Health support system and health support method

Abstract

To support promotion of a user's health by outputting flexible and proper evaluation information related to the health, on the basis of biological information of the user.SOLUTION: At least any one or more elements of soundness out of lifestyle, exercise, sleep and stress are determined based on biological information of a user. Then, a generation instruction containing at least any one or more pieces of biological information out of lifestyle, exercise, sleep and stress, and containing the soundness corresponding thereto, is used as input of a generative model, and evaluation information obtained from the generative model is outputted.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a health support system and a health support method. [Background technology]

[0002] Wearable devices aim to collect biometric information such as vital signs, exercise, and sleep, monitor the health status of individual users in real time, and provide appropriate health guidance. Specifically, wearable devices collect vital data such as heart rate, number of steps, and sleep patterns, and display the results through a health management application. However, it has been difficult for users to determine how to improve their lifestyle habits based on the results.

[0003] Patent Document 1 discloses a technology that can support the treatment of a user even when the user has a complex condition with multiple diseases. It also discloses that a patient's improvement goal, obtained by inputting the patient's personal data into a trained model capable of outputting improvement goals for improving a complex disease state, is output as an improvement goal to be achieved by the patient. It also discloses that lifestyle habits include at least one of the user's stress, the user's sleep time, the user's exercise amount, the user's diet, the user's smoking amount, and the user's alcohol consumption, and that improvement goals for the user's lifestyle habits can be output. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] International Publication No. 2023 / 127461 Summary of the Invention [Problem to be solved by the invention]

[0005] Patent Document 1 discloses that advice regarding behavioral goals is output according to output conditions, and that this advice is, for example, praising the patient when the patient is actively taking action toward achieving the improvement goal. Since such advice is mechanically output according to the output conditions, flexible and accurate advice that corresponds to the user's condition is desired.

[0006] An object of the present invention is to provide a technology for supporting a user's health promotion by outputting flexible and appropriate evaluation information related to the user's health based on the user's biometric information. [Means for solving the problem]

[0007] [1] Based on the user's biometric information, determine the health level of at least one of lifestyle habits, exercise, sleep, and stress; A health support system that inputs generation instructions including at least one of biological information of lifestyle habits, exercise, sleep, and stress, and the corresponding health level, into a generation model and outputs evaluation information obtained from the generation model. [2] The health support system described in [1], wherein the biometric information is measured by a biometric device worn by the user and acquired via communication. [3] The health support system described in [1] or [2], wherein the evaluation information includes suggestions, advice, or comments for the mental health state or its improvement. [4] The health support system described in [3], wherein the generative model is additionally trained using training data related to mental health support. [5] A health support system described in any of [1] to [4], wherein the generation instructions include instructions to evaluate the user's current biometric information or health level relative to the user's past biometric information or health level. [6] The health support system described in [5], wherein the generation instructions include instructions to evaluate the user's current biometric information or health level against the average value of the user's biometric information or health level over a specified period of time. [7] The biometric information is lifestyle data including wake-up time and / or bedtime; Exercise data, including exercise duration; Sleep data, including sleep duration, stress data including a stress value; The health support system according to any one of [1] to [6], wherein the health level is determined based on target value ranges set for each of lifestyle habits, exercise, sleep, and stress. [8] A point processing unit issues points to the user according to the issuing conditions, The health support system according to any one of [1] to [7], wherein the issuance conditions are set according to the stage of the health level and attributes of the user.

[0008] According to the invention of [1], by inputting a user's biometric information and the corresponding health level into a generative model, flexible and appropriate evaluation information generated according to the input can be provided to the user. In particular, by inputting the health level, the generative model can determine the state of the biometric information from a health perspective based on the health level and generate appropriate evaluation information.

[0009] The invention according to [2] makes it possible to accumulate biometric information of users and improve the quality of feedback based on the accumulated information.

[0010] The inventions according to [3] and [4] make it possible to generate specialized evaluation information, particularly from the perspective of mental health care.

[0011] The inventions in [5] and [6] make it possible to provide an appropriate evaluation by comparing the user's past state with their current state.

[0012] The invention according to [7] makes it possible to appropriately set target values ​​for data that is particularly important in health support, thereby improving the quality of the generated evaluation information.

[0013] [8] The invention of the present invention can increase the motivation of users to improve their health by issuing points according to the health level. [Effects of the Invention]

[0014] According to the present invention, a technique for supporting a user's health promotion by outputting flexible and appropriate evaluation information related to health can be provided. [Brief explanation of the drawings]

[0015] [Figure 1] FIG. 1 is a block diagram of a system according to an embodiment of the present invention. [Figure 2] FIG. 2 is a diagram illustrating a hardware configuration of the present embodiment. [Figure 3] FIG. [Figure 4] 3 is a flowchart of the present embodiment. [Figure 5] 3 shows an example of a data configuration according to the present embodiment. [Figure 6] 10 shows an example of an evaluation screen display according to the present embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0016] Hereinafter, a health support system and a health support method according to an embodiment of the present invention will be described with reference to the drawings. Note that the embodiment shown below is an example of the present invention, and the present invention is not limited to the embodiment below, and various configurations can be adopted.

[0017] In this embodiment, the configuration, operation, etc. of a health support system and a health support device are described, but similarly configured health support methods, computer programs, and program recording media on which the programs are recorded also achieve similar effects. For example, by using a program recording media, the programs can be installed on a computer. The series of processes according to this embodiment described below are provided as a computer-executable program, and can be provided via a non-transitory computer-readable recording medium such as a CD-ROM or a flexible disk, or even via a communication line.

[0018] The health support system is composed of multiple computer devices. A first computer device has an arithmetic device such as a CPU (Central Processing Unit) and a storage device. The computer device can function as a health support device by executing a first program stored in the storage device using the arithmetic device. A second computer device has an arithmetic device such as a CPU and a storage device. The computer device can function as a user terminal by executing a second program stored in the storage device using the arithmetic device. The health support method is realized by processing of the computer devices including the health support device and the user terminal.

[0019] In this description, health support refers to providing an evaluation of a user's lifestyle, exercise, sleep, and stress status, thereby aiming to maintain or improve those statuses. Lifestyle, exercise, sleep, and stress are closely related to the state of physical or mental health, and it is desirable to notify the user as soon as possible when any disruption occurs in these. In this embodiment, an example particularly suitable for supporting mental health will be described.

[0020] FIG. 1 shows a block diagram of a health support system 1. The health support system 1 comprises a health support device 2, a user terminal 3, a biometric measurement device 4, a generation device 5, and a memory DB. The health support device 2, the user terminal 3, the generation device 5, and the memory DB are each connected to a communication network NW and configured to be able to communicate with each other. The memory DB is configured as a database installed inside or outside the health support device 2, and is configured to be able to communicate data with at least the health support device 2. Each user has a user terminal 3 and a biometric measurement device 4, and there may be multiple of these.

[0021] The health support device 2 has, as functional components, an acquisition unit 21 that acquires various data, a judgment unit 22 that performs judgment processing based on the acquired data, an output unit 23 that performs processing to generate output using the judgment results, and a point processing unit 24 that performs processing related to the issuance and consumption of points.

[0022] The biometric device 4 measures the biometric information of the user. The biometric device 4 may be a wearable device attached to a part of the user's body. Examples of wearable devices include, but are not limited to, smart watches, fitness trackers, and smart rings. The biometric device 4 has a wireless communication function and transmits the measured biometric information of the user to the user terminal 3 at any time or at predetermined intervals.

[0023] The user terminal 3 acquires biometric information from the biometric measurement device 4. The user terminal 3 transmits the acquired biometric information to the health support device 2. The user terminal 3 may also perform a determination process based on the biometric information and transmit the determination result to the health support device 2. The determination unit 22 may be configured to be provided in the user terminal 3 instead of the health support device 2.

[0024] The generation device 5 executes a process of generating a response content to the data included in the generation instruction. The generation device 5 receives the generation instruction from the health support device 2, generates the response content, and transmits the response content to the health support device 2 that is the sender. The generation device 5 has a generation model 50, and by inputting the data included in the generation instruction into the generation model 50, the response content can be obtained as an output.

[0025] In this embodiment, the generative model 50 employs a large-scale language model (LLM). The LLM is a type of natural language processing model that is machine-learned using large-scale natural language data. For example, the LLM outputs a text response to a text input related to a question or instruction. Note that the LLM is not limited to text input; it can also handle input of data such as images, videos, and audio, and can also handle output of data such as images, videos, and audio by linking with other engines or models. For example, the LLM can generate a response by voice output in response to a generation instruction given by voice input. In this embodiment, the generative model 50 is not limited to the LLM, and may employ other models or algorithms that generate a response to an input.

[0026] In this embodiment, an example will be described in which the generative model 50 is stored in the generating device 5, but a configuration in which the health support device 2 is equipped with the generative model 50 may also be employed.

[0027] The memory unit DB stores various data for each user. User information is assigned user identification information such as an ID, allowing individuals to be identified. The user information includes biometric information or is linked to the ID or other information of the biometric information, and is configured to be able to reference the biometric information. The biometric information is information related to health, including at least one of lifestyle habits, exercise, and sleep, and is recorded including the measurement time when the data was measured. The measurement time includes the date and time.

[0028] FIG. 2(a) shows a hardware configuration diagram of the health support device 2. The health support device 2 includes a control device 201, a storage device 202, and a communication device 203 as its hardware configuration, with each component device being connected via a bus interface. In this embodiment, the health support device 2 can use a computer device such as a server device or a personal computer. The health support device 2 is not limited to the configuration shown in FIG. 2, and may be configured with multiple computer devices as long as they can realize the above-mentioned functional components (21-24) as a whole.

[0029] The control device 201 is configured with one or more processors such as a CPU, and controls the overall processing of the health support device 2 by executing a health support program, an OS (Operating System), and other applications. The storage device 202 is a hard disk drive (HDD), solid state drive (SSD), flash memory, RAM (Random Access Memory), etc., and stores the health support program and various data. The communication device 203 is a communication interface for wired communication, wireless communication, etc., and controls data communication with external devices. The communication device 203 realizes data communication with external devices by controlling communication with the communication network NW.

[0030] 2(b) shows a hardware configuration diagram of the user terminal 3. The user terminal 3 includes, as its hardware configuration, a control device 301, a storage device 302, a communication device 303, an input device 304, and an output device 305. The user terminal 3 may also include a GPS communication device. In this embodiment, the user terminal 3 may be a smartphone, a personal computer, a tablet terminal, or the like.

[0031] The control device 301 is composed of one or more processors such as a CPU, and controls the overall processing of the user terminal 3 by executing terminal programs, an OS, other applications, etc. The storage device 302 is an HDD, SSD, flash memory, RAM, etc., and stores a browser application and various data. The communication device 303 controls communication with the communication network NW and realizes data communication with at least the health support device 2. The input device 304 is an input interface that accepts input operations by the user, and is composed of a microphone, touch panel, mouse, keyboard, etc. The output device 305 is composed of a display that displays and outputs, etc. The GPS communication device can acquire the position coordinates of the user terminal 3 via GPS communication.

[0032] FIG. 3 shows a processing sequence diagram of the health support system 1.

[0033] The biometric device 4 measures biometric information of the user and transmits the biometric information to the user terminal 3 (S101). The biometric information is measured by the biometric device 4 worn by the user.

[0034] The user terminal 3 receives the biometric information, assigns user identification information to the biometric information, and transmits the biometric information to the health support device 2 (S102). In S102, the user terminal 3 may determine the health level of the biometric information and transmit the result to the health support device 2.

[0035] The health support device 2 receives biometric information from the user terminal 3 and determines the corresponding health level. The health support device 2 transmits a generation instruction to the generation device 5 (S103) that includes health information on at least one of lifestyle habits, exercise, sleep, and stress based on the biometric information, and the corresponding health level. Here, the generation instruction includes instructions to generate evaluation information related to the user's health.

[0036] The generation device 5 inputs a generation instruction to the generation model 50 and generates evaluation information as an output of the generation model 50. The generation device 5 transmits the generated evaluation information as a response to the health support device 2 (S104). The health support device 2 transmits an output based on the evaluation information acquired from the generation device 5 to the user terminal 3 (S105). The output may be the evaluation information itself, or the evaluation information processed to fit the display format of the user terminal 3.

[0037] The user terminal 3 can display the evaluation information on a display unit such as a display in accordance with the output acquired from the health support device 2. The output format can be audio, image, or the like, and is not limited to display. This allows the user to receive evaluation information on their own biometric information.

[0038] FIG. 4 shows a processing flowchart in the health support device 2.

[0039] The acquisition unit 21 acquires biometric information from the user terminal 3 (S201). The acquisition unit 21 stores the acquired biometric information for each user in the storage unit DB. The storage unit DB stores the data in a format that allows the measured data of the biometric information to be distinguished by day, week, and month.

[0040] FIG. 5 shows an example of the data structure of biometric information. In this embodiment, the biometric information includes at least one of lifestyle habits, exercise, sleep, and stress. The biometric information is measured at any time, at predetermined time intervals, or in response to an instruction from the user terminal 3. The biometric information is processed by either the biometric measurement device 4 or the user terminal 3 so as to have the format of each data item shown in FIG. 5. This processing may also be performed by the health support device 2. The data items of the biometric information shown in FIG. 5 are merely examples, and do not limit the inclusion of other data items instead of or in addition to these.

[0041] Various types of measured biological information are classified into data items related to lifestyle habits, exercise, sleep, and stress and stored in the storage unit DB, which are defined as health information. In this embodiment, the health information is selectively extracted from data items included in the biological information that are important in mental health evaluation and support. Therefore, the health information is not limited to including other data items that are important from the perspective of mental health care.

[0042] 5(a), the biological information related to vital signs includes a data ID, a heart rate, a blood oxygen level, a heart rate variability (HRV), a stress value, etc. In this embodiment, the stress value is expressed as a score of 0 to 100 and is calculated based on the HRV, but is not limited to this and may be calculated by adding one or more other items.

[0043] As shown in FIG. 5(b), the biological information related to exercise includes a data ID, the number of steps, the calorie consumption, the exercise time, and the exercise record. The calorie consumption is calculated based on the heart rate, the number of steps, and the exercise time, but is not limited to these, and may be calculated by adding one or more other items or replacing the other items. The exercise record is performed by selecting an exercise subject such as a sport and recording the transition of the exercise subject, the heart rate, the number of steps, etc. In addition, in this embodiment, the biological information related to exercise includes the time and time period when the exercise was performed.

[0044] As shown in FIG. 5(c), the sleep-related biological information includes a data ID, bedtime, wake-up time, sleep content, sleep efficiency, timing, sleep heart rate, sleep HRV, sleep activity state, etc. Sleep content includes sleep types such as deep sleep, light sleep, and REM sleep, and sleep duration for each sleep type. Sleep efficiency indicates the proportion of actual sleep state in total sleep. Sleep state is determined from various sensor values, heart rate, HRV, etc. Timing is indicated as a graded evaluation value depending on whether the midpoint of sleep is between midnight and 3:00 AM. Sleep activity state is indicated as a graded evaluation value depending on the amount of activity during sleep. Bedtime, wake-up time, sleep content, and sleep activity state are determined based on heart rate and sensor values ​​from the acceleration sensor and gyroscope of the biometric device 4. Furthermore, sleep time is measured, for example, by the time from bedtime to wake-up time, but if the sleep is light or if movement is detected and it is determined that the person is awake, that time may be subtracted.

[0045] Biometric information related to lifestyle habits indicates whether a user has a regular lifestyle. The biometric information related to lifestyle habits includes a data ID, bedtime, wake-up time, time or time period of exercise, and dietary status. A regular lifestyle refers to a state in which there is little variation from day to day in bedtime, wake-up time, time or time period of exercise, etc. The time period for exercise may further include a time period or exercise subject that is preferable from a health perspective, such as a morning walk. Furthermore, the dietary status includes meal contents input via the user terminal 3 and answers to a diet-related questionnaire, and is an item indicating whether the user is eating regular meals. Each data item of the biometric information related to lifestyle habits is common to the data items of biometric information related to exercise and sleep, and may refer to these.

[0046] The determination unit 22 determines the health level of at least one of lifestyle habits, exercise, sleep, and stress based on the user's biological information. The health level indicates how healthy the lifestyle habits are by a graded level or score. In this embodiment, the health level is indicated in four levels, "◎", "◯", "△", and "×", in descending order of healthiness.

[0047] The judgment unit 22 judges the health level using judgment conditions. The judgment conditions are set as one or more target value ranges, and the health level is judged depending on which range the value falls into. Different judgment conditions can be set for lifestyle habits, exercise, sleep, and stress. Note that other additional conditions may be set as judgment conditions, and the health level may be judged depending on whether or not they are met.

[0048] For example, the lifestyle habit assessment criteria may be as follows: if yesterday's wake-up time or bedtime matches within 15 minutes of the previous week's and if the user has slept for at least seven hours, the health level is assessed as "◎"; if yesterday's wake-up time or bedtime matches within one hour and the user has slept for at least six hours, the health level is assessed as "◯"; if the wake-up time or bedtime differs by two hours or more, the health level is assessed as "△"; and if the wake-up time or bedtime differs by three hours or more, the health level is assessed as "×." Furthermore, the lifestyle habit assessment criteria may further include an additional condition that the user answers "◯" to the question "Eat regularly" as a result of a questionnaire sent via the user terminal 3. Similarly, the exercise assessment criteria determine the health level according to the range of exercise time. The sleep assessment criteria determine the health level according to the range of sleep time. The stress assessment criteria determine the health level according to the range of stress scores.

[0049] The output unit 23 transmits a generation instruction including at least one of biological information of lifestyle habits, exercise, sleep, and stress and a corresponding health level to the generation device 5 (S203). The generation device 5 receives the generation instruction in S203 and processes it in the generative model 50. An example of a generation instruction related to lifestyle habits is shown below.

[0050] You are a leading mental health counselor. Please write a piece of writing for your client about lifestyle habits based on the following criteria: <Condition> ·About 100 characters. ·Using the "desu" and "masu" style. - Check yesterday's health status "lifestyle" results and sleep data. If your child's wake-up and bedtimes have not been fixed for the past week, encourage them to do so as much as possible. · Never criticize in a strong tone, as you may not be able to keep it in place due to work or other reasons. If your child has consistent wake-up and bedtimes, praise them for this and encourage them to continue with these habits.

[0051] As described above, the generation instruction includes an instruction as to which biometric information or health level to refer to. Furthermore, the generation instruction may include an instruction as to the data to be compared with the data to be evaluated, in addition to the data to be evaluated. Furthermore, the generation instruction may include an instruction to encourage improvement or maintenance depending on the health level of the data to be evaluated. Furthermore, when encouraging improvement, the generation instruction may include an instruction to propose specific improvement plans or measures.

[0052] In this embodiment, the generation instruction includes an instruction to evaluate the user's current biometric information or health level against the user's past biometric information or health level. The past biometric information and health level are stored in the storage unit DB, and data from a predetermined period, such as the past week or month, is referenced. The past data may also refer to an aggregated or averaged value of data from the predetermined period. For example, a generation instruction related to exercise may include an instruction to evaluate the user's current exercise time against the average exercise time for the past week. Because a generation instruction for current biometric information is sent with past biometric information as a comparison target, the generative model 50 can generate an evaluation that changes depending on the user's accumulation of past information.

[0053] Similarly, generation instructions for exercise, sleep, and stress are set. For example, the generation instructions for exercise include instructions for exercise duration, etc., depending on the biological information and health level related to exercise. The generation instructions for sleep include instructions to prioritize evaluation of sleep duration depending on the biological information and health level related to sleep, and to evaluate other sleep-related data items if the health level is above a predetermined level. The generation instructions for stress include instructions to advise on methods and ways of thinking to relieve anxiety when the stress level is high, depending on the stress level and health level. These are merely examples and do not limit the content of the generation instructions.

[0054] In the highly specialized field of mental health, for example, it may be difficult for the generative model 50 to properly determine what bedtimes and wake-up times constitute healthy lifestyle habits. By including content that refers to the health level in the generation instructions, the generative model 50 can properly process how healthy the lifestyle habits, etc. were. In addition, the generative model 50 can generate flexible evaluations based on the user's accumulated biometric information, and can generate evaluation information that points out small changes in the user's biometric information.

[0055] The generative model 50 generates evaluation information for at least one of lifestyle habits, exercise, sleep, and stress in accordance with the generation instructions. The evaluation information indicates comments on the health-related conditions, as well as suggestions and advice for improving the conditions. In this embodiment, the evaluation information particularly includes suggestions, advice, or comments on the mental health condition or for improving the mental health condition.

[0056] The generating device 5 transmits the evaluation information generated by the generative model 50 to the health support device 2. The output unit 23 acquires the evaluation information corresponding to the generation instruction (S204).

[0057] The output unit 23 transmits an output based on the obtained evaluation information to the user terminal 3 (S205). The output unit 23 may output the evaluation information for each of the lifestyle habits, exercise, sleep, and stress individually, or may output an integrated version of the evaluation information for each of the lifestyle habits, exercise, sleep, and stress.

[0058] 6(a) shows an example of the display of the evaluation screen W10 on the user terminal 3. The user terminal 3 can acquire output from the health support device 2 and receive an evaluation of the biometric information. The evaluation screen W10 includes an evaluation information area W11, a health information area W12, a health level display W13, and a biometric information area W14.

[0059] The evaluation information area W11 displays evaluation information. In Fig. 6(a), the evaluation information area W11 displays an integrated content of evaluation information for lifestyle habits, exercise, sleep, and stress.

[0060] The health information area W12 displays biological information (health information) related to lifestyle habits, exercise, sleep, and stress. In FIG. 6(a), the health information area W12 displays some data items such as bedtime, wake-up time, exercise time, and sleep time, but other data items may also be displayed. The health information area W12 also displays health indicators W13 for lifestyle habits, exercise, sleep, and stress corresponding to each health information item. The biological information area W14 displays other data items of biological information.

[0061] 6(b) shows an example of a detailed evaluation screen W20 displaying detailed evaluation information for each of lifestyle habits, exercise, sleep, and stress. The detailed evaluation screen W20 is transitioned to and displayed when any of lifestyle habits, exercise, sleep, and stress is specified in the health information area W12 of the evaluation screen W10. FIG. 6(b) shows an example of the detailed evaluation screen W20 related to stress.

[0062] The detailed evaluation screen W20 comprises a detailed evaluation information area W21, a current area W22, and a history area W23. The detailed evaluation information area W21 displays individual evaluation information for lifestyle habits, exercise, sleep, and stress. The current area W22 displays the user's current or most recent health information. The history area W23 displays the user's past health information. The detailed evaluation information area W21 displays evaluations of the health information in the current area W22 and the history area W23.

[0063] In this embodiment, the generative model 50 is subjected to additional training (fine tuning). Additional training refers to a process of making the generative model 50 learn missing knowledge in a specialized field, etc. In this embodiment, the generative model 50 is additionally trained using training data related to mental health support.

[0064] As an example, the large-scale language model is configured as a pre-trained model that has been trained for general purposes. The pre-trained model can be further trained to learn a specific task or a specific field of expertise, thereby becoming a generative model 50 that realizes a generation process suited to the purpose. The trained generative model 50 can be used by issuing a generation instruction via the health support device 2.

[0065] The health support device 2 acquires the learning data to be used for additional learning and instructions for additional learning using the learning data via an administrator terminal (not shown). In accordance with the instructions, the health support device 2 transmits the learning data to the generation device 5 and causes the generation device 5 to perform additional learning of the generative model 50. Note that the generation device 5 may acquire the learning data from the administrator terminal and perform additional learning of the generative model 50.

[0066] The training data in this embodiment can be data from books and papers written by mental health specialists and counselors on mental illnesses, etc. These data relate to methods for avoiding stress (improving resilience) from the perspective of mental health care, as well as appropriate lifestyle habits, exercise, and sleep. After additional training, the generative model 50 can generate evaluation information including appropriate improvements and comments according to the generation instructions. This allows users to obtain daily evaluation information, such as answers from specialists and counselors, about their own biometric information, thereby maintaining and improving their mental health.

[0067] In one embodiment, the training data may be data posted on a social networking service (SNS), preferably posted by a predetermined user such as a mental health specialist or counselor through their SNS account.

[0068] The health support device 2 stores the SNS account information of a predetermined user in the storage unit DB. The account information includes at least a user ID. Extraction conditions may also be set for the account information. The extraction conditions may include, for example, keywords related to mental health, and enable the extraction of posted data related to mental health from the posted data. The health support device 2 acquires the posted data based on the account information. The posted data is used as learning data for additional learning of the generative model 50.

[0069] The health support device 2 may have the generative model 50 determine the posted data to be used as learning data. The health support device 2 can extract posted data related to mental health from the posted data by transmitting to the generating device 5, for example, a generation instruction including the above-mentioned extraction conditions and posted data, and an instruction to extract posted data according to the extraction conditions. The extracted posted data is used as learning data for additional learning of the generative model 50.

[0070] The point processing unit 24 issues points to the user according to the issuing conditions. The point processing unit 24 also performs a process of consuming points according to point usage instructions. The number of points held by the user is linked to user information and stored in the storage unit DB. Points can be exchanged for various products and services or used as coupons.

[0071] In this embodiment, the storage unit DB stores conditions for issuing points. The conditions for issuing points are set so that different numbers of points are awarded depending on the level of health. For example, if the health level is "◎", 100 points are awarded, if it is "◯", 50 points are awarded, if it is "△", 30 points are awarded, and if it is "×", 0 points are awarded. Note that the allocation of points is not limited to this.

[0072] The conditions for issuing points based on health level are set to the average or aggregated value of health level for a predetermined period such as daily, weekly, monthly, etc. Furthermore, the conditions for issuing points based on health level may be set for each of lifestyle habits, exercise, sleep, and stress, or may be set for the average or aggregated value of these health levels.

[0073] Furthermore, the issuance conditions are set according to the attributes of the user. User information includes user attributes such as gender, age, and area (place of residence, etc.). The issuance conditions specify whether or not to issue points, or the number of points to be issued, by specifying these attributes. For example, conditions can be set such as issuing 10 points to those aged 45 to 64 or older, 20 points to those aged 65 or older, and not issuing points to other age groups.

[0074] The issuing conditions can be set by combining the health level and the user attributes. The issuing conditions can be set by a terminal device of an administrator or a company.

[0075] Points are categorized by point type. Type 1 points have no usage restrictions on exchange for various products, etc. Type 2 points have usage restrictions on exchange for specific products, etc. For example, type 2 points are restricted in usage to products, etc. from specific companies. The scope of these usage restrictions can be set by the administrator or the terminal device of the company, etc.

[0076] The point processing unit 24 receives an instruction to use points via the user terminal 3. The instruction to use points includes identification information of the product or the like and the number of points to be consumed. The instruction to use points is sent to the health support device 2 by receiving a designation of the product or the like on a product or the like selection screen displayed on the user terminal 3. Furthermore, when exchanging products or the like at a store or the like, the user terminal 3 may send identification information of the product or the like to the health support device 2, and the point processing unit 24 may receive an instruction to use points. The identification information of the product or the like may be input by reading a two-dimensional code or by manual input.

[0077] The point processing unit 24 calculates the number of points of the user according to the number of points to be consumed included in the usage instruction, and updates the number of points of the user stored in the storage unit DB with the calculated number of points.

[0078] A limit may be set on the number of times that one product, etc. can be exchanged. When the upper limit of the number of exchanges for a product, etc. is reached, the display of the product, etc. on the user terminal 3 is restricted, or the instruction to use the product, etc. is restricted.

[0079] The point processing unit 24 may generate suggested information based on the point issuing conditions. The suggested information includes suggestions for improving health to satisfy the point issuing conditions. For example, if the weekly average health is set as the point issuing condition, the suggested information suggests what lifestyle habits, exercise, sleep, or stress improvements should be made for the remaining days to increase the number of points. The suggested information may also include a warning if the number of points is likely to decrease. The generated suggested information is sent to the user terminal 3.

[0080] These pieces of suggested information can also be generated by the generative model 50. In this case, the output unit 23 transmits a generation instruction including the biometric information, the health level, and the point issuing conditions to the generation device 5. The output unit 23 acquires the suggested information from the generation device 5 and transmits it to the user terminal 3.

[0081] As described above, by issuing points according to the degree of health, it is possible to increase the motivation of the user to improve their health. [Explanation of symbols]

[0082] 1. Health support system 2 Health support equipment 21 Acquisition Department 22 Judgment section 23 Output section 24 Point Processing Section 3. User terminal 4. Biometric devices 5 Generator DB storage

Claims

1. Based on the user's biological information, the health level of at least one of lifestyle habits, exercise, sleep, and stress is determined; A health support system that inputs generation instructions including at least one of biometric information of lifestyle habits, exercise, sleep, and stress, and the corresponding health level, into a generation model and outputs evaluation information obtained from the generation model.

2. The health support system according to claim 1 , wherein the biological information is measured by a biological measurement device worn by the user and acquired through communication.

3. The health support system according to claim 1 or 2, wherein the evaluation information includes suggestions, advice, or comments regarding the state or improvement of mental health.

4. The health support system according to claim 3 , wherein the generative model is additionally trained using training data related to mental health support.

5. The health support system according to claim 1 or 2, wherein the generation instruction includes an instruction to evaluate the user's current biometric information or health level relative to the user's past biometric information or health level.

6. The health support system according to claim 5 , wherein the generation instruction includes an instruction to evaluate the user's current biometric information or health level against an average value of the user's biometric information or health level for a predetermined period of time.

7. The biological information is lifestyle habits including wake-up time and / or bedtime; Exercise data, including exercise duration; Sleep data, including sleep duration, stress data including a stress value; 3. The health support system according to claim 1, wherein the health level is determined based on target value ranges set for each of lifestyle habits, exercise, sleep, and stress.

8. a point processing unit that issues points to the user according to issuing conditions; 3. The health support system according to claim 1, wherein the issuance conditions are set according to the level of health and attributes of the user.

9. A health support method using a system including a biometric measurement device, a user terminal, and a health support device, comprising: The user terminal acquires the user's biometric information from the biometric measurement device, the health support device determines a health level of at least one of lifestyle habits, exercise, sleep, and stress based on the biological information of the user; A health support method that inputs generation instructions including at least one of biometric information of lifestyle habits, exercise, sleep, and stress and the corresponding health level into a generation model, and outputs evaluation information obtained from the generation model.

Images