Data acquisition and analysis device

Abstract

To provide a data gathering analysis device capable of estimating the health status of a user corresponding to user's metal and physical decline with age.SOLUTION: A health status estimation device 100 comprises: a data acquisition part 104 which acquires user information on one user (including at least one of attribute information, position information, terminal operation information, application use information, and health care information) that a terminal 10 that the one user has acquires; a health status estimation mode 105a for estimating the health status corresponding to the mental and physical decline with age; and a health status estimation part 105 which inputs the user information to the health status estimation model 105a to estimate the health status of the one user. Information associated with the sociability includes the application information obtained based upon an operation log on the terminal 10.SELECTED DRAWING: Figure 2

Description

Technical Field

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

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 and mainly indicates a state in which the motor function has declined due to a disorder of the locomotor apparatus. Therefore, it is impossible to estimate the decline in the mental or social aspects of the user due to aging. Further, in the invention described in Patent Document 2, frailty is determined from biological data such as vital values and amount of exercise 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 state 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 comprises: an acquisition unit that acquires information of a user acquired by a terminal held by a user; a health status estimation model for estimating the user's health status in accordance with physical and mental aging; and an estimation unit that inputs the information into the health status estimation model to estimate the user's health status, wherein the information includes information relating to sociability, and the information relating to sociability includes application usage information obtained based on operation logs and sensor values ​​for the terminal, and the application usage information includes at least one of the following for an application installed on the user terminal: the name of the application, the type of the application, setting information within the application, setting change information for the application, the number of times the application has been used, and the usage time of the application. [Effects of the Invention]

[0007] According to the present invention, it is possible to estimate the user's physical and mental health status in accordance with aging. [Brief explanation of the drawing]

[0008] [Figure 1] This figure shows the system configuration of the health status estimation system disclosed herein. [Figure 2] This diagram shows the functional configuration of the health status estimation device 100. [Figure 3] This figure shows specific examples of learning information. [Figure 4] This figure shows specific examples of user information and mental state information. [Figure 5] This is a flowchart showing the method for generating the health status estimation model 105a and the estimation method using the health status estimation model 105a. [Figure 6] This is a flowchart showing the process of generating the health status estimation model 105a in the health status estimation model generation unit 103. [Figure 7] This is a flowchart showing the process of supplementing mental state information in process S205. [Figure 8]This is a flowchart showing the health status estimation process in process S104. [Figure 9] This flowchart shows the process for notifying the data items that contributed to the estimation in the health status estimation process S104. [Figure 10] This flowchart shows the process of stratifying users by age, gender, family structure, mental state, and social activities in the generation process of the health status estimation model generation unit 103. [Figure 11] This figure shows an example of the hardware configuration of a health status estimation device 100 according to one embodiment of the present disclosure. [Modes for carrying out the invention]

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

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

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

[0012] The user-declared information management device 30 stores attribute information for each user. In addition to age, etc., it may also store chief complaint, present illness, past medical history, physical findings, laboratory findings, or medical history including mental state information. This information is obtained in advance through declarations from the user.

[0013] The attribute information acquisition device 50 is a device that acquires the user's attribute information 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. Note that it may also be information indicating other attributes of the user. Further, the attribute information may include medical history information including mental state information. For example, information on whether the user is in a depressive state or not.

[0014] The position information acquisition device 60 is a device that acquires position information regarding the user's position from the terminal log collection device 20. The position information includes at least one of the latitude and longitude where the user was located or the visited location, information indicating whether the user went out or not, the home stay time 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 movement of the user, the walking distance of the user, the walking time of the user, or the walking speed of the user. These position 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 terminal usage frequency, the number of power ON / OFF times, the history of changes in various function settings, the number of incoming and outgoing calls, the call time, the battery remaining amount, 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 app usage information acquisition device 80 is a device that acquires the usage information of applications (hereinafter abbreviated as apps) operated by users 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 app setting change information, the number of times the app is used, and the usage time of the app. As types of apps, there are fitness apps (such as pedometers) for promoting users' exercise, medical apps (such as blood pressure monitors, pulse meters, and capillary oxygen concentration meters) for managing users' 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 from each other. These app usage information are information indicating exercise function, cognitive function, lifestyle, or sociality, respectively.

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

[0018] In addition, although not shown in the figure, there may be a device for acquiring 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 for acquiring the user's behavior history information for weekdays, holidays, or each 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 for acquiring 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 obtained by these various acquisition devices and estimates the user's health status. In this disclosure, the user's health status includes not only physical health status but also mental health status (cognitive function), and represents a health status appropriate to aging. This health status appropriate to aging indicates whether or not the person is frail or pre-frail, and is a state in which physical and cognitive functions have declined, but can be prevented from becoming dependent on care through treatment or prevention.

[0020] Figure 2 shows the functional configuration of the health status estimation device 100. As shown in the figure, the health status estimation device 100 is composed of a data storage unit 101, a health status estimation model generation unit 102, a mental state estimation model generation unit 103, a data acquisition unit 104, a health status estimation unit 105, a contributing data derivation unit 106, and a result notification unit 107.

[0021] The data storage unit 101 is the part that stores training information for generating the health status estimation model 105a. The training information includes user information, mental state information, and health status information for each user. User information is the user's attribute information and behavioral information. Mental state information is, for example, information indicating a depressive state. Health status information indicates whether the user is frail or pre-frail. This training information is pre-prepared information.

[0022] Figure 3(a) shows a specific example of learning information. As shown in the figure, user information, mental state information, and health state information are stored for each user and each date and time. User information is based on the information acquired by each acquisition device, as described above. For the sake of explanation, detailed information is omitted in the figure. Mental state information (presence or absence of depression) and health state information (presence or absence of frailty or pre-frailty) are obtained based on the user's declaration. The date and time is the date and time when the user's information was acquired.

[0023] This training information is pre-prepared by the system operator. However, as shown in Figure 3(b), some user information within the training data may be missing. For example, in Figure 3(b), there is no description for the location information of user ID:ccc. In such cases, this information may be supplemented during the prediction model generation process based on information from other users.

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

[0025] The mental state estimation model generation unit 103 is responsible for generating a mental state estimation model 103a to supplement the user's mental state information. When the health state estimation model generation unit 102 generates a health state estimation model, it requires the user's mental state information from the training information, but this information may be missing (see Figure 3(b)). In that case, it generates a mental state estimation model 103a to supplement the user's mental state information. The health state estimation model generation unit 102 can obtain mental state information by inputting user information into the mental state estimation model 103a.

[0026] The data acquisition unit 104 is responsible for acquiring user information from various acquisition devices, such as the attribute information acquisition device 50. User information includes at least one of attribute information, location information, terminal operation information, application usage information, and healthcare information. Of this information, location information, terminal operation information, application usage information, and healthcare information are treated as user behavior information.

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

[0028] Figure 4 shows specific examples of user information and mental state information. This user information and mental state information are acquired by the data acquisition unit 104 (see Figure 4(a)). This user information and mental state information for a single user are input to the health status estimation model 105a, and the health status estimation model 105a outputs the health status information of that single user (whether or not they are frail or pre-frail).

[0029] The contributing data derivation unit 106 is responsible for deriving which user information data items or mental state information (data items) contributed to the estimation of the user's health status when the health status estimation model 105a is used to predict the health status. To derive these data items, the contributing data derivation unit 106 uses, for example, known techniques such as Shape and Permutation Importance. These data items are attribute information, location information, terminal operation information, application usage information, and further subdivided information (coordinate information, usage time information, etc.) from the user information.

[0030] The result notification unit 107 is responsible for notifying the user of the user's health status estimated by the health status estimation unit 105 and the data items derived by the contributing data derivation unit 106. The result notification unit 107 may transmit this information to the user's terminal 10, or to another terminal. If the result notification unit 107 is a display, it may also notify the user by displaying the information.

[0031] The result notification unit 107 may have a function to notify the user of their health status, the risks associated with their health status, and messages encouraging the user to improve their behavior (behavioral change). For example, the result notification unit 107 generates a message from the derived data items and health status that encourages the user to take actions that improve their health status, and notifies the user of this message. As a method for generating the message, data items that contribute to the health status are extracted from the data items using a known algorithm such as SHAPS, and a message is generated that encourages improvement regarding those data items. Health status includes not only physical health status but also mental health status (cognitive function), and indicates a health status appropriate for aging. This health status appropriate for aging indicates whether or not the person is frail or pre-frail, and is a state in which physical and cognitive functions have declined, but it is possible to prevent the person from becoming in need of long-term care through treatment or prevention. Health risk refers to, for example, the likelihood of developing a disease, the likelihood of a disease becoming more severe or developing another disease if one already has one, and the likelihood of developing health conditions that are not diseases but increase the likelihood of developing a disease, such as frailty or obesity. This risk can be calculated by creating a risk estimation model using machine learning based on user information, questionnaires obtained from users, health checkup results, medical claims data, etc.

[0032] The operation of the health status estimation device 100 configured in this way will now be explained. Figure 5 is a flowchart showing the method for generating the health status estimation model 105a and the estimation method using the health status estimation model 105a in the health status estimation device 100. The health status estimation model generation unit 102 acquires all or part of the user information, mental state information, and health status information from the data storage unit 101 as learning information (S101). The health status estimation model generation unit 102 detects abnormal values ​​from the user information, mental state information, and health status information, removes them, and imputes missing values ​​(S102). An abnormal value is a numerical value that is clearly abnormal, and is an extremely large or small number. For example, the number of times the app is used may be an unusually large number. In such cases, the average value of other learning information is taken into consideration and the value is imputed, but it is not limited to this and may be a predetermined value.

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

[0034] The health status estimation unit 105 estimates the user's health status using the generated health status estimation model 105a (S104). The result notification unit 107 notifies the user of the estimated health status (S105). In addition, the contributing data derivation unit 106 may derive data items that contributed to the estimation result when estimating the user's health status, and the result notification unit 107 may also notify the user of these data items. In the diagram, processes S103 and S104 are shown to be executed in a continuous sequence, but this is not the only way to do so. Process S103 may be terminated, and process S104 may be started when the estimation process begins. Furthermore, processes S103 and S104 and S105 may be performed on separate devices.

[0035] Next, we will explain the details of the process S103, which involves generating the health status estimation model 105a. Figure 6 is a flowchart showing the detailed operation of this process.

[0036] The health status estimation model generation unit 102 processes some of the data items (age in attribute information, coordinate information in location information, etc.) of the learning information acquired by the data acquisition unit 104 as needed (S201). For example, the health status estimation model generation unit 102 may calculate whether the user went out or not from the latitude and longitude information included in the location information, the amount of time the user stayed at home, the distance the user traveled to their destination, the user's travel time, the user's travel speed, the user's means of transportation, the user's walking distance, the user's walking time, or the user's walking speed, and may also normalize this data. Similarly, new data items may be calculated or normalized from terminal operation information, application usage information, healthcare information, etc.

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

[0038] The health status estimation model generation unit 102 then obtains further learning information for an arbitrary period from this learning information (S203). The health status estimation model generation unit 102 then clusters the users of the learning information into one or more groups using the user information (S204). The user information includes the user's behavioral information as well as at least one of the following: the user's age or age group, the user's gender, or the user's family structure.

[0039] In addition to the above, clustering may also be performed based on mental state or social activities. In this disclosure, social activities are defined based on a portion of user information, including location information (whether or not the user goes out, time spent at home, etc.), device operation information (device usage time, number of times the device is used, etc.), and application usage information. For example, it is assumed that users with similar location information and similar device operation information are engaging in the same social activities, and clustering of users and their learning information is performed based on this information. In addition, social activities may also be defined based on behavioral history, conversational audio, etc.

[0040] For clustering, you may use methods such as Support Vector Machine or K-means clustering, or you may use stratification using data such as user age, gender, and family structure.

[0041] The health status estimation model generation unit 102 performs a supplementation process for user learning information that does not include mental state information (S205). This supplementation process 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 correlated with health status (frailty or pre-frailty) from the supplemented training information using an arbitrary method (a known machine learning method or feature selection tool) (S207). Mental state information is selected as essential. Known machine learning methods or feature selection tools include Lasso, ElasticNet, and Boruta (XGBoost, LightGBM, RandomForest).

[0043] The health status estimation model generation unit 102 applies the selected data items to any machine learning method to generate a health status estimation model 105a for period T1 (S208). For example, multiple regression, Lasso, ElasticNet, XGBoost, LightGBM, RandomForest, SVM, and Kmeans are known as machine learning methods. The selected data items shall be behavioral information that indicates user behavior. For example, in Figure 3, the user information shall include at least one of location information, terminal operation information, application usage information, and healthcare information.

[0044] Here, we will explain the processing of supplementing mental state information in process S205. Figure 7 is a flowchart of the detailed processing. The health state estimation model generation unit 102 starts loop processing for each cluster that was clustered in process S205 (S205a). For example, the user's behavioral characteristics change depending on the behavioral information (location information, terminal operation information, etc.) among the user information. As this changes the mental state, it is good to supplement mental state information for each user (especially for each user's behavioral information).

[0045] The health state estimation model generation unit 102 generates a mental state estimation model 103a by applying the user's learning information, which includes mental state information, to a known machine learning method (S205b). The learning process is performed using user information as input (explanatory variables) and mental state information as output (dependent variable). Note that some of the user information (user behavior information) may also be used as input.

[0046] Then, the health state estimation model generation unit 102 applies the mental state estimation model 103a to the learning information of a user for whom mental state information is missing, and estimates the mental state information of that user (S205c). For example, the learning information of that user is missing mental state information (see Figure 3(b)), and the unit estimates whether or not that mental state information indicates a depressive state.

[0047] Processes S206b and S206c are performed cluster by cluster based on user information (S205d). This process generates cluster-specific mental state estimation models 103a, and estimates the user's mental state for each cluster.

[0048] Next, the health status estimation process in process S104 will be explained. Figure 8 is a flowchart showing the health status estimation process. The health status estimation unit 105 processes the data items of the user information and mental state information of the target user acquired by the data acquisition unit 104 as necessary (S301). For example, the health status estimation unit 105 may calculate whether the user went out or not from the latitude and longitude information included in the location information, the amount of time the user stayed at home, the distance the user traveled to their destination, the user's travel time, the user's travel speed, the user's means of transportation, the user's walking distance, the user's walking time, or the user's walking speed, and may also normalize this data. Similarly, new data items may be calculated or normalized in the case of terminal operation information, application usage information, healthcare information, etc.

[0049] The health status estimation unit 105 then extracts learning information (user information and mental state information) for the period necessary for data completion (S302).

[0050] The health status estimation unit 105 supplements the data items of the input information that are insufficient for applying the health status estimation model 105a based on the extracted training information (S303). For example, it supplements the data with the average value of data of the same sex and age (a years before and after) and similar BMI (b years before and after). Sex, age, and BMI are calculated based on attribute information (or healthcare information) in the training information. If mental state information is missing, the mental state estimation model 103a generated in Figure 7 may be used.

[0051] The health status estimation unit 105 applies the supplemented input information to the health status estimation model 104a and estimates the health status (S304).

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

[0053] Next, we will explain the process for notifying the data items that contributed to the estimation. Figure 9 is a flowchart of this process. As shown in the figure, processes S301 to S304 are the same as the process in Figure 8. The contributing data derivation unit 106 obtains the data items that contributed to the estimation result using the health status estimation model 104a (S304a).

[0054] The result notification unit 107 then notifies the user of the estimated health status and also notifies the user of information regarding the data items that contributed to the estimation (S305a). The information regarding the data items includes results that can be improved from the health status. For example, if the contributing data items are location information items such as whether or not the user goes out, the amount of time spent at home, or the distance traveled, the information regarding the data items would be a message encouraging improvement. For example, if the location information of the user information indicates that the user does not go out often or does not travel much, an example of such a message might be, "Take a walk once a day."

[0055] Next, a modified version of the generation process of the health status estimation model generation unit 102 will be described. Figure 10 is a flowchart of that process. Processes S201 to S203 are the same as in Figure 6.

[0056] The health status estimation model generation unit 102 starts a process that loops through items such as age, gender, family structure, mental state, or social activities. That is, the health status estimation model generation unit 102 clusters the learning information based on age, gender, family structure, mental state (presence or absence of depression), or social activities, and obtains learning information for each cluster (S211).

[0057] In this disclosure, social activities are defined based on user information, specifically a portion of location information (such as whether the user is out or not, and the amount of time spent at home), a portion of device operation information (such as device usage time and the number of times the device is used), and application usage information. For example, users with similar location information and similar device operation information are presumed to be engaging in the same social activities, and clustering of users and their learning information is performed based on this information. In addition, social activities may also be defined based on behavioral history, conversation audio, etc.

[0058] The health status estimation model generation unit 102 extracts data items that are highly related to health status using any method, such as machine learning or a feature selection tool (S212). These data items will include data items related to specific mental states.

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

[0060] The health status estimation model generation unit 102 repeats these processes to generate health status estimation models for each cluster (S214).

[0061] Next, the effects of the health status estimation device 100 of the present disclosure will be described. The health status estimation device 100 of the present disclosure includes a data acquisition unit 104 that acquires information of a user (for example, including at least one of behavioral information such as location information, terminal operation information, application usage information, healthcare information, and other information other than behavioral information) acquired by a terminal 10 held by a user, a health status estimation model 105a for estimating the health status of a user in accordance with aging in mind and body, and a health status estimation unit 105 that inputs user information into the health status estimation model 105a and estimates the health status of a user.

[0062] This age-related health status in mind and body includes at least one of frailty or pre-frailty. Furthermore, health status may be estimated including the risk of such health status, and in this disclosure, the estimated health status may include such risk.

[0063] This configuration allows for the estimation of age-appropriate physical and mental health status based on user information. In this disclosure, in particular, it estimates whether the user is frail or pre-frail.

[0064] Furthermore, in this disclosure, the health status estimation unit 105 inputs mental state information related to the user's mental state, in addition to the user's information, into the health status estimation model 105a to estimate the health status.

[0065] Health conditions such as frailty are greatly influenced by mental state, such as depression. In this disclosure, by considering the user's mental state, it is possible to estimate their health status accurately. In this disclosure, depression is given as an example of a mental state, but other conditions may be included, such as adjustment disorders including simple depression.

[0066] In this disclosure, user information includes at least one of the following: motor function information, cognitive function information, lifestyle information, sociability information, and attribute information. While the above description distinguishes between behavioral information and attribute information for convenience, behavioral information may also include attribute information. In this disclosure, when simply referred to as "information," it includes both, but may also include other types of information.

[0067] In this disclosure, as an example, information regarding motor function includes at least one of the following: number of steps, stride length, number of times stairs are climbed and descended, speed when climbing and descending stairs, distance traveled, energy expenditure, energy expenditure at rest, exercise time, walking with both legs supported, and gait asymmetry.

[0068] Step count, stride length, number of times stairs are ascended and descended, speed when ascending and descending stairs, and distance traveled are obtained from the sensor values ​​(motion sensor, etc.) of terminal 10. Energy consumption may be calculated based on the above step count, etc., using a predetermined formula, or it may be calculated using an energy calculation application. Resting energy consumption and exercise time are determined from the sensor values ​​(motion sensor, etc.) of terminal 10 to distinguish between resting and exercise time, and resting energy consumption is determined by a predetermined formula or application.

[0069] Walking double-leg support time is the time the user is standing on both feet, based on the gait cycle, and is determined by the motion sensors of terminal 10. Walking asymmetry indicates that asymmetrical steps have been detected within the walking period. This is also determined by the motion sensors of terminal 10.

[0070] Furthermore, information regarding cognitive function includes, for example, at least one of the following: the time required to unlock the device, the time required to use an app after unlocking the device, the number of times the device has been opened, the number of times the device has been closed, the number of calls made, the duration of calls, the number of incoming calls, and the number of outgoing calls. The time required to unlock the device refers to the time from when the user picks up the device until it is unlocked. Other parameters are also measured using the device's motion sensor and other sensors.

[0071] Furthermore, information regarding lifestyle habits may include, for example, at least one of the following: wake-up time, bedtime, sleep duration, number or percentage of app usage, number of camera shots taken, and device settings change history.

[0072] These times are measured using the sensor values ​​of terminal 10 (motion sensor, etc.) and other sensors to determine the start and end times, and their usage is also measured.

[0073] Furthermore, information regarding sociability includes, for example, at least one of the following: time spent at home, number of location data points obtained, time spent outside, and number of places visited.

[0074] This information is based on location information acquired by device 10. Location information is obtained via GPS, but is not limited to this.

[0075] Furthermore, attribute information may include, as an example, at least one of the following: the user's age or age group or date of birth, the user's gender, the user's family structure, the user's occupation, the user's place of residence, the population density or level of population density 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] This information is pre-configured by the user. This information is obtained from a user-declared information management device 30 or similar on the network.

[0077] Furthermore, the health status estimation model 105a is a learning model that is trained based on the user information of the clustered learning information, which is then clustered into one or more user information groups from the learning information of multiple users.

[0078] Since a user's health status varies depending on their behavioral characteristics, the health status estimation model 105a should be tailored to the specific behavioral characteristics of that user.

[0079] Here, user information refers to at least one of the following: user behavior information or user attribute information. User attribute information refers to at least one of the following: user age or age group, user gender, user family structure, user occupation, user mental state, or user medical history. User behavior information may also include user attribute information.

[0080] Furthermore, in this disclosure, the health status 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 status information of multiple users, and a health status estimation model generation unit 102 that functions as a learning unit for learning a health status estimation model 105a by machine learning, using the learning information as input and health status information as output.

[0081] This configuration allows for the generation of a health status estimation model 105a from user information and health status information.

[0082] Furthermore, in this disclosure, the data storage unit 101 stores learning information that further includes mental state information of multiple users, and the health state estimation model generation unit 102 generates (learns) a health state estimation model 105a by adding the mental state information.

[0083] This configuration allows for the generation of a health status estimation model 105a that takes mental state into account. Health status, particularly frailty, is greatly influenced by mental state. Therefore, by generating a health status estimation model 105a that takes mental state into account, a highly accurate estimation model can be constructed.

[0084] Furthermore, in this disclosure, the health state estimation device 100 further comprises a mental state estimation model generation unit 103 that takes user information (which may include behavioral information, non-behavioral information, attribute information, etc.) from the learning information stored in the data storage unit 101 as input and mental state as output to generate (learn) a mental state estimation model 103a, and a supplementation unit that, for a specific user for whom mental state information is not stored in the data storage unit 101, inputs the specific user's information into the mental state estimation model 103a to estimate the mental state of the specific user and supplements the learning information. In this case, the health state estimation model generation unit 102 functions as the supplementation unit.

[0085] This configuration allows for the appropriate supplementation of learning information that lacks mental state information.

[0086] Furthermore, in the health status estimation device 100, the health status estimation model generation unit 102 extracts learning information of users of a predetermined age group from among the learning information of multiple users, and generates a health status estimation model 105a based on the extracted learning information.

[0087] Since health conditions such as frailty are age-related, it is advisable to use learning materials appropriate for one's age.

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

[0089] The block diagram used in the description of the above embodiment shows functional units. These functional blocks (components) are realized by any combination of at least one of hardware and software. Furthermore, the method of realizing each functional block is not particularly limited. That is, each functional block may be realized using one device that is physically or logically coupled, or it may be realized using two or more physically or logically separated devices that are directly or indirectly connected (for example, using wired or wireless connections). A functional block may also be realized by combining the above one device or the above multiple devices with software.

[0090] Functions include, but are not limited to, judgment, decision, judgment, calculation, calculation, processing, derivation, investigation, exploration, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, assumption, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating (mapping), and assigning. For example, a functional block (configuration part) that enables transmission is called a transmitting unit or transmitter. As mentioned above, the method of implementation is not particularly limited.

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

[0092] In the following explanation, the term "device" can be replaced with "circuit," "device," "unit," etc. The hardware configuration of the health status estimation device 100 may include one or more of the devices shown in the figure, or it may be configured to omit some of the devices.

[0093] Each function in the health status estimation device 100 is realized by loading predetermined software (programs) onto hardware such as the processor 1001 and memory 1002, which allows the processor 1001 to perform calculations, control communication by the communication device 1004, and control at least one of the reading and writing of data in the memory 1002 and storage 1003.

[0094] The processor 1001 controls the entire computer, for example, by running the operating system. The processor 1001 may be composed of a central processing unit (CPU) that includes interfaces with peripheral devices, control units, arithmetic units, registers, etc. For example, the health status estimation model generation unit 102 and the health status estimation unit 105 described above may be implemented by the processor 1001.

[0095] Furthermore, the processor 1001 reads programs (program code), software modules, data, etc., from at least one of the storage 1003 and the communication device 1004 into the memory 1002 and executes various processes accordingly. The program used is one that causes the computer to execute at least a part of the operations described in the above embodiment. For example, the health state estimation model generation unit 102 may be implemented by a control program stored in the memory 1002 and running on the processor 1001, and other functional blocks may be implemented similarly. The above-described processes have been explained as being executed by one processor 1001, but they may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The program may also be transmitted from a network via a telecommunications line.

[0096] Memory 1002 is a computer-readable recording medium and may consist of at least one of the following: ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), RAM (Random Access Memory), etc. Memory 1002 may also be called a register, cache, main memory, etc. Memory 1002 can store executable programs (program code), software modules, etc., for carrying out the health state estimation method according to one embodiment of the present disclosure.

[0097] Storage 1003 is a computer-readable recording medium and may consist of at least one of the following: 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 multipurpose disc, a Blu-ray® disc), a smart card, flash memory (e.g., a card, a stick, a key drive), a floppy® disk, a magnetic strip, etc. Storage 1003 may also be called an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, server, or other suitable medium including at least one of memory 1002 and storage 1003.

[0098] The communication device 1004 is hardware (transmitting / receiving device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as a network device, network controller, network card, communication module, etc. The communication device 1004 may be configured to include high-frequency switches, duplexers, filters, frequency synthesizers, etc., in order to implement at least one of frequency division duplex (FDD) and time division duplex (TDD). For example, the data acquisition unit 104 described above may be implemented by the communication device 1004. The data acquisition unit 104 may be implemented with physically or logically separated transmitting and receiving units.

[0099] The input device 1005 is an input device that accepts input from an external source (e.g., a keyboard, mouse, microphone, switch, button, sensor, etc.). The output device 1006 is an output device that outputs to an external source (e.g., a display, speaker, LED lamp, etc.). The input device 1005 and the output device 1006 may be configured as an integrated unit (e.g., a touch panel).

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

[0101] Furthermore, the health status estimation device 100 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), or an FPGA (Field Programmable Gate Array), and some or all of each functional block may be realized by such hardware. For example, the processor 1001 may be implemented using at least one of these hardware components.

[0102] Information notification is not limited to the embodiments described herein and may be carried out by other means. For example, information notification may be carried out by physical layer signaling (e.g., DCI (Downlink Control Information), UCI (Uplink Control Information)), upper layer signaling (e.g., RRC (Radio Resource Control) signaling, MAC (Medium Access Control) signaling, broadcast information (MIB (Master Information Block), SIB (System Information Block))), other signals, or combinations thereof. RRC signaling may also be called RRC messages, and may be, for example, RRC Connection Setup messages, RRC Connection Reconfiguration messages, etc.

[0103] The processing procedures, sequences, flowcharts, etc., of each aspect / embodiment described herein may be reordered, provided they are consistent with each other. For example, the methods described herein present various step elements in an exemplary order and are not limited to that specific order.

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

[0105] The determination may be made by a value represented by 1 bit (0 or 1), by a boolean value (true or false), or by a numerical comparison (for example, a comparison with a predetermined value).

[0106] Each aspect / embodiment described herein may be used individually, in combination, or switched between as needed during implementation. Furthermore, notification of specific information (e.g., notification that "X is") is not limited to explicit notification, but may also be implicit (e.g., by not providing such notification).

[0107] Although the present disclosure has been described in detail above, it will be clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the intent and scope of the present disclosure as defined by the claims. Therefore, the descriptions in the present disclosure are illustrative and not intended to be restrictive in any way.

[0108] Software should be broadly interpreted 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, and so on, whether they are called software, firmware, middleware, microcode, hardware description languages, or by any other name.

[0109] Furthermore, 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 technology (such as coaxial cable, fiber optic cable, twisted pair, or digital subscriber line (DSL)) and wireless technology (such as infrared or microwave), then at least one of these wired and wireless technologies is included in the definition of a transmission medium.

[0110] The information, signals, etc. described in this disclosure may be represented using any of the various different techniques. For example, the data, instructions, commands, information, signals, bits, symbols, chips, etc. that 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] Furthermore, the information, parameters, etc., described in this disclosure may be expressed using absolute values, relative values ​​from a predetermined value, or corresponding other information.

[0112] In this disclosure, terms such as "Mobile Station (MS)," "user terminal," "User Equipment (UE)," and "terminal" 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 several other appropriate terms.

[0114] As used in this disclosure, the terms “determining” and “determining” may encompass a wide variety of actions. “Determining” may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, inquiry (e.g., searching in a table, database, or other data structure), and ascertaining. “Determining” may also include, for example, receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, and accessing (e.g., accessing data in memory). Furthermore, "judgment" and "decision" can include considering something as having been "judged" or "decided" after resolving, selecting, choosing, establishing, comparing, etc. In other words, "judgment" and "decision" can include considering something as having been "judged" or "decided" after some action. Also, "judgment (decision)" can be reinterpreted as "assuming," "expecting," or "considering."

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

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

[0117] Where the terms “include,” “including,” and variations thereof are used in this disclosure, these terms are intended to be inclusive, as is the term “comprising.” Furthermore, the term “or” as used in this disclosure is not intended to mean exclusive OR.

[0118] In this disclosure, if articles are added through translation, such as a, an, and the in English, this disclosure may include the fact that the noun following these articles is plural.

[0119] In this disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "combine" may be interpreted similarly to "different." [Explanation of Symbols]

[0120] 10...Terminal, 20...Terminal log collection device, 30...User-reported information management device, 50...Attribute information acquisition device, 60...Location information acquisition device, 70...Terminal operation information acquisition device, 80...App 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...Contributing data derivation unit, 107...Result notification unit.

Claims

1. An acquisition unit that acquires information about a user obtained by a terminal held by that user, A health status estimation model for estimating the health status in accordance with physical and mental aging, An estimation unit that inputs the information into the health status estimation model to estimate the health status of one user, When estimating a health status using the aforementioned health status estimation model, a contributing data derivation unit derives data items that contributed to the estimation of the health status of one user, Equipped with, The aforementioned information includes application usage information obtained based on operation logs for the terminal, The aforementioned application usage information includes at least one of the following for an application installed on the terminal: the name of the application, the type of the application, the settings information within the application, the information on changes to the application's settings, the number of times the application has been used, and the duration of use of the application. Data collection and analysis device.

2. The aforementioned data items include at least one of the following: attribute information, location information, device operation information, application usage information, and healthcare information in user information. The data acquisition and analysis apparatus according to claim 1.

3. The aforementioned data items include mental state information, The data acquisition and analysis apparatus according to claim 1 or 2.

4. The information regarding the estimated health status includes at least one of the following: the health status estimated by the health status estimation model, the health status risk, and the content of behavioral changes that may contribute to improving the health status. A data acquisition and analysis device according to any one of claims 1 to 3.

5. In a data collection and analysis method for terminals that use a health status estimation model to estimate health status according to physical and mental aging, An acquisition step of acquiring information of a user obtained by a device held by that user, An estimation step of inputting the information into the health status estimation model to estimate the health status of the user, A contribution data step is used to derive the data items that contributed to the estimation of the health status of a particular user when estimating the health status using the aforementioned health status estimation model. Equipped with, The aforementioned information includes application usage information obtained based on operation logs for the terminal, The aforementioned application usage information includes at least one of the following for an application installed on the terminal: the name of the application, the type of the application, the settings information within the application, the information on changes to the application's settings, the number of times the application has been used, and the duration of use of the application. Data collection and analysis methods.

Images