Information processing apparatus, information processing method, and program

Abstract

To provide an information processor capable of making an optimum proposal according to the health condition of each person.SOLUTION: In an information processor, face video data acquisition means acquires a face video of an object person. The disease risk estimation means estimates disease risk scores including a disease risk score of the mind, a disease risk score of the brain, and a disease risk score of the body based on the facial image of the target person. The suggestion means determines suggestion content to the target person on the basis of a combination of the disease risk score of the mind, the disease risk score of the brain, and the disease risk score of the body. The information processing apparatus can provide a service or a product optimized for the target person.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present disclosure relates to estimating health status. [Background technology]

[0002] Life insurance companies often set a flat rate for life insurance premiums for all policyholders. However, because health conditions vary from person to person, it is not necessarily appropriate to set a flat rate for all policyholders. Patent Document 1 describes a premium setting system that takes into account the contribution of smiles to health and changes premiums according to smiles. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] International Publication WO2016 / 178327 Summary of the Invention [Problem to be solved by the invention]

[0004] However, even with the technique of Patent Document 1, it is not always possible to set an optimized fee for each individual.

[0005] One object of the present disclosure is to provide an information processing device that can make optimal suggestions according to the health condition of each individual. [Means for solving the problem]

[0006] According to one aspect of the present disclosure, there is provided an information processing device, A facial image data acquisition means for acquiring a facial image of a subject; a disease risk estimation means for estimating a disease risk score including a mental disease risk score, a brain disease risk score, and a body disease risk score based on the facial image of the subject; A suggestion means for determining a suggestion to the subject based on a combination of the mental disease risk score, the brain disease risk score, and the body disease risk score; Equipped with.

[0007] In another aspect of the present disclosure, an information processing method includes: 1. A computer-implemented information processing method, comprising: Acquire the target person's facial image, Based on the facial image of the subject, a disease risk score including a mental disease risk score, a brain disease risk score, and a body disease risk score is estimated; The content of a suggestion to the subject is determined based on a combination of the mental disease risk score, the brain disease risk score, and the body disease risk score.

[0008] In yet another aspect of the disclosure, a program includes: Acquire the target person's facial image, Based on the facial image of the subject, a disease risk score including a mental disease risk score, a brain disease risk score, and a body disease risk score is estimated; The computer executes a process of determining the content of a suggestion to the subject based on a combination of the mental disease risk score, the brain disease risk score, and the body disease risk score. [Effects of the Invention]

[0009] According to the present disclosure, it is possible to provide optimal suggestions according to each person's health condition. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a diagram illustrating the overall configuration of a health management system according to the present disclosure. [Figure 2] FIG. 1 is a block diagram illustrating a hardware configuration of an information processing device according to the present disclosure. [Figure 3] FIG. 1 is a block diagram illustrating a functional configuration of an information processing device according to the present disclosure. [Figure 4] 10 is an example of a selection table. [Figure 5] 10 is a flowchart of a disease risk estimation process. [Figure 6] This is an example of the health items of the insured person. [Figure 7] FIG. 10 is a block diagram showing a functional configuration of another information processing device according to the present disclosure. [Figure 8] FIG. 10 is a diagram conceptually illustrating another health management system according to the present disclosure. [Figure 9] FIG. 10 is a block diagram showing a functional configuration of another information processing device according to the present disclosure. [Figure 10] 10 is a flowchart of a process performed by another information processing device according to the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0011] Hereinafter, preferred embodiments of the present disclosure will be described with reference to the drawings.

[0012] First Embodiment [Overall configuration] 1 shows the overall configuration of a health management system to which an information processing device according to the present disclosure is applied. The health management system 1 includes a terminal device 5 of an insured person, an information processing device 10, and a terminal device 20 of a life insurance company.

[0013] The insured's terminal device 5 is operated by the insured or the like and is used to photograph the insured's face. The terminal device 5 may be configured, for example, as a smartphone or tablet terminal owned by the insured, or as a camera device installed at the premises of the life insurance company. The terminal device 5 communicates with the information processing device 10 and the terminal device 20 of the life insurance company via a network such as the Internet.

[0014] The information processing device 10 estimates the health condition of the insured person from an image of the insured person's face. The information processing device 10 also proposes healthcare-related services and products, such as health maintenance and health promotion, based on the insured person's health condition. The information processing device 10 also reviews insurance premiums based on the insured person's health condition. The information processing device 10 is configured, for example, by a server device, and communicates with the insured person's terminal device 5 and the life insurance company's terminal device 20 via a network such as the Internet.

[0015] The terminal device 20 of the life insurance company is operated by a person in charge of the life insurance company, etc. The terminal device 20 may execute some of the processes executed by the information processing device 10. Specifically, the terminal device 20 receives the health condition of the insured person from the information processing device 10, and can propose services and products, and review insurance premiums. The terminal device 20 is configured, for example, by a personal computer or a server device, and communicates with the terminal device 5 of the insured person and the information processing device 10 via a network such as the Internet.

[0016] [Hardware configuration] 2 is a block diagram showing the hardware configuration of an information processing device 10 according to the first embodiment. As shown in the figure, the information processing device 10 includes an interface (I / F) 11, a processor 12, a memory 13, a recording medium 14, and a database (DB) 15.

[0017] The I / F 11 communicates with the insured's terminal device 5 and the life insurance company's terminal device 20 via a network such as the Internet.

[0018] The processor 12 is a computer such as a CPU (Central Processing Unit) and controls the entire information processing device 10 by executing a pre-prepared program. The processor 12 may be a GPU (Graphics Processing Unit), a DSP (Digital Signal Processor), an MPU (Micro Processing Unit), an FPU (Floating Point Number Processing Unit), a PPU (Physics Processing Unit), a TPU (Tensor Processing Unit), a quantum processor, a microcontroller, or a combination thereof. The processor 12 executes a disease risk estimation process, which will be described later.

[0019] The memory 13 is configured by a ROM (Read Only Memory), a RAM (Random Access Memory), etc. The memory 13 is also used as a working memory while the processor 12 is executing various processes.

[0020] The recording medium 14 is a non-volatile, non-transitory recording medium such as a disk-shaped recording medium or a semiconductor memory, and is configured to be detachable from the information processing device 10. The recording medium 14 records various programs to be executed by the processor 12. When the information processing device 10 executes various processes, the programs recorded on the recording medium 14 are loaded into the memory 13 and executed by the processor 12.

[0021] For example, DB 15 may store information about the insured person in association with the insured person ID. DB 15 may also store past facial images and past health conditions of the insured person in association with the insured person ID. The insured person ID is an ID for uniquely identifying the insured person.

[0022] In addition to the above, the information processing device 10 may also include a display device such as a liquid crystal display, and an input device such as a keyboard and a mouse. These display device and input device are used by, for example, an administrator of the information processing device 10 to perform necessary management.

[0023] [Function Configuration] 3 is a block diagram showing the functional configuration of the information processing device 10 according to the first embodiment. The information processing device 10 functionally includes a face image data acquisition unit 101, a disease risk estimation unit 102, and a proposal unit 103.

[0024] The face image data acquisition unit 101 acquires a face image of the insured person captured by the terminal device 5. The face image data acquisition unit 101 outputs the face image to the disease risk estimation unit .

[0025] The disease risk estimation unit 102 estimates the health condition of the insured person. In this embodiment, a disease risk score obtained by scoring disease risk is used as an index representing the health condition of the insured person. In this embodiment, the disease risk score is expressed as two values: 0 (low risk) and 1 (high risk). Hereinafter, a disease risk score of 0 will also be simply referred to as "low disease risk," and a disease risk score of 1 will also be simply referred to as "high disease risk."

[0026] The disease risk estimation unit 102 determines a disease risk score based on the facial image of the insured person. In this embodiment, the disease risk includes a mental disease risk, a brain disease risk, and a physical disease risk. The disease risk estimation unit 102 determines the score of each disease risk and outputs the determination result to the suggestion unit 103.

[0027] Specifically, the disease risk estimation unit 102 estimates values ​​of health-related items (hereinafter also referred to as "health items") based on the facial image of the insured person. Then, the disease risk estimation unit 102 determines whether each disease risk is high based on the estimation results of each item. Health items include, for example, the insured person's drowsiness, concentration level, stress, cognitive function, vital signs (heart rate, respiration, SpO2, blood pressure, blood sugar level, cholesterol level, etc.), etc.

[0028] (1) Risk of mental illness The disease risk estimation unit 102 estimates the insured person's drowsiness, concentration level, stress, etc. based on the facial image of the insured person, and determines whether the insured person has a high risk of mental illness. For example, the disease risk estimation unit 102 determines that the insured person has a high risk of mental illness if the insured person is very drowsy, not concentrating, or has high stress. The disease risk estimation unit 102 may determine the risk of mental illness using one of the items drowsiness, concentration level, and stress, or may determine the risk of mental illness using a combination of multiple items.

[0029] (2) Risk of brain disease The disease risk estimation unit 102 estimates the insured person's drowsiness, concentration level, cognitive function, etc. based on the facial image of the insured person, and determines whether the brain disease risk is high. For example, the disease risk estimation unit 102 determines that the brain disease risk is high if the insured person is very drowsy, not concentrating, or has low cognitive function. The disease risk estimation unit 102 may determine the brain disease risk using one item from among drowsiness, concentration level, and cognitive function, or may determine the brain disease risk using a combination of multiple items.

[0030] (3) Risk of physical illness The disease risk estimation unit 102 estimates the insured person's drowsiness and vital signs (heart rate, respiration, SpO2, blood pressure, blood sugar level, cholesterol level, etc.) based on the facial video of the insured person, and determines whether the physical disease risk is high. For example, if the insured person is very drowsy or if the vital signs are abnormal values, the disease risk estimation unit 102 determines that the physical disease risk is high. The disease risk estimation unit 102 may determine the physical disease risk using one item of drowsiness or each vital sign, or may determine the physical disease risk using a combination of multiple items.

[0031] In the above (1) to (3), when determining disease risk by combining multiple items, the disease risk estimation unit 102 scores the estimation results for the multiple items based on predetermined criteria. Then, the disease risk estimation unit 102 determines whether the disease risk is high or not based on the total or average value of each score. Note that the disease risk estimation unit 102 may determine whether the disease risk is high or not using a machine learning model. This machine learning model is, for example, a machine learning model that has been trained in advance to input estimation results for multiple items and output a disease risk score.

[0032] The disease risk estimation unit 102 outputs the results of the determination of each disease risk obtained by the above (1) to (3) to the proposing unit 103.

[0033] The disease risk estimation unit 102 may express the disease risk score as a continuous value indicating the degree of disease risk, instead of the binary values ​​of 0 and 1. For example, if the range of continuous values ​​is from 0 to 100, the closer to 100 the score is, the higher the disease risk.

[0034] The proposal unit 103 makes a proposal suitable for the insured person based on the assessment result of each disease risk. For example, the proposal unit 103 selects a service suitable for the insured person from a plurality of services prepared in advance. Also, the proposal unit 103 selects an insurance product suitable for the insured person from a plurality of insurance products prepared in advance.

[0035] Specifically, the suggestion unit 103 selects a service based on the assessment result of each disease risk. Fig. 4 shows a service selection table. The selection table in Fig. 4 defines the relationship between a service and a combination of disease risks. Regarding disease risks, "high" indicates that the risk of the disease is high.

[0036] The proposing unit 103 selects a service based on a combination of the assessment results of each disease risk, with reference to the table shown in Fig. 4. For example, if all three disease risks are high, the proposing unit 103 selects "frailty check," "consultation by medical experts," "provision of information on nursing care facilities," and "second opinion." Note that, if there are multiple services as described above, the proposing unit 103 may select at least one or more services.

[0037] 4, blank spaces indicate a low risk of the disease. For example, if the risk of a mental disease is high and the risk of a brain and body disease is low, the suggestion unit 103 selects "stress check" and "provision of communication function."

[0038] 4, blank spaces may indicate that the disease risk may be high or low. For example, if the risk of a mental disease is high, the suggestion unit 103 may select "stress check" as the service to be suggested, regardless of the level of the risk of a brain or body disease.

[0039] Furthermore, the proposing unit 103 selects an insurance product based on a combination of the assessment results of each disease risk. For example, the proposing unit 103 selects health promotion insurance when all of the risks of disease in the mind, brain, and body are low, selects dementia insurance when the risk of disease in the brain is high, and selects nursing care insurance when any of the risks of disease in the mind, brain, and body is high.

[0040] The proposal unit 103 outputs the proposal content to the terminal device 20 of the life insurance company. By referring to the proposal content, the person in charge at the life insurance company can consider appropriate health support and counseling for the insured person.

[0041] In the above configuration, the face image data acquisition unit 101 is an example of a face image data acquisition means, the disease risk estimation unit 102 is an example of a disease risk estimation means, and the proposing unit 103 is an example of a proposing means.

[0042] [Processing flow] Next, the disease risk estimation process performed by the information processing device 10 will be described.

[0043] 5 is a flowchart of a disease risk estimation process performed by the information processing device 10. This process is realized by the processor 12 shown in FIG. 2 executing a program prepared in advance and operating as each element shown in FIG.

[0044] First, the face image data acquisition unit 101 acquires a face image of the insured person captured by the terminal device 5 (step S11). The face image data acquisition unit 101 outputs the face image to the disease risk estimation unit .

[0045] Next, the disease risk estimation unit 102 determines the mental disease risk, brain disease risk, and physical disease risk of the insured person based on the facial image (step S12). Specifically, the disease risk estimation unit 102 estimates the insured person's drowsiness, concentration level, stress, cognitive function, vital signs, etc. Then, based on the estimation results, the disease risk estimation unit 102 determines whether each disease risk is high or not. The disease risk estimation unit 102 outputs the determination results of each disease risk to the suggestion unit 103.

[0046] Next, the proposal unit 103 makes a proposal suitable for the insured person based on the judgment result of each disease risk (step S13). The proposal unit 103 outputs the contents of the proposal to the terminal device 20 of the life insurance company. Then, the processing ends.

[0047] [Method of estimating health items] Next, we will explain how to estimate the values ​​of the insured person's health items. Figure 6 shows examples of the insured person's health items, which include the insured person's sleepiness, concentration level, stress, cognitive function, vital signs, as well as edema, wrinkles, and risk of frailty.

[0048] (1) Estimation of drowsiness The disease risk estimation unit 102 detects the movement of the insured person's eyelids from the facial image of the insured person and estimates the drowsiness level based on the detected movement. Drowsiness is expressed on a five-point scale, with the higher the number, the stronger the drowsiness. Note that methods for estimating drowsiness from facial images are described in, for example, the following documents. The following documents are incorporated herein by reference: M. Tsujikawal, Y. Onishil, Y. Kiuchil, T. Ogatsuul, A. Nishino and S. Hashimoto, “Drowsiness Estimation from Low-Frame-Rate Facial Videos using Eyelid Variability Features”, 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Honolulu, HI, USA, 2018, pp. 5203-5206.

[0049] If the insured person feels very sleepy, the disease risk estimation unit 102 determines that the insured person has a high risk of mental illness, a high risk of brain illness, and a high risk of physical illness. The disease risk estimation unit 102 may also determine the disease risk taking into account the time when the facial image was captured. For example, if the insured person feels very sleepy during the daytime (1:00 PM to 3:00 PM), the disease risk estimation unit 102 determines that the insured person has a high risk of mental illness and a high risk of physical illness.

[0050] (2) Estimation of concentration The disease risk estimation unit 102 detects the eyelid movement, gaze, facial expression, etc. of the insured person from the facial image of the insured person, and estimates the concentration level based on the detected movement. The concentration level is expressed in two stages: concentration and non-concentration. Note that methods for estimating the concentration level from facial images are described in, for example, the following documents. The following documents are incorporated herein by reference: Terumi Umematsu, Masanori Tsujikawa, Hideyuki Sawada, "Evaluation of Cognitive Test Results Using Concentration Estimation from Facial Videos", Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA), pp.261-266, November 2022.

[0051] When the insured person is not concentrating (disconcentrated), the disease risk estimation unit 102 determines that the risk of mental illness or brain illness is high. The disease risk estimation unit 102 may also determine the disease risk by taking into account the time when the facial image was captured or the insured person's declaration. For example, when the insured person is not concentrating while working or at work, the disease risk estimation unit 102 determines that the risk of mental illness or brain illness is high.

[0052] (3) Stress estimation The disease risk estimation unit 102 measures heart rate variability from facial images of the insured person using rPPG (Remote Photoplethysmography) technology and calculates a stress index (LF / HF). Note that methods for measuring heart rate variability from facial images are described in, for example, the following documents. The following documents are incorporated herein by reference: Terumi Umematsu and Masanori Tsujikawa, "Heart rate estimation from facial videos based on ICA with reference", The 39th International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), July 2017.

[0053] Furthermore, the following document proposes a stress estimation method using non-contact heart rate measurement from a facial image. The following document is incorporated herein by reference. Akimi Umematsu, Takenori Tsujikawa, Hideyuki Sawada, "Real-time stress estimation using non-contact heart rate measurement robust to facial movements," Transactions of Information Processing Society of Japan, Vol. 65, No. 7, pp. 1150-1161, 2024.

[0054] If stress is consistently high, the disease risk estimation unit 102 determines that the risk of mental illness is high. Specifically, if LF / HF is always higher than the reference value (sympathetic nerves are always dominant) or if LF / HF does not fall below the reference value (parasympathetic nerves are not dominant), the disease risk estimation unit 102 determines that the risk of mental illness is high.

[0055] (4) Estimation of cognitive function The disease risk estimation unit 102 calculates the percentage of the insured person's eyes that are closed and the eyelid movement speed from the facial image of the insured person, and estimates cognitive function based on the calculated values. The disease risk estimation unit 102 may express cognitive function in three levels: "cognitively normal," "mild cognitive impairment," and "dementia," or may express it as a score equivalent to the Mini-Mental State Examination (MMSE), which is one evaluation of cognitive function. Note that a method for estimating cognitive function from facial image is described, for example, in International Application No. PCT / JP2023 / 041209 previously filed by the present inventor. The disclosure of the specification of this application is incorporated herein by reference.

[0056] When cognitive function is low, that is, when the patient has "mild cognitive impairment" or "dementia," the disease risk estimation unit 102 determines that the risk of brain disease is high.

[0057] (5) Estimation of vital signs In Figure 6, vital signs include heart rate, respiration, SpO2, blood pressure, blood glucose level, and cholesterol.

[0058] (5)-1. Heart Rate The disease risk estimation unit 102 estimates the heart rate by calculating the change in luminance of the face color from the facial image of the insured person. Note that a method for estimating the heart rate from a facial image is described in, for example, the following document. The following document is incorporated herein by reference: Terumi Umematsu and Masanori Tsujikawa, "Heart rate estimation from facial videos based on ICA with reference", The 39th International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), July 2017.

[0059] The disease risk estimation unit 102 compares the estimated heart rate with a preset reference value and determines whether it is normal or abnormal. If the determination result is abnormal, the disease risk estimation unit 102 determines that the physical disease risk is high. Note that the disease risk estimation unit 102 may also determine the disease risk based on the insured person's resting heart rate. In this case, if the insured person's resting heart rate is higher than the reference value, the disease risk estimation unit 102 determines that the physical disease risk is high.

[0060] Furthermore, the disease risk estimation unit 102 can estimate SpO2, blood pressure, blood sugar level, and the like from changes in brightness of facial color.

[0061] (5)-2. Breathing The disease risk estimation unit 102 estimates the respiration from the facial image of the insured person using a prepared RR (Respiratory rate) estimation model or the like. Note that a method for estimating the respiration from the facial image is described in, for example, the following document. The following document is incorporated herein by reference. Akamatsu, Yusuke, Terumi Umematsu and Hitoshi Imaoka. "CalibrationPhys: Self-Supervised Video-Based Heart and Respiratory Rate Measurements by Calibrating Between Multiple Cameras", IEEE Journal of Biomedical and Health Informatics 28 (2023): 1460-1471.

[0062] The disease risk estimation unit 102 compares the estimated respiration with a preset reference value and determines whether it is normal or abnormal. If the determination result is abnormal, the disease risk estimation unit 102 determines that the body has a high disease risk.

[0063] (5)-3. Cholesterol The disease risk estimation unit 102 estimates the BMI from the facial image of the insured person using a BMI prediction model prepared in advance. Then, the disease risk estimation unit 102 determines whether or not the cholesterol level is high based on the BMI. If the cholesterol level is high, the disease risk estimation unit 102 determines that the physical disease risk (risk of obesity) is high.

[0064] (6) Estimation of edema The disease risk estimation unit 102 estimates the presence or absence of edema from the facial image of the insured person using a prepared edema estimation model or the like. Note that a method for estimating edema from a facial image is described in, for example, the following document. The following document is incorporated herein by reference: Y. Akamatsu, Y. Onishi, H. Imaoka, J. Kameyama and H. Tsurushima, "Edema Estimation From Facial Images Taken Before and After Dialysis via Contrastive Multi-Patient Pre-Training", in IEEE Journal of Biomedical and Health Informatics, vol. 27, no. 3, pp. 1419-1430, March 2023

[0065] If the insured person has edema, the disease risk estimation unit 102 determines that the insured person has a high risk of physical disease (risk of kidney disease, heart disease, etc.).

[0066] (7) Wrinkle estimation The disease risk estimation unit 102 estimates whether or not the subject has wrinkles on the earlobes (whether or not the subject has Frank's sign) by image analysis of the face image of the insured person. If the subject has wrinkles on the earlobes, the disease risk estimation unit 102 determines that the subject has a high risk of physical disease (risk of heart disease, etc.).

[0067] (8) Estimation of risk of frailty The disease risk estimation unit 102 estimates whether or not the insured person is at risk of frailty by using the insured person's gait data in addition to the facial image of the insured person. A method for estimating the risk of frailty is described, for example, in Patent Application No. 2024-078683 previously filed by the present inventor. The disclosure of the specification of this application is incorporated herein by reference. If there is a risk of frailty, the disease risk estimation unit 102 determines that the risk of disease in the brain and body is high.

[0068] The above-described methods for estimating the values ​​of health items are merely examples, and are not intended to be limiting. Furthermore, while the disease risk estimation unit 102 expresses the value of each health item as a binary value or a tiered value, such as a 3-tier or 5-tier value, the degree of the health item may alternatively be expressed as a continuous number ranging from 0 to 100.

[0069] [Variations] Next, a modification of the first embodiment will be described.

[0070] (Variation 1) The information processing device 10 of the first embodiment selects services and insurance products suitable for the insured person based on the insured person's current disease risk. In addition to the above, the information processing device 10 may select services and insurance products taking into consideration the insured person's future disease risk.

[0071] The facial image data acquisition unit 101 periodically acquires facial images of the insured person and stores the acquired images. The disease risk estimation unit 102 generates a prediction model by machine learning using linear regression based on past data. The disease risk estimation unit 102 then predicts future disease risk based on the prediction model. The past data includes the date and time when the insured person's facial image was acquired, the values ​​of health items and disease risk at that time, etc. The disease risk estimation unit 102 may also use LSTM (Long Short Term Memory) to train the prediction model. In this case, the disease risk estimation unit 102 uses time-series data including the insured person's facial image and the date and time when the facial image was acquired as past data. Future prediction using LSTM is described in, for example, the following literature. The following literature is incorporated herein by reference. Terumi Umematsu, Akane Sano., and Rosalind Picard, "Daytime Data and LSTM can Forecast Tomorrow's Stress, Health, and Happiness", Proceedings of the 41st International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), p. 2186-2190, July 2019.

[0072] The proposal unit 103 selects a service or insurance product using either or both of the current disease risk and the future disease risk.

[0073] (Variation 2) The information processing device 10 can determine the disease risk in more detail by combining the estimation results for a plurality of health items.

[0074] Specifically, the disease risk estimation unit 102 may evaluate each disease risk score in four levels: "lower risk," "low risk," "high risk," and "higher risk" by combining estimation results for multiple health items. For example, with respect to a combination of drowsiness and concentration level, if the insured person is not drowsy and is not concentrating, the disease risk estimation unit 102 may determine that the risk of brain and mental diseases is higher. Furthermore, with respect to a combination of drowsiness and cognitive function, if the insured person is very drowsy and has high cognitive function, the disease risk estimation unit 102 may determine that the risk of mental or physical diseases is higher. Furthermore, with respect to a combination of concentration level and cognitive function, if the insured person is not concentrating and has high cognitive function, the disease risk estimation unit 102 may determine that the risk of mental diseases is higher.

[0075] Furthermore, the disease risk estimation unit 102 may narrow down the disease risk by combining the estimation results of multiple health items. For example, if the insured person is very sleepy, it may be determined that the disease risks of the mind, brain, and body are all high, but if the insured person is very sleepy but has high cognitive function, it may be determined that the disease risks of the mind and body are high among the three disease risks.

[0076] (Variation 3) In the first embodiment, the users of the health management system are described as life insurance companies and insured persons, but users of the health management system are not limited to these. For example, instead of life insurance companies, health insurance associations, shared facilities such as apartment complexes and nursing homes, and commercial facilities such as convenience stores may also use the health management system.

[0077] In the case of a health insurance association, the insured person captures a facial image using a terminal device owned by the insured person or a camera device installed in the workplace. The information processing device 10 estimates a disease risk score based on the facial image of the insured person. The information processing device 10 then determines whether specific health guidance is necessary based on the disease risk score. The information processing device 10 also refers to the current disease risk score and past disease risk scores, and suggests health support or counseling from experts depending on changes in the scores. By referring to the disease risk score and the content of the suggestion, a health insurance association staff member can provide the insured person with specific health guidance, health support, or counseling as needed.

[0078] In the case of a shared facility, facility users capture facial images using a camera device installed in the facility. The information processing device 10 estimates a disease risk score based on the facial image of the user. Then, based on the disease risk score, the information processing device 10 makes product suggestions, lifestyle suggestions, and information about events and consultation sessions. By referring to the disease risk score and the content of the suggestions, staff at the shared facility or facility users can identify services and products that are suitable for the facility users.

[0079] In the case of a commercial facility, a customer captures a facial image using a camera device installed in the facility. The information processing device 10 estimates a disease risk score based on the facial image of the customer. The information processing device 10 then suggests products and services offered by the commercial facility based on the disease risk score. For example, if the customer has high blood pressure, the information processing device 10 can suggest a food for specified health use that has the effect of lowering blood pressure. By referring to the disease risk score and the content of the proposal, the commercial facility staff or the customer can identify services and products that are suitable for the customer.

[0080] The proposals shown above are merely examples and are not limited to these.

[0081] (Variation 4) The functional configuration of the information processing device 10 may include an insurance premium calculation unit 104 in addition to the face image data acquisition unit 101, the disease risk estimation unit 102, and the proposal unit 103. The insurance premium calculation unit 104 is an example of an insurance premium calculation means.

[0082] 7 is a block diagram showing the functional configuration of the information processing device 10a according to Modification 2. The insurance premium calculation unit 104 receives the judgment results of each disease risk from the disease risk estimation unit 102 and the proposal content from the proposal unit 103.

[0083] The insurance premium calculation unit 104 can review the insurance premiums for the insurance that the insured person has subscribed to. For example, the insurance premium calculation unit 104 may determine a coefficient according to each disease risk score and calculate the insurance premium by multiplying the current insurance premium by the coefficient. The coefficient is set in advance by the life insurance company. It is assumed that the life insurance company sets a coefficient for each insurance product according to the combination of each disease risk score. Note that the insurance premium calculation method shown above is an example and is not limited to this.

[0084] Furthermore, the insurance premium calculation unit 104 can calculate the insurance premium for the insurance product input from the proposal unit 103. For example, the insurance premium calculation unit 104 can calculate the insurance premium so that the lower the disease risk score, the lower the premium, and so that the higher the disease risk score, the higher the premium.

[0085] In addition, the insurance premium calculation unit 104 may refer to the insured person's disease risk score from the past to the present, and if the disease risk score remains high, may propose to the life insurance company to increase the insurance premium, or if the disease risk score decreases, may propose to the life insurance company to discount the insurance premium or provide special benefits.

[0086] (Variation 5) The information processing device 10 of the first embodiment transmits a proposal suitable for the insured person to the life insurance company. Alternatively, the information processing device 10 may provide the disease risk score of the insured person to the life insurance company.

[0087] Fig. 8 is a diagram conceptually illustrating a health management system 1x in Modification 5. Fig. 8 includes a terminal device 5a of the insured person, a terminal device 5b of the family member, an information processing device 10x, and a terminal device 20a of the life insurance company. It is assumed that a self-care application program provided by the information processing device 10x is installed on the terminal device 5a of the insured person and the terminal device 5b of the family member.

[0088] The insured person takes a facial image via the self-care app and transmits the facial image to the information processing device 10x. The insured person may also perform a self-check via the self-care app and transmit the answer to the information processing device 10x. The self-check includes, for example, a self-check regarding cognitive function.

[0089] The information processing device 10x calculates a disease risk score based on the facial image of the insured person. Then, the information processing device 10 stores the disease risk score in the DB in association with the insured person ID. Note that, if there is a response to the self-check, the information processing device 10 may, for example, assign a weight set according to the content of the self-check to the disease risk score determined from the facial image of the insured person, to calculate the final disease risk score of the insured person.

[0090] The person in charge of the life insurance company accesses the information processing device 10 via the terminal device 20a and refers to the disease risk score of the insured person. The person in charge of the life insurance company determines content suitable for the insured person based on the disease risk score. The person in charge of the life insurance company provides the determined content to the terminal device 5a.

[0091] The insured person and his / her family members can also refer to the disease risk score of the insured person via the terminal devices 5a and 5b, which allows the insured person's family members to understand the health condition of the insured person.

[0092] Second Embodiment 9 is a block diagram showing the functional configuration of an information processing apparatus according to Embodiment 2. The information processing apparatus 200 includes a face image data acquisition unit 201, a disease risk estimation unit 202, and a suggestion unit 203.

[0093] 10 is a flowchart of processing by the information processing device of the second embodiment. The face image data acquisition means 201 acquires a face image of the subject (step S201). The disease risk estimation means 202 estimates a disease risk score including a mental disease risk score, a brain disease risk score, and a body disease risk score based on the face image of the subject (step S202). The suggestion means 203 determines the content of a suggestion to the subject based on a combination of the mental disease risk score, the brain disease risk score, and the body disease risk score (step S203).

[0094] According to the information processing device 200 of the second embodiment, it is possible to make optimal suggestions according to the health condition of each individual, thereby enabling the information processing device 200 to provide services and products that are optimized for each individual.

[0095] Although the present disclosure has been described above with reference to the embodiments and examples, the present disclosure is not limited to the above-described embodiments and examples. Various modifications that can be understood by a person skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure. [Explanation of symbols]

[0096] 1. Health Management System 5, 20 Terminal equipment 10. Information processing equipment 15 Database (DB) 101 Facial image data acquisition unit 102 Disease Risk Estimation Department 103 Proposal Department 104 Insurance Premium Calculation Department

Claims

1. A facial image data acquisition means for acquiring a facial image of a subject; a disease risk estimation means for estimating a disease risk score including a mental disease risk score, a brain disease risk score, and a body disease risk score based on the facial image of the subject; A suggestion means for determining a suggestion to the subject based on a combination of the mental disease risk score, the brain disease risk score, and the body disease risk score; An information processing device comprising:

2. The information processing device according to claim 1 , further comprising insurance premium calculation means for calculating an insurance premium for the subject based on the disease risk score.

3. A storage means for storing past data including a past facial image of the subject and a past disease risk score, The disease risk estimation means predicts a future disease risk score of the subject using a first machine learning model configured to input past data and output a future disease risk score; The information processing device according to claim 1 , wherein the suggestion means determines the content of the suggestion to the subject based on the future disease risk score.

4. the disease risk estimation means estimates values ​​of health items of the subject based on the facial image of the subject, and determines the disease risk score based on the estimated values ​​of the health items; The information processing device according to claim 1 , wherein the health items include drowsiness, concentration level, stress, cognitive function, and vital signs.

5. The mental illness risk score is determined based on at least one item of the subject's sleepiness, concentration, and stress, The brain disease risk score is determined based on at least one item of the subject's sleepiness, concentration, and cognitive function, The information processing device according to claim 4 , wherein the physical disease risk score is determined based on at least one of sleepiness and vital signs of the subject.

6. The information processing device according to claim 4 , wherein the disease risk estimation means estimates the disease risk score of the subject using a second machine learning model configured to input values ​​of health items and output a disease risk score.

7. 3. The information processing device according to claim 2, wherein the insurance premium calculation means reviews the insurance premium based on a past disease risk score and a current disease risk score.

8. The proposed content is a product or service that will help maintain or improve the health of the subject, The information processing apparatus according to claim 1 , wherein the suggesting unit transmits the content of the suggestion to a terminal device of the target person.

9. 1. A computer-implemented information processing method, comprising: Acquire the target person's facial image, Based on the facial image of the subject, a disease risk score including a mental disease risk score, a brain disease risk score, and a body disease risk score is estimated; An information processing method that determines the content of suggestions to be made to the subject based on a combination of the mental disease risk score, the brain disease risk score, and the body disease risk score.

10. Acquire the target person's facial image, Based on the facial image of the subject, a disease risk score including a mental disease risk score, a brain disease risk score, and a body disease risk score is estimated; A program that causes a computer to execute a process of determining the content of suggestions to be made to the subject based on a combination of the mental disease risk score, the brain disease risk score, and the body disease risk score.

Images