as part of the system 100. In a variation, the health service subsystem 680 may be provided as a separate system that interfaces with the system 100. In addition, the health service subsystem 680 provides an example of a system on which the example of FIG. 6 is implemented.

  Referring to FIG. 6B, the health service subsystem 680 includes a system interface 682, a customer data store 684, and service determination logic 686. The health service subsystem 680 may also include a service customer interface 688, such as a web page or application page. The service customer provides input to access the service customer interface 688 and provide specific logic or parameters for the service decision logic 686 in addition to the inputs for defining the health services provided. Service customer input 685 may include, for example, supplemental content for viewing by a user of system 100 in addition to text data definitions (eg, health or life insurance terms) for the services provided. This input may be stored in service data store 684.

  In some variations, service customer input 685 may further input parameters 683 and other logic (eg, rules) for service decision logic 686. The parameters 683 and rules may include, for example, a user (i) receiving a service, (ii) receiving a particular aspect or hierarchy of the service, and / or (iii) a service or hierarchy according to a particular price structure. It may include a definition of the qualifications required to do that. For example, a service may include a hierarchy of assistance, or a multi-tier cost structure, where each tier includes (i) a threshold health outcome score or set of scores, (ii) a health outcome threshold combination, and / or ( iii) may be provided to the user based on qualifications such as one or more of other health outcome determinations.

  System interface 682 may interface with user health database 680 to determine a given user or user-based health outcome score 689. In variations, the system interface 682 may communicate with push or trigger components on the system 100. This push or trigger component obtains a specific health result score and pushes the health result score to the system interface 682. In some embodiments, end users are excluded from handling health outcome data. The output of health determination logic 686 may correspond to notification 691. Notification 691 may specify the result of health determination logic 686. These results may be communicated to the user or to a health service assistance provider.

Gameplay Many embodiments have described the use of gameplay and logic as a mechanism to increase usage response and participation. More user responses and participation can be found by: (i) finding more qualified candidates who are willing to provide real health information to develop health correlations to questions, Allowing users to increase the size of the control group, (ii) more predictive correlations based on larger statistical samples, and (iii) better predictions of individual users' health It can have a number of advantages, including data points. In addition, the use of game logic can conceal health correlation questions from general viewing, thereby allowing the user to “deceive” (eg, learn) the questions to receive a good health score. Provides a mechanism to be prevented.

  FIG. 7A illustrates an exemplary method for providing a game-based environment in which user responses allow prediction of health outcomes for individual users. In describing the exemplary method of FIG. 7A, reference may be made to the elements of FIG. 1, FIG. 2, or FIG. 3 to indicate suitable components for performing the described steps or sub-steps.

  With reference to the example of FIG. 7A, a set of questions may be stored. Here at least some of the questions are based on core claims about health (702). For example, questions may be stored in question library 152 after being processed using the system described in the example of FIG. The stored questions include both (i) health correlation questions (704) and (ii) non-health correlation questions that are used to determine health outcome or to determine for the user. obtain. The latter questions may be related to health, but these questions are unrelated to health, or these questions are of little relevance to health perceptions, Therefore, it is determined that there is no correlation with actual human health (706). As described in other examples, a gaming environment may be implemented in which trivia questions are provided, whereby the user receives recreational assistance from participating in answering the questions.

  As described in yet another example, when a health correlation question is processed, a health correlation parameter may be determined (710). For example, the question analysis subsystem 200 can be used to determine the health correlation parameters 151 for a given question. As explained in yet another example, the health correlation parameters may be based on people (712) in the control group who have knowledge of the assertion underlying the particular question (or lack of knowledge about such claim).

  To facilitate participation and the development of accurate health outcome scores as well as decisions, a gaming environment may be established in which users are asked questions in a competitive or semi-competitive situation (720). An example of a game environment is shown in the environment shown through the interfaces of FIGS. 8A-8H.

  User responses to trivia questions are recorded. Note that these responses include both a score for health correlation questions (730) and a score for all questions (or alternatively, a non-health correlation score) (732). As described in the example of FIG. 6, the health correlation question may be scored 740 to determine a health service for the user. This score is hidden from the user or not known to the user and can be determined independently of the overall game score.

  Conversely, the overall game score may be published in a social or gaming environment to provide a user with credentials in a community of services provided through the system 100 (742). For example, the user may use the latter game score to achieve credentials, which may give the user authority to message board discussions and community platform question-and-answer forums.

  In some variations, the game score may also provide a mechanism for providing health-based suggestions to the user (744). For example, the user's knowledge base can be evaluated based on topic subjects, and the user's weaknesses or strengths for a particular topic related to health can be used to infer physiological or mental information about the user.

  FIG. 7B illustrates a knowledge-based suggestion engine according to one or more embodiments. With reference to FIGS. 1 and 7B, for example, the response analysis component 164 can include a suggestion engine 780. Proposal engine 780 may use information about the user's knowledge to generate proposal 785. Note that the proposal 785 may include content that conveys user-specific activities, lifestyle choices, or growth areas (related to knowledge or lifestyle) for growth.

  In one implementation, suggestions 785 may be based on determining a user's strengths or weaknesses regarding a particular health topic. The suggestion engine 780 may include a process 782 that correlates the topic score with the suggestion logic 790 after obtaining the user's topic score 781. Proposal logic 790 may include rules 791 and 793 for selecting suggestions for the user based on different topic scores and criteria. For example, the suggestion logic 790 may include rules for presenting suggestions for a particular topic to the user if the user's score is lower than a threshold for the topic. For example, if a topic related to heart health may be defined and if the user's topic score related to heart health is below a threshold, a set of suggestions 785 to improve the user's heart health is generated and communicated to the user. Can be. Similarly, if the user's knowledge is strong on a particular topic and it is interpreted as profitable, suggestion logic 790 may use this score to indicate a high level suggestion. For example, if the user has a high score in the topic of weightlifting, the suggestions provided to the user may be specific techniques or suggestions based on the question with the highest difficulty level (eg, determined from the calibration component 230 of FIG. 2). May be included.

  In some implementations, activity monitor 770 may provide device data 774 to suggestion logic 790. Note that device data 774 may include an indication of the user's overall health / fitness level. These devices may include a GPS receiver to record statistical information such as pace, distance, elevation difference, route history, and workout summary. In addition, these devices may include sensors such as accelerometers, gyroscopes, compass, ambient light sensors, heart rate sensors, among other features that can track and record health / fitness parameters. . Examples of device data 774 include, among other things, heart rate and heart rate trends, steps, distance traveled, rising rank, number of calories burned, fraction of activity, sleep quality, blood glucose level, and cholesterol level. Proposal logic 790 may then use device 774 alone or in combination with rules 791, 793 and topic score 781 to create proposal set 785. For example, if the topic score 781 indicates that the user does not know much about cholesterol, but the device data 774 indicates that the user's cholesterol level is good, the suggestion logic 790 does not suggest a cholesterol related question. You can choose as you like.

  In a variation, a set of proposals 785 generated for any one topic may be associated with a question or a subtopic of the question. Proposal filter 792 may filter proposal 785 so that those suggestions that the user may know are removed based on the questions that the user has correctly answered.

  Further, the proposal logic 790 may include combination rules. The combination rule selects suggestions 785 for the user based on criteria provided by the user's topic score in two or more topics. Combinatorial rules may specify subject relevance between topics so that the user's knowledge of one topic benefits other topics and vice versa. In one implementation, if a user's topic score for one topic is above a threshold and a topic score for another topic is below a threshold, the user's activity or interest in one topic is the user's knowledge about the second topic Or suggestions can be provided that assume lifestyle support. For example, a user may have a high score for weightlifting topics but a low score for nutrition or sleep. The suggestions provided to the user may specify a recommended time for the user to sleep to increase muscle mass.

  As another example, if the user is strong on subjects such as weight training but weak in nutrition, the suggestion engine should (i) develop a knowledge of nutrition in order to provide suggestions (Ii) nutritional information regarding training may be specified. For example, the proposal may suggest what the user should eat during training, how nutritional intake will affect performance in training, and that the user should confirm with the nutritionist and appropriate Expected results that can be achieved through proper diet and weight training. Such an example shows a suggestion that a user may make based on what is strong in his knowledge base for one topic but weak for other topics. In such a scenario, the relationship between the two topics can be determined in order to programmatically generate activities and learning subtopics that may benefit or assist the user.

  Based on different threshold decisions, similar proposals can be determined and linked to the user's topic score. In one implementation, if the user's score is low for two topics related to the subject, the suggestion to the user is subject to the assumption that the user is suffering from a health or psychological problem related to the topic, Can be selected.

  Further, topical analysis can also be used to infer characteristics for responders without making a mathematical correlation to the control group. For example, an individual who has a low score in both nutrition and exercise may be presumed to be obese, potentially diabetic, and / or suffering from other health-related problems (such as depression) . Based on such analysis, the suggestion engine may indicate growth areas for the user's knowledge. The suggestion engine 780 may, for example, publish a diet to the user for weight loss, recommend a psychiatrist (if the user is assumed to be depressed with high confidence), (next May provide suggested activities, such as recommending the user to visit a nutritionist and / or personal trainer (if it is assumed that the user is overweight) or diabetes and / or Alternatively, it may be suggested to encourage the user to check the blood glucose level for high cholesterol. Such activities are performed when the user has a low score for knowledge in topics that have a synergistic effect or relationship with each other when considered for physiological or mental health.

  FIG. 7C illustrates an exemplary method for selecting questions to be provided to the user based on data obtained from the activity monitoring device. In describing the exemplary method of FIG. 7A, reference may be made to the elements of FIG. 1, FIG. 2, or FIG. 3 to indicate suitable components for performing the described steps or sub-steps.

  Referring to the example of FIG. 7A, a set of questions is stored. Here, at least some of these questions are based on a core-correlated claim to health (750). For example, questions may be stored in question library 152 after being processed using the system described in the example of FIG. The stored questions are both (i) health correlation questions (752) and (ii) non-health correlation questions that are used to determine health outcome scores or to determine for the user. May be included. While the latter questions may be related to health, these questions are not determined to be correlated or healthy, or these questions are of little relevance to health perceptions, Therefore, there is no correlation with actual human health (754). As described in other examples, a gaming environment may be implemented in which trivia questions are provided, whereby the user receives recreational assistance from participating in answering the questions.

  Further, as described in other examples, when processing health correlation questions, health correlation parameters may be determined (755). For example, the question analysis subsystem 200 can be used to determine the health correlation parameters 151 for a given question. Furthermore, as explained in other examples, health correlation parameters may be based on people in the control group who have knowledge of the claims that underlie a particular question (or lack of knowledge about such claims) (760).

  In some aspects, the question selection 120 may obtain data generated by the activity monitoring device 191 to select questions in a context (762). This includes information about exercise (764) such as steps per day, calories burned, average activity level, as well as direct health indicators (763) such as heart rate, blood glucose and cholesterol levels. Can be included. These devices typically include sensors such as accelerometers, gyroscopes, compass, GPS, and light sensors that can be used to calculate specific health parameters such as sleep quality and distance traveled per day, among others. (765). In addition, GPS and clock data may be combined 766 with other health / fitness data to determine the user's schedule and the user's location.

  After obtaining activity monitoring device data, question selection 120 may select questions 768 taking these data into account. For example, if the health data indicates that the user's blood pressure is high, a question about a method for lowering blood pressure may be selected. If the user's sleep quality is shown to be poor, questions about good sleep tips can be selected. If the user has just finished exercising, a question about post-exercise recovery may be selected. If the user decides to run a new run, questions about basic knowledge about running are selected, and if the user is an advanced runner, more advanced questions can be selected instead.

  Location data and time data may also be used to interpret the user's schedule and select appropriate schedule related questions. For example, if these data indicate that the user has been commuting on the metro for a long time every week, questions about exercises for long-time commuters may be presented. If the user is found to be in a restaurant, questions about healthy food selection are presented, and if the user is in a grocery store, questions about vegetables, organic food, and nutrition are presented. Can be done.

  To facilitate participation and the development of accurate health outcome scores as well as decisions, a gaming environment may be established in which users are asked questions in a competitive or semi-competitive situation (720). An example of a game environment is shown in the environment shown through the interfaces of FIGS. 8A-8H.

Exemplary Interface FIGS. 8A-8H illustrate an exemplary interface for use with one or more embodiments described herein. The interfaces described in FIGS. 8A-8H may be implemented using, for example, the system described in the example of FIG. Accordingly, the elements of FIG. 1 may be referred to to indicate suitable components for implementing the interfaces described herein.

  In FIG. 8A, interface 800 provides a topic selection 804 to the user (eg, nutrition). The interface 800 may display information from the user profile 138, such as a game score 802 (provided as user profile game data 119 in the example of FIG. 1), and a badge or certificate 805.

  Panel 810 of FIG. 8B shows a question 812 in the form of a trivia. A set of answers 814 may be provided to the user. From answer 814, the user can make a choice to influence his score.

  FIG. 8C shows a panel 820 that provides feedback 825 to the user for correct answers and for auxiliary information regarding correct answers and / or the underlying claims of the question. In FIG. 8D, an additional panel 830 may be provided to the user when the user provides an answer. In this panel 830, the underlying claim 832 behind the question is displayed. Other information (such as the percentage of individuals who answered the question correctly) may be displayed to the user. This feature 834 may also reflect the difficulty level of the question.

  FIG. 8E shows a panel 840 on which an optional menu is provided. The user can select from a menu of options. As shown, the provided functions include games (eg, standings) and community interactions (eg, discussion) in the game and social environments described in the example of FIG. In addition, the menu of options may include a health report function 842 that may display, for example, suggestions determined from the example of FIG.

  FIG. 8F shows a panel 850 that provides a game summary for the user, which displays the user's overall score 852 as well as the achievement of a badge and award mark 854 indicating the number of questions answered by the user, and so on. To do.

  FIG. 8G shows a panel 860 on which a ranking table 862 is provided. The ranking table may be topic specific and / or categorized at the user level.

  FIG. 8H shows a panel 870 that enables social interaction, games and knowledge base forums through the system described in the example of FIG. Among other social interaction features, one or more knowledge-based “twins” may be designated for the user. A twin is one or more of (i) a knowledge profile about health or a specific topic related to health, and / or (ii) similar or identical health outcome values or decisions, closely shared with the user It can correspond to the individual to As an additional example or variation, the twin may also include similar demographic profiles (eg, having the same gender, age, and / or race). The same twin can be shown to each other as a mechanism for building social interactions and sharing experiences, especially to distribute health-based knowledge, information, and services.

Computer System One or more embodiments described herein that provide methods, techniques, and actions performed by a computing device may be performed programmatically or as a computer-implemented method. Programmatic means through the use of code or computer-executable instructions. Steps that are performed programmatically may or may not be automated.

  One or more embodiments described herein may be implemented using programmatic modules or components. A programmatic module or component may include a program, subroutine, part of a program, or software or hardware component capable of performing the tasks or functions described herein. As used herein, a module or component may reside on a hardware part independently of other modules or components. Alternatively, the module or component may be a shared element or process of another module, program, or machine.

  Further, one or more embodiments described herein may be implemented through instructions executed by one or more processors. These instructions may be carried on a computer readable medium. The opportunities illustrated or described in the following drawings provide examples of processing resources and computer-readable media on which instructions for implementing embodiments of the present invention are carried and / or executed. In particular, the numerous machines shown in embodiments of the present invention include a processor or processors and various forms of memory for holding data and instructions. Examples of computer readable media include permanent memory storage devices, such as a hard drive on a personal computer or server. Other examples of computer storage media include portable storage such as CD or DVD units, flash memory or solid state memory (such as those carried on many cell phones and consumer electronic devices), and magnetic memory. A unit. Computers, terminals, network-enabled devices (eg, mobile devices such as cell phones) are all examples of machines and devices that utilize instructions stored on a processor, memory, and computer-readable media. In addition, embodiments may be implemented in the form of a computer program or in the form of a computer usable carrier medium capable of carrying such a program.

  FIG. 9 is a block diagram that illustrates a computer system upon which embodiments described herein may be implemented. For example, in the situation of FIGS. 1, 2, 6B, and 7B, a network service or system may be implemented using one or more computer systems described by FIG. Further, the method described in FIGS. 4, 5, 6A, and 7A may be implemented using the computer system described in the example of FIG.

  In one embodiment, computer system 900 includes a processor 904, memory 906 (including non-transitory memory), a storage device, and a communication interface 918. Computer system 900 includes at least one processor 904 for processing information. Computer system 900 also includes memory 906, such as random access memory (RAM) or other dynamic storage device, for storing information and instructions executed by processor 904. Memory 906 may be used to store temporary variables or other intermediate information when executing instructions executed by processor 904. Computer system 900 may also include read only memory (ROM) or other static storage device for storing static information and instructions for processor 904. Communication interface 918 may allow computer system 900 to communicate with one or more networks through the use of network link 920 (wireless or wired).

  In one implementation, the memory 906 performs the functions described in the exemplary system or subsystem of FIG. 1, FIG. 2, FIG. 6B, or FIG. 7B, or in FIG. 4, 5, 6A, or FIG. Instructions for implementing functions implemented through the exemplary methods described may be stored. Similarly, processor 904 may provide the functionality described in the exemplary system or subsystem of FIG. 1, FIG. 2, FIG. 6B, or FIG. 7B, or FIG. 4, FIG. 5, FIG. Instructions may be executed when performing the operations described in the exemplary method.

  The embodiments described herein relate to the use of computer system 900 to implement the functionality described herein. The memory 906 includes, for example, a question library 931 (eg, the question library 152 of FIG. 1) that includes values for the health correlation parameters 933 of some questions (eg, see also the health correlation parameters 151 of FIG. 1). Reference) can be stored. Memory 906 also stores instructions 941 for determining a health score to determine one or more correlated health parameters for the user in combination with user participation in response to questions in an interactive community or gaming environment. Can do.

  According to one embodiment, the functions described herein may be performed by computer system 900 in response to processor 904 executing one or more sequences of one or more instructions contained in memory 906. . Such instructions may be read into memory 906 from other machine-readable media, for example through non-transitory storage. By executing the sequence of instructions contained in memory 906, processor 904 performs the processing steps described herein. In alternative embodiments, hardwired circuitry may be used in place of or in combination with software instructions to implement the embodiments described herein. Thus, the embodiments described herein are not limited to any specific combination of hardware circuitry and software.

  Although exemplary embodiments have been described in detail herein with reference to the accompanying drawings, specific embodiments and variations on the details are included in this disclosure. It is intended that the scope of the embodiments described herein be defined by the claims and their equivalents. Furthermore, certain features described herein may be combined individually or as part of one embodiment with other individually described features or with parts of other embodiments. It is considered a thing. Therefore, not explaining a combination does not prevent the inventor (one or more persons) from claiming rights for such a combination.

Claims (20)

A method for providing a service, implemented by one or more processors, and
Storing a set of questions, each question storing a question based on a documented claim about human health;
Associating each question in the set of questions with a correlated health parameter, the correlated health parameter comprising: (i) people in a control group having independent knowledge of the claims underlying the question; (Ii) a value of a pre-determined health parameter for each person in the control group, wherein the value of the pre-determined health parameter for each person is indicative of the person's health And associating, based at least in part on
Obtaining data generated by one or more activity monitoring devices;
Selecting one or more questions from the set of questions for display to a user based at least in part on the data generated by the one or more activity monitoring devices;
Displaying the one or more selected questions to the user;
Including a method. Determining a response score for the user based on the correctness of responses to the one or more questions;
Determining a health parameter value for a health outcome based at least in part on the correlated health parameter for at least some of the one or more questions;
The method of claim 1, further comprising:   The method of claim 2, wherein determining the health parameter value comprises determining the likelihood of the health outcome for the user over a future time period.   The method of claim 2, wherein determining the health parameter value is based at least in part on the acquired data from the one or more activity monitoring devices. Based on the correctness of the response to the one or more questions, determine a health topic that the user is relatively unfamiliar with and provide information to enhance the user's knowledge of the topic about,
The method of claim 2 further comprising:   Based on the correctness of the response to the one or more questions, the user is asked when the topic response score of the user is relatively high for the first topic and relatively low for the second topic. The method of claim 4, further comprising determining a topic subject for advice.   The data generated by the one or more activity monitoring devices includes (i) the distance traveled during the exercise routine, (ii) the type of exercise routine performed by the user, and (iii) the duration of the exercise routine (Iv) biometric data obtained from monitoring the user using one or more sensors of the activity monitoring device, (v) the location of the user at a given time, or (vi) the user The method of claim 1, comprising one or more of the times at which a particular activity was performed.   The method of claim 1, wherein the one or more activity monitoring devices include a wearable electronic device worn on the user's wrist that synchronizes with the user's mobile communications device.   The health outcome includes (i) an estimated number of visits or stays to a medical health facility by the user in a given period, and (ii) an estimate of the disease time that the user will experience in a given period. The method of claim 2, comprising: at least one of: (iii) an expected number of prescriptions that the user will need over a given period of time.   The method of claim 2, wherein the health parameter value is invisible to the user and the response score is displayed to the user.   The method of claim 1, wherein displaying the one or more selected questions to the user comprises providing an online multi-user trivia game to the user.   The method of claim 2, further comprising selecting to provide health services to the user based at least in part on the health parameter value. A method for selecting a health question for presentation to a user, performed by one or more processors, and
Obtaining data generated by one or more activity monitoring devices;
Selecting one or more questions from a set of questions for display to the user based on the data generated by the one or more activity monitoring devices;
Providing the user with the one or more questions, wherein the one or more questions are such that individual questions are each associated with one or more of the plurality of topics. Including and providing multiple questions for each of the health related topics of
Including a method. Determining a score for the user answering each question in the one or more questions, including determining a topic score for one or more of the plurality of topics;
Based on at least the topic score of the first topic, the user is provided with a set of suggestions including activities that the user can perform to improve the user's mental or physiological health regarding the topic To identify,
The method of claim 12, further comprising:   The method of claim 12, wherein the data generated by the one or more activity monitoring devices includes health indicators, exercise statistics, sensor data, and corresponding locations and times.   The method of claim 12, wherein the one or more activity monitoring devices are devices worn on the user's wrist that synchronize with the user's mobile communications device. When executed by one or more processors of a computer,
Storing a set of questions, each question storing a question based on a documented claim about human health;
Associating each question in the set of questions with a correlated health parameter, the correlated health parameter comprising: (i) people in a control group having independent knowledge of the claims underlying the question; (Ii) a value of a pre-determined health parameter for each person in the control group, wherein the value of the pre-determined health parameter for each person indicates the health of the person And associating, based at least in part on
Obtaining data generated by one or more activity monitoring devices;
Selecting one or more questions from the set of questions for display to the user based on the data generated by the one or more activity monitoring devices;
Displaying the one or more selected questions to the user;
A computer-readable medium storing instructions for causing the computer to execute an operation including: Determining a response score for the user based on the correctness of responses to the one or more questions;
Determining a health parameter value for a health outcome based at least in part on the correlated health parameter for at least some of the one or more questions;
The computer-readable medium of claim 17, further comprising instructions for performing.   The computer-readable medium of claim 17, wherein the data generated by the one or more activity monitoring devices includes health indicators, exercise statistics, sensor data, and corresponding locations and times.   The health outcome includes (i) an estimated number of visits or stays to a medical health facility by the user in a given period, and (ii) an estimate of the disease time that the user will experience in a given period. The computer readable medium of claim 17, comprising at least one of: (iii) an expected number of prescriptions that the user will need over a given duration.

Images