Data collection and analysis device

Abstract

The purpose of the present invention is to provide a data collecting / analyzing device capable of estimating the health state of a user in accordance with the aging of the body and mind of the user.　A health state estimating device 100 of the present disclosure is provided with: a data acquiring unit 104 for acquiring user information (including at least one of attribute information, position information, terminal operation information, app utilization information, and health care information) about one user acquired by a terminal 10 carried by the one user; a health state estimation model 105a for estimating health state corresponding to aging of body and mind; and a health state estimating unit 105 for inputting the user information into the health state estimation model 105a to estimate the health state of the one user.　The health state corresponding to the aging of body and mind includes at least one of frail and prefrail.

Description

Technical Field

[0001] The present invention relates to a data collection and analysis device for estimating a user's health condition.

Background Art

[0002] Patent Document 1 describes an invention for evaluating the correlation degree and influence degree between the health degree of an area of interest in health and preventive intervention actions based on biological information acquired over time.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0004] The health degree in the invention described in Patent Document 1 indicates locomotive syndrome, mainly indicating a state in which the motor function has declined due to disorders of the locomotor organs. Therefore, it is impossible to estimate the decline in the mental or social aspects of the user associated with aging. Further, in the invention described in Patent Document 2, frailty is determined from biological data such as vital signs and exercise volume and their reference values, but improvement in its accuracy is required.

[0005] An object of the present invention is to provide a data collection and analysis device capable of estimating the health condition according to aging in the physical and mental aspects of a user in order to solve the above problems.

Means for Solving the Problems

[0006] The data collection and analysis device of the present invention includes an acquisition unit that acquires information of one user acquired by a terminal held by the one user, a health state estimation model for estimating a health state according to aging of the mind and body, and an estimation unit that inputs the information into the health state estimation model to estimate the health state of the one user.

Effect of the Invention

[0007] According to the present invention, it is possible to estimate the health state according to the aging of the user's mind and body.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Embodiments for Carrying Out the Invention

[0009] Embodiments of the present disclosure will be described with reference to the accompanying drawings. Whenever possible, the same parts will be denoted by the same reference numerals and redundant descriptions will be omitted.

[0010] FIG. 1 is a diagram showing the system configuration of the health state estimation system of the present disclosure. As shown in the figure, this health state estimation system includes a terminal log collection device 20, an attribute information acquisition device 50, a position information acquisition device 60, a terminal operation information acquisition device 70, an app usage information acquisition device 80, a healthcare information acquisition device 90, and a health state estimation device 100.

[0011] The terminal log collection device 20 is a device that collects various sensor values and operation log information of the terminal 10 owned by the user.

[0012] The user declaration information management device 30 stores the attribute information for each user. In addition to age, etc., it may also store medical histories such as chief complaints, current medical histories, past medical histories, physical findings, examination findings, or mental state information. These pieces of information are information obtained in advance through declarations from the user or the like.

[0013] The attribute information acquisition device 50 is a device that acquires the attribute information of the user stored in the user declaration information management device 30 via a network. The user's attribute information indicates at least one of the user's age, gender, family composition, and occupation. In addition, information indicating other attributes of the user may also be used. The attribute information may also include medical history information including mental state information. For example, information on whether the user is in a depressive state or not.

[0014] The location information acquisition device 60 is a device that acquires location information regarding the user's location from the terminal log collection device 20. The location information includes at least one of the latitude and longitude or the visited location where the user was located, information indicating whether the user went out, the time of staying at home when the user stayed at home, the moving distance to the user's destination, the moving time of the user, the moving speed of the user, the means of transportation of the user, the walking distance of the user, the walking time of the user, or the walking speed of the user. These location information are information indicating the user's motor function, information indicating the user's lifestyle, or information indicating the user's sociality.

[0015] The terminal operation information acquisition device 70 is a device that acquires terminal operation information regarding the user's terminal 10 from the terminal log collection device 20. The terminal operation information is information regarding the user's operation of the terminal 10, and includes at least one of, for example, the terminal usage time, the number of times the terminal is used, the number of times the power is turned on / off, the history of changes in various function settings, the number of incoming and outgoing calls, the call time, the remaining battery level, and the time until the battery is restored. These terminal operation information are information indicating the user's cognitive function or information indicating the user's sociality.

[0016] The application usage information acquisition device 80 is a device that acquires usage information of applications (hereinafter abbreviated as apps) operated by the user installed on the terminal 10 from the terminal log collection device 20. The app usage information includes at least one of the app name, the type of app, the setting information in the app, the change information of the app settings, the number of times the app is used, and the usage time of the app. As the types of apps, there are fitness apps (such as pedometers) for promoting the user's exercise, medical apps (such as blood pressure monitors, pulse meters, and capillary oxygen concentration meters) for managing the user's health, map apps for providing map information, route guidance apps, game apps, video viewing apps, camera apps, SNS apps, etc., and they may be distinguished. These app usage information are information indicating the motor function, cognitive function, lifestyle, or sociality, etc. respectively.

[0017] The healthcare information acquisition device 90 is a device that acquires healthcare information regarding the health and exercise of a user detected in the terminal 10 from the terminal log collection device 20. The healthcare information includes at least one of the number of steps, walking distance, walking speed, calorie consumption, running distance, exercise time or amount of exercise in sports or gym, and BMI of the user. Note that the BMI may be acquired as attribute information.

[0018] In addition, although not shown in the figure, there may be a device that acquires the user's behavior history information, conversation voice information, information related to meals, health-related questionnaires, etc. For example, as the behavior history information, there may be a device that acquires the user's behavior history information for each weekday, holiday or day of the week. This behavior history information is information indicating cognitive function, lifestyle, or sociality. Also, as information related to meals, there may be a device that acquires the number of meals, meal content, and calorie intake. This information related to meals is information indicating oral function or lifestyle. The questionnaire is an answer to a plurality of questions regarding the health status. These information are information pre-registered by the user to be estimated or other users.

[0019] The health status estimation device 100 is a data collection and analysis device that acquires various information acquired by these various acquisition devices and estimates the health status of the user. In the present disclosure, the health status of the user includes not only the physical health status but also the mental health status (cognitive function), and indicates the health status according to aging. This health status according to aging indicates whether the user is frail or pre-frail, and although the physical function and cognitive function are declining, it is a state in which the need for care can be prevented by treatment or prevention.

[0020] FIG. 2 is a diagram showing the functional configuration of the health status estimation device 100. As shown in the figure, the health status estimation device 100 includes a data storage unit 101, a health status estimation model generation unit 102, a mental status estimation model generation unit 103, a data acquisition unit 104, a health status estimation unit 105, a contribution data derivation unit 106, and a result notification unit 107.

[0021] The data storage unit 101 is a part that stores learning information for generating the health state estimation model 105a. The learning information includes user information, mental state information, and health state information for each user. The user information is the user's attribute information and behavior information. The mental state information is, for example, information indicating a depressive state. The health state information indicates being frail or pre-frail. This learning information is information prepared in advance.

[0022] Fig. 3(a) is a diagram showing a specific example of the learning information. As shown in the figure, for each user and the date and time thereof, user information, mental state information, and health state information are stored. The user information is based on the information acquired by each acquisition device as described above. The detailed information thereof is omitted in the figure for convenience of explanation. The mental state information (presence or absence of a depressive state) and the health state information (presence or absence of frailty or pre-frailty) are information obtained based on the declaration by the user. The date and time is the date and time when the user information of that user was acquired.

[0023] This learning information is information prepared in advance by the operator of this system. Note that, as shown in Fig. 3(b), some of the user information in the learning information may be missing. For example, in Fig. 3(b), there is no description in the position information of user ID: ccc. In such a case, at the time of generating the prediction model, it may be complemented based on the information of other users.

[0024] The health state estimation model generation unit 102 is a part that learns the health state estimation model 104a based on the learning information stored in the data storage unit 101. The learning information includes user information, mental state information, and health state information for each user. The health state estimation model generation unit 102 learns the health state estimation model by performing machine learning with the user information and the mental state information as inputs (explanatory variables) and the health state information as an output (objective variable). Details will be described later.

[0025] The mental state estimation model generation unit 103 is a part that generates a mental state estimation model 103a for complementing the mental state information of the user. When the health state estimation model generation unit 102 generates a health state estimation model, it requires the mental state information of the user among the learning information, but there may be a case where it is missing (see Fig. 3(b)). In that case, a mental state estimation model 103a for complementing the mental state information of the user is generated. The health state estimation model generation unit 102 can obtain the mental state information by inputting the user information into the mental state estimation model 103a.

[0026] The data acquisition unit 104 is a part that acquires user information from each acquisition device such as the attribute information acquisition device 50. The user information includes at least one of attribute information, location information, terminal operation information, application usage information, and healthcare information. Among these information, the location information, terminal operation information, application usage information, and healthcare information are treated as user behavior information.

[0027] The health state estimation unit 105 is a part that inputs the user information and mental state information of the user to be estimated, which are acquired by the data acquisition unit 104, into the health state estimation model 105a, and estimates the health state of the user.

[0028] Fig. 4 is a diagram showing specific examples of user information and mental state information. These user information and mental state information are the information acquired by the data acquisition unit 104 (see Fig. 4(a)). The user information and mental state information of one user are input into the health state estimation model 105a, and the health state information (whether frail or pre-frail) of the one user is output from the health state estimation model 105a.

[0029] When predicting the health status using the health status estimation model 105a, the contribution data derivation unit 106 is a part that derives which data items of user information or mental state information (data items) contributed to the estimation of the user's health status. To derive the data items, the contribution data derivation unit 106 uses, for example, known techniques such as Shap and Permutation Importance. These data items are more refined information (such as coordinate information and usage time information) of the attribute information, location information, terminal operation information, application usage information, and healthcare information in the user information.

[0030] The result notification unit 107 is a part that notifies the user of the health status of the user estimated by the health status estimation unit 105 and the data items derived by the contribution data derivation unit 106. The result notification unit 107 may transmit this information to the terminal 10 owned by the user, or may transmit it to other terminals. Also, when the result notification unit 107 is a display, it may notify the user by displaying.

[0031] This result notification unit 107 may have a function of notifying messages that prompt the user's health status, the risk of the health status, and behavior improvement (behavior modification). For example, the result notification unit 107 generates and notifies a message that prompts the user to perform an action that improves the health status from the above-derived data items and the health status. As a method for generating a message, data items that contribute to the health status among the data items are extracted using a known algorithm such as shap, and a message that prompts improvement of the data items is generated. The health status includes not only the physical health status but also the mental health status (cognitive function), and indicates the health status according to aging. This health status according to aging indicates whether the user is frail or pre-frail, and although the physical function and cognitive function are declining, it is a state in which the need for care can be prevented by treatment or prevention. The risk of the health status means, for example, the possibility of contracting a disease, the possibility of exacerbation or contracting another disease if already suffering from a disease, and the possibility of being in a health state that increases the risk of contracting a disease even though it is not a disease such as frailty or obesity. A risk estimation model utilizing machine learning may be created and obtained from user information, questionnaires obtained from the user, health examination results, receipt data, etc.

[0032] The operation of the health status estimation device 100 configured as described above will be described. FIG. 5 is a flowchart showing a method for generating the health status estimation model 105a in the health status estimation device 100 and a method for estimation using the health status estimation model 105a. The health status estimation model generation unit 102 acquires all or part of the user information, mental state information, and health status information as learning information from the data storage unit 101 (S101). The health status estimation model generation unit 102 detects outliers from the user information, mental state information, and health status information, removes them, and also complements the missing values (S102). An outlier is a numerical value that is clearly abnormal and extremely large or small. For example, it is conceivable that the number of times of using the application is a value that cannot be normal. In such a case, it is complemented with the average value in consideration of other learning information, but it is not limited to this and may be a predetermined numerical value.

[0033] Then, the health state estimation model generation unit 102 generates a health state estimation model 105a based on the learning information by machine learning (S103).

[0034] The health state estimation unit 105 estimates the user's health state using the generated health state estimation model 105a (S104). The result notification unit 107 notifies the estimated health state of the user (S105). Also, the contribution data derivation unit 106 may derive the data items that contributed to the estimation result when estimating the user's health state, and the result notification unit 107 may notify the data items together. Note that in the figure, it is described that the processes S103 and S104 are executed in a series of flows, but of course it is not limited to this. Once the process S103 is completed, the process S104 may be started when starting the estimation process. Also, these processes S103 and the processes S104 and S105 may be performed by different devices.

[0035] Next, the details of the generation process of the health state estimation model 105a in the process S103 will be described. FIG. 6 is a flowchart showing the detailed operation.

[0036] The health state estimation model generation unit 102 processes some of the data items (such as the age of the attribute information, the coordinate information of the position information, etc.) of the learning information acquired by the data acquisition unit 104 as necessary (S201). For example, the health state estimation model generation unit 102 may calculate whether the user has gone out from the latitude and longitude information included in the position information, the time of staying at home when the user was staying at home, the moving distance to the user's destination, the moving time of the user, the moving speed of the user, the means of movement of the user, the walking distance of the user, the walking time of the user, or the walking speed of the user, etc., and may normalize these data. Similarly, new data items may be calculated or normalized in the terminal operation information, app usage information, healthcare information, etc.

[0037] The health state estimation model generation unit 102 acquires learning information (user information, mental state information, and health state information) of users of any age or older (S202). For example, it acquires user information, mental state information, and health state information of users aged 65 or older.

[0038] The health state estimation model generation unit 102 further acquires learning information for an arbitrary period from these learning information (S203). Then, the health state estimation model generation unit 102 clusters one or more users of the learning information using the user information (S204). The user information includes at least one of the user's behavior information, the user's age or age group, the user's gender, or the user's family composition.

[0039] In addition to these, clustering may also be performed based on mental state or social activities. In the present disclosure, social activities are defined based on a part of the location information (such as the presence or absence of going out, the time of staying at home, etc.), a part of the terminal operation information (such as the usage time of the terminal, the number of times of using the terminal, etc.), and the app usage information among the user information. For example, it is estimated that users with the same location information and the same terminal operation information are performing the same social activities, and clustering of the users and their learning information is performed based on these information. In addition, social activities may be defined based on behavior history, conversation voice, etc.

[0040] For clustering, for example, Support Vector Machine, Kmeans clustering, etc. may be used, or for example, stratification may be used using data such as the user's age, gender, family composition, etc.

[0041] The health state estimation model generation unit 102 performs the complement processing on the learning information of users who do not include mental state information (S205). This complement processing is performed for each cluster clustered based on the user information.

[0042] The health status estimation model generation unit 102 selects data items that are highly related to the health status (frail or pre-frail) from the learning information subjected to the complementation process using an arbitrary method (known machine learning or feature selection tool) (S207). Note that the mental state information is selected as essential. Here, as known machine learning or feature selection tools, Lasso, ElasticNet, Boruta (XGBoost, LightGBM, RandomForest), etc. are known.

[0043] The health status estimation model generation unit 102 applies the selected data items to an arbitrary machine learning method to generate a health status estimation model 105a for the period T1 (S208). For example, as machine learning methods, multiple regression, Lasso, ElasticNet, XGBoost, LightGBM, RandomForest, SVM, Kmeans are known. Note that the selected data items are at least behavior information indicating the user's behavior. For example, in FIG. 3, among the user information, it includes at least one of position information, terminal operation information, application usage information, and healthcare information.

[0044] Here, the complementation process of the mental state information in the process S205 will be described. FIG. 7 is a flowchart showing the detailed process. The health status estimation model generation unit 102 starts a loop process for each cluster clustered in the process S205 (S205a). For example, among the user information, the behavior characteristics of the user change according to the behavior information (position information, terminal operation information, etc.). As a result, the mental state changes, so it is better to complement the mental state information for each user information (especially for each user's behavior information).

[0045] The health status estimation model generation unit 102 applies the learning information of the users including the mental state information in the learning information to a known machine learning method to generate a mental state estimation model 103a (S205b). The learning process is performed with the user information as the input (explanatory variable) and the mental state information as the output (objective variable). Note that a part of the user information (the user's behavior information) may be used as the input.

[0046] Then, the health state estimation model generation unit 102 applies the mental state estimation model 103a to the learning information of the user lacking mental state information to estimate the mental state information of the user (S205c). For example, the learning information of that user lacks mental state information (see Fig. 3(b)), and it is estimated whether the mental state information is in a depressive state or not.

[0047] Process S206b and process S206c are performed for each cluster based on the user information (S205d). By this process, the mental state estimation model 103a for each cluster is generated, and the mental state of the user is estimated for each cluster.

[0048] Next, the health state estimation process of process S104 will be described. Fig. 8 is a flowchart showing the health state estimation process. The health state estimation unit 105 processes the data as necessary in each data item of the user information and mental state information of the user to be estimated acquired by the data acquisition unit 104 (S301). For example, the health state estimation unit 105 may calculate whether the user has gone out from the latitude and longitude information included in the position information, the time of staying at home when the user stayed at home, the moving distance to the user's moving destination, the moving time of the user, the moving speed of the user, the moving means of the user, the walking distance of the user, the walking time of the user, or the walking speed of the user, etc., and these data may be normalized. Similarly, new data items may be calculated or normalized in the terminal operation information, app usage information, healthcare information, etc.

[0049] Then, the health state estimation unit 105 extracts the learning information (user information and mental state information) for the period necessary for data complementation (S302).

[0050] The health condition estimation unit 105 complements, based on the extracted learning information, the data among the data items of the input information that is insufficient for the application of the health condition estimation model 105a (S303). For example, it is complemented with the average value of data of the same gender, the same age range (within a years before and after), and the same BMI (within b before and after). Gender, age, BMI, etc. are calculated based on the attribute information (or healthcare information) in the learning information. When the mental state information is missing, the mental state estimation model 103a generated in FIG. 7 may be used.

[0051] The health condition estimation unit 105 applies the complemented input information to the health condition estimation model 104a to estimate the health condition (S304).

[0052] The result notification unit 107 notifies the estimated health condition (S305).

[0053] Next, the process for notifying the data items that contributed to the estimation will be described. FIG. 9 is a flowchart showing that process. As shown in the figure, processes S301 to S304 are the same as the processes in FIG. 8. The contribution data derivation unit 106 acquires the data items that contributed to the estimation result using the health condition estimation model 104a (S304a).

[0054] Then, the result notification unit 107 notifies the user of the estimated health condition and also notifies information regarding the data items that contributed to the estimation (S305a). The information regarding the data items includes the results for improvement from the health condition. For example, when the contributed data items are among the location information items such as the presence or absence of going out, the staying time at home, the moving distance, etc., the information regarding the data items is a message that encourages improving it. For example, when it can be determined that the user goes out little and moves little by looking at the location information of the user information, examples of such messages are "Let's go for a walk once a day".

[0055] Next, a modification example of the generation process by the health state estimation model generation unit 102 will be described. FIG. 10 is a flowchart showing the process. Processes S201 to S203 are the same as those in FIG. 6.

[0056] The health state estimation model generation unit 102 starts a process of looping by item of age, gender, family composition, mental state, or social activity. That is, the health state estimation model generation unit 102 clusters the learning information for users of the same age, same sex, same family composition, same mental state (presence or absence of depression state), or same social activity, and obtains the learning information for each cluster (S211).

[0057] In the present disclosure, social activity is defined based on a part of the location information (presence or absence of going out, home stay time, etc.), a part of the terminal operation information (usage time of the terminal, number of times of using the terminal, etc.), and application usage information among the user information. For example, it is estimated that users with the same location information and the same terminal operation information are performing the same social activity, and clustering of the users and their learning information is performed based on these information. In addition, social activity may be defined based on action history, conversation voice, etc.

[0058] The health state estimation model generation unit 102 extracts data items that are highly related to the health state by an arbitrary method using machine learning or a feature selection tool, etc. (S212). This data item shall include a data item related to a specific mental state.

[0059] The health state estimation model generation unit 102 generates the health state estimation model 105a for the period T1 by an arbitrary machine learning method based on the extracted data items (S213).

[0060] The health state estimation model generation unit 102 repeats these processes in order to generate a health state estimation model for each cluster (S214).

[0061] Next, the operation and effect of the health state estimation device 100 of the present disclosure will be described. The health state estimation device 100 of the present disclosure includes a data acquisition unit 104 that acquires information of a single user (for example, including at least one of position information which is behavior information, terminal operation information, application usage information, healthcare information, and other information other than behavior information) acquired by a terminal 10 held by the single user, a health state estimation model 105a for estimating a health state according to aging of the mind and body, and a health state estimation unit 105 that inputs user information into the health state estimation model 105a to estimate the health state of a single user.

[0062] This health state according to aging of the mind and body includes at least one of frail or pre-frail. Note that the health state may be estimated including the risk of the health state. In the present disclosure, the health state to be estimated may include the risk.

[0063] With this configuration, it is possible to estimate a health state according to aging of the mind and body based on user information. In the present disclosure, it is particularly estimated to be frail or pre-frail.

[0064] Further, in the present disclosure, the health state estimation unit 105 inputs mental state information regarding the mental state into the health state estimation model 105a in addition to the user information to estimate the health state.

[0065] Health states such as frailty are also greatly affected by the mental state, for example, the depressive state. In the present disclosure, by considering the mental state of the user, an accurate health state can be estimated. Note that in the present disclosure, the depressive state is taken as an example of the mental state, but other states may be included, for example, adjustment disorders including simply a depressive state.

[0066] In the present disclosure, user information includes at least one of information related to motor functions, information related to cognitive functions, information related to lifestyle habits, information related to sociality, and attribute information. In the above description, for the sake of convenience, action information and attribute information are distinguished, but action information may also include attribute information. When simply referred to as information in the present disclosure, it shall include both, but may also include other information.

[0067] In the present disclosure, as an example, information related to motor functions includes at least one or more of the number of steps, step width, number of times of going up and down stairs, speed of going up and down stairs, moving distance, energy consumption, resting energy consumption, exercise time, walking double-support time, and walking asymmetry.

[0068] The number of steps, step width, number of times of going up and down stairs, speed of going up and down stairs, and moving distance are obtained from each sensor value (such as a motion sensor) of the terminal 10. The energy consumption may be calculated based on a predetermined calculation formula based on the above number of steps, etc., or may be calculated by an energy calculation application. The resting energy consumption and exercise time are determined by each sensor value (such as a motion sensor) of the terminal 10 during rest and exercise, and the resting energy consumption is obtained by a predetermined mathematical formula or application.

[0069] The walking double-support time is the time when the user stands on both feet based on the walking cycle, and is obtained by a motion sensor or the like of the terminal 10. The walking asymmetry indicates that an asymmetric step has been detected during the walking period, and is also obtained by a motion sensor or the like of the terminal 10.

[0070] Also, as an example, information related to cognitive functions includes at least one or more of the time required to unlock the terminal, the time required to use an application after unlocking the terminal, the number of times the terminal is opened, the number of times the terminal is closed, the number of calls, the call time, the number of incoming calls, and the number of outgoing calls. The time required to unlock the terminal indicates the time from when the user picks up the terminal until it is unlocked. Regarding other parameters as well, they are measured using other sensors such as the motion sensor of the terminal 10.

[0071] Also, as an example, the information regarding lifestyle habits includes at least one or more of the wake-up time, bedtime, sleep time, the number of times or usage ratio of an app, the number of camera shootings, and the terminal setting change history.

[0072] For each of these times and the like, the start time and end time are measured using each sensor value (such as a motion sensor) of the terminal 10 and other sensors, and their usage is also measured.

[0073] Also, as an example, the information regarding sociability includes at least one or more of the home stay rate, the number of location information acquisitions, the time away from home, and the number of visited destinations.

[0074] These information are based on the location information acquired by the terminal 10. The location information is obtained by GPS, but it is not limited to this.

[0075] Also, as an example, the attribute information includes at least one or more of the user's age or age group or date of birth, the user's gender, the user's family composition, the user's occupation, the user's place of residence, the population density rate or population density level of the user's place of residence, the user's height, the user's weight, the user's BMI, the user's body type, the user's mental state, or the user's medical history.

[0076] These information are information set by the user in advance. These information are obtained from a user declaration information management device 30 or the like on the network.

[0077] Also, the health state estimation model 105a is a learning model that is clustered into one or more of the user information among the learning information of a plurality of users and is learned based on the user information of the clustered learning information.

[0078] Since the health state changes according to the user's behavior characteristics, the health state estimation model 105a should be prepared according to the user's behavior characteristics.

[0079] Here, the user information is at least one of the user's behavior information and the user's attribute information. The user's attribute information is at least one of the user's age or age group, the user's gender, the user's family composition, the user's occupation, the user's mental state, or the user's medical history. Also, the user's behavior information may include the user's attribute information.

[0080] In addition, in the present disclosure, the health state estimation device 100 includes a data storage unit 101 that functions as a learning information storage unit for storing learning information including information and health state information of a plurality of users, and uses the learning information to input information and output health state information, and functions as a learning unit for learning the health state estimation model 105a by machine learning, and a health state estimation model generation unit 102.

[0081] According to this configuration, the health state estimation model 105a can be generated from the user information and the health state information.

[0082] In addition, in the present disclosure, the data storage unit 101 stores learning information further including the mental state information of a plurality of users, and the health state estimation model generation unit 102 generates (learns) the health state estimation model 105a by further adding the mental state information.

[0083] With this configuration, a health state estimation model 105a that takes into account the mental state can be generated. The health state, especially in the case of frailty, etc., is greatly affected by the mental state. Therefore, by generating a health state estimation model 105a that takes into account the mental state, an accurate estimation model can be constructed.

[0084] In addition, in the present disclosure, the health state estimation device 100 uses, as input, user information (which may include, for example, behavior information, information other than behavior, attribute information, etc.) among the learning information stored in the data storage unit 101, and outputs a mental state, and generates (learns) a mental state estimation model 103a with a mental state estimation model generation unit 103. For a specific user who does not store mental state information in the data storage unit 101, the mental state estimation model 103a is input with the information of the specific user, the mental state of the specific user is estimated, and a complementation unit that complements the learning information is further provided. In this case, the health state estimation model generation unit 102 functions as the complementation unit.

[0085] With this configuration, even for learning information lacking mental state information, it can be appropriately complemented.

[0086] In addition, in the present disclosure, in the health state estimation device 100, the health state estimation model generation unit 102 extracts learning information of users of a predetermined age among the learning information of a plurality of users, and generates a health state estimation model 105a based on the extracted learning information.

[0087] Since health states such as frailty occur based on aging, it is preferable to use learning information according to age.

[0088] As described above, these learning processes do not necessarily have to be performed by the health state estimation device 100, and the health state estimation device 100 may use a learning model generated by another learning model generation device.

[0089] The block diagrams used in the description of the above embodiments show blocks of functional units. These functional blocks (components) are realized by any combination of at least one of hardware and software. Also, the method of realizing each functional block is not particularly limited. That is, each functional block may be realized using one physically or logically combined device, or two or more physically or logically separated devices may be directly or indirectly (e.g., using wired, wireless, etc.) connected and realized using these multiple devices. The functional block may be realized by combining software with the above one device or the above multiple devices.

[0090] Functions include, but are not limited to, judgment, decision, determination, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, solution, selection, selection, establishment, comparison, assumption, expectation, regarded as, notification (broadcasting), notification (notifying), communication (communicating), forwarding, configuration (configuring), reconfiguration (reconfiguring), allocation (allocating, mapping), assignment (assigning), etc. For example, a functional block (component) that functions to transmit is called a transmitting unit or a transmitter. In any case, as described above, the realization method is not particularly limited.

[0091] For example, the health state estimation device 100 in an embodiment of the present disclosure may function as a computer that performs the processing of the health state estimation method of the present disclosure. FIG. 11 is a diagram showing an example of the hardware configuration of the health state estimation device 100 according to an embodiment of the present disclosure. The above-described health state estimation device 100 may physically be configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, and the like.

[0092] In the following description, the term "device" can be read as a circuit, a device, a unit, etc. The hardware configuration of the health state estimation device 100 may be configured to include one or more of each device shown in the figure, or may be configured without including some devices.

[0093] Each function in the health state estimation device 100 is realized by causing a processor 1001 to read a predetermined software (program) onto hardware such as the processor 1001, the memory 1002, etc., so that the processor 1001 performs calculations, controls communication by the communication device 1004, and controls at least one of reading and writing data in the memory 1002 and the storage 1003.

[0094] The processor 1001 controls the entire computer by operating an operating system, for example. The processor 1001 may be constituted by a central processing unit (CPU: Central Processing Unit) including an interface with peripheral devices, a control device, an arithmetic device, a register, etc. For example, the above-described health state estimation model generation unit 102, health state estimation unit 105, etc. may be realized by the processor 1001.

[0095] Also, the processor 1001 reads a program (program code), software module, data, etc. from at least one of the storage 1003 and the communication device 1004 into the memory 1002, and executes various processes according to these. As the program, a program that causes a computer to execute at least a part of the operations described in the above embodiments is used. For example, the health state estimation model generation unit 102 may be stored in the memory 1002 and realized by a control program operating in the processor 1001, and the same may be true for other functional blocks. Although it has been described that the above various processes are executed by one processor 1001, they may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. Note that the program may be transmitted from a network via a telecommunication line.

[0096] The memory 1002 is a computer-readable recording medium and may be constituted by at least one of, for example, ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), RAM (Random Access Memory), etc. The memory 1002 may be referred to as a register, cache, main memory (main storage device), etc. The memory 1002 can store a program (program code), software module, etc. executable for implementing the health state estimation method according to an embodiment of the present disclosure.

[0097] Storage 1003 is a computer-readable recording medium, which may be composed of, for example, at least one of an optical disc such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disc, a digital versatile disc, a Blu-ray (registered trademark) disc), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy (registered trademark) disk, a magnetic strip, etc. Storage 1003 may also be referred to as an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, a server, or other appropriate media including at least one of the memory 1002 and the storage 1003.

[0098] The communication device 1004 is hardware (a transmission / reception device) for performing communication between computers via at least one of a wired network and a wireless network, and is also referred to as, for example, a network device, a network controller, a network card, a communication module, etc. The communication device 1004 may be configured to include, for example, a high-frequency switch, a duplexer, a filter, a frequency synthesizer, etc. in order to implement at least one of frequency division duplex (FDD: Frequency Division Duplex) and time division duplex (TDD: Time Division Duplex). For example, the above-mentioned data acquisition unit 104, etc. may be realized by the communication device 1004. The data acquisition unit 104 may be physically or logically separated into a transmission unit and a reception unit.

[0099] The input device 1005 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) for receiving an external input. The output device 1006 is an output device (e.g., a display, a speaker, an LED lamp, etc.) for performing an output to the outside. Note that the input device 1005 and the output device 1006 may have an integrated configuration (e.g., a touch panel).

[0100] Also, each device such as the processor 1001 and the memory 1002 is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus or may be configured using different buses for each device.

[0101] Further, the health state estimation device 100 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA), and some or all of each functional block may be realized by the hardware. For example, the processor 1001 may be implemented using at least one of these hardware components.

[0102] The notification of information is not limited to the modes / embodiments described in the present disclosure, and may be performed using other methods. For example, the notification of information may be implemented by physical layer signaling (e.g., downlink control information (DCI), uplink control information (UCI)), upper layer signaling (e.g., radio resource control (RRC) signaling, medium access control (MAC) signaling, notification information (master information block (MIB), system information block (SIB))), other signals, or a combination thereof. Also, the RRC signaling may be referred to as an RRC message, and may be, for example, an RRC connection setup message, an RRC connection reconfiguration message, or the like.

[0103] The processing procedures, sequences, flowcharts, etc. of each aspect / embodiment described in this disclosure may be reordered as long as there is no contradiction. For example, regarding the methods described in this disclosure, the elements of various steps are presented using an exemplary order and are not limited to the specific order presented.

[0104] The input / output information, etc. may be stored in a specific location (e.g., memory) or may be managed using a management table. The input / output information, etc. may be overwritten, updated, or appended. The output information, etc. may be deleted. The input information, etc. may be transmitted to other devices.

[0105] The determination may be made based on a value represented by 1 bit (0 or 1), may be made based on a boolean value (Boolean: true or false), or may be made based on a numerical comparison (e.g., comparison with a predetermined value).

[0106] Each aspect / embodiment described in this disclosure may be used alone, in combination, or may be switched and used during execution. Also, the notification of predetermined information (e.g., the notification of "being X") is not limited to being explicitly performed and may be performed implicitly (e.g., without performing the notification of the predetermined information).

[0107] As described above in detail regarding this disclosure, it is obvious to those skilled in the art that this disclosure is not limited to the embodiments described in this disclosure. This disclosure can be implemented in modified and changed forms without departing from the spirit and scope of this disclosure as determined by the description of the claims. Therefore, the description of this disclosure is for the purpose of exemplary explanation and has no restrictive meaning for this disclosure.

[0108] Software should be broadly construed to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, execution threads, procedures, functions, etc., whether called software, firmware, middleware, microcode, hardware description language, or by any other name.

[0109] Also, software, instructions, information, etc. may be transmitted and received via a transmission medium. For example, if software is transmitted from a website, server, or other remote source using at least one of wired technologies (such as coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), etc.) and wireless technologies (such as infrared, microwave, etc.), at least one of these wired and wireless technologies is included within the definition of the transmission medium.

[0110] The information, signals, etc. described in this disclosure may be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc., which may be referred to throughout the above description, may be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0111] Also, the information, parameters, etc. described in this disclosure may be represented using absolute values, relative values from a predetermined value, or in terms of corresponding other information.

[0112] In this disclosure, terms such as "mobile station (MS)", "user terminal", "user equipment (UE)", "terminal", etc. may be used interchangeably.

[0113] A mobile station may also be referred to by those skilled in the art as a subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, or some other suitable term.

[0114] As used in this disclosure, the terms "determining" and "determination" may encompass a wide variety of operations. "Determining" and "determination" may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up (e.g., searching in a table, database, or other data structure), ascertaining, and considering something as having "determined" or "determined" something. Also, "determining" and "determination" may include considering something as having "determined" or "determined" something received (e.g., receiving information), transmitted (e.g., transmitting information), input, output, accessed (e.g., accessing data in a memory), etc. Further, "determining" and "determination" may include considering something as having "determined" or "determined" something resolved, selected, chosen, established, compared, etc. That is, "determining" and "determination" may include considering something as having "determined" or "determined" some operation. Also, "determining (determination)" may be read as "assuming", "expecting", "considering", etc.

[0115] The terms "connected" and "coupled," or any variations thereof, mean any direct or indirect connection or coupling between two or more elements, and can include the presence of one or more intermediate elements between two elements that are "connected" or "coupled" to each other. The coupling or connection between elements can be physical, logical, or a combination thereof. For example, "connected" may be read as "accessed." As used in this disclosure, two elements can be considered to be "connected" or "coupled" to each other using at least one of one or more wires, cables, and printed electrical connections, as well as, by way of some non-limiting and non-inclusive examples, electromagnetic energy having wavelengths in the radio frequency region, microwave region, and optical (both visible and invisible) region.

[0116] As used in this disclosure, the recitation "based on" does not mean "based solely on" unless otherwise specified. In other words, the recitation "based on" means both "based solely on" and "based at least in part on."

[0117] In this disclosure, when the terms "include," "including," and variations thereof are used, these terms are intended to be inclusive in the same manner as the term "comprising." Further, the term "or" as used in this disclosure is not intended to be exclusive.

[0118] In this disclosure, for example, when articles are added by translation, such as a, an, and the in English, the disclosure may include that the nouns following these articles are in the plural form.

[0119] In the present disclosure, the term "A and B are different" may mean that "A and B are different from each other". Note that the term may also mean that "A and B are each different from C". Terms such as "separate" and "coupled" may be interpreted in the same way as "different".

Description of Signs

[0120] 10... Terminal, 20... Terminal Log Collection Device, 30... User Report Information Management Device, 50... Attribute Information Acquisition Device, 60... Location Information Acquisition Device, 70... Terminal Operation Information Acquisition Device, 80... Application Usage Information Acquisition Device, 90... Healthcare Information Acquisition Device, 100... Health Status Estimation Device, 101... Data Storage Unit, 102... Health Status Estimation Model Generation Unit, 103... Mental State Estimation Model Generation Unit, 103a... Mental State Estimation Model, 104... Data Acquisition Unit, 104a... Health Status Estimation Model, 105... Health Status Estimation Unit, 105a... Health Status Estimation Model, 106... Contribution Data Derivation Unit, 107... Result Notification Unit.

Claims

Claim 1 An acquisition unit that acquires information of a single user acquired by a terminal held by the single user; A health state estimation model for estimating a health state according to physical and mental aging; An estimation unit that inputs the information into the health state estimation model and estimates the health state of the single user; Comprising; The information includes information related to sociality; The information related to sociality includes application usage information and going-out time obtained based on an operation log and sensor values for the terminal; The application usage information includes at least one of the name of the application, the type of the application, setting information in the application, setting change information of the application, the number of times the application is used, and the usage time of the application in the application installed on the terminal; A data collection and analysis device.

Images