WO2023189853A1 - Health state determination method and health state determination system - Google Patents

Abstract

This health state determination method includes: a first acquisition step (S40) for acquiring reference characteristics for determining the health state of a subject, the reference characteristics indicating the relationship between a first index and a second index, each of which is an index relating to a person's health or comfort felt by a person; and a control step (S44 or S52) for presenting, to the subject, a menu for improving the health state, on the basis of data indicating the subject's current health state and health state determination criteria for a class to which the subject belongs, determined on the basis of the acquired reference characteristics.

Description

Health status determination method and health status determination system

The present invention relates to a health condition determination method and a health condition determination system.

In recent years, interest in health has increased. As a technique for understanding a person's health condition, Patent Document 1 discloses a biological information measuring device that can quickly determine the condition of a person using a simple method.

JP2016-52463A

The present invention provides a health condition determination method and a health condition determination system that can support improvement of a subject's health condition.

A health condition determination method according to one aspect of the present invention is a health condition determination method executed by a computer, and includes reference characteristics for determining a subject's health condition, each of which is based on the person's health or how the person feels. a first acquisition step of acquiring a reference characteristic indicating a relationship between a first index and a second index that are indicators related to comfort; and based on data indicating the current health condition of the subject and the acquired reference characteristic. The method includes a control step of presenting a menu for improving a health condition to the subject or executing the menu based on determined criteria for a health condition in a class to which the subject belongs.

A health condition determination system according to one aspect of the present invention provides a first index and a second index, each of which is a reference characteristic for determining a subject's health condition and is an index related to a person's health or comfort felt by the person. an acquisition unit that acquires a reference characteristic indicating a relationship between the above, data indicating the current health condition of the subject, and a criterion for determining a health condition in a class to which the subject belongs, which is determined based on the acquired reference characteristic; and a control unit that presents a menu for improving the health condition to the subject or executes the menu based on the above.

A health condition determination method and a health condition determination system according to one aspect of the present invention can support improvement of a subject's health condition.

FIG. 1 is a diagram showing the functional configuration of a health condition determination system according to an embodiment. FIG. 2 is a diagram showing a first example of a master curve. FIG. 3 is a flowchart of the master curve generation operation of the health condition determination system according to the embodiment. FIG. 4 is a first diagram for explaining another example of the master curve x and the master curve y. FIG. 5 is a second diagram for explaining another example of the master curve x and the master curve y. FIG. 6 is a diagram showing a second example of the master curve. FIG. 7 is a diagram showing a third example of the master curve. FIG. 8 is a diagram showing a fourth example of the master curve. FIG. 9 is a diagram showing an example of setting a plurality of classes. FIG. 10 is a flowchart of the operation for determining which class a subject belongs to. FIG. 11 is a flowchart of operations that support improvement of the subject's health condition.

Hereinafter, embodiments will be specifically described with reference to the drawings. Note that the embodiments described below are all inclusive or specific examples. The numerical values, shapes, materials, components, arrangement positions and connection forms of the components, steps, order of steps, etc. shown in the following embodiments are merely examples, and do not limit the present invention. Further, among the constituent elements in the following embodiments, constituent elements that are not described in the independent claims will be described as arbitrary constituent elements.

Note that each figure is a schematic diagram and is not necessarily strictly illustrated. Furthermore, in each figure, substantially the same configurations are denoted by the same reference numerals, and overlapping explanations may be omitted or simplified.

(Embodiment)
[composition]
First, the configuration of a health condition determination system according to an embodiment will be described. FIG. 1 is a block diagram showing the functional configuration of a health condition determination system according to an embodiment.

The health condition determination system 10 is a system for determining the health condition of a subject. As shown in FIG. 1, the health condition determination system 10 includes a server device 20, a plurality of sensors 31, a first information terminal 40, a control device 51, an environment adjustment device 52, a sensor 53, and a second information terminal 40. It includes an information terminal 60 and a third information terminal 70. Further, in FIG. 1, a plurality of facilities 30 and a plurality of facilities 50 are also illustrated. Although the facility 30 and the facility 50 are distinguished for convenience of explanation, the facility 50 may be included in a plurality of facilities 30.

The server device 20 is a computer that performs information processing to determine the health condition of the subject. The server device 20 includes a communication section 21, an information processing section 22, and a storage section 23.

The communication unit 21 allows the server device 20 to communicate with the plurality of sensors 31, the first information terminal 40, the control device 51, the second information terminal 60, and the third information terminal 70 via a wide area communication network 80 such as the Internet. This is a communication circuit (communication module) for performing the following. The communication unit 21 is, for example, a wireless communication circuit that performs wireless communication, but may also be a wired communication circuit that performs wired communication. There are no particular limitations on the communication standard for communication performed by the communication unit 21.

The information processing unit 22 performs information processing to determine the health condition of the subject. The information processing unit 22 is implemented, for example, by a microcomputer, but may also be implemented by a processor. The information processing section 22 includes an acquisition section 24, a calculation section 25, a determination section 26, a control section 27, a verification section 28, and an analysis section 29 as functional components. The functions of the acquisition section 24, the calculation section 25, the determination section 26, the control section 27, the verification section 28, and the analysis section 29 are performed by, for example, a microcomputer or a processor constituting the information processing section 22 stored in the storage section 23. This is achieved by executing a computer program.

The storage unit 23 is a storage device in which computer programs and the like executed by the information processing unit 22 are stored. The storage unit 23 is realized by, for example, a semiconductor memory.

The sensor 31 is provided in each of the plurality of facilities 30 and senses people located within the facility 30 in a non-contact manner. The sensor 31 is, for example, a non-contact vital sensor such as a radio wave sensor, but may also be a camera (image sensor) or the like. The sensor 31 may be a contact-type vital sensor, such as a mat-like (sheet-like) sensor, that performs sensing by contacting a person located within the facility 30, and the specific form of the sensor 31 is not particularly limited. . As will be described later, when a parameter related to the comfort felt by a person is used to generate a master curve (for example, a parameter that indicates whether a person is comfortable or uncomfortable in two or more levels), the sensor 31 is configured to measure the environment rather than the person. It may also be a sensor that senses the To supplement the method for obtaining parameters related to comfort, parameters related to comfort may be obtained by manually inputting subjective evaluation results, or may be obtained by manually inputting subjective evaluation results, or by determining whether a person feels uncomfortable due to a change in the settings of the environment adjustment device 52. It may be considered. Note that at least one sensor 31 may be provided in each of the plurality of facilities 30, and two or more sensors 31 may be provided in one facility 30.

The first information terminal 40 is held by a person and measures biometric data of the person. The first information terminal 40 includes, for example, a pulse wave sensor, a blood pressure sensor, a sweat sensor, a body temperature sensor, a breathing sensor, an activity sensor, an electroencephalogram sensor, and the like. That is, the first information terminal 40 measures biological data such as the subject's pulse wave, blood pressure, amount of perspiration, body temperature, respiration, amount of activity, and brain waves. The first information terminal 40 is, for example, a wristband-shaped or wristwatch-shaped information terminal worn on the wrist of the subject, but may also be an earhook-shaped information terminal. Further, the first information terminal 40 is not limited to such a wearable information terminal, but may be a portable information terminal such as a smartphone or a tablet terminal, which has a sensor as described above.

The control device 51 is provided in a facility 50 where the subject is located, and controls the environment adjustment device 52 based on the determination result of the subject's health condition. As the control device 51, for example, an EMS (Energy Management System) controller having a function of managing power consumption in the facility 50 is used, but other controllers without a function of managing power consumption may be used. Good too.

The environment adjustment device 52 is installed in the facility 50 where the subject is located, and controls the environment around the subject. Specifically, the environment adjustment device 52 is a lighting device, an air conditioner, an air blower, a ventilation device, a scent generator, a speaker device, and the like. That is, the environment adjustment device 52 adjusts (controls) light, temperature, airflow, carbon dioxide concentration, scent, sound, etc. around the subject. When the facility 50 is a residence, the environment adjustment device 52 is provided in an indoor space such as a living room, a bathroom, a bedroom, or a toilet in the facility 50, and adjusts the environment in these indoor spaces.

The sensor 53 is installed in the facility 50 where the subject is located, and senses the subject. The sensor 53 is, for example, a non-contact vital sensor such as a radio wave sensor, but may also be a camera (image sensor) or the like. The sensor 53 may be a contact-type vital sensor, such as a mat-like (sheet-like) sensor, that performs sensing by contacting a person located within the facility 50, and the specific form of the sensor 53 is not particularly limited. . As will be described later, when a parameter related to comfort felt by a person is used to generate a master curve, the sensor 53 may be a sensor that senses the environment rather than the person. Note that at least one sensor 53 may be provided in the facility 50, and two or more sensors 53 may be provided in one facility 50.

The second information terminal 60 is held by the subject and measures biometric data of the subject. The second information terminal 60 includes, for example, a pulse wave sensor, a blood pressure sensor, a sweat sensor, a body temperature sensor, a breathing sensor, an activity sensor, an electroencephalogram sensor, and the like. That is, the second information terminal 60 measures biological data such as the subject's pulse wave, blood pressure, amount of perspiration, body temperature, respiration, amount of activity, and brain waves. The second information terminal 60 is, for example, a wristband-shaped or wristwatch-shaped information terminal worn on the wrist of the subject, but may also be an earhook-shaped information terminal. Further, the second information terminal 60 is not limited to such a wearable information terminal, but may be a portable information terminal such as a smartphone or a tablet terminal, which has a sensor as described above.

The third information terminal 70 is an information terminal that the subject uses as a user interface of the health status determination system 10, and specifically, the third information terminal 70 is an information terminal that the subject uses as a user interface for the health status determination system 10. It is an information terminal. The third information terminal 70 is, for example, a portable information terminal such as a smartphone or a tablet terminal, but may also be a stationary information terminal such as a personal computer.

The third information terminal 70 is, for example, a general-purpose information terminal, and has a dedicated application program installed thereon so that it can receive notifications (notification information described below) about health condition determination results from the server device 20. . Note that in this specification, for convenience, the second information terminal 60 and the third information terminal 70 are distinguished as different information terminals, but the second information terminal 60 and the third information terminal 70 are different information terminals. It is not necessary and may be a single information terminal.

[Master curve generation operation]
In order to determine the health condition of a subject, the health condition determination system 10 calculates in advance a reference characteristic called a master curve, and stores the calculated master curve in the storage unit 23 of the server device 20. FIG. 2 is a diagram showing an example of a master curve.

The master curve shown in Figure 2 is a two-dimensional coordinate (in other words, a coordinate space) in which the horizontal axis (also referred to as ) is a curve showing the relationship between the amount of activity and the amount of food. The operation of generating such a master curve will be described below. FIG. 3 is a flowchart of the master curve generation operation.

First, the acquisition unit 24 of the server device 20 acquires the amount of activity of each of a plurality of people (S11). The amount of activity is an example of first data indicating a first index regarding the subject's health or the comfort felt by the subject. The amount of activity can be expressed as the amount of calories consumed. For example, the acquisition unit 24 acquires the amount of activity measured by the first information terminal 40, which the communication unit 21 receives from the first information terminal 40. When the amount of activity can be sensed by the sensor 31, the acquisition unit 24 may acquire the amount of activity sensed by the sensor 31 (the amount of activity determined by the sensing result). In this case, the acquisition unit 24 acquires the amount of activity that the communication unit 21 receives from the sensor 31. Note that the amount of activity here is, for example, the amount of activity over a predetermined period such as about several hours or one day (24 hours).

Next, the acquisition unit 24 acquires the amount of meals of each of the plurality of people (S12). The amount of food is an example of second data indicating a second index regarding the subject's health or the comfort felt by the subject. The amount of food can be expressed as calorie intake.

For example, the acquisition unit 24 acquires the amount of meal measured by the first information terminal 40, which the communication unit 21 receives from the first information terminal 40. There is a known technology for estimating calorie intake by measuring the movement of body fluids into and out of body cells using a bioimpedance sensor included in a wristwatch-shaped wearable terminal. Measure (estimate) the amount of food you eat using technology.

If the sensor 31 is a camera installed in a dining area of the facility 30 and can sense (estimate) the amount of food, the acquisition unit 24 detects the amount of food sensed by the sensor 31 (the amount of food determined by the sensing result). amount) may be obtained. In this case, the acquisition unit 24 acquires the amount of food that the communication unit 21 receives from the sensor 31. Note that the amount of meals here is, for example, the amount of meals per meal or per day.

In order to generate a master curve, it is necessary to link the amount of activity and the amount of food consumed by the same person. For example, when both the amount of activity and the amount of food are acquired from the first information terminal 40, the acquisition unit 24 acquires the amount of activity and the amount of food at the same time (during the same communication). It is possible to link a person's activity level with the amount of food they eat. When the first information terminal 40 transmits the amount of activity and meal amount with the identification information of the first information terminal 40 attached, the acquisition unit 24 transmits the amount of activity and meal amount of the same person based on the identification information. can be linked to the amount of

Further, when both the amount of activity and the amount of food are acquired from the sensor 31, the acquisition unit 24 acquires the amount of activity and the amount of food at the same time (during the same communication), thereby improving the activity of the same person. It is possible to link the quantity with the amount of food. In this case, it is assumed that the sensor 31 is installed in a private room or the like so that the sensor 31 senses the amount of activity and meal of a specific individual. Further, under such a premise, if the sensor 31 transmits the amount of activity and the amount of food with the identification information of the sensor 31 attached, the acquisition unit 24 can calculate the activity of the same person based on the identification information. It is possible to link the quantity with the amount of food.

When one of the amount of activity and the amount of food is acquired from the first information terminal 40 and the other from the sensor 31, the identification information of the first information terminal 40 held by a person and the person as the sensing target are determined. By storing information indicating the correspondence with the identification information of the sensor 31 in advance in the storage unit 23, the amount of activity and the amount of meals can be linked.

Note that it is not essential that the amount of activity and the amount of meals be acquired from the first information terminal 40 or the sensor 31. For example, the information may be provided to the server device 20 from another server device that manages information in which the amount of activity and the amount of meals are paired, and the acquisition unit 24 may acquire this information. Further, the acquisition unit 24 may acquire information in which the amount of activity and the amount of meals are paired, which is manually input to the server device 20 through a user interface device (not shown).

Next to step S12, the calculation unit 25 calculates a master curve based on the acquired activity amounts and meal amounts for a plurality of people (S13). The master curve is an example of a reference characteristic that is a reference characteristic for determining a subject's health condition and indicates the relationship between the first index indicated by the master curve x and the second index indicated by the master curve y.

The calculation unit 25 plots points determined by the linked activity amount and meal amount on the above two-dimensional coordinates for the number of acquired activity amount and meal amount data (that is, for the number of people), A master curve is calculated by applying an approximation formula to multiple plotted points. There is no particular limitation on what kind of approximation formula to apply, and various existing approximation formulas may be applied.

Next, the calculation unit 25 sets an upper limit curve and a lower limit curve (shown in FIG. 3) with respect to the master curve based on the master curve (S14). The calculation unit 25 calculates, for example, that the upper limit curve and the lower limit curve are criteria used in determining the health condition using the master curve. The calculation unit 25 sets an upper limit curve and a lower limit curve for the master curve, for example, based on the variation (standard deviation) of the data on which the master curve is based. The calculation unit 25 may be manually input to the server device 20 by the designer of the health condition determination system 10 through a user interface device (not shown). Note that depending on the type of master curve, only one of the upper limit curve and the lower limit curve may be set.

Further, the calculation unit 25 stores the calculated master curve, the set upper limit curve, and the set lower limit curve in the storage unit 23 (S15).

In this way, the health condition determination system 10 can calculate a master curve based on the amount of activity and meal amount for multiple people and store it in the storage unit 23.

In addition, when at least one of the amount of activity and the amount of food is determined based on the sensing results of the sensor 31 installed in the facility 30, the health condition can be determined by sensing in multiple types of facilities 30. A suitable master curve can be calculated.

For example, if the multiple types of facilities 30 include hospitals, nursing care facilities, general housing, and training facilities, people hospitalized in hospitals, people living in nursing facilities, people living in housing, and training facilities It is possible to obtain the amount of activity and amount of food consumed by people using the facility. In other words, data on the amount of activity and food intake from people in poor health to those in good health is available. More specifically, as shown in Figure 3, people who require care, people who are being treated for illness, people who are not sick, people who are healthy, people who are training (healthier people), and athletes. Data on the amount of activity and amount of food consumed by (even more healthy people) is available. It can be said that the master curve calculated based on the amount of activity and the amount of food eaten by people with a wide variety of health conditions is suitable for determining health conditions.

Note that the amount of activity is an example of the master curve x (first data), and the amount of meals is an example of the master curve y (second data). Other first indicators relating to health or comfort may be used as the master curve x, and other second indicators relating to health or comfort may be used as the master curve y. As the master curve x and the master curve y, two types of indicators that have a certain degree of correlation and are not the same may be used. FIG. 4 is a diagram for explaining another example of the master curve x and the master curve y.

In the example of FIG. 4, by using a radio wave sensor as the sensor 31, the acquisition unit 24 acquires multiple types of parameters that can be used as the master curve x from the sensing results of the sensor 31. Specifically, LF (Low Frequency)/HF (High Frequency), heart rate variability parameters, and heart rate can be acquired based on RRI (RR Interval), which is the sensing result of the radio wave sensor.

LF/HF is the LF component (e.g., 0.05Hz to 0.15Hz component) and HF component (e.g., 0.15Hz to 0.40Hz component) of the power spectrum obtained by frequency analysis of RRI. This is a parameter indicating the ratio of When the acquisition unit 24 acquires LF/HF as the master curve x, the acquisition unit 24 acquires parameters related to comfort, parameters related to relaxation level, parameters related to stress, parameters related to manic depression, and concentration level as master curve y. , parameters related to sleep, parameters related to frailty, parameters related to MCI (Mild Cognitive Impairment), parameters related to vascular age, parameters related to ovulation day, etc. These parameters may be acquired based on the sensing results of the sensor 31, measured by the first information terminal 40, the results of subjective evaluation (questionnaire, etc.), the results of a predetermined test, etc. may be obtained based on.

The heart rate variability parameter is a time domain parameter determined based on the RRI. Specifically, the heart rate variability parameter here is SDNN (Standard deviation of all RR interval) or RMSSD (Root Mean Square of Successive Differ). ences), etc. When the acquisition unit 24 acquires these heart rate variability parameters as the master curve x, it acquires parameters related to hypertension, hyperglycemia, or high lipids as the master curve y. These parameters may be acquired based on the sensing results of the sensor 31, measured by the first information terminal 40, or based on the results of subjective evaluation (questionnaire etc.).

The heart rate is a parameter that is determined based on the RRI and indicates the number of times the heart beats per minute. When the acquisition unit 24 acquires the heart rate as the master curve x, the acquisition unit 24 acquires a parameter related to the amount of activity, a parameter related to the quality of the meal, etc. as the master curve y. These parameters may be acquired based on the sensing results of the sensor 31, measured by the first information terminal 40, or based on the results of subjective evaluation (questionnaire etc.).

Further, FIG. 5 is a diagram for explaining still another example of the master curve x and the master curve y. FIG. 5 shows two parameter sets that can be used as the master curve x and the master curve y (whichever one can be used as the master curve x(y)). Such parameter sets include a set of parameters related to comfort and parameters related to degree of relaxation. In addition, such a set of parameters includes parameters related to sleep, activity level, diet quality, stress, MCI, hyperglycemia (diabetes), and hormonal cancer (prostate cancer, breast cancer). This includes a pair of associated parameters. Further, the set of parameters as described above includes a set of a parameter related to either MCI or hyperglycemia, and a parameter related to frailty.

Specific examples of master curves using the parameters shown in FIGS. 4 and 5 include master curves shown in FIGS. 6 to 8. FIG. 6 is a diagram showing an example of a master curve showing the relationship between LF/HF and sleep quality (sleep depth). FIG. 7 is a diagram showing an example of a master curve showing the relationship between the daily sleeping hours of people under the age of 50 and the incidence of MCI when the person becomes 60 years of age or older. The horizontal axis indicates that the sleeping time is shorter on the right side. FIG. 8 is a diagram showing an example of a master curve showing the relationship between LF/HF and the incidence of manic depression.

Furthermore, the parameters that can be used as the master curve x (first data) described above are merely examples. The master curve x may be any parameter that indicates the first index related to a person's health (including beauty) or comfort felt by the person, and specifically includes heart rate, pulse, flow line, amount of activity, sleep, posture, Any parameter may be used as long as it is related to at least one of skin, skin, and facial expression. Note that the master curve x may be a parameter indicating a human physiological index.

Similarly, the parameters that can be used as the master curve y (second data) described above are merely examples. The master curve y may be any parameter that indicates a second index related to a person's health (including beauty) or the comfort that a person feels. Any parameter may be used as long as it is related to at least one of function, body shape, aging, pre-illness, illness, treatment, and nursing.

As explained above, the health condition determination system 10 acquires first data and second data for a plurality of people, each of which indicates an index related to a person's health or the comfort felt by the person, and Based on the first data and the second data, a master curve ( Standard characteristics) are calculated, and an upper limit curve and a lower limit curve, which are criteria for determining the subject's health condition, are set for the master curve. The calculated master curve, the set upper limit curve, and the set lower limit curve are stored in the storage unit 23.

Note that the reference characteristic does not necessarily have to be a curve, and may be a straight line. The same applies to the judgment criteria. Further, the master curve may be calculated (generated) by a designer of the health condition determination system 10 or the like, and stored (registered) in the storage unit 23.

[Determination of the class to which the target person belongs]
Next, the operation of dividing the master curve into a plurality of classes and determining which class a subject belongs to will be explained. For example, the calculation unit 25 sets multiple classes for the master curve. FIG. 9 is a diagram showing an example of setting a plurality of classes. In the example of FIG. 9, the plurality of classes are set according to the amount of activity, and include 15 classes from class A to class O. A class can also be referred to as a segment. In the following description, a predetermined range (an upper limit curve and a lower limit curve) and a master curve in which a class is set are defined as reference characteristics.

FIG. 10 is a flowchart of the operation for determining which class the target person belongs to. The acquisition unit 24 of the server device 20 acquires the amount of activity of the subject (S31). For example, the acquisition unit 24 acquires the amount of activity measured by the second information terminal 60, which the communication unit 21 receives from the second information terminal 60. When the amount of activity can be sensed by the sensor 53, the acquisition unit 24 may acquire the amount of activity sensed by the sensor 53 (the amount of activity determined by the sensing result). In this case, the acquisition unit 24 acquires the amount of activity that the communication unit 21 receives from the sensor 53. The acquisition unit 24 may acquire the amount of activity manually input into the third information terminal 70 by the subject from the third information terminal 70.

Next, the determining unit 26 determines to which class the target person belongs, from class A to class O, based on the target person's activity amount obtained in step S31 (S32). The determination unit 26 may determine the class of the subject by majority vote by performing determination multiple times based on the amount of activity acquired in different periods.

[Operations to support improvement of health condition]
The health condition determination system 10 can perform operations that support improvement of the subject's health condition. Hereinafter, such an operation will be explained with reference to FIG. 11. FIG. 11 is a flowchart of operations that support improvement of the subject's health condition.

In the following description of FIG. 11, it is assumed that the class (segment) of the subject has been determined in advance by the class determination operation described above. In order to simplify the explanation, it is assumed that only one predetermined range defined by an upper limit curve and a lower limit curve is set for each class. The predetermined range is, for example, a range in which the upper limit is the average value of the values indicated by the upper limit curve, and the lower limit is the average value of the values indicated by the lower limit curve.

Specifically, for class A, a first predetermined range determined by a first upper limit value and a first lower limit value is set, and for class B, a first predetermined range determined by a second upper limit value and a second lower limit value is set. A second predetermined range is set, and so on. Different predetermined ranges are set for each class. In other words, the predetermined range is a criterion. The predetermined range set for each class is stored in the storage unit 23 in advance.

First, the acquisition unit 24 of the server device 20 acquires the master curve from the storage unit 23 (S40). Specifically, the acquisition unit 24 acquires the master curves shown in FIGS. 2 and 9.

Next, the acquisition unit 24 acquires the amount of meals of the subject (S41). The amount of food is an example of data indicating the subject's health condition. For example, the acquisition unit 24 acquires the amount of meal measured by the second information terminal 60, which the communication unit 21 receives from the second information terminal 60. If the sensor 53 is a camera installed in a dining area of the facility 50 and can sense (estimate) the amount of food, the acquisition unit 24 detects the amount of food sensed by the sensor 53 (the amount of food determined by the sensing result). amount) may be obtained. In this case, the acquisition unit 24 acquires the amount of food that the communication unit 21 receives from the sensor 53. The acquisition unit 24 may acquire from the third information terminal 70 the amount of meals manually input into the third information terminal 70 by the subject.

Next, the determination unit 26 determines whether the amount of food of the subject obtained in step S41 is outside the predetermined range set for the class to which the subject belongs (S42). The process in step S42 corresponds to the process of determining the health condition of the subject. As described above, the predetermined range is stored in the storage unit 23 in advance. Note that the class of the target person is stored in the storage unit 23 in association with a user account (a user account linked to a dedicated application program described later) for the target person to receive services through the health condition determination system 10, for example. is stored in

Note that "outside the predetermined range" in step S42 basically assumes that it is outside a wide upper limit value and a wide lower limit value within the class. If classes are not used, pinpoint upper and lower limits may be used. However, if the class is not used, the process of reviewing the class in step S48 is omitted.

First, in step S42, the operation when the determination unit 26 determines that the acquired amount of the subject's meal is outside the predetermined range (Yes in S42) will be described. In this case, the control unit 27 notifies the subject regarding the health condition (in other words, alerts) (S43). Specifically, the control unit 27 generates notification information and causes the communication unit 21 to transmit the generated notification information to the third information terminal 70. On the display of the third information terminal 70 that has received the notification information, a notification screen for notifying the deterioration of the health condition (inappropriate amount of meals) is displayed. The process of the third information terminal 70 receiving notification information and displaying a notification screen based on the received notification information is realized, for example, by installing a dedicated application program in the third information terminal 70 in advance.

This notification screen (notification information) includes a menu for improving the target person's activities. That is, the control unit 27 aims to correct the health condition (optimize the amount of food) by presenting (recommending) a menu for improving the subject's activities (S44).

A plurality of types of improvement menus are prepared in advance in the storage unit 23, and are selected from the plurality of types based on, for example, the position of a point indicating the amount of food of the subject in two-dimensional coordinates. The improvement menu is based on at least one data indicating the subject's resting state of health (not limited to the amount of food, but at least one of the above-mentioned first index and second index). It may be selected from among them. The selection algorithm for the improvement menu is determined, for example, by the designer of the health condition determination system 10, but may also be determined by a machine learning model or the like.

Thereafter, the determination unit 26 determines whether the activity improvement menu presented in step S44 has been executed (S45). For example, when the subject executes the activity improvement menu, the subject makes a predetermined input to the third information terminal 70, and the determination unit 26 determines whether the activity improvement menu is executed depending on the presence or absence of such a predetermined input. Determine whether or not. Further, when the activity improvement menu is a menu related to the number of steps or sleep time, the determination unit 26 determines whether the activity improvement menu is executed by acquiring sensing results from the sensor 53 or the second information terminal 60. It is possible to determine whether or not the

If the determination unit 26 determines that the activity improvement menu has been executed (Yes in S45), it determines whether the subject's meal amount has returned to the above-mentioned predetermined range (S46). The process in step S46 corresponds to the process of determining the health condition of the subject. Specifically, the determination unit 26 performs the same processing as step S41 and step S42. If the determining unit 26 determines that the amount of food eaten by the subject has returned to within the predetermined range (Yes in S46), the operation ends. On the other hand, if the determination unit 26 determines that the amount of food of the subject has not returned to the predetermined range (No in S46), it is determined whether the cumulative number of notifications in step S43 exceeds the upper limit number. (S47). In other words, the cumulative number of notifications in step S43 is the number of times it has been determined that the amount of food is outside a predetermined range (not appropriate).

If the determination unit 26 determines that the cumulative number of notifications does not exceed the upper limit (No in S47), a notification regarding the health condition in step S43 is performed (S43). On the other hand, if the determination unit 26 determines that the cumulative number of notifications exceeds the upper limit (S47: Yes), the control unit 27 reviews the class to which the target person belongs (S48). In other words, if the subject's health condition frequently deteriorates or if the subject's health condition continues to deteriorate, the control unit 27 suspects that the class determination is inappropriate and determines the class. Attempt to review. Specifically, the control unit 27 changes the class from one of classes A to O to another by performing the class determination operation in FIG. 10 again, but the algorithm for reviewing the class is particularly limited. Not done.

After the process of step S48, the control unit 27 notifies the verification unit 28 that the cumulative number of notifications to the target person has exceeded the upper limit (S49). When the target person is notified that the number of notifications has exceeded the upper limit, the cumulative number of notifications is reset to zero. Note that even if it is determined in step S45 that the activity improvement menu was not executed by the subject (No in S45), the control unit 27 verifies that the activity improvement menu was not executed by the subject. Notify department 28.

In this way, in the health condition determination system 10, the control unit 27 controls the subject person when it is determined that the value of the data indicating the subject's health condition (the amount of food in FIG. 9) is outside the predetermined range. Present a menu of improvement activities. Here, the determination unit 26 determines whether or not the data value is outside the predetermined range multiple times, and the control unit 27 determines whether the data value is outside the predetermined range based on the number of times it is determined that the data value is outside the predetermined range. Then, the class to which the subject belongs is corrected (reviewed) and the verification unit 28 is notified. More specifically, the control unit 27 determines the number of times it was determined that the data value was outside the predetermined range and the data value did not return to within the predetermined range even after executing the activity improvement menu. Based on this, the verification unit 28 is notified.

Such a health condition determination system 10 can improve the health condition of the target person by presenting the target person with an activity improvement menu, and can also review the class to which the target person belongs.

Next, in step S42, the operation when the determination unit 26 determines that the acquired amount of the subject's meal is within the above-mentioned predetermined range (No in S42) will be described. In this case, the determination unit 26 determines whether or not the variation in the amount of meals is large (S50). For example, the determination unit 26 considers the difference between the maximum amount and the minimum amount of food over a predetermined period such as one week as the magnitude of the fluctuation, and determines that the fluctuation is large when the difference exceeds a threshold value. It is determined that the fluctuation is small when is less than or equal to the threshold value. Further, the determination unit 26 calculates the variation (standard deviation or variance) in the amount of meals over a predetermined period, and determines that the variation is large when the calculated variation exceeds a threshold value, and determines that the variation is large when the calculated variation is below the threshold value. It may be determined that the fluctuation is small.

If the determination unit 26 determines that the obtained amount of the subject's meal is within the above-mentioned predetermined range but the fluctuation is large (Yes in S50), the control unit 27 sends a notification ( In other words, an alert) is performed (S51). Specifically, the control unit 27 generates notification information and causes the communication unit 21 to transmit the generated notification information to the third information terminal 70. On the display of the third information terminal 70 that has received the notification information, a notification screen is displayed to notify that there is a tendency for the health condition to deteriorate (the amount of food fluctuates greatly). The process of the third information terminal 70 receiving notification information and displaying a notification screen based on the received notification information is realized, for example, by installing a dedicated application program in the third information terminal 70 in advance.

This notification screen (notification information) includes a menu for improving the environment around the target person. That is, the control unit 27 aims to correct the health condition (suppress fluctuations in the amount of meals) by presenting (recommending) a menu for improving the surrounding environment of the subject (S52). A plurality of types of improvement menus are prepared in advance in the storage unit 23, and are selected from among the plurality of types based on, for example, the amount of variation in the amount of food eaten by the subject.

The improvement menu is based on at least one data indicating the subject's resting state of health (not limited to the amount of food, but at least one of the above-mentioned first index and second index). It may be selected from among them. The selection algorithm for the improvement menu is determined, for example, by the designer of the health condition determination system 10, but may also be determined by a machine learning model or the like.

Thereafter, the determination unit 26 determines whether the environment improvement menu presented in step S44 has been executed (S53). For example, when the subject executes the environment improvement menu, the subject makes a predetermined input to the third information terminal 70, and the determination unit 26 determines whether the environment improvement menu is executed depending on the presence or absence of such a predetermined input. Determine whether or not. Further, the determination unit 26 can also determine whether the environment improvement menu has been executed by inquiring the control device 51 about the control history (operation history) of the environment adjustment device 52.

If the determination unit 26 determines that the environment improvement menu has been executed (Yes in S53), it determines whether the fluctuation in the amount of food of the subject has been suppressed to below the threshold value (S54). The process in step S54 corresponds to the process of determining the health condition of the subject. Specifically, the determination unit 26 performs the same processing as step S41, step S42, and step S50. If the determination unit 26 determines that the variation in the amount of food of the subject has been suppressed to below the threshold value (Yes in S54), the operation ends. On the other hand, if the determination unit 26 determines that the variation in the amount of food of the subject has not been suppressed to below the threshold value (No in S54), it is determined whether the cumulative number of notifications in step S51 exceeds the upper limit number. A determination is made (S55). In other words, the cumulative number of notifications in step S51 is the number of times it has been determined that the variation in meal amount exceeds the threshold (the variation is large).

If the determination unit 26 determines that the cumulative number of notifications does not exceed the upper limit (No in S55), a notification regarding the health condition in step S51 is performed (S51). On the other hand, if the determination unit 26 determines that the cumulative number of notifications has exceeded the upper limit (Yes in S55), the control unit 27 determines that the cumulative number of notifications to the target person has exceeded the upper limit, etc. The verification unit 28 is notified (S56). When the target person is notified that the number of notifications has exceeded the upper limit, the cumulative number of notifications is reset to zero. Note that even if it is determined in step S53 that the environment improvement menu was not executed by the target person (No in S53), the control unit 27 verifies that the environment improvement menu was not executed by the target person. Notify department 28.

In this way, in the health condition determination system 10, when it is determined that the value of the data indicating the subject's health condition is within a predetermined range, a menu for improving the environment around the subject is presented. Here, when the determination unit 26 determines that the data value is within a predetermined range, it further performs determination regarding data fluctuation. The determination unit 26 performs determination regarding data fluctuations multiple times, and the control unit 27 notifies the verification unit 28 based on the number of times it is determined that the data value is within a predetermined range but the fluctuation is large. conduct. Specifically, the control unit 27 determines that the data value is within a predetermined range but the fluctuation is large, and that the data fluctuation is not suppressed even if the environment improvement menu is executed. The verification unit 28 is notified based on the number of times the verification has been performed.

Such a health condition determination system 10 can improve the health condition of the subject by presenting the subject with an environmental improvement menu.

Note that in steps S52 and S53, the environment improvement menu was executed by the subject. However, the environment improvement menu may be automatically executed by the control unit 27.

For example, the control unit 27 generates control information for realizing an environmental improvement menu determined according to the degree of variation in the amount of food eaten by the subject, and transmits the generated control information to the communication unit 21 and the control device 51. Let it be sent. The control device 51 controls the environment adjustment device 52 based on the received control information. That is, the control unit 27 (control device 51) can execute a menu for improving the environment around the subject.

[Learning the improvement menu]
According to steps S44 to S46 of the improvement support operation in FIG. 11, the health condition determination system 10 can acquire as information the change in the amount of food consumed by the subject as a result of executing the activity improvement menu. Here, the acquisition unit 24 can improve the activity by acquiring various data other than the amount of meals (data that can be acquired through the sensor 53 and the second information terminal 60) before and after executing the activity improvement menu. Information indicating the degree of influence of the improvement menu on various data can be acquired (stored in the storage unit 23).

Impact information indicating the degree of influence of such an activity improvement menu on various data (information indicating the relationship between Input/Output) can be used as learning data for a machine learning model. Specifically, by having the machine learning model learn influence information, the control unit 27 uses the machine learning model to improve the activity when selecting the activity improvement menu in step S44. Improvement menus can be selected and presented.

Note that this machine learning model may be constructed as a machine learning model customized exclusively for one target person using the influence information of a single target person, or may be constructed as a machine learning model customized exclusively for that target person, or may be constructed as a machine learning model customized exclusively for that target person using influence information of one target person, or may be constructed as a machine learning model customized exclusively for that target person using influence information of one target person, or may be constructed as a machine learning model customized exclusively for that target person using influence information of one target person, or may be constructed as a machine learning model customized only for that target person using influence information of one target person, or may be constructed as a machine learning model customized exclusively for that target person using influence information of one target person, or may be constructed as a machine learning model customized only for that target person using influence information of one target person. may be constructed as a machine learning model for subjects belonging to the same class using influence information. At least by building machine learning models for each class, it is thought that it will be possible to propose effective menus for improving activities.

Furthermore, according to steps S52 to S54, the health condition determination system 10 can acquire as information the change in the amount of food consumed due to the execution of the environmental improvement menu. Here, if the acquisition unit 24 acquires various data other than the amount of food (biological data that can be acquired through the sensor 53 and the second information terminal 60) before and after executing the environment improvement menu, the acquisition unit 24 can control The unit 27 can acquire information indicating the degree of influence of the environment improvement menu on various data (store changes in various data in the storage unit 23).

Impact information indicating the degree of influence of such an environment improvement menu on various data (information indicating the relationship between Input/Output) can be used as learning data for a machine learning model. Specifically, by having the machine learning model learn influence information, the control unit 27 uses the machine learning model to improve the environment when selecting the environment improvement menu in step S52. Improvement menus can be selected and presented.

Note that this machine learning model may be constructed as a machine learning model customized exclusively for one target person using the influence information of a single target person, or may be constructed as a machine learning model customized exclusively for that target person, or may be constructed as a machine learning model customized exclusively for that target person using influence information of one target person, or may be constructed as a machine learning model customized exclusively for that target person using influence information of one target person, or may be constructed as a machine learning model customized exclusively for that target person using influence information of one target person, or may be constructed as a machine learning model customized only for that target person using influence information of one target person, or may be constructed as a machine learning model customized exclusively for that target person using influence information of one target person, or may be constructed as a machine learning model customized only for that target person using influence information of one target person. may be constructed as a machine learning model for subjects belonging to the same class using influence information. At least by building a machine learning model for each class, it is considered possible to propose effective menus for improving the environment.

[Verification of master curve]
In step S49 of the improvement support operation in FIG. 11, the control unit 27 notifies the verification unit 28. Here, the control unit 27 notifies the verification unit 28 when the subject's health condition frequently deteriorates or when the subject's health condition continues to deteriorate. Since the curve itself may not be appropriate, it may be necessary to verify the master curve.

Therefore, the verification unit 28 may verify the master curve upon receiving the notification from the control unit 27. For example, the verification unit 28 performs at least one of a first correction process for enlarging or reducing the master curve in the vertical axis direction and a second correction process for enlarging or reducing the master curve in the horizontal axis direction. Correct.

How to perform the correction may be instructed by the administrator of the health condition determination system 10 through a user interface (not shown), or the correction may be repeated using a trial and error method. After correction is repeated several times using the trial and error method, the correction parameters (amount of enlargement or reduction) can be automatically determined using a machine learning model built using the information obtained during trial and error as learning data. It is possible.

Additionally, the verification unit 28 may correct the classification method set in the master curve. For example, the verification unit 28 corrects the number of classes to be set and the boundary values of the classes. Alternatively, the verification unit 28 integrates the current classes (in the example of FIG. 9, a total of 15 classes from class A to class O) by a predetermined number (for example, three) so as to reduce the total number of classes. You may do so.

How to perform the correction may be instructed by the administrator of the health condition determination system 10 through a user interface (not shown), or the correction may be repeated using a trial and error method. After correction is repeated several times using the trial and error method, it is also possible to automatically determine correction parameters using a machine learning model constructed using the information obtained during the trial and error as learning data.

Additionally, the verification unit 28 may correct a predetermined range (at least one of the upper limit curve and the lower limit curve) set in the master curve.

For example, the verification unit 28 widens the predetermined range so that the cases in which the determination is Yes in step S42 and the cases in which the determination is No in step S46 are reduced (the health condition is less likely to be considered to have deteriorated). (relaxing the judgment criteria).

How to make the correction may be instructed by the administrator of the health condition determination system 10 through a user interface (not shown), or the predetermined range may be expanded step by step using a trial and error method. After correction is repeated several times using the trial and error method, it is also possible to automatically determine correction parameters (correction amount) using a machine learning model built using the information obtained during trial and error as learning data. .

The verification unit 28 may correct at least one of the master curve, the classification method set in the master curve, and the predetermined range based on the notification received by the verification unit 28. Please note that the corrections here are intended to be customized specifically for the individual subject, and after the corrections, the learning content explained in the learning section of the improvement menu above will be reset or carried over by linking information, etc. be exposed.

Here, the verification unit 28 may perform the correction not in the sense of customizing for the individual subject, but in the sense of customizing for the class. For example, if the verification unit 28 receives a predetermined number of notifications regarding multiple subjects belonging to the same class (for example, if multiple subjects belonging to class A are frequently determined to be in poor health), In such cases, at least one of the master curve for the class, the classification method, and the predetermined range may be corrected.

An example in which the master curve is verified based on the notification in step S49 of the improvement support operation in FIG. 11 has been described above. Verification of the master curve may be performed based on the notification. The notification in step S56 is performed when the value of data such as the amount of food fluctuates significantly within a predetermined range. Therefore, for example, a correction may be made to narrow the predetermined range (to tighten the criteria so that it is easier to consider that the health condition has deteriorated) so that the fluctuation in the data value is determined to be outside the predetermined range. There are cases where this could be done.

Although the verification unit 28 is described as a component (function) included in the server device 20, it may be a device different from the server device 20 and included in the health condition determination system 10 (for example, another server device). It may be realized as a component included in the health condition determination system 10, or it may be realized as a component included in a system other than the health condition determination system 10. The verification unit 28 is an example of a verification system.

[Extraction of biological data to be monitored]
By the way, as explained in the section on learning the improvement menu, it is desirable that various biometric data be acquired through the sensor 53 and the second information terminal 60 when learning the improvement menu. However, since the second information terminal 60 (for example, a wearable information terminal) has limitations on CPU performance, memory capacity, etc., the biometric data monitored (obtained) through the second information terminal 60 is , the more narrowed down the better.

Therefore, the analysis unit 29 analyzes biological data that is likely to fluctuate due to changes in activities or the environment, based on influence information (information indicating the above-mentioned Input/Output relationship) of multiple subjects belonging to the same class. The second information terminal 60 may be allowed to extract (monitor) only the extracted biometric data. The analysis unit 29 extracts biometric data by, for example, extracting a parameter with a high weight or a hidden layer in a neural network. The analysis unit 29 may extract biological data using sensitivity analysis or covariance structure analysis instead of the neural network.

The analysis unit 29 also compares the influence information of the plurality of subjects belonging to the first class and the influence degree information of the plurality of subjects belonging to the second class different from the first class. Accordingly, biometric data that should be monitored intensively by subjects belonging to the first class may be extracted. In this comparison, important factors are identified. At this time, the analysis unit 29 may consider important factors by, for example, generating a critical path, and may perform modeling of complex factors.

Although the analysis unit 29 is described as a component (function) included in the server device 20, it is a device different from the server device 20 and included in the health condition determination system 10 (for example, another server device). It may be realized as a component included in the health condition determination system 10, or it may be realized as a component included in a system other than the health condition determination system 10.

[Modified example]
The storage unit 23 may store a plurality of types of master curves in which at least one of master curve x (first data) and master curve y (second data) is different. For example, the plurality of types of master curves are calculated individually, but they can also be calculated using the sensing results of one sensor 31. Specifically, as explained using FIG. 4 above, if multiple types of first data can be acquired based on the sensing results of the sensor 31, the calculation unit 25 uses this to Multiple types of master curves corresponding to the first data can be calculated.

When multiple types of master curves are stored in the storage unit 23 in this way, the determination unit 26 can determine the health condition of the subject using each of the multiple types of master curves. At this time, the health condition of the subject is determined at predetermined time intervals (units such as hours/days/weeks/months/years) suitable for judgment using the master curve, depending on the type of master curve. .

Furthermore, the health condition determination system 10 may store (accumulate) the subject's first data, the subject's second data, and the subject's health condition determination result in the storage unit 23 in association with each other. Once data from multiple subjects is accumulated, these data can be used as training data to build a machine learning model for determining health status. In this way, the present invention may be implemented as a method for generating learning data for constructing a machine learning model. In addition, the health condition determination system 10 is a system that determines the health condition of a subject using the machine learning model constructed in this way, and notifies the determination result or controls the environment based on the determination result. May be realized. As mentioned above, optimization of the master curve is also facilitated by correction or machine learning. Furthermore, it is also possible to compare and analyze the master curve itself for each subject's attributes, for example, external environment such as residential area or race.

[Effects etc.]
As explained above, the health condition determination method executed by a computer such as the health condition determination system 10 uses reference characteristics for determining the health condition of a subject, each of which is based on a person's health or the comfort felt by the person. a first acquisition step of acquiring reference characteristics indicating the relationship between the first index and the second index, which are indicators regarding the subject; and a control step of presenting a menu for improving the subject's health condition to the subject or executing the menu based on the health condition determination criteria in the class to which the subject belongs. The reference characteristic corresponds to the master curve in the above embodiment, and the determination criterion corresponds to the upper limit curve and lower limit curve in the above embodiment.

Such a health condition determination method can support improvement of the subject's health condition.

For example, the health condition determination method further includes a second acquisition step of acquiring changes in the subject's biometric data due to execution of the menu, a process of storing the acquired changes in the biometric data, and an acquisition step. and an information processing step of performing at least one of a process of learning the degree of influence of execution of the menu on the subject's biometric data based on the change in the biometric data of the subject.

Such a health condition determination method can collect and accumulate information for improving the health condition.

For example, the health condition determination method further includes a determination step of determining whether the data value is outside a predetermined range indicated by the determination criterion. In the control step, if it is determined that the data value is outside the predetermined range indicated by the determination criteria, a menu for improving the subject's activities is presented as a menu, and if the data value is within the predetermined range. If it is determined that this is the case, a menu for improving the environment around the subject is presented as a menu, or the menu for improving the environment is executed.

Such a health condition determination method selects an improvement menu according to the first case where the subject's health condition is poor and the second case where the subject's health condition is good (or tends to be slightly bad). You can switch the type.

Also, for example, in the control step, a menu is selected based on data indicating the health condition of the subject at rest.

In such a health condition determination method, a menu can be selected based on data indicating the subject's resting health condition. Note that data showing health conditions at rest has fewer environmental fluctuations than data showing health conditions at rest, and it is easier to capture changes in physical condition over time than data showing health conditions at rest. is better than the data showing.

Furthermore, for example, the health condition determination method further includes a changing step of changing the class to which the subject belongs based on the number of times it has been determined that the data value is outside a predetermined range.

Such a health condition determination method can optimize the class to which the subject belongs.

For example, the health condition determination method further includes a first notification step of notifying a verification system that verifies the reference characteristics based on the number of times the data value is determined to be outside a predetermined range. . The verification system corresponds to the verification unit 28 in the above embodiment.

Such a health condition determination method can optimize reference characteristics in cases where data values are likely to be determined to be outside a predetermined range.

For example, in the first notification step, the number of times it was determined that the data value was outside the predetermined range and the data value did not return to the predetermined range even after executing the activity improvement menu Based on this, the verification system will be notified.

Such a health condition determination method can optimize reference characteristics in cases where data values are likely to be determined to be outside a predetermined range.

For example, in the determination step, it is determined whether the data value is outside a predetermined range indicated by the determination criteria, and if it is determined that the data value is within the predetermined range, Make further determinations regarding data fluctuations. The health condition determination method further includes a second notification step of notifying a verification system that verifies the reference characteristics based on the number of times it is determined that the data value is within a predetermined range but has a large variation. .

Such a health condition determination method can notify when the data value is within a predetermined range but has large fluctuations.

For example, in the second notification step, it is determined that the data value is within a predetermined range but the fluctuation is large, and it is determined that the data fluctuation is not suppressed even if the environment improvement menu is executed. The verification system is notified based on the number of times the verification has been performed.

Such a health condition determination method can notify when the data value is within a predetermined range but fluctuates greatly and no improvement is seen.

For example, in the health condition determination method, the verification system further corrects at least one of the reference characteristics, the classification method set for the reference characteristics, and the predetermined range based on the notification received by the verification system. including a correction step.

Such a health condition determination method is useful in cases where data values are likely to be judged to be outside a predetermined range, etc. By correcting this, it is possible to optimize the reference characteristics.

Also, for example, in the information processing step, menus that are effective in improving the subject's health condition are learned.

Such a health condition determination method can learn menus that are effective in improving the subject's health condition.

For example, the health condition determination method further includes a change in the first biometric data of the subject who belongs to the first class when the menu is executed, and a change in the first biometric data of the subject who belongs to the second class different from the first class. By comparing the second biometric data of the subject with the change when the menu is executed, an analysis step is performed to extract the biometric data that should be monitored intensively for the subject who belongs to the first class. include.

Such a health condition determination method can extract biological data that should be monitored intensively by subjects belonging to the first class.

Also, for example, in the analysis step, biological data that should be monitored intensively by subjects belonging to the first class is extracted by identifying important factors in the comparison.

Such a health condition determination method can extract biological data that should be monitored intensively by subjects belonging to the first class by identifying important factors. Since important factors are assumed to differ depending on each class, the health condition determination method makes it possible to propose more detailed analysis or improvement. On the other hand, there is a possibility that important factors spanning multiple classes may occur, and in such a case, it is possible to use covariance analysis, correlation analysis, etc. as an approach such as so-called horizontalization.

The health condition determination system 10 also shows a relationship between a first index and a second index, each of which is a reference characteristic for determining the health condition of a subject and is an index related to a person's health or comfort felt by the person. The acquisition unit 24 acquires the standard characteristics, the data indicating the current health condition of the target person, and the health condition determination criteria for the class to which the target person belongs, which are determined based on the acquired standard characteristics. The control unit 27 presents a menu for improving the condition to the subject or executes the menu.

Such a health condition determination system 10 can support improvement of the subject's health condition.

(Other embodiments)
Although the embodiments have been described above, the present invention is not limited to the above embodiments.

For example, in the above embodiments, the health condition determination system is realized by a plurality of devices, but it may be realized as a single device. For example, the health condition determination system may be realized as a single device corresponding to a server device. When the health condition determination system is realized by a plurality of devices, the components (particularly functional components) included in the health condition determination system may be distributed to the plurality of devices in any manner.

For example, in the embodiments described above, the processing executed by a specific processing unit may be executed by another processing unit. Further, the order of the plurality of processes may be changed, or the plurality of processes may be executed in parallel.

Furthermore, in the above embodiments, each component may be realized by executing a software program suitable for each component. Each component may be realized by a program execution unit such as a CPU or a processor reading and executing a software program recorded on a recording medium such as a hard disk or a semiconductor memory.

Additionally, each component may be realized by hardware. Each component may be a circuit (or integrated circuit). These circuits may constitute one circuit as a whole, or may be separate circuits. Further, each of these circuits may be a general-purpose circuit or a dedicated circuit.

Furthermore, the general or specific aspects of the present invention may be implemented in a system, device, method, integrated circuit, computer program, or computer-readable recording medium such as a CD-ROM. Further, the present invention may be realized by any combination of a system, an apparatus, a method, an integrated circuit, a computer program, and a recording medium.

For example, the present invention may be realized as a health condition determination method, or may be realized as a program for causing a computer to execute a health condition determination method (in other words, a computer program product), or such a program It may be realized as a computer-readable non-transitory recording medium recorded with.

Other embodiments may be obtained by making various modifications to each embodiment that a person skilled in the art would think of, or may be realized by arbitrarily combining the components and functions of each embodiment without departing from the spirit of the present invention. The present invention also includes such forms.

10 Health condition determination system 20 Server device 21 Communication unit 22 Information processing unit 23 Storage unit 24 Acquisition unit 25 Calculation unit 26 Judgment unit 27 Control unit 28 Verification unit 29 Analysis unit 30, 50 Facility 31, 53 Sensor 40 First information terminal 51 Control device 52 Environment adjustment device 60 Second information terminal 70 Third information terminal 80 Wide area communication network

Claims (15)

1. A method for determining a health condition performed by a computer, the method comprising:
   A first acquisition step of acquiring reference characteristics indicating a relationship between a first index and a second index, each of which is a reference characteristic for determining a subject's health condition and is an index related to a person's health or comfort felt by the person. and,
   A menu for improving the health condition based on data indicating the current health condition of the target person and a criterion for determining the health condition in the class to which the target person belongs, which is determined based on the acquired reference characteristics. a control step of presenting the menu to the subject or executing the menu.
2. moreover,
   a second acquisition step of acquiring changes in biometric data of the subject due to execution of the menu;
   At least one of a process of storing a change in the acquired biometric data, and a process of learning the degree of influence of execution of the menu on the subject's biometric data based on the change in the acquired biometric data. The health condition determination method according to claim 1, further comprising an information processing step of performing.
3. Furthermore, a determination step of determining whether the value of the data is outside a predetermined range indicated by the determination criterion,
   In the control step,
   If it is determined that the value of the data is outside a predetermined range indicated by the determination criterion, presenting a menu for improving the subject's activities as the menu;
   According to claim 1, when it is determined that the value of the data is within the predetermined range, a menu for improving the environment around the subject is presented as the menu, or a menu for improving the environment is executed. A method for determining the health status of.
4. The health state determination method according to claim 1, wherein in the control step, the menu is selected based on data indicating the health state of the subject at rest.
5. The health condition determining method according to claim 3, further comprising a changing step of changing the class to which the subject belongs based on the number of times it has been determined that the value of the data is outside the predetermined range.
6. The health according to claim 3, further comprising a first notification step of notifying a verification system that verifies the reference characteristic based on the number of times the value of the data is determined to be outside the predetermined range. Condition determination method.
7. In the first notification step, it is determined that the value of the data is outside the predetermined range and that the value of the data does not return to within the predetermined range even after executing the improvement menu for the activity. The health condition determination method according to claim 6, wherein the verification system is notified based on the number of times.
8. In the determination step,
   determining whether the value of the data is outside a predetermined range indicated by the determination criterion;
   If it is determined that the value of the data is within the predetermined range, further determining regarding fluctuations in the data;
   The health condition determination method further includes a second step of notifying a verification system that verifies the reference characteristic based on the number of times it is determined that the value of the data is within the predetermined range but has a large variation. The health condition determination method according to claim 3, further comprising a notification step.
9. In the second notification step, it is determined that the value of the data is within the predetermined range but the fluctuation is large, and the fluctuation of the data is not suppressed even if the environment improvement menu is executed. The health condition determination method according to claim 8, wherein the verification system is notified based on the number of times the determination has been made.
10. Further, a correction step in which the verification system corrects at least one of the reference characteristic, the classification method set for the reference characteristic, and the predetermined range based on the notification received by the verification system. The method for determining a health condition according to claim 6.
11. 3. The health condition determining method according to claim 2, wherein in the information processing step, the menu that is effective in improving the health condition of the subject is learned.
12. Furthermore, a change in the first biometric data of the subject who belongs to a first class when the menu is executed, and a change in the first biometric data of the subject who belongs to a second class different from the first class. The method further comprises an analysis step of extracting biometric data that should be monitored intensively by the subject who belongs to the first class by comparing the biometric data with a change when the menu is executed. 12. The health condition determination method according to 11.
13. The health condition determination method according to claim 12, wherein in the analysis step, biological data that should be monitored intensively by the subject who belongs to the first class is extracted by identifying important factors in the comparison. .
14. A program for causing a computer to execute the health condition determination method according to any one of claims 1 to 13.
15. an acquisition unit that acquires a reference characteristic indicating a relationship between a first index and a second index, each of which is a reference characteristic for determining a subject's health condition and is an index related to a person's health or comfort felt by the person;
    A menu for improving the health condition based on data indicating the current health condition of the target person and a criterion for determining the health condition in the class to which the target person belongs, which is determined based on the acquired reference characteristics. a control unit that presents the menu to the subject or executes the menu.

Images