Methods, devices, programs, and systems for measuring the health status of subjects.

Abstract

The present invention provides methods, apparatus, programs, and systems for evaluating the overall health status of a person through simple tests. [Solution] A method for measuring the health status of a subject, performed in a computer device 30 equipped with a processor at the subject's home H, includes the steps of: the processor acquiring a dataset for a parameter set in step S1; the processor transmitting the dataset to a server device S in step S3; the processor receiving health status information derived from the dataset from the server device in step S4; and the processor representing the health status of user U as a position on a health status positioning map of health status information in step S5, and automatically acquiring other data from the dataset in response to acquiring at least one data from the dataset.

Description

Technical Field

[0001] The present invention relates to a method for measuring the health of a subject and the like.

Background Art

[0002] The stage before the onset of disease from health is called pre-disease. In a situation where there is concern about the economic collapse of the country due to the soaring medical costs in a declining birthrate and aging society, the development of a technology for visualizing and quantifying the state from health to pre-disease in order to prevent the onset of disease is desired.

[0003] For example, Patent Document 1 discloses a technique for evaluating the health state of a subject by acquiring data of a plurality of test items for a plurality of subjects and creating a function using a plurality of test data among the test items as variables.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, in the conventional technology as described above, measurements are made along specific axes such as lifestyle-related diseases such as diabetes and arteriosclerosis, cancer, dementia, sarcopenia, liver diseases, and kidney diseases, following the paths of health, pre-disease, and disease, and risk assessments are performed. Therefore, there is a problem that it is impossible to evaluate the degree of health of a person's overall health. To address this problem, the inventors have invented means (health positioning maps, health functions, etc.) that can evaluate various health risks (International Application No. PCT / JP2019 / 43062).

[0006] The applicant developed a method for easily assessing health risks at home or other locations, stemming from this invention. This is because conventional methods, as described above, require invasive tests such as blood tests, which cannot be easily performed at home or other locations.

[0007] One aspect of the present invention aims to provide a means for evaluating the overall health status of a person through a simple examination. [Means for solving the problem]

[0008] The present invention provides, for example, the following items: (Item 1) A method for measuring the health status of a subject, Step (1): Obtaining a dataset for a parameter set, wherein the parameter set includes autonomic nervous system parameters, body composition parameters, and questionnaire parameters, and Step (1) is, I. To obtain data on the autonomic nerve parameters using an autonomic nerve measuring device for measuring the autonomic nerve parameters, II. Obtaining data for the body composition parameters using a body composition analyzer, III. To acquire data for the questionnaire parameters using a questionnaire processing device for measuring the questionnaire parameters, This includes, Step (2): Send the dataset to the server device, Step (3): Receiving health information derived from the dataset from the server device, Step (4): Represent the health status as a position on the health status positioning map of the health status information. A method that includes this. (Item 2) The parameter set further includes blood pressure parameters, as described in item 1. (Item 3) Step (1) above is, IV. Obtaining data for the blood pressure parameters using a blood pressure monitor, The method described in item 2, including the method described in item 2. (Item 4) The method according to any one of items 1 to 3, wherein step (1) includes acquiring the dataset using at most four measuring instruments. (Item 5) The method described in item 4, wherein each of the four measuring instruments is portable or handheld. (Item 6) The method according to any one of items 1 to 3, wherein step (1) includes acquiring the dataset using a single measuring instrument. (Item 7) The method according to any one of items 1 to 6, wherein the health information includes the values ​​of the X axis and the Y axis in the health positioning map, and step (4) includes displaying the health information on the health positioning map based on the values ​​of the X axis and the Y axis. (Item 8) The method according to item 7, wherein step (3) includes the measuring instrument used in step (1) receiving health information, including the X-axis values ​​and Y-axis values ​​in the health positioning map, from the server device. (Item 9) The method according to item 7 or item 8, wherein step (4) includes the measuring instrument used in step (1) displaying the health information on the health positioning map displayed on the display unit of the measuring instrument based on the X-axis value and the Y-axis value. (Item 10) Step (5): The first and second positions on the health positioning map are determined by repeating steps (1) to (4) at least twice, Step (6): Evaluate the health status of the subject based on the trajectory including the first position and the second position. The method described in any one of items 1 to 9, further including the method described in any one of items 1 to 9. (Item 11) The method according to item 10, wherein step (5) includes repeating steps (1) to (4) at least twice in one day. (Item 12) The method according to any one of items 1 to 11, wherein step (1) includes automatically acquiring at least a part of the dataset without making the subject aware of it. (Item 13) The method according to any one of items 1 to 12, wherein step (1) includes automatically acquiring data for the autonomic nerve parameters and data for the body composition parameters without making the subject aware of it in response to acquiring data for the questionnaire parameters. (Item 14) The method according to any one of items 1 to 13, wherein the server device is configured to derive the health information using a health function that correlates the dataset with the position of the subject on the health positioning map. (Item 15) The method according to any one of items 1 to 14, wherein the differences between the time when data for the autonomic nerve parameters is acquired, the time when data for the body composition parameters is acquired, and the time when data for the questionnaire parameters is acquired are each within about 5 minutes. (Item 16) The method according to any one of items 1 to 15, wherein steps (2) to (4) are performed within a predetermined time. (Item 17) The method according to item 16, wherein the predetermined time is about 1 minute. (Item 18) The health positioning map is created using a parameter set for creating a health positioning map, The method according to any one of items 1 to 17, wherein the parameter set is a part of the parameter set for creating a health positioning map. (Item 19) A method for controlling a device according to the health of a subject, The method described in item 1 involves generating commands to control the device based on the position of the health information on the health positioning map, To control the equipment in accordance with the aforementioned command. A method that includes this. (Item 20) After controlling the aforementioned device, By repeating steps (1) to (4) above, the second position on the health positioning map is determined, Based on the aforementioned position and the second position, a second command for controlling the device is generated. The method described in item 19, further including the method described in item 19. (Item 21) A device for measuring the health status of a subject, An acquisition means for obtaining a dataset for a parameter set, wherein the parameter set includes autonomic nervous system parameters, body composition parameters, and questionnaire parameters, and the acquisition means is I. Obtaining data for the autonomic nerve parameters from an autonomic nerve measuring device for measuring the autonomic nerve parameters, II. Obtaining data for the body composition parameters from a body composition analyzer, III. Obtaining data for the questionnaire parameters from a questionnaire processing device for measuring the questionnaire parameters. A means for obtaining, configured to perform the following: A transmission means for transmitting the aforementioned dataset to a server device, A receiving means for receiving health information derived from the aforementioned dataset from the server device, A means for representing the health status as a position on a health status positioning map of the health status information, A device equipped with the following features. (Item 22) A program for measuring the health status of a subject, wherein the program is executed on a computer device, and the program Step (1): Obtaining a dataset for a parameter set, wherein the parameter set includes autonomic nervous system parameters, body composition parameters, and questionnaire parameters, and Step (1) is, I. Obtaining data for the autonomic nerve parameters from an autonomic nerve measuring device for measuring the autonomic nerve parameters, II. Obtaining data for the body composition parameters from a body composition analyzer, III. Obtaining data for the questionnaire parameters from a questionnaire processing device for measuring the questionnaire parameters, This includes, Step (2): Send the dataset to the server device, Step (3): Receiving health information derived from the dataset from the server device, Step (4): Represent the health status as a position on the health status positioning map of the health status information. A program that causes the computer device to perform a process including the following. (Item 23) A system for measuring the health status of a subject, the system comprising a terminal device and a server device, The aforementioned terminal device is Step (1): Obtain the dataset for the parameter set, Step (2): Send the dataset to the server device. It is configured to do the following: The server device is Step (A): Derive health information using a health function that correlates the dataset with the position of the subject on the health positioning map, Step (B): Transmit the health information to the terminal device. It is configured to do the following: The aforementioned terminal device is Step (3): Receiving the health information from the server device, Step (4): Represent the health status as a position on the health status positioning map of the health status information. A system configured to perform the following further. [Effects of the Invention]

[0009] According to one aspect of the present invention, a means for evaluating a person's overall health status through a simple examination can be provided. This enables the provision of a technology that allows for the real-time measurement of health status in home and office environments, tracking of changes in that status, and a technology that enables the development of personalized solutions for improving daily living habits using this technology. [Brief explanation of the drawing]

[0010] [Figure 1A] This diagram shows an example of the flow of a new service for visualizing the user's health status. [Figure 1B] This figure shows an example of screen 1000, which displays the user's health status. [Figure 2] This figure shows an example of the configuration of the server device 100. [Figure 3A] This figure shows an example of the configuration of the processor unit 120 in one embodiment. [Figure 3B] This figure shows an example of the configuration of the processor unit 130 in another embodiment. [Figure 3C] This figure shows an example of the configuration of the processor unit 140 in yet another embodiment. [Figure 3D] This figure shows an example of a data flow in one embodiment of the present invention. [Figure 3E] This figure shows an example of the configuration of a terminal device 300 in one embodiment of the present invention. [Figure 4] This figure shows an example of the data structure of the first dataset stored in the database unit 200. [Figure 5A] This flowchart shows an example of processing in server device 100. [Figure 5B]This flowchart shows another example of processing in server device 100. [Figure 6] This flowchart shows another example of processing in server device 100. [Figure 7A] This flowchart shows another example of processing in server device 100. [Figure 7B] This flowchart shows an example of a subsequent process following process 700, as shown in Figure 7A. [Figure 8] This figure shows an example of data flow in a method implemented in the computer system 10 of the present invention. [Figure 9A] This figure shows an example of a health assessment map created by the health assessment device described above. [Figure 9B] This figure shows the results of clustering the plotted distribution patterns in this embodiment. [Figure 10] This figure shows a health positioning map created in one embodiment. [Figure 11] This figure shows the results of comparing the mapping position on a health positioning map before and after taking reduced CoQ10 for three months. [Figure 12] This figure shows the results of comparing the parameters of test items before and after taking reduced CoQ10 for three months. [Figure 13] This figure shows the correlation coefficients between the measured and predicted values ​​of the health function using the second parameter set for 4 measurement items (19 items), and the correlation coefficients between the measured and predicted values ​​of the health function using the second parameter set for 3 measurement items (18 items). [Figure 14] This figure shows the results of Example 6. [Modes for carrying out the invention]

[0011] Embodiments of the present invention will be described below with reference to the drawings. In this specification, "approximately" means ±10% of the following numerical value.

[0012] 1. A service to visualize the user's health status. The inventors of this invention have developed a new service for visualizing a user's health status. This service acquires various data related to the user's health and, based on the acquired data, provides the user with information on where their health status falls on a health positioning map. Here, a health positioning map refers to a map having multiple regions characterized by health-related information.

[0013] Each region of the health positioning map can be characterized as, for example, various states of health. For instance, one region of the health positioning map could be characterized as a young adult mental health disease risk group, another region as a middle-aged to elderly lifestyle-related disease risk group, and yet another region as an elderly diabetes risk group. For example, one region of the health positioning map could be characterized as a pre-disease group for a certain health condition, and yet another region as a high-risk group for that health condition. These characterizations are merely examples, and various other characterizations are possible. For example, as shown in Figure 1B later, health levels could be characterized as A to C, based on physical health and mental health. Such characterizations are simple and allow for an intuitive understanding of the health status. The characterization of each area in the health positioning map can be determined, for example, by analyzing the trends of multiple subjects belonging to each area.

[0014] This new service allows users to obtain information on where their health status falls on a health positioning map based on the results of simple measurements they can take at home. This new service also allows users to visually see their health status on the health positioning map in real time.

[0015] Figure 1A shows an example of the flow of a new service for visualizing the user's health status.

[0016] In step S1, user U performs several measurements at home H. The measurements include, for example, measurements using measuring instruments 20 and measurements using a computer device 30. Measuring instruments 20 are any measuring instruments available at home H, including, but not limited to, a body composition analyzer 21 and a blood pressure monitor 22. Computer device 30 are any computer devices available at home H, including, but not limited to, a smartphone 31 and a personal computer 32. Measurements using measuring instruments 20 include measurements using the body composition analyzer 21, thereby obtaining data on body composition. Measurements using measuring instruments 20 may further include measurements using the blood pressure monitor 22, thereby obtaining data on blood pressure. Measurements using computer device 30 include measurements of autonomic nervous system function using a camera, thereby obtaining data on autonomic nervous system function. Measurements using computer device 30 include measurements using a questionnaire for user U, thereby obtaining data including living conditions and / or subjective evaluations.

[0017] For example, a blood pressure monitor may be a type of blood pressure monitor worn on the body (e.g., an upper arm blood pressure monitor, a wristwatch-type blood pressure monitor, a ring-type blood pressure monitor) or a non-contact blood pressure monitor (e.g., a blood pressure monitor that measures blood pressure from an image of the face or finger taken with a camera). For example, a body composition analyzer may be a type of body composition analyzer that is placed on top of the user during measurement, or a type of body composition analyzer that can be worn on the body (e.g., a wristwatch-type body composition analyzer).

[0018] In the example shown in Figure 1, four measurements are performed using three devices (body composition analyzer, blood pressure monitor, and computer device 30), but the present invention is not limited thereto. For example, four measurements may be performed using four devices (for example, body composition measurement using the body composition analyzer 21, blood pressure measurement using the blood pressure monitor 22, autonomic nervous system function measurement using an autonomic nervous system measuring device capable of measuring autonomic nervous system function, and questionnaire measurement using a questionnaire processing device capable of acquiring data from questionnaires), or four measurements may be performed using two devices (for example, body composition measurement and blood pressure measurement using a device capable of measuring body composition and blood pressure, autonomic nervous system function measurement and questionnaire measurement using the computer device 30), or four measurements may be performed using one device (for example, measurements using a device capable of measuring body composition, blood pressure, autonomic nervous system function, and data from questionnaires). Alternatively, for example, three measurements may be performed using three devices (e.g., body composition measurement using a body composition analyzer 21, autonomic nervous system function measurement using an autonomic nervous system measuring device capable of measuring autonomic nervous system function, and questionnaire measurement using a questionnaire processing device capable of acquiring data from questionnaires), or three measurements may be performed using two devices (e.g., body composition measurement using a device capable of measuring body composition, autonomic nervous system function measurement and questionnaire measurement using a computer device 30), or three measurements may be performed using one device (e.g., measurements using a device capable of measuring body composition, autonomic nervous system function, and questionnaire data). Thus, the devices used for measurement may be multiple separate devices or a single device. In the case of measurement using a single device, the single device may be a computer device 30 (e.g., a smartphone 31, a personal computer 32, a tablet, etc.). Alternatively, the single device may be a device other than the computer device 30. In this case, the computer device 30 is used for information communication and information display.

[0019] Measurements using such measuring instruments are non-invasive. Such measurements can be performed quickly with simple actions, such as simply attaching a device, standing on it, being filmed, or answering questions. Furthermore, these simple and non-invasive measurements using a small number of measuring instruments allow for the acquisition of multiple data points almost simultaneously, thus reducing or negating the time difference between each data point. For example, by performing multiple measurements almost simultaneously, the difference between the completion time of the earliest acquired measurement and the completion time of the latest acquired measurement (i.e., the time difference between data points) can be reduced to within 1 second, 2 seconds, 5 seconds, 10 seconds, 15 seconds, 20 seconds, 30 seconds, 1 minute, 2 minutes, 3 minutes, 5 minutes, 10 minutes, 30 minutes, 1 hour, 2 hours, or 6 hours. For example, it is preferable to have a difference of 5 minutes or less between the completion time of the earliest acquired measurement and the completion time of the latest acquired measurement. This is because if the time difference between each data point is within 5 minutes, the effect of the time difference between data points can be ignored. In particular, since data measured by autonomic nervous system monitors and blood pressure monitors can fluctuate moment by moment, it is preferable to be able to ignore the effect of time differences with other data. This makes it possible to represent the accurate health status at a given point in time on a health status positioning map.

[0020] Measurement may be performed consciously or unconsciously by User U. For example, measurement can be performed automatically when predetermined conditions are met, without the user U being aware of it. Measurement can also be performed without the user U being aware of it, for example, by using measuring equipment attached to User U's body. For example, by using measuring equipment attached to User U's body, measurement can be performed regardless of whether User U is indoors or outdoors (for example, whether User U is walking or standing still). Alternatively, or in addition to the above, measurement can be performed without the user U being aware of it, for example, by using measuring equipment installed within User U's range of movement. For example, by using measuring equipment installed within User U's range of movement, measurement can be performed regardless of what User U is doing within that range of movement (for example, whether User U is walking or standing still). Measuring devices installed within the user U's range of movement include, but are not limited to, sensors mounted on furniture used by user U (e.g., chairs, beds, etc.), sensors mounted on electronic devices used by user U (e.g., personal computers, refrigerators, air conditioners, smart speakers, etc.), and sensors installed in rooms such as user U's home. For example, blood pressure can be automatically measured by a blood pressure monitor worn on the body when predetermined conditions are met. For example, body composition can be automatically measured by a body composition analyzer worn on the body when predetermined conditions are met. For example, body composition can be automatically measured by a body composition analyzer mounted on the seat of the user's chair when predetermined conditions are met. For example, autonomic nervous system function can be automatically measured by a camera on the computer device 30 when predetermined conditions are met. For example, autonomic nervous system function can be automatically measured by a camera mounted on electronic devices used by user U when predetermined conditions are met. For example, autonomic nervous system function can be automatically measured by a camera installed in a room such as user U's home when predetermined conditions are met.For example, data including living conditions and / or subjective evaluations can be automatically measured from communication with electronic devices used by User U (e.g., smart speakers). Predetermined conditions include, for example, when a predetermined time arrives (temporal conditions), when entering / leaving a predetermined place (geographical conditions), when performing a predetermined action (behavioral conditions), etc. The predetermined time may be, for example, a predetermined time within a day (e.g., between 6 a.m. and 8 a.m., between 11 a.m. and 1 p.m., between 4 p.m. and 6 p.m., between 9 p.m. and 12 a.m., or 6 a.m., 12 p.m., 6 p.m., 12 a.m., etc.), or a predetermined time interval (e.g., every hour, every three hours, every six hours, every twelve hours, etc.). The predetermined place includes, but is not limited to, an office, home, living room, bedroom, etc. The prescribed actions include, but are not limited to, sitting in a chair, lying in bed, or staying within the field of view of a camera mounted on an electronic device used by User U or a camera installed in a room at User U's home for a certain period of time (e.g., 10 seconds, 30 seconds, 1 minute) or longer.

[0021] In one embodiment, a predetermined action could be, for example, acquiring at least one piece of data. For example, the other four measurements can be performed automatically in response to acquiring data from at least one of the four measurements, without the user U being aware of it. For example, body composition, autonomic nervous system function, and / or blood pressure could be automatically measured in response to the user U consciously answering a questionnaire. This allows the user U to perform multiple measurements with the simple action of answering a questionnaire.

[0022] In step S2, the data measured in step S1 is input into the computer device 30. For example, data on body composition measured using the body composition analyzer 21 is input into the computer device 30. This may be done, for example, by establishing communication between the body composition analyzer 21 and the computer device 30, or by the user U inputting the measurements from the body composition analyzer 21 into the computer device 30. For example, data on blood pressure measured using the blood pressure monitor 22 is input into the computer device 30. This may be done, for example, by establishing communication between the blood pressure monitor 22 and the computer device 30, or by the user U inputting the measurements from the blood pressure monitor 22 into the computer device 30. In step S1, data on autonomic nervous system function and data from the questionnaire were measured using the computer device 30, so this data has already been input into the computer device 30.

[0023] In step S3, the data acquired in step S2 is transmitted from the computer device 30 to the service provider's server device S via the network 40. The server device S can derive user U's health status information based on the measurement results of user U received from the computer device 30. User U's health status information includes information indicating which area on the health status positioning map user U is located in.

[0024] In step S4, the health information derived by the server device S is transmitted from the server device S to the computer device 30 via the network 40.

[0025] In step S5, the computer device 30 displays to user U, based on the health information, which region on the health positioning map user U's health status falls into. User U can recognize their own health status by referring to the information associated with the region on the health positioning map to which their health status is located. For example, if their health status belongs to the region characterized as health status B on the health positioning map as shown in Figure 1B, user U can recognize that their health status is neither bad nor good. This makes it possible to encourage user U to make efforts to improve their health status. For example, if their health status belongs to the region characterized as the young-age mental health disease risk group on the health positioning map, user U can recognize their own health status as having a risk of mental health disease. This makes it possible to encourage user U to take measures to prepare for the risk of mental health disease.

[0026] The process from performing the measurements in steps S1 to S5 to displaying the health positioning map may be done consciously by the user or automatically by the user unconsciously. In other words, user U can easily recognize their own health position on the health positioning map by performing the various measurements. Alternatively, by automating the measurement process as well, all steps from S1 to S5 can be automated. This allows user U to recognize their own health position on the health positioning map without the burden of taking measurements.

[0027] Since the data obtained from the measurement in step S1 does not require much time for analysis, the time from when the data is acquired by the computer device 30 in step S2 until the health positioning map is displayed in step S5 can be shortened. This allows the user to immediately know their health status. In particular, by continuously performing the measurement in step S1 using a body-worn measuring device, for example, the user can visually recognize changes in their health status in real time. Here, the time from when the data is acquired by the computer device 30 in step S2 until the health positioning map is displayed in step S5 can be, for example, 0.01 seconds, 0.02 seconds, 0.05 seconds, 0.1 seconds, 0.2 seconds, 0.5 seconds, within 1 second, within 3 seconds, within 5 seconds, within 10 seconds, within 20 seconds, within 30 seconds, within 45 seconds, within 1 minute, within 5 minutes, within 10 minutes, within 1 hour, within 2 hours, within 12 hours, within 24 hours, etc. This high level of responsiveness reduces user waiting times, alleviates the psychological burden on users during measurement, and prevents a decline in user motivation for measurement.

[0028] Furthermore, by repeating steps S1 to S5 described above after a predetermined period of time has elapsed, user U can recognize the time-series changes in their health status. For example, user U can recognize the direction their health status is heading by referring to the time-series changes in their position on the health status positioning map. For example, if user U's health status was in the region characterized as health status B on the health status positioning map as shown in Figure 1B, and after a predetermined period of time, their health status is still in the region characterized as health status B on the health status positioning map, but is approaching the region characterized as health status C, then user U can recognize that their health status is heading in the direction of health status C. This makes it possible, for example, to encourage user U to take care to prevent their health status from deteriorating. For example, if a user's health status was previously characterized as belonging to the "Young Adult Mental Health Disease Risk Group" on a health positioning map, and after a predetermined period, their health status, while still belonging to the "Young Adult Mental Health Disease Risk Group," moves closer to the "Middle-Aged / Elderly Lifestyle Disease Risk Group," then user U can recognize that their health status is moving towards the middle-aged / elderly lifestyle disease risk direction. This allows, for example, to encourage user U to take measures to prepare for the risk of lifestyle diseases.

[0029] For example, by performing steps S1 to S5 described above before an event, user U can recognize their current health status. Then, by performing steps S1 to S5 described above after the event, user U can recognize their current health status. By comparing the health status obtained in this way before the event with the health status after the event, user U can recognize the impact of the event on their health status. Events include, but are not limited to, infectious disease outbreaks (such as Covid-19), natural disasters (for example, damage caused by storms, heavy rain, heavy snow, floods, storm surges, earthquakes, tsunamis, volcanic eruptions, and other unusual natural phenomena), overtime work, experiences (direct experiences or simulated experiences (for example, experiences via VR (virtual reality), AR (augmented reality), etc.)), and communication with other people or animals.

[0030] For example, by performing steps S1 to S5 described above at the beginning of the day (for example, between 6:00 AM and 12:00 PM), user U can recognize their current health status. Then, by performing steps S1 to S5 again at the end of the day (for example, between 6:00 PM and 12:00 AM), user U can recognize their current health status. By comparing the health status obtained at the beginning of the day with the health status at the end of the day, user U can recognize the diurnal variation in their health status. If this health status primarily represents fatigue level, user U can objectively recognize how much fatigue has accumulated due to their activities throughout the day.

[0031] For example, by performing steps S1 to S5 described above at the end of the day (for example, between 6 PM and 12 AM), user U can recognize their current health status. Then, by performing steps S1 to S5 again at the beginning of the next day (for example, between 6 AM and 12 PM), user U can recognize their current health status. By comparing the health status at the end of the day with the health status at the beginning of the next day, user U can recognize the nocturnal fluctuations in their health status. These nocturnal fluctuations in health status can correspond to the body's resilience or elasticity, allowing user U to objectively recognize how much they have recovered through sleep during the night.

[0032] Steps S1 to S5 described above can be performed, for example, at predetermined times during the day. These predetermined times may be, for example, fixed times during the day (e.g., between 6am and 8am, between 11am and 1pm, between 4pm and 6pm, between 9pm and midnight, or 6am, midnight, 6pm, midnight, etc.), fixed intervals (e.g., every hour, every three hours, every six hours, etc.), or times freely set by the user. For example, by performing steps S1 to S5 in the morning (e.g., between 6am and 8am, or at 6am), midday (e.g., between 11am and 1pm, or at midnight), evening (e.g., between 4pm and 6pm, or at 6pm), and night (e.g., between 9pm and midnight, or at midnight), fluctuations in health status due to daily activities can be tracked in detail.

[0033] By evaluating and accumulating health status over short periods in this way, it becomes possible to capture subtle fluctuations in health status and evaluate health from a new perspective. Since health status can be assessed through simple tests conducted at home, this type of short-term health assessment becomes easily accessible. Furthermore, this data can be used to develop personalized solutions for improving daily living habits.

[0034] The above examples illustrate four simple non-invasive tests that can be performed at home, but measurements are not limited to non-invasive tests. For example, measurements may include invasive tests. In this specification, "invasive test" refers to a test that harms the subject's body (for example, by blood sampling by injection or tissue excision), and "non-invasive test" refers to a test that does not harm the subject's body in any way. Typical invasive tests are those that detect the amount of components contained in blood or plasma, while typical non-invasive tests include those that detect components in the subject's excretions (urine, breath, saliva), autonomic nervous system function tests, cognitive function tests, questionnaires, and VAS (Visual Analogue Scales). In this specification, "invasive parameter" refers to a parameter obtained by an invasive test, and "non-invasive parameter" refers to a parameter obtained by a non-invasive test.

[0035] In the example above, we explained that the measurement was performed at home H, but the location of the measurement is not limited to home H. For example, the measurement may be performed at a company, pharmacy, community center, cafe, etc., other than a testing facility. It is precisely because a simple measurement is sufficient that it can be performed at a location other than a testing facility. Of course, the measurement may also be performed at a hospital or specialized testing facility.

[0036] Figure 1B shows an example of a screen 1000 that displays the user's health status. Screen 1000 can be displayed on the screen of, for example, the user U's computer device 30 (e.g., a personal computer, smartphone, tablet, etc.) and provided to the user.

[0037] Screen 1000 includes a health positioning map display unit 1100 and a radar chart display unit 1200.

[0038] The health positioning map display unit 1100 displays a health positioning map. In this health positioning map, the horizontal axis is related to physical health, with larger values ​​on the horizontal axis indicating poorer physical health, while the vertical axis is related to mental health, with larger values ​​on the vertical axis indicating poorer mental health.

[0039] The health positioning map displayed on the health positioning map display unit 1100 includes 10 regions. Of these 10 regions, one region is characterized as health level A, three regions are characterized as health level B, and six regions are characterized as health level C. Here, health level A indicates good health, health level B indicates average health, and health level C indicates poor health requiring attention.

[0040] Users can recognize their own health status based on where their health level falls on the health positioning map. In the example shown in Figure 1B, the user's health level is plotted with a star, indicating that the user's health level belongs to the area characterized as health level B. For example, by plotting the health levels of multiple users belonging to a certain group on a single health positioning map, it is possible to understand how healthy a particular user is within that group. This is useful, for example, in corporate labor management. For instance, a company's labor relations manager can look at a health positioning map where the health levels of the company's employees are plotted to consider whether organizational intervention is necessary or possible. For example, if the health level of a particular employee is plotted in a worse position than that of other employees, they can consider whether or not intervention should be taken for that employee. Alternatively, for example, if the health level of employees in a particular department is plotted in a worse position than that of employees in other departments, they can consider whether or not intervention should be taken for that department.

[0041] The radar chart display unit 1200 displays a radar chart. This radar chart shows the health status on a 6-point scale from 0 to 5 from six perspectives (musculoskeletal system, metabolic system, autonomic nervous system, sleep-wake rhythm, mental health, and fatigue). The musculoskeletal system perspective shows the state of muscle strength related to exercise, the metabolic system perspective shows the state of energy metabolism in the body and obesity, the autonomic nervous system perspective shows the state of nerve regulation related to concentration and relaxation, the sleep-wake rhythm perspective shows the state of sleep and drowsiness, the mental health perspective shows the state of mood swings, and the fatigue perspective shows the state of mental and physical fatigue. Users can recognize at a glance which perspective is responsible for their health status. Since the radar chart displayed on the radar chart display unit 1200 is characterized by health-related information on each axis, and the user's score is mapped to each axis, such a radar chart can be considered a type of health positioning map in this specification.

[0042] Screen 1000 may include a health ranking display section (not shown). The health ranking display section shows the user's health ranking within a specific group. This specific group may include, for example, a group of people with the same last name as the user, a group of people of the same age as the user, or a group of people of the same age and last name as the user. Such a ranking display makes it easier to intuitively understand one's own health. Furthermore, by displaying directions on what to do to improve the ranking, it is possible to encourage behavioral change in the user using the principle of competition.

[0043] The services described above can be implemented, for example, by the computer system 10 described below.

[0044] 2. Computer System Configuration Figure 2 shows an example of the configuration of computer system 10.

[0045] The computer system 10 comprises a server device 100 and at least one terminal device 300.

[0046] The server device 100 is connected to the database unit 200. The server device 100 is also connected to at least one terminal device 300 via a network 400. The server device 100 is, for example, a computer installed in a service provider that offers a new service for visualizing users' health status.

[0047] Network 400 can be any type of network. Network 400 may be, for example, the Internet or a LAN. Network 400 may be a wired network or a wireless network.

[0048] Figure 2 depicts three terminal devices 300, but the number of terminal devices 300 is not limited to these. The number of terminal devices 300 can be any number of one or more. An example of a terminal device 300 is a computer held by a user, but it is not limited to this. For example, it could be a computer installed in a hospital, a computer installed in an office room where examinations can be performed, etc. Here, the computer can be any type of computer. For example, terminal device 300 could be any type of terminal device such as a smartphone, tablet, personal computer, or smart glasses.

[0049] The server device 100 comprises an interface unit 110, a processor unit 120, and a memory unit 150.

[0050] The interface unit 110 exchanges information with the outside of the server device 100. The processor unit 120 of the server device 100 can receive information from the outside of the server device 100 via the interface unit 110 and can transmit information to the outside of the server device 100. The interface unit 110 can exchange information in any format.

[0051] The interface unit 110 includes, for example, an input unit that enables information to be input to the server device 100. The manner in which the input unit enables information to be input to the server device 100 is irrelevant. The interface unit 110 also includes, for example, an output unit that enables information to be output from the server device 100. The manner in which the output unit enables information to be output from the server device 100 is irrelevant.

[0052] The processor unit 120 executes the processing of the server device 100 and controls the overall operation of the server device 100. The processor unit 120 reads the program stored in the memory unit 150 and executes the program. This makes it possible to make the server device 100 function as a system that executes desired steps. The processor unit 120 may be implemented by a single processor or by multiple processors.

[0053] The memory unit 150 stores programs necessary for executing the server device 100's processing, as well as data necessary for executing those programs. The memory unit 150 may store programs that cause the processor unit 120 to perform processing for creating a health positioning map (for example, programs that implement the processing shown in Figures 5A and 5B described later), programs that cause the processor unit 130 to perform processing for creating a health function (for example, programs that implement the processing shown in Figure 6 described later), and programs that cause the processor unit 140 to perform processing for estimating the user's health (for example, programs that implement the processing shown in Figures 7A and 7B described later). Here, it is not specified how the programs are stored in the memory unit 150. For example, the programs may be pre-installed in the memory unit 150. Alternatively, the programs may be installed in the memory unit 150 by being downloaded via a network. In this case, the type of network is not specified. The memory unit 150 can be implemented by any storage means.

[0054] The database unit 200 may store, for example, data obtained from multiple subjects. It may also store, for example, data from a health positioning map generated by the server device 100. Furthermore, it may store, for example, a health function generated by the server device 100. Finally, it may store health information indicating the user's health status derived by the server device 100. This health information, when the user's consent is obtained, can be stored in the database unit 200 and made available for research use by other users.

[0055] Figure 3A shows an example of the configuration of the processor unit 120 in one embodiment. The processor unit 120 may have a configuration for processing the creation of a health positioning map.

[0056] The processor unit 120 includes an acquisition means 121, a processing means 122, a mapping means 123, a clustering means 124, and a characterization means 125.

[0057] The acquisition means 121 is configured to acquire a first dataset for each of the multiple subjects, for a first parameter set described later. For example, the acquisition means 121 acquires a dataset of multiple items (for example, 232 items in one embodiment) per subject. The first parameter set may be an extracted parameter set obtained by, for example, acquiring an initial parameter set dataset, correlating each data point in the initial parameter set dataset, and extracting parameters whose correlation coefficient is greater than or equal to a predetermined threshold. In this case, the extracted parameter set may be extracted to include the four basic parameters described later. The first parameter set may also be an extracted parameter set obtained by, for example, acquiring an initial parameter set dataset and using machine learning to extract a parameter set that has a high influence on the health positioning map from the initial parameter set dataset.

[0058] The acquisition means 121 can, for example, receive data about multiple subjects stored in the database unit 200 via the interface unit 110 and acquire the received data. The acquisition means 121 can, for example, receive data about multiple subjects stored in the database unit 200 from the computer system of a testing facility (e.g., a hospital, research institute, etc.) via the interface unit 110 and acquire the received data. The acquired first data set is passed to the processing means 122 for subsequent processing.

[0059] The database unit 200 may store a first dataset for a first parameter set.

[0060] Figure 4 shows an example of the data structure of the first dataset stored in the database unit 200.

[0061] The database unit 200 stores a first dataset for each of the multiple subjects, corresponding to the first parameter set. Each of the multiple subjects is assigned an ID. For example, the database unit 200 stores a set of values ​​(first dataset) for each parameter of the first parameter set, such as age, muscle mass, BMI, body fat percentage, ultrasound conduction velocity, osteoporosis index, etc.

[0062] Referring again to Figure 3A, in one embodiment, the acquisition means 121 may be configured to acquire first data contained in some of the multiple regions included in the created health positioning map as sub-first data. Alternatively, the acquisition means 121 may be configured to acquire first data contained in some of the multiple regions identified by the clustering means 124, which will be described later, as sub-first data. The acquisition means 121 can acquire first data in regions selected by the health positioning map creator. The health positioning map creator can input the region selection to the server device 100 via the interface unit 110. The health positioning map creator can select regions to which specific groups of subjects may belong in order to create a health positioning map focused on a particular group of subjects, such as a group of male subjects, a group of female subjects, a young adult group (a group under 40 years old), a middle-aged adult group (a group between 40 and 60 years old), or an elderly adult group (a group over 60 years old). The acquired sub-first data can be passed to the clustering means 124 for subsequent processing.

[0063] The processing means 122 is configured to process the first dataset acquired by the acquisition means 121. By processing the first dataset, the processing means 122 can output the first data.

[0064] The processing by the processing means 122 may include any processing as long as it can map the output first data. When creating a positioning map based on mixed male and female data, it is preferable to perform gender correction.

[0065] The processing by processing means 122 may include, for example, dimensionality reduction processing. Dimensionality reduction processing is the process of converting m-dimensional data into n-dimensional data, where m > n. Dimensionality reduction processing can be performed using, for example, multi-dimensional scaling (MDS), principal component analysis, multiple regression analysis, or machine learning, but the means of dimensionality reduction processing are not limited to these. It is preferable that the dimensionality reduction processing reduces the first dataset to 2-dimensional or 3-dimensional data. This is because mapping the 2-dimensional or 3-dimensional data using the mapping means 123 described later results in a map in 2-dimensional or 3-dimensional space, making it easier to understand visually. Dimensionality reduction processing may be performed using multi-dimensional scaling. This is because mapping the first data obtained by multi-dimensional scaling using the mapping means 123 described later results in a map that is easier to understand visually.

[0066] The processing by processing means 122 may include, for example, standardization processing. Standardization processing is the process of aligning the scale of the data for each parameter in the first dataset. Standardization processing may include, for example, the process of calculating a Z score (processing to correct the data so that the mean is 0 and the standard deviation is 1), the process of calculating a T score (processing to correct the data so that the mean is 50 and the standard deviation is 10), etc. Processing means 122 may perform standardization processing on the data of the first dataset for all parameters in the first parameter set, or it may perform standardization processing on the data of the first dataset for specific parameters.

[0067] The processing means 122 may perform standardization on the first dataset of the entire group of subjects, or it may perform standardization on the first dataset of a specific population among the group of subjects. The specific population among the group of subjects includes, but is not limited to, a group of male subjects, a group of female subjects, a young adult group (a group under 40 years old), a middle-aged adult group (a group between 40 and 60 years old), an elderly adult group (a group 60 years and older), etc. The processing means 122 can form any population from the group of subjects and perform standardization on the first dataset of that population.

[0068] For example, the processing means 122 can perform standardization on the male subject group by classifying the first dataset from multiple subjects into a dataset of male subjects and a dataset of female subjects, and standardizing the dataset of male subjects, or by standardizing the dataset of female subjects, it can perform standardization on the female subject group, or it can do both. Performing standardization on the male subject group and / or the female subject group in this way is preferable for parameters in the first parameter set that have gender differences (e.g., triglyceride concentration in the blood), and more preferable for parameters in the first parameter set that have significant gender differences (e.g., red blood cell count in the blood). This is because it eliminates gender differences and makes it possible to create a health positioning map that is not biased by gender differences.

[0069] The processing by the processing means 122 may include, for example, weighting processing. Weighting processing is the process of assigning weights to at least some of the data in the first dataset. For example, weights may be assigned by adding a predetermined number to at least some of the data in the first dataset, or weights may be assigned by multiplying at least some of the data in the first dataset by a predetermined number. The predetermined number to be added or multiplied may be constant or different for each data to be weighted. For example, the predetermined number can be varied so as to assign larger or smaller weights to data that have a large impact on the health function derived by the derivation means 133 described later. Alternatively, for example, the predetermined number can be varied so as to assign larger or smaller weights to data that have a small impact on the health function derived by the derivation means 133 described later.

[0070] The processing means 122 may perform weighting on the first dataset of all subjects, or it may perform weighting on the first dataset of a specific population among the subjects. The processing means 122 can form an arbitrary population from the subjects and perform weighting on the first dataset of that population. The population on which weighting is performed may be the same as or different from the population on which the standardization process described above is performed.

[0071] The mapping means 123 is configured to map the first data, which is the output of the processing means 122, for each of the multiple subjects. Mapping by the mapping means 123 is a process of associating n-dimensional first data with a position in n-dimensional space. By mapping the first data, the mapping means 123 can output a map in which the first data of each of the multiple subjects is mapped. For example, if the first data is two-dimensional, the mapping means 123 can output a two-dimensional map by mapping the first data so that it is associated with a position in two-dimensional space, i.e., on a plane. Figure 9A is a diagram showing an example of the mapping result by the mapping means 123. As shown in Figure 9A, the mapping means 123 outputs a map for multiple subjects by plotting points determined by the first data obtained by the processing means 122 in two-dimensional space (multi-dimensional space). The mapping means 123 may also output a map (radar chart) in which the first data of each of the multiple subjects is mapped by, for example, mapping n-dimensional first data onto a radar chart having n axes.

[0072] The clustering means 124 is configured to cluster the first data mapped by the mapping means 123. Clustering by the clustering means 124 is a process of dividing the mapped first data into a plurality of clusters and identifying the region to which each of the plurality of clusters belongs. In this specification, "region" refers to a certain range in an n-dimensional space and has an extent of n dimensions. The clustering means 124 can divide the mapped first data into any number of clusters. For example, it is preferable for the clustering means 124 to divide the mapped first data into at least three clusters. This is because by using three clusters (for example, clusters such as good health, average health, and poor health as shown in Figure 1B), a health positioning map that can be intuitively understood by the user can be created. The number of clusters to which the mapped first data is divided may depend on the number of subjects N. In the example shown in Figure 9A, the clustering means 124 classifies the first data mapped by the mapping means 123 into four clusters. The clustering means 124 can cluster data using any known method. For example, the clustering means 124 can divide data into multiple clusters using a non-hierarchical clustering method (e.g., k-means method, k-means++ method, PAM method, etc.). Preferably, the clustering means 124 can divide data into multiple clusters using the k-means method. This is because the results of clustering using the k-means method better reflect the trends of the subject population and contain richer information compared to the results of clustering using other methods. The clustering means 124 can identify multiple regions, for example, by defining the boundaries that separate each of the multiple clusters. Defining the boundaries can be done using any known process. For example, in the radar chart example described above, the clustering means 124 can simply distinguish the values ​​of each axis from the values ​​of the other axes and identify multiple axes as multiple regions.

[0073] In one embodiment, the clustering means 124 may be further configured to cluster the sub-first data acquired by the acquisition means 121. The clustering means 124 can divide the sub-first data into a plurality of clusters and identify the respective regions to which the plurality of clusters belong. The clustering means 124 can divide the sub-first data into any number of clusters.

[0074] The characterization means 125 is configured to characterize at least a portion of the multiple regions identified by the clustering means 124. The characterization means 125 may, for example, characterize at least a portion of the multiple regions based on information input to the server device 100 via the interface unit 110 by the health positioning map creator. For example, the health positioning map creator can analyze the characteristics of subjects corresponding to the first data contained in each of the multiple regions and input information on which that region should be characterized based on the analysis results. Alternatively, the characterization means 125 may characterize at least a portion of the multiple regions without relying on input from the health positioning map creator. For example, the characterization means 125 may characterize at least a portion of the multiple regions based on their relative position in the health positioning map, or it may characterize at least a portion of the multiple regions based on machine learning.

[0075] In this way, a health positioning map is created in which at least some of the multiple regions are characterized. In one embodiment, when some of the multiple regions identified by clustering sub-first data are characterized, the health positioning map becomes a health positioning map for some of the subjects among the multiple subjects.

[0076] The health positioning map created by the processor unit 120 is output to the outside of the server device 100, for example, via the interface unit 110. The health positioning map may be sent to the database unit 200 via the interface unit 110 and stored in the database unit 200. Alternatively, it may be sent to the processor unit 130, which will be described later, for the purpose of creating a health function. As will be described later, the processor unit 130 may be a component of the same server device 100 as the processor unit 120, or it may be a component of a different computer system.

[0077] Figure 3B shows an example of the configuration of the processor unit 130 in another embodiment. The processor unit 130 may have a configuration for creating a health function for mapping the health status of a subject onto a health status positioning map. The processor unit 130 may be a processor unit provided by the server device 100 as a replacement for the processor unit 120 described above, or it may be a processor unit provided by the server device 100 in addition to the processor unit 120. If the processor unit 130 is a processor unit provided by the server device 100 in addition to the processor unit 120, the processor unit 120 and the processor unit 130 may be implemented by the same processor, or they may be implemented by different processors.

[0078] The processor unit 130 includes a first acquisition means 131, a second acquisition means 132, and a derivation means 133.

[0079] The first acquisition means 131 is configured to acquire a health positioning map. The acquired health positioning map may be a health positioning map created by the processor unit 120 described above, or a health positioning map created in a different way, as long as it is created using the first parameter set. The acquired health positioning map is passed to the derivation means 133 for subsequent processing.

[0080] The second acquisition means 132 is configured to acquire a second data set for a second parameter set, described later, for at least a portion of the multiple subjects. In this specification, the second parameter set is also simply referred to as the "parameter set." The second parameter set is a part of the first parameter set. The second parameter set may include parameters not present in the first parameter set. The second acquisition means 132 can, for example, acquire data for a portion of the multiple subjects stored in the database unit 200 via the interface unit 110. The acquired second data set is passed to the derivation means 133 for subsequent processing.

[0081] The derivation means 133 is configured to derive a health function that correlates the second dataset obtained by the second acquisition means 132 with the position on the health positioning map obtained by the first acquisition means 131. The derivation means 133 can derive the health function by, for example, machine learning, decision tree analysis, random forest regression, multiple regression analysis, principal component analysis, etc. The health function can be derived for each axis of the n-dimensional health positioning map, for example. For example, if the health positioning map is two-dimensional, a health function X that correlates the second dataset with the X coordinate on the health positioning map and a health function Y that correlates the two datasets with the Y coordinate on the health positioning map can be derived. The derivation means 133 may, for example, arbitrarily increase or decrease the number of variables in the health function to create multiple health functions with identification accuracy, i.e., a group of health functions (hereinafter also referred to as a group of multiple pattern health functions). For example, the derivation means 133 may create (1) health functions that use data from blood test items and data from other items as variables, and (2) health functions that use only data from blood test items as variables, each having a similar degree of accuracy. Alternatively, the derivation means 133 may create a group of health functions as a set of multiple patterns, in which data selected from a set of data from items other than blood test items are used as variables.

[0082] The health function can be, for example, a regression model. The regression model may be a linear regression model or a nonlinear regression model. The derivation means 133 can derive each coefficient of the regression model by machine learning for at least some of the subjects among the multiple subjects, with the second dataset as the independent variable and the coordinates on the health positioning map of those subjects as the dependent variable. When the second dataset obtained from the subjects is input as the independent variable of such a machine-learned regression model, the coordinates on the health positioning map of those subjects are output. The health status of those subjects can be mapped onto the health positioning map using the output coordinates.

[0083] The health function can be, for example, a neural network model. The neural network model has an input layer, at least one hidden layer, and an output layer. The number of nodes in the input layer of the neural network model corresponds to the number of dimensions of the input data. That is, the number of input nodes corresponds to the number of parameters in the second parameter set. The hidden layer of the neural network model can contain any number of nodes. The number of nodes in the output layer of the neural network model corresponds to the number of dimensions of the output data. That is, if the neural network model outputs the X coordinate on the health positioning map, the number of nodes in the output layer is 1. For example, if the neural network model outputs n coordinates on an n-dimensional health positioning map, the number of nodes in the output layer is n. The derivation means 133 can derive the weight coefficients of each node by machine learning for at least some of the subjects among the multiple subjects, using the second dataset as input training data and the position on the health positioning map of those subjects as output training data.

[0084] For example, a set of (input training data, output training data) for machine learning could be (second dataset for a second parameter set for a first subject, coordinates on the health positioning map of the first subject), (second dataset for a second parameter set for a second subject, coordinates on the health positioning map of the second subject), ... (second dataset for a second parameter set for an i-th subject, coordinates on the health positioning map of the i-th subject), ... etc. When the second dataset obtained from subjects is input to the input layer of such a machine learning-trained neural network model, the coordinates on the health positioning map of those subjects are output to the output layer. Using the output coordinates, the health status of those subjects can be mapped onto the health positioning map.

[0085] The health function created by the processor unit 130 is output to the outside of the server device 100, for example, via the interface unit 110. The health function may be sent to the database unit 200 via the interface unit 110 and stored in the database unit 200. Alternatively, it may be sent to the processor unit 140, which will be described later, for the purpose of estimating the user's health. As will be described later, the processor unit 140 may be a component of the same server device 100 as the processor unit 130, or it may be a component of a different computer system.

[0086] Figure 3C shows an example of the configuration of the processor unit 140 in yet another embodiment. The processor unit 140 may have a configuration for processing to estimate the user's health status. The processing by the processor unit 140 can estimate the user's health status by estimating which area on the health status positioning map the user's health status is located in. The processor unit 140 may be a processor unit provided by the server device 100 as a replacement for the processor units 120 and 130 described above, or it may be a processor unit provided by the server device 100 in addition to the processor units 120 and / or 130 described above. If the processor unit 140 is a processor unit provided by the server device 100 in addition to the processor units 120 and / or 130, then the processor units 120, 130, and 140 may all be implemented by the same processor, or they may all be implemented by different processors, or two of the processor units 120, 130, and 140 may be implemented by the same processor.

[0087] The processor unit 140 includes a third acquisition means 141, a fourth acquisition means 142, an output generation means 143, and an output mapping means 144.

[0088] The third acquisition means 141 is configured to acquire a health function. The health function is a function that correlates the dataset for the second parameter set described above with the position on the health positioning map. The acquired health function may be a health function created by the processor unit 130 described above, or a health function created in a different way, as long as it can correlate the user dataset with the position on the health positioning map. The health positioning map may be a health positioning map created by the processor unit 120 described above, or a health positioning map created in a different way, as long as it is created using the first parameter set. The acquired health function is passed to the output generation means 143 for subsequent processing.

[0089] The fourth acquisition means 142 is configured to acquire a user dataset for the user's second parameter set. The fourth acquisition means 142 can, for example, acquire a user dataset stored in the database unit 200 via the interface unit 110. Alternatively, the fourth acquisition means 142 can, for example, acquire a user dataset from a terminal device 300 via the interface unit 110. The acquired user dataset is passed to the output generation means 143 for subsequent processing.

[0090] The output generation means 143 is configured to generate output from the health function. The output generation means 143 generates output from the health function by inputting the user dataset acquired by the fourth acquisition means 142 into the health function acquired by the third acquisition means 141. This output is referred to herein as "health information". The health information includes coordinates on the health positioning map (e.g., X-axis values, Y-axis values).

[0091] For example, if the health function is a regression model as described above, inputting the user dataset as the independent variable of the regression model will output the coordinates on the health positioning map.

[0092] For example, if the health function is a neural network model as described above, inputting the user dataset into the input layer of the neural network model will output coordinates on the health positioning map.

[0093] The output mapping means 144 is configured to map the output generated by the output generation means 143 onto the health positioning map. Since the output generated by the output generation means 143 is a coordinate, the output mapping means 144 can map that coordinate into the n-dimensional space of the health positioning map.

[0094] The output mapped onto the health positioning map by the processor unit 140 is output to the outside of the server device 100, for example, via the interface unit 110. The output can then be transmitted to a terminal device 300, for example, via the interface unit 110.

[0095] In the example described above, the processor unit 140 is provided with output mapping means 144, but the processor unit 140 does not necessarily have to provide output mapping means 144. Instead of the processor unit 140 providing output mapping means 144, the terminal device 300 may have a function to represent health information as a position on a health positioning map. In this case, the output from the output generation means 143, i.e., health information, is transmitted to the terminal device 300 via the interface unit 110.

[0096] Furthermore, each component of the server device 100 described above may consist of a single hardware component or multiple hardware components. If it consists of multiple hardware components, the manner in which each hardware component is connected is irrelevant. Each hardware component may be connected wirelessly or by wire. The server device 100 of the present invention is not limited to a specific hardware configuration. Configuring the processor units 120, 130, and 140 with analog circuits instead of digital circuits is also within the scope of the present invention. The configuration of the server device 100 of the present invention is not limited to those described above insofar as it can realize its functions.

[0097] Figure 3D shows an example of data flow 1 by a server device 100 in one embodiment. As shown in Figure 3D, data flow 1 includes a data acquisition step 10, a data processing step 20, a health assessment map creation step 30, a clustering map creation step 40, a health function value calculation step 50, a positioning map creation step 60, and an output step 70. For example, the data acquisition step 10, the data processing step 20, the health assessment map creation step 30, and the clustering map creation step 40 have functions as a health positioning map creation device and can be implemented, for example, by a server device 100 equipped with the processor unit 120 described above. In addition, the data acquisition step 10 and the health function value calculation step 50 have functions as a health function value calculation device and can be implemented, for example, by a server device 100 equipped with the processor unit 140 described above. In the output step 70, the data generated in the data processing step 20, the health assessment map creation step 30, the clustering map creation step 40, the health function value calculation step 50, or the positioning map creation step 60 is output, and is displayed, for example, on a display device (e.g., a liquid crystal display).

[0098] The dataset acquired in data acquisition step 10 is sent to data processing step 20.

[0099] The data processing step 20 performs, for example, correction 21 and dimensionality reduction 22, as shown in Figure 3D. The data processing step 20 can be implemented, for example, by the processing means 122 of the processor unit 120 described above.

[0100] Correction 21 is the process of correcting the data acquired in data acquisition step 10. Specifically, correction 21 corrects each data acquired in data acquisition step 10 so that the values ​​of the data acquired in data acquisition step 10 fall within a predetermined range (for example, the mean is 0 and the standard deviation is 1). The corrected data is then sent to dimensionality reduction 22.

[0101] Dimensionality reduction 22 reduces the dimensions of multiple data passed from data acquisition step 10 or correction step 21. Specifically, dimensionality reduction 22 uses multiple regression analysis, multidimensional scaling, principal component analysis, or machine learning to reduce the dimensions of multiple data (multidimensional data) passed from data acquisition step 10 or correction step 21 to an arbitrary dimension (2 dimensions in this embodiment). The dimensionally reduced data may be in the form of a function, for example. For example, this function is a function for calculating an indicator related to health. The function is, for example, a function in which some or all of the data contained in the first data are variables, and is created by giving greater weight to data that have a particularly large impact among various disease factors. In this embodiment, the function is created using a linear or nonlinear model of some or all of the data contained in the first data. In one embodiment, a 2-dimensional function is created (in this embodiment, consisting of a function X on the horizontal axis (hereinafter referred to as the first function) and a function Y on the vertical axis (hereinafter referred to as the second function)). The created function is passed to the health assessment map creation step 30 and the output step 70.

[0102] In this embodiment, dimensionality reduction 22 creates a two-dimensional function by reducing multidimensional data to two dimensions, as described above. The first and second functions are functions whose variables are all or some of the multiple data passed from the data acquisition step 10 or correction step 21, and are functions calculated by multiple regression analysis, multidimensional scaling, principal component analysis, or machine learning. In this invention, "machine learning" means either machine learning including deep learning or machine learning not including deep learning. The variables that constitute the first and second functions may be completely identical or completely different, or some of the variables may overlap with each other.

[0103] The health assessment map creation step 30 can be implemented, for example, by the mapping means 123 of the processor unit 120 described above. In the health assessment map creation step 30, for example, a map for evaluating health (hereinafter referred to as the health assessment map) is created using the data processed in the data processing step 20, and more specifically, using a function created by dimensionality reduction. In this embodiment, since the function is two-dimensional, the health assessment map is a two-dimensional map. Figure 9A shows an example of a health assessment map. As shown in Figure 9A, in the health assessment map creation step 30, a health assessment map is created by plotting points determined by the first function and the second function for multiple subjects in a two-dimensional space (multidimensional space).

[0104] The clustering map creation step 40 can be implemented, for example, by the clustering means 124 and characterization means 125 of the processor unit 120 described above. In the clustering map creation step 40, for example, multiple points plotted on the health assessment map created in the health assessment map creation step 30 are clustered into several clusters, and a map characterizing multiple regions (hereinafter referred to as the health positioning map) is created. In the clustering map creation step 40 in this embodiment, a non-hierarchical clustering method (k-means method in this embodiment) is used to cluster the multiple plotted points into any number of clusters. In the example shown in Figure 9A, the points are classified into four clusters. By characterizing at least one of these four regions with health-related information, the health positioning map is created.

[0105] The created health positioning map may be output in the output step 70, passed to the health function value calculation step 50, or passed to the health prediction positioning map creation step 60.

[0106] The health function value calculation step 50 and the health prediction positioning map creation step 60 can be implemented, for example, by the processor units 130 and 140 described above. In the health function value calculation step 50, a health function is first created based on the health positioning map. The number of variables in the health function can be arbitrarily increased or decreased to create multiple health functions, i.e., a group of health functions, that have accuracy in identification. Next, the health function value is calculated for subjects different from those from whom the first dataset was acquired in order to create the health function. Specifically, the health function value for a subject is calculated by applying the created health function to the data of the target subject (newly acquired data) acquired in the data acquisition step 10. Since the health function is a multidimensional function, the health function value is also naturally a multidimensional value.

[0107] The health prediction positioning map creation step 60 plots the health function values ​​of subjects calculated in the health function value calculation step 50 onto the health assessment map created in the health assessment map creation step 30 or the health status positioning map created in the clustering map creation step 40, thereby creating a health prediction positioning map. This makes it possible to predict the health status of subjects for whom data has been newly measured.

[0108] Furthermore, step 60, which involves creating a health prediction positioning map, may also involve plotting the health function values ​​calculated in step 50 using data acquired at time intervals for a single subject onto the health assessment map or the health status positioning map to create a health prediction positioning map. This allows for the evaluation of the degree of change in the subject's health status.

[0109] Furthermore, data obtained from new subjects can also be used to update the health function. In the health function value calculation step 50, it is possible to update the health function by using data obtained from new subjects, or data output from the correction step 21 using such data. This makes it possible to evaluate a wider range of health risks and improve the accuracy of health risk assessment.

[0110] Each step of data flow 1 (in particular, data processing step 20, health assessment map creation step 30, clustering map creation step 40, health function value calculation step 50, and health prediction positioning map creation step 60) may be implemented by logic circuits (hardware) formed on an integrated circuit (IC chip) or the like, or by software. In the latter case, the health assessment device 1 is equipped with a computer that executes instructions for a program, which is software that implements each function. This computer is equipped with, for example, one or more processors and a computer-readable recording medium that stores the above program. The object of the present invention is achieved when the processor in the computer reads the above program from the recording medium and executes it. For example, a CPU (Central Processing Unit) may be used as the above processor. This is possible. The recording medium can be a "non-temporary tangible medium," such as ROM (Read Only Memory), as well as tape, disk, card, semiconductor memory, programmable logic circuit, etc. It may also further include RAM (Random Access Memory) for deploying the program. The program may also be supplied to the computer via any transmission medium capable of transmitting the program (such as a communication network or broadcast wave). One aspect of the present invention can also be realized in the form of a data signal embedded in a carrier wave, in which the program is embodied by electronic transmission.

[0111] According to the data flow described above, a health positioning map and / or health function can be created using various data. In other words, a health positioning map and / or health function can be created that comprehensively calculates the health status of a subject, rather than using existing health indicators for individual diseases. Therefore, a health positioning map and / or health function can be created that can assess various health risks (i.e., assess the overall health status of a subject).

[0112] Furthermore, by combining the various data measured in data acquisition step 10, a health positioning map and / or health function can be flexibly created. In other words, there is a very high degree of flexibility in selecting the items to be measured in data acquisition step 10.

[0113] In one embodiment, a health function is created by machine learning using a second dataset as input data. This makes it possible to create a health function that can more accurately generate indicators of the subject's health status.

[0114] Furthermore, in one embodiment, gender-based data correction is performed before creating a health positioning map using the first dataset. This makes it possible to create a health positioning map that can accommodate any gender.

[0115] Furthermore, in one aspect of the present invention, the first data may include only data obtained by non-invasive measurements. According to the above configuration, data can be obtained without harming the subject, such as through blood tests.

[0116] Furthermore, in one embodiment, a map for evaluating health can be created using the function created in the data processing step 20. Specifically, if the function is a multidimensional vector, a map for evaluating health is created by plotting the points determined by the function for multiple subjects in a multidimensional space. This allows for a visual confirmation of the health status of the subjects.

[0117] Furthermore, in one embodiment 1, points plotted in a multidimensional space are clustered. By referring to the data of subjects belonging to each clustered cluster, it is possible to identify what kind of subjects each cluster represents and to characterize those clusters. As a result, by plotting newly measured subject data on a health positioning map, it becomes possible to predict the health status of the measured subjects.

[0118] Figure 3E shows an example of the configuration of the terminal device 300.

[0119] The terminal device 300 includes an interface unit 310, a camera 320, a display unit 330, a memory unit 340, and a processor unit 350.

[0120] The interface unit 330 exchanges information with the outside of the terminal device 300. The processor unit 320 of the terminal device 300 can receive information from the outside of the terminal device 300 via the interface unit 310 and can transmit information to the outside of the terminal device 300. The interface unit 310 can exchange information in any format.

[0121] The interface unit 310 includes, for example, an input unit that enables information to be input to the terminal device 300. The manner in which the input unit enables information to be input to the terminal device 300 is not limited. For example, if the input unit is a touch panel, the user may input information by touching the touch panel. Alternatively, if the input unit is a mouse, the user may input information by operating the mouse. Alternatively, if the input unit is a keyboard, the user may input information by pressing keys on the keyboard. Alternatively, if the input unit is a microphone, the user may input information by inputting voice into the microphone. Alternatively, if the input unit is a camera, the information captured by the camera may be input. Alternatively, if the input unit is a data reading device, the information may be input by reading information from a storage medium connected to the terminal device 300. Alternatively, if the input unit is a receiver, the receiver may input information by receiving information from outside the terminal device 300 via the network 400.

[0122] The interface unit 310 includes, for example, an output unit that enables the output of information from the terminal device 300. The mode by which the output unit enables the output of information from the terminal device 300 is not specified. For example, if the output unit is a speaker, the information may be output by sound from the speaker. Alternatively, if the output unit is a data writing device, the information may be output by writing the information to a storage medium connected to the terminal device 300. Alternatively, if the output unit is a transmitter, the information may be output by the transmitter transmitting the information to the outside of the terminal device 300 via the network 400. In this case, the type of network is not specified. For example, the transmitter may transmit the information via the Internet or via a LAN.

[0123] The terminal device 300 can receive measurement data from any measuring instrument by communicating with the instrument via the interface unit 310.

[0124] The terminal device 300 can receive data on body composition parameters from the body composition analyzer by communicating with the body composition analyzer via the interface unit 310, for example.

[0125] A body composition analyzer is any device capable of measuring a subject's body composition. A body composition analyzer may be, for example, a type that the subject places on top of during measurement, or a type that can be worn on the body (e.g., a wristwatch-type body composition analyzer). A body composition analyzer may also be implemented by a terminal device 300, for example, by installing an application for measuring body composition.

[0126] The terminal device 300 can receive data on blood pressure parameters from a blood pressure monitor by communicating with the blood pressure monitor via the interface unit 310, for example.

[0127] A blood pressure monitor is any device capable of measuring a subject's blood pressure. A blood pressure monitor can be, for example, a body-worn type (e.g., an upper arm blood pressure monitor, a wristwatch-type blood pressure monitor, a ring-type blood pressure monitor) or a non-contact blood pressure monitor (e.g., a blood pressure monitor that measures blood pressure from an image of the face or finger captured by a camera). The blood pressure monitor may also be implemented by a terminal device 300, for example, by installing an application for measuring blood pressure. The blood pressure monitor may also measure the subject's body temperature. In this case, the body temperature may be measured non-contact (e.g., from an image captured by a camera) or in contact.

[0128] The terminal device 300 can receive data on autonomic nerve parameters from the autonomic nerve measuring device by communicating with the autonomic nerve measuring device via the interface unit 310, for example.

[0129] An autonomic nervous system measuring device is any device capable of measuring the autonomic nervous system function of a subject. An autonomic nervous system measuring device may, for example, be a device capable of detecting heart rate variability. An autonomic nervous system measuring device may be implemented by a terminal device 300, for example, by installing an application for measuring autonomic nervous system function. An autonomic nervous system measuring device can measure pulse wave data as data for autonomic nervous system parameters, for example. An autonomic nervous system measuring device can, for example, acquire pulse wave data from an image of the subject captured by a camera, and derive data for autonomic nervous system parameters from the pulse wave data.

[0130] The terminal device 300 can receive data for questionnaire parameters by, for example, communicating with the questionnaire processing device via the interface unit 310.

[0131] The questionnaire processing device can be any device capable of obtaining data from the questionnaire responses by having subjects answer a questionnaire and processing the subjects' responses. The questionnaire processing device may be, for example, an electronic device (e.g., a game console) capable of processing the subjects' responses to the questionnaire. The questionnaire processing device may be implemented by a terminal device 300, for example, by installing an application that allows subjects to answer a questionnaire. The questionnaire processing device may be, for example, a device capable of optically reading the questionnaire response sheets. In one embodiment, the questionnaire processing device can measure, for example, age, data for subjective evaluation parameters, and / or data for living situation parameters as data for questionnaire parameters. In another embodiment, the questionnaire processing device can measure, for example, age, subjective evaluation of QOL (Quality of Life), subjective evaluation of fatigue, subjective evaluation of psychology, living situation, etc., as data for questionnaire parameters.

[0132] The questionnaire processing device may be, for example, a device capable of deriving questionnaire parameters from data obtained from the subject. Such a questionnaire processing device can obtain data indicating lifestyle from data obtained from an activity tracker (e.g., sleep time, exercise time, etc.). Alternatively, such a questionnaire processing device may have the functionality of an activity tracker and automatically obtain questionnaire parameters from data obtained from the subject. Alternatively, such a questionnaire processing device may have an imaging function and automatically obtain questionnaire parameters from images taken of the subject (e.g., the subject's facial expressions).

[0133] The questionnaire processing equipment may be, for example, a group of questionnaire processing equipment consisting of multiple measuring instruments capable of deriving questionnaire parameters. For example, at least one questionnaire parameter can be obtained from one measuring instrument, and at least one questionnaire parameter can be obtained from another measuring instrument.

[0134] The terminal device 300 can receive temperature data, for example, by communicating with a thermometer via the interface unit 310. Temperature data may include, for example, air temperature and body temperature.

[0135] A thermometer may measure temperature in a non-contact manner (for example, from an image of a face or finger captured by a camera, or by bringing the temperature-sensing part close to the object to be measured) or in a contact manner (for example, by bringing the temperature-sensing part into contact with the object to be measured). A non-contact thermometer may be implemented using an electronic device (e.g., terminal device 300) by connecting the temperature-sensing part to the earphone jack of the electronic device. A contact thermometer can measure body temperature in places such as the armpit, mouth, or ear. A thermometer that measures body temperature in the ear may be of the earphone type (wired earphone, wireless earphone, etc.). Such a contact thermometer may also be implemented using an electronic device (e.g., terminal device 300) by connecting the temperature-sensing part to the earphone jack of the electronic device, or by wirelessly connecting to the electronic device.

[0136] The measuring instruments described above may be portable or handheld. In this specification, a “portable” measuring instrument means an instrument that can be carried by human power. In this specification, a “handheld” measuring instrument means an instrument intended to be carried in daily life. Because portable or handheld measuring instruments are not limited to a specific location, their use facilitates simple measurements at any location and time. The advantage of the present invention is that it allows for the simple evaluation of a user's overall health status using parameters that can be measured using a small number of portable or handheld instruments (for example, 10 or fewer, 5 or fewer, 4 or fewer, preferably 3 or fewer).

[0137] Preferably, the measuring instrument described above does not include a function to measure bone density parameters, particularly the speed of sound (SOS). In a typical embodiment, the measuring instrument described above does not require a function to measure bone density parameters, particularly the speed of sound (SOS). Measuring bone density parameters requires a dedicated equipment configuration and a skilled operator. By not including or requiring a function to measure bone density parameters, the measuring instrument can be made portable or handheld, as described above, or the same functions as the measuring instrument described above can be implemented on the terminal device 300. This facilitates easy measurement at any location and time.

[0138] The measuring instrument described above may be server-linked. A server-linked measuring instrument is a device that has the function of communicating with a server and can directly transmit measured data to the server. In this case, the measuring instrument described above does not need to communicate with the terminal device 300.

[0139] The measuring instruments described above may be implemented by separate devices or by a single device having multiple functions. For example, at least one of the measuring instruments described above may be implemented by the terminal device 300. This reduces the number of measuring instruments and alleviates the burden on the user for measurement. For example, by implementing all of the measuring instruments described above by the terminal device 300, the user can perform measurements using only the terminal device 300.

[0140] The acquisition of data using the above-mentioned measuring instruments may be performed by the subject consciously taking the measurements, or by the subject unconsciously taking the measurements. The acquisition of data using the above-mentioned measuring instruments may be performed without the subject's awareness, for example, by automatically taking measurements when predetermined conditions are met. Measurement may be performed without the subject's awareness, for example, by using measuring instruments attached to the subject's body. For example, by using measuring instruments attached to the subject's body, measurements can be taken regardless of whether the subject is indoors or outdoors (for example, whether the subject is walking or standing still). Alternatively, or in addition to the above, measurements may be performed without the subject's awareness, for example, by using measuring instruments installed within the subject's range of activity. For example, by using measuring instruments installed within the subject's range of activity, measurements can be taken regardless of what the subject is doing within that range of activity (for example, whether the subject is walking or standing still). Measurement devices installed within the subject's range of movement include, but are not limited to, sensors mounted on furniture used by the subject (e.g., chairs, beds, etc.), sensors mounted on electronic devices used by the subject (e.g., personal computers, refrigerators, air conditioners, smart speakers, etc.), and sensors installed in rooms such as the subject's home. For example, data for blood pressure parameters can be automatically measured by a blood pressure monitor worn on the body when predetermined conditions are met. For example, data for body composition parameters can be automatically measured by a body composition analyzer worn on the body when predetermined conditions are met. For example, data for body composition parameters can be automatically measured by a body composition analyzer mounted on the seat of the user's chair when predetermined conditions are met. For example, data for autonomic nervous system parameters can be automatically measured by a camera equipped in an autonomic nervous system measuring device when predetermined conditions are met.For example, data on autonomic nervous system parameters can be automatically derived from images of the subject taken automatically by a camera mounted on an electronic device or terminal device 300 used by the subject when predetermined conditions are met. For example, data on autonomic nervous system parameters can be automatically derived from images of the subject taken automatically by a camera installed in a room such as the subject's home when predetermined conditions are met. For example, data on questionnaire parameters can be automatically acquired from communication with an electronic device (e.g., a smart speaker) used by the subject. Predetermined conditions include, for example, when a predetermined time has arrived (temporal conditions), when entering / leaving a predetermined place (geographical conditions), when performing a predetermined action (behavioral conditions), etc. The specified time may be, for example, a predetermined time within a day (e.g., between 6:00 AM and 8:00 AM, between 11:00 AM and 1:00 PM, between 4:00 PM and 6:00 PM, between 9:00 PM and 12:00 AM, or 6:00 AM, 12:00 PM, 6:00 PM, 12:00 AM, etc.), or a predetermined interval of time (e.g., every hour, every three hours, every six hours, every twelve hours, etc.). The specified place includes, but is not limited to, an office, home, living room, bedroom, etc. The specified action includes, but is not limited to, sitting in a chair, lying in bed, or being within the camera's field of view for a certain period of time (e.g., 10 seconds, 30 seconds, 1 minute or more).

[0141] In one embodiment, a predetermined action may be, for example, acquiring at least one piece of data. For example, in response to acquiring at least one piece of data from among blood pressure parameters, body composition parameters, autonomic nervous system parameters, and questionnaire parameters, the system may automatically acquire other pieces of data from among blood pressure parameters, body composition parameters, autonomic nervous system parameters, and questionnaire parameters. For example, a questionnaire processing device may automatically measure data for blood pressure parameters, body composition parameters, and autonomic nervous system parameters in response to acquiring data for questionnaire parameters from the results of a subject consciously answering a questionnaire. This makes it possible to automatically acquire multiple pieces of data simply by having the subject consciously perform the simple action of answering a questionnaire.

[0142] In one embodiment, the terminal device 300 may perform specific preprocessing on data received from a small number of measuring instruments (for example, 10 or fewer, 5 or fewer, 4 or fewer, preferably 3 or fewer) before transmitting the data to the server device 100 for subsequent processing. This specific preprocessing can, for example, streamline the subsequent processing of data received from a small number of measuring instruments.

[0143] For example, the terminal device 300 may perform specific preprocessing on a portion of the data received from a small number of measuring instruments, or it may perform specific preprocessing on all of the data received from a small number of measuring instruments. For example, the terminal device 300 may perform a first preprocessing on a first subset of the data received from a small number of measuring instruments, and perform a second preprocessing on a second subset of the data received from a small number of measuring instruments, which is different from the first preprocessing. For example, the terminal device 300 can perform a first preprocessing on data acquired by measurements made consciously by the subject, and a second preprocessing on data acquired by measurements made unconsciously by the subject.

[0144] In one embodiment, the terminal device 300 may organize the data received from a small number of measuring instruments into a specific data structure and then transmit it to the server device 100. By organizing the data into a specific data structure, for example, the subsequent processing of the data received from a small number of measuring instruments can be made more efficient.

[0145] For example, the terminal device 300 may organize a portion of the data received from a small number of measuring instruments into a specific data structure, or it may organize all of the data received from a small number of measuring instruments into a specific data structure. For example, the terminal device 300 may organize a first subset of the data received from a small number of measuring instruments into a first data structure, and organize a second subset of the data received from a small number of measuring instruments into a second data structure different from the first. For example, the terminal device 300 can organize data acquired by measurements consciously performed by the subject into a first data structure, and data acquired by measurements unconsciously performed by the subject into a second data structure.

[0146] The terminal device 300 may communicate with network-connectable devices, such as network-connectable electrical products (so-called "IoT devices"), via the interface unit 310. This allows the terminal device 300 to control the devices according to, for example, health status (e.g., location on a health status positioning map). In this case, the devices may be controlled by combining data on the surrounding environment (e.g., temperature, climate, weather, brightness, etc.) with health status (e.g., location on a health status positioning map).

[0147] The device is, for example, an air conditioner. Terminal device 300 can control the air conditioner to maintain an appropriate indoor temperature and / or humidity according to the user's health level. The device is, for example, lighting. Terminal device 300 can control the lighting to maintain an appropriate brightness according to the user's health level. The device is, for example, a music player. Terminal device 300 can control the music player to play appropriate music (e.g., music to relax the mind and body, music to boost motivation, audio to guide yoga, stretching, or aerobic exercise, etc.) according to the user's health level. The device is, for example, a video player. Terminal device 300 can control the video player to play appropriate videos (e.g., videos to relax the mind and body, videos to boost motivation, videos for yoga, stretching, or aerobic exercise, etc.) according to the user's health level.

[0148] The device is, for example, a fragrance diffuser. Terminal device 300 can control the fragrance diffuser to release an appropriate fragrance (e.g., a fragrance that relaxes the mind and body, a fragrance that increases motivation, etc.) according to the user's health level. The device is, for example, a smart speaker. Terminal device 300 can control the smart speaker to allow the user to converse or chat with an appropriate person (e.g., a close friend or family member) or an appropriate avatar to help them relax, according to their health level. The device is, for example, exercise equipment. Terminal device 300 can control the exercise equipment to provide an appropriate exercise program according to the user's health level. The device is, for example, an information terminal. The terminal device 300 can control the information terminal to display arbitrary information (e.g., menus for meals, beverages, or snacks, exercise menus, etc.) according to the user's health status, and the terminal device 300 can also control the information terminal to provide arbitrary services (e.g., health monitoring services by family or affiliated organizations (e.g., companies, etc.), health point services, etc.) according to the user's health status. The information terminal may be the terminal device 300 itself, or it may be a separate device from the terminal device 300.

[0149] Camera 320 is any camera capable of capturing still images or videos. It may be a camera built into the terminal device 300, or an external camera attached to the terminal device 300. For example, if an autonomic nervous system measuring device is implemented by the terminal device 300, images captured by camera 320 can be used to derive data for autonomic nervous system parameters.

[0150] Camera 320 may be a camera capable of acquiring at least one of the following: data on body composition parameters, data on blood pressure parameters, data on autonomic nervous system parameters, and data on questionnaire parameters, or for example, all of these data. This makes it possible to replace at least one of the following: a body composition analyzer, a blood pressure monitor, an autonomic nervous system measuring device, and a questionnaire processing device, or for example, all of these devices, with Camera 320.

[0151] The display unit 330 is any display that shows a screen.

[0152] The memory unit 340 stores programs necessary for executing the processing of the terminal device 300, as well as data necessary for executing those programs. The memory unit 340 also stores a program that causes the processor unit 350 to perform processing for measuring the health status of the subject (for example, a program that implements the processing shown in Figure 8, which will be described later). Here, it is not relevant how the program is stored in the memory unit 340. For example, the program may be pre-installed in the memory unit 340. Alternatively, the program may be installed in the memory unit 340 by being downloaded via the network 350. In this case, the type of network is not relevant. The memory unit 340 can be implemented using any storage means.

[0153] The processor unit 350 controls the operation of the entire terminal device 300. The processor unit 350 reads the program stored in the memory unit 340 and executes the program. This makes it possible to make the terminal device 300 function as a device that executes desired steps.

[0154] In embodiments where the blood pressure monitor is implemented by the terminal device 300, the processor unit 350 may be configured to acquire data on blood pressure by, for example, analyzing images acquired by the camera 320. The processor unit 350 can acquire data on blood pressure by, for example, using a known application to analyze a video of a face acquired by the camera 320. The processor unit 350 can acquire data on blood pressure by, for example, using a known application to analyze a video of a fingertip acquired by a camera.

[0155] In an embodiment in which the autonomic nervous system measuring device is implemented by a terminal device 300, the processor unit 350 may be configured to acquire data on autonomic nervous system function by, for example, analyzing images acquired by a camera 320. The processor unit 350 can acquire data on autonomic nervous system function from images using methods known in the art.

[0156] In another embodiment in which the autonomic nervous system measuring device is implemented by the terminal device 300, the processor unit 350 may, for example, acquire images using the camera 320 that can be used to derive data for autonomic nervous system parameters, and transmit the acquired images to the server device 100 via the interface unit 310 for analysis. In this embodiment, the processor unit 350 does not have the function of deriving data for autonomic nervous system parameters; instead, the server device 100 has that function. This reduces the processing load on the terminal device 300.

[0157] In an embodiment in which the questionnaire processing device is implemented by a terminal device 300, the processor unit 350 may be configured to acquire data for questionnaire parameters by, for example, presenting the questionnaire to the user via a display unit 330 and processing the answers to the questionnaire input via an interface unit 310. The processor unit 350 can acquire data for questionnaire parameters from the answers to the questionnaire using methods known in the art.

[0158] In another embodiment in which the questionnaire processing device is implemented by the terminal device 300, the processor unit 350 may, for example, receive responses to the questionnaire and transmit the received responses to the server device 100 via the interface unit 310 for analysis. In this embodiment, the processor unit 350 does not have the function of deriving data for questionnaire parameters; instead, the server device 100 has that function. This reduces the processing load on the terminal device 300.

[0159] In the example shown in Figure 3E, each component of the terminal device 300 is located inside the terminal device 300, but the present invention is not limited to this. Any of the components of the terminal device 300 may be located outside the terminal device 300. For example, the camera 320, the display unit 330, the memory unit 340, and the processor unit 350 may each be composed of separate hardware components, and each hardware component may be connected via any network. In this case, the type of network is not limited. Each hardware component may be connected, for example, via the Internet, via a LAN, wirelessly, or via a wired connection.

[0160] In the example shown in Figure 2, the database unit 200 is located outside the server device 100, but the present invention is not limited to this. It is also possible to provide at least a portion of the database unit 200 inside the server device 100. In this case, at least a portion of the database unit 200 may be implemented by the same storage means as the storage means implementing the memory unit 150, or by storage means different from the storage means implementing the memory unit 150. In any case, at least a portion of the database unit 200 is configured as a storage unit for the server device 100. The configuration of the database unit 200 is not limited to a specific hardware configuration. For example, the database unit 200 may consist of a single hardware component or multiple hardware components. For example, the database unit 200 may be configured as an external hard disk drive for the server device 100, or as storage on the cloud connected via the network 400.

[0161] 3. First parameter set The inventors focused on the physiological or biochemical mechanisms common to health vulnerability and chronic fatigue in order to assess the overall health status of subjects. While not intended to be theoretically bound, based on previous fatigue medicine research and health vulnerability follow-up studies, common mechanisms may exist for fatigue, chronic fatigue, health vulnerability, aging, and disease onset. These mechanisms are: (1) "Bioxidation (rusting)" indicates the progression of bio-oxidation and a decrease in antioxidant capacity. (2) A "decrease in repair energy" indicating a delay in the release of the above-mentioned biological oxidation, (3) "Inflammation" indicating that oxidized (rusted) cells have been detected, and (4) "Autonomic nervous system function" which indicates the function of sensing and adjusting the above (1) to (3). Therefore, by comprehensively evaluating these parameters (1) to (4), it becomes possible to determine a state of health vulnerability that has not yet progressed to disease (i.e., "pre-disease").

[0162] Based on the theory described above, in a typical embodiment, the first parameter set for obtaining the first dataset in the present invention may include "biogenic parameters," "repair energy reduction parameters," "inflammation parameters," and "autonomic nervous system function parameters." In this specification, the following four parameters—(1) "biogenic parameters," (2) "repair energy reduction parameters," (3) "inflammation parameters," and (4) "autonomic nervous system function parameters"—may be collectively referred to as the four basic parameters.

[0163] The first parameter set is a set of parameters used to create a health positioning map. In this specification and the claims, the first parameter set is also referred to as the "parameter set for creating a health positioning map."

[0164] (Bioxidation parameters) Reactive oxygen species (ROS) oxidize and denature many biomacromolecules that make up cells, such as DNA, lipids, proteins, and enzymes, in the body, impairing cellular function. Oxidative denaturation caused by ROS is thought to be linked to various diseases and aging.

[0165] On the other hand, the body contains antioxidant enzymes such as superoxide dismutase (SOD) and catalase, as well as antioxidants such as coenzyme Q10, vitamin C, and vitamin E, to prevent cell dysfunction caused by reactive oxygen species.

[0166] Therefore, the measurement of "biological oxidation parameters" in the present invention may include measuring oxidative damage caused by reactive oxygen species, measuring antioxidant capacity, or measuring the balance between oxidative damage and antioxidant capacity. The measurement of oxidative damage caused by reactive oxygen species may be performed by directly measuring the amount of reactive oxygen species, or by measuring oxidative damage to proteins, lipids, or nucleic acids.

[0167] Methods for measuring oxidative damage are well known in the art, and those skilled in the art can appropriately select and measure the target of measurement. In the present invention, specific markers used as indicators of oxidative damage by reactive oxygen species include, but are not limited to, d-ROMs (Derivatives of Reactive Oxygen Metabolites), which directly measure the amount of reactive oxygen species in the blood; carbonyl protein content (PCC), which is an indicator of oxidative damage to proteins; 4-hydroxynonenal and isoplastane, which are indicators of oxidative damage to lipids; and 8-OHdG (8-hydroxydeoxyguanosine), which is an indicator of oxidative damage to nucleic acids.

[0168] Methods for measuring antioxidant capacity are well known in the field, and those skilled in the art can appropriately select and measure the target of measurement. In the present invention, specific markers used as indicators of antioxidant capacity include, but are not limited to, BAP (Biological Antioxidant Potential), which quantifies the reducing power to iron, serum thiol status, glutathione measurement, vitamin C content measurement, total coenzyme Q10 amount, and the ratio of reduced coenzyme Q10. Total coenzyme Q10 amount and the ratio of reduced coenzyme Q10 can be measured, for example, using LC-MS / MS (specifically, they can be calculated, for example, from the concentrations of reduced and oxidized coenzyme Q10 detected by multiple reaction monitoring).

[0169] In this invention, the marker that indicates the balance between oxidative damage and antioxidant capacity is the Oxidation Stress Index (OSI), but is not limited to this. In this invention, the OSI is d-ROMs / BAP.

[0170] Preferred biooxidation parameters in the present invention include BAP, total coenzyme Q10 amount, reduced coenzyme Q10 ratio, and OSI.

[0171] Typically, biooxidation parameters are parameters that can be measured by non-invasive tests.

[0172] (Repair energy reduction parameter) Even if biological tissue is damaged by oxidation, the body has mechanisms to repair the damaged tissue. ATP is necessary for tissue damage in the body. However, if ATP production decreases, the repair of damaged tissue will be delayed. Decreased ATP production also leads to delayed fatigue recovery. In this invention, the "repair energy reduction parameter" is an arbitrary parameter that indicates a decrease in ATP production.

[0173] ATP is produced via glycolysis, the TCA cycle, and the electron transport chain, with the largest amount of ATP being produced in the final electron transport chain stage. Coenzyme Q10 is an important coenzyme that plays a role in the electron transport chain. Therefore, the "repair energy reduction parameters" in this invention include, but are not limited to, the total amount of coenzyme Q10, the ratio of reduced coenzyme Q10, and metabolites of glycolysis and the TCA cycle (e.g., pyruvate, lactate, citrate, isocitrate, succinate, fumarate, malic acid, etc.). It should be noted that the total amount of coenzyme Q10 and the ratio of reduced coenzyme Q10 are both "biological oxidation parameters" because they possess antioxidant capacity, and "repair energy reduction parameters" because they contribute to ATP production. Preferred "repair energy reduction parameters" in this invention may include the total amount of coenzyme Q10 and the ratio of reduced coenzyme Q10.

[0174] The methods for measuring the total amount of coenzyme Q10 and the ratio of reduced coenzyme Q10 are as described above. Metabolites of glycolysis and the citric acid cycle can be measured by extracting compounds that reflect glycolysis and the citric acid cycle from metabolome analysis.

[0175] Typically, the repair energy reduction parameter is a parameter that can be measured by non-invasive testing.

[0176] (Inflammation parameters) When a large amount of tissue is damaged by oxidation in a living organism, a large amount of local inflammation occurs through an immune response. The types of inflammation parameters and methods of measurement are well known in the field, and those skilled in the art can appropriately select and measure inflammation parameters.

[0177] Inflammation parameters in this invention include, but are not limited to, CRP (C-Reactive Protein), WBC (white blood cell count), albumin, red blood cell count, interleukin-1β, and interleukin-6.

[0178] Typically, inflammatory parameters are those that can be measured by non-invasive tests.

[0179] (Autonomic nervous system function parameters) A chronological examination of health vulnerability reveals that the first signs of health vulnerability are a decline in autonomic nervous system function (especially parasympathetic nervous system function), followed by a decrease in sleep quality, then the accumulation of fatigue, and finally, decreased motivation, depressive tendencies, immune system dysfunction such as allergies, endocrine abnormalities such as menstrual irregularities, and digestive system abnormalities. Therefore, abnormalities in autonomic nervous system function are an important parameter for identifying the initial stages of health vulnerability.

[0180] In this invention, autonomic nervous system function is evaluated from heart rate parameters. Specifically, the heart rate parameters used in this invention include, but are not limited to, the following. ·Average HR This refers to the average total heart rate over a 5-minute period. • Activity of the entire autonomic nervous system; TP (Total Power = ms) 2 ) This is the calculated total power value of the power spectrum at frequencies of 0-0.4 Hz (VLF, LF, HF) during a 5-minute measurement. This value is said to reflect the overall activity of the autonomic nervous system, which is mainly dominated by sympathetic nervous system activity, and is a value related to fatigue. • Overall activity of the sympathetic nervous system; VLF (Very Low Frequency ms) 2 ) This is a power spectrum in the frequency range of approximately 0.0033 to 0.04 Hz. Generally, this parameter is said to represent the overall activity of the very slow mechanisms of sympathetic nervous system function. • Sympathetic nervous system activity; LF (low frequency ms) 2 ) This is a power spectrum in the frequency range of approximately 0.004 to 0.15 Hz, and this value primarily reflects the activity of the (vasomotor) sympathetic nervous system. • Parasympathetic nerve activity; HF (high frequency ms) 2 ) This is a power spectrum in the frequency range of approximately 0.15 to 0.4 Hz, and this value reflects the activity of the parasympathetic nervous system (vagus nerve). • Balance between the sympathetic and parasympathetic nervous systems; LF / HF ratio This is the ratio of LF (low frequency) to HF (high frequency) power, and this value represents the overall balance between the sympathetic and parasympathetic nervous systems. Generally, a higher value indicates sympathetic nervous system dominance, while a lower value indicates parasympathetic nervous system dominance.

[0181] The above heart rate parameters, which represent autonomic nervous system function, can be measured by methods known in the art, but they can also be measured by a precise methodology that simultaneously measures electrocardiograms and fingertip pulse waves and performs heart rate variability analysis (see Japanese Patent Publication No. 5455071 and Japanese Patent Publication No. 5491749; these documents are incorporated herein by reference). For example, the autonomic nervous system function parameters of the present invention may be measured using the FMCC-VSM301 (Fatigue Science Research Institute Co., Ltd., Osaka, Japan), a simple autonomic nervous system measurement device that can simultaneously measure electrocardiograms and pulse waves.

[0182] Preferred "autonomic nervous system function parameters" in the present invention may include, but are not limited to, mean HR, TP, LF, HF, and LF / HF. Since the values ​​of HF and LF have a large variance and do not follow a normal distribution, it is preferable to evaluate TP, LF, HF, and LF / HF, which are related to HF and LF, by logarithmic transformation. Therefore, more preferred "autonomic nervous system function parameters" in the present invention include mean HR, ln(TP), ln(LF), ln(HF), and ln(LF / HF).

[0183] Typically, autonomic nervous system function parameters are parameters that can be measured by non-invasive tests.

[0184] (Further first parameter set) The first parameter set of the present invention may include one or more of the following parameters in order to create a positioning map that more appropriately evaluates the overall health status of the subject.

[0185] • Basic parameters Basic parameters include known parameters that represent the physical condition and health status of the subject. The basic parameters of the present invention include, but are not limited to, age, height, weight, waist circumference, body composition, bone density, blood pressure, muscle strength, body temperature, and WH ratio.

[0186] Body composition includes, but is not limited to, muscle mass, BMI (Body Mass Index = weight / height), and body fat percentage. Body composition can also be measured using parameters such as bioelectrical impedance analysis (BIA). BIA is a technique that quantitatively measures the components of the human body from the impedance generated when an electric current is passed through the body. For example, body composition analyzers manufactured by InBody Japan Co., Ltd. can measure body composition using BIA.

[0187] Bone density can be measured using various methods, including the MD method, which involves X-ray imaging of the hand bones and measuring the density from the images; the ultrasound method, which uses ultrasound to measure the heel bone; the QCT method, which uses CT scans; and the DEXA method (Dual energy X-ray absorptiometry), which uses X-rays and a computer. In this invention, parameters obtained by any of these measurement methods can be used.

[0188] In this invention, bone density parameters include ultrasonic conduction velocity (SOS = Speed ​​of Sound), osteoporosis assessment (Osteoporosis Index; for example, OSIRIS (Osteoporosis Index of Risk)), and Young Adult Mean (YAM = Young Adult Mean; average BMD (Bone Mineral Density) for younger age groups; bone density = bone mass ÷ area (unit: g / cm²). 2 Examples of such parameters include, but are not limited to, the percentage obtained by comparing the subject's BMD value with the reference value (reference value) set at 100%, and the T-score (a value defined by setting the average BMD value (reference value) for young ages to 0 and the standard deviation to 1SD). The measurement methods for these basic parameters are well known in the field.

[0189] Blood pressure is conventionally measured in this field, and systolic blood pressure can be used as a basic parameter in this invention.

[0190] Muscle strength is conventionally measured in this field, and muscle mass and the average of left and right grip strength can be used as the basic parameters of this invention.

[0191] The WH ratio (waist-hip ratio) is calculated by dividing the waist circumference by the hip circumference and is used as an indicator of obesity. The WH ratio can be used to determine whether an obese person has a "pear-shaped" or "apple-shaped" body type.

[0192] The basic parameters of the present invention may preferably include age, muscle mass, BMI, body fat percentage, SOS, OI, systolic blood pressure, and average grip strength between the left and right hands.

[0193] Basic parameters are those that can be measured by non-invasive tests.

[0194] • Blood parameters In addition to the above-mentioned biological oxidation parameters, it is preferable that the first parameter set also includes blood parameters commonly used to evaluate the target renal excretion, hepatobiliary-pancreatic, and detoxification systems.

[0195] These blood parameters include, but are not limited to, HbA1c (hemoglobin A1c; a glycated protein in which glucose is bound to hemoglobin), ALP (alkaline phosphatase), ALT (alanine aminotransferase), AST (aspartate aminotransferase), BS (blood glucose level), BUN (blood urea nitrogen), CK (creatine kinase; a plasma muscle cell enzyme that can be used to evaluate the exercise, skeletal, and muscular function systems), G-GT (gamma-glutamyl transpeptidase), HDL-C (HDL-cholesterol), HGB (hemoglobin), LD (lactate dehydrogenase), LDL-C (LDL cholesterol), TG (triglycerides; neutral fats), TP (total protein), UA (uric acid), amylase, albumin, potassium, creatinine, chloride, cortisol, sodium, eGFR, vitamins (e.g., vitamin B1), and mineral levels (iron, copper, calcium, etc.).

[0196] Typically, blood parameters are parameters that can be measured by invasive tests.

[0197] • Cognitive function parameters According to the inventors' research, cognitive function declines when fatigue accumulates. Therefore, the first parameter of the present invention may further include a cognitive function parameter.

[0198] The cognitive function parameters of this invention are based on a simple cognitive function test called TMT (Trail Making), in which the user traces in order with a pencil the numbers from 1 to 25 written on a single sheet of paper. These can be obtained through methods such as the Advanced Trail Making Test (ATMT), which performs TMT on a touch panel, and the modified ATMT developed by the inventors (K. Mizuno et al. Brain & Development 33 (2011) 412-420). Although TMT, ATMT, and modified ATMT differ in methodology, they all measure the same thing, and these are all cognitive function parameters of the present invention.

[0199] The inventors have prepared five tasks as a modified ATMT for evaluating various elements of cognitive function, which can be used individually or in combination. Furthermore, the evaluation of each of these cognitive tasks may be performed by total reaction time or by the total number of correct answers.

[0200] Cognitive function parameters are parameters that can be measured by non-invasive tests.

[0201] • Vascular and skin parameters According to the inventors' research, accumulated fatigue can affect blood vessels and skin. Therefore, preferably, the first parameter set of the present invention may also include vascular and skin parameters.

[0202] Vascular parameters include, but are not limited to, vascular age, average capillary length, vascular turbidity, and number of vessels. Average capillary length, vascular turbidity, and number of vessels can preferably be easily measured by image processing of the capillary pathways in the fingernail bed. Image processing of capillary pathways and measurement of these parameters can be performed, for example, with a capillary scope manufactured by Atto Co., Ltd. (Osaka, Japan). Skin parameters include, but are not limited to, the moisture content, transepidermal water loss, and gloss of the skin on the arm. Methods for measuring the moisture content, transepidermal water loss, and gloss of the skin on the arm are well known in this field.

[0203] Vascular and skin parameters are parameters that can be measured by non-invasive examinations.

[0204] • Subjective evaluation parameters The first parameter set of the present invention may include subjective evaluation parameters of the subject in addition to objective parameters obtained by the measurements described above. By adding subjective evaluations to the first parameter set in addition to objective parameters obtained from various measurement values, it is possible to reflect the physical, fatigue, and mental state of the subject, which cannot be fully grasped from the measurement of various components alone, in the health positioning map.

[0205] In one embodiment, the subjective evaluation parameters in the present invention may include subjective evaluations such as fatigue, sleep, and mental state. The subjective evaluation parameters in the present invention may also include subjective evaluations related to personality and temperament.

[0206] The subjective assessment of fatigue may include one or more of the following: a subjective assessment of the duration of fatigue, questions about impairment due to fatigue, a fatigue Visual Analogue Scale (VAS), the Chalder Fatigue Scale (CFQ), a fatigue symptom score (CFQ11) calculated using 11 items from the CFQ (Tanaka M et al., Psychol Rep_2010, 106, 2, 567-575), a questionnaire or VAS regarding presenteeism, and a questionnaire regarding fatigue. A "questionnaire about impairment due to fatigue" refers to a question that confirms the subject's subjective assessment of whether or not there is a causal relationship between fatigue and any impairment. Examples of such questions may include whether the subject feels that fatigue interferes with their work, housework, or studies, or questions about diseases that may be the cause of their fatigue. A "questionnaire regarding fatigue" asks whether the subject is aware of any symptoms of fatigue, such as whether they feel lethargic or whether they feel tired even after a full night's sleep. For presenteeism questionnaires, you can use, for example, the WHO's Health and Work Performance Questionnaire (HPQ) or the Work Limitations Questionnaire (WLQ).

[0207] Subjective assessments of sleep may include one or more questionnaires regarding sleep quality, including the time of sleep onset and wake-up, average sleep duration, VAS score for sleepiness, and sleep quality.

[0208] Subjective assessments of mental state may include one or more of the following: VAS and questionnaires for depression, and VAS and questionnaires for motivation. A "questionnaire for depression" refers to questions about any symptoms of depression, which may include whether one feels depressed or whether one finds socializing with others burdensome. One example is the K6 total (a commonly used index developed by Kessler et al. to represent mental health issues).

[0209] In the above, the "questionnaire" may be evaluated based on the answers to specific questions, or it may be evaluated by assigning a score to the answers to a large number of questions.

[0210] Subjective parameters are parameters that can be measured by non-invasive tests.

[0211] • Living conditions parameters The first parameter set of the present invention may include lifestyle parameters in addition to objective parameters and subjective evaluation parameters. Lifestyle parameters in the present invention are facts about the lifestyle of the subject and may include, for example, years of education, length of marriage, whether or not the person lives with their partner, smoking status (yes / no, frequency and / or amount), drinking status (yes / no, frequency and / or amount), working hours, exercise (yes / no, frequency and / or amount), eating habits (whether or not the person feels they eat too early, frequency of snacking after dinner, frequency of skipping breakfast, etc.), medical history, medication status, supplement intake status, etc.

[0212] Living conditions parameters are parameters that can be measured by non-invasive tests.

[0213] • Further parameters The first parameter set of the present invention may include parameters based on data related to the evaluation of brain function and the nervous system, the cardiovascular and respiratory system, and the renal excretion, hepatobiliary and pancreatic, and detoxification system.

[0214] For example, data related to the evaluation of brain function and the neuropsychiatric system may include, in addition to those mentioned above, data on communication function, activity levels (during the day and during sleep), brain morphology measurements using MRI (Magnetic Resonance Imaging) (which can measure functional decline in areas of brain tissue contraction), resting-state fMRI, and nerve fiber fascicle anisotropy (size and robustness of nerve fiber bundles).

[0215] In addition to those mentioned above, data related to the evaluation of cardiovascular and respiratory function may include blood flow (e.g., which can be measured by a Doppler flowmeter) and exhaled gas component analysis (NO (asthma), acetone (diabetes), etc.). Data related to exhaled gas component analysis can be measured by analysis using mass spectrometry or ion mobility analyzers.

[0216] Data related to the evaluation of renal excretion, hepatobiliary-pancreatic, and detoxification functions may include data such as skin gas component analysis, in addition to those mentioned above. Data related to skin gas component analysis can be measured using mass spectrometry or a highly sensitive variable laser detector.

[0217] (Preferred first parameter set) In one embodiment, the first parameter set of the present invention may include a bio-oxidation parameter, a repair energy reduction parameter, an inflammation parameter, and an autonomic nervous system function parameter (four basic parameters). By creating a health positioning map based on data for this first parameter set including the four basic parameters, it becomes possible to determine a state of health vulnerability that has not yet progressed to disease (i.e., "pre-disease").

[0218] In another embodiment, the first parameter set of the present invention may include four basic parameters, basic parameters, cognitive function parameters, and subjective parameters. While not intended to be theoretical, it is believed that by adding basic parameters, cognitive function parameters, and subjective parameters to the four basic parameters, a broader assessment of fatigue and mental state can be achieved. Preferably, the subjective parameters include assessments of one or more of fatigue, sleep, and mental state, and more preferably, assessments of fatigue.

[0219] In yet another embodiment, the first parameter set of the present invention may include four basic parameters, basic parameters, cognitive function parameters, subjective parameters, and blood parameters. While not intended to be theoretical, adding blood parameters, which can accurately assess endocrine system function, to the four basic parameters, basic parameters for evaluating fatigue and mental state, cognitive function parameters, and subjective parameters to the first parameter set would enable a broader assessment of health, including even more different perspectives.

[0220] In yet another preferred embodiment, the first parameter set of the present invention may include four basic parameters, basic parameters, cognitive function parameters, subjective parameters, blood parameters, vascular and skin parameters, and lifestyle parameters.

[0221] The first parameter set of the present invention typically includes both invasive and non-invasive parameters. This ensures that even when the second parameter set, described later, consists solely of non-invasive parameters, the positioning map used as the basis for evaluation still reflects information on invasive parameters. As a result, an evaluation including the effects of parameters obtainable only through invasive testing can be performed using only non-invasive parameters. This is one of the notable effects of the present invention.

[0222] The first parameter set may be, for example, an extracted parameter set obtained by acquiring an initial parameter set dataset, correlating each data point in the initial parameter set dataset, and extracting parameters whose correlation coefficient is greater than or equal to a predetermined threshold, or it may be an extracted parameter set obtained by using machine learning to extract a parameter set that has a high impact on the health positioning map from the initial parameter set dataset.

[0223] 4. Second parameter set The second parameter set is a part of the first parameter set and is a set of parameters used to derive the health function. By using the second parameter set, the subject's condition can be appropriately represented on the health positioning map using fewer parameters than the first parameter set. In this specification and the claims, the second parameter set is also simply referred to as the “parameter set.” The second parameter set may include parameters not present in the first parameter set.

[0224] In a preferred embodiment of the present invention, the second parameter set may consist only of non-invasive parameters. However, since the positioning map for evaluating this second parameter set may include invasive parameters, evaluating the overall health of a subject using a second parameter set consisting only of non-invasive parameters allows for an evaluation that essentially includes the effects of invasive parameters. This is one of the remarkable effects of the present invention. Furthermore, estimating a user's health status from such a parameter set that does not include invasive test results enables users to easily know their health status regardless of the location of the test. For example, users can learn about their health status through simple tests not only in hospitals, but also in places like companies, pharmacies, community centers, cafes, and their homes.

[0225] In one embodiment, a second parameter set consisting only of non-invasive parameters may include the following parameters: (1) Body composition parameters (2) Autonomic nerve parameters (3) Questionnaire parameters

[0226] Here, (2) autonomic nervous system parameters may include data related to pulse waves. (3) questionnaire parameters may include, for example, age, lifestyle parameters, and / or subjective evaluation parameters. Subjective evaluation parameters included in questionnaire parameters may include subjective evaluations of QOL (Quality of Life), subjective evaluations of fatigue, and subjective evaluations of psychology.

[0227] (1) Body composition parameters may be at least part of the basic parameters of the first parameter set described above. Preferably, body composition parameters may include at least one of BMI and WH ratio, more preferably both BMI and WH ratio. This allows for a correlation between a visually understandable indicator such as body type and the subject's status on the health positioning map. In this case, BMI and WH ratio may or may not be included in the first parameter set. For example, BMI may be included in the first parameter set, while the WH ratio may not be included in the first parameter set. (2) Autonomic nervous system parameters may be at least part of the autonomic nervous system function parameters of the first parameter set described above. (3) Questionnaire parameters may be at least part of the basic parameters, lifestyle parameters, and / or subjective evaluation parameters of the first parameter set described above.

[0228] (1) Data for body composition parameters is measured by a body composition analyzer, (2) data for autonomic nerve parameters is measured by an autonomic nerve measuring device, and (3) data for questionnaire parameters can be measured by a questionnaire processing device. Thus, the parameters in (1) to (3) are parameters that can be measured by at most three measuring devices. This reduces the burden on the user for measurement and facilitates measurement at locations other than inspection facilities such as at home. In a preferred embodiment, either one or both of the body composition parameter and the autonomic nerve parameter are automatically measured unconsciously without the user's awareness, and these parameters are combined with the latest questionnaire parameters to evaluate the overall health on the user's health positioning map.

[0229] The second parameter set in this embodiment is (4) Blood pressure parameter may further be included. By including (4) blood pressure, the prediction accuracy of health status is improved compared to the case of only the parameters in (1) to (3). In a preferred embodiment, any one, any two, or all three of the body composition parameter, the autonomic nerve parameter, and the blood pressure parameter are automatically measured unconsciously without the user's awareness, and these parameters are combined with the latest questionnaire parameters to evaluate the overall health on the user's health positioning map.

[0230] (4) Data for blood pressure parameters can be measured by a sphygmomanometer. Thus, the parameters in (1) to (4) are parameters that can be measured by at most four measuring devices. This improves the prediction accuracy while still reducing the burden on the user for measurement and facilitates measurement at any location and at any time, such as at home.

[0231] In these embodiments, the second parameter set does not include parameters that are complex to measure or time-consuming to measure among the non-invasive parameters. For example, the second parameter set does not include cognitive function parameters and bone density parameters. Rather, the second parameter set consists of parameters that can be easily measured using simple measuring devices, and in one embodiment, consists of parameters that can be measured using at most four measuring devices, in another embodiment, consists of parameters that can be measured using at most three measuring devices, and in yet another embodiment, consists of parameters that can be measured using one measuring device. As a result, the burden on the user for measurement is reduced, and easy measurement at locations other than inspection facilities such as home is achieved.

[0232] In a preferred embodiment, the above automatically measurable parameters can be automatically measured without the user's awareness, triggered by predetermined conditions (e.g., contact with various devices or the distance between various devices and the user falling within a certain range) with each parameter measuring device within the time range set by the user.

[0233] 5. Processing by computer systems FIG. 5A shows an example of the processing in the server device 100. The processing 500 is processing for creating a health positioning map. The processing 500 is executed in the processor unit 120 of the server device 100.

[0234] In step S501, the acquisition means 121 of the processor unit 120 acquires a first data set for the first parameter set for each of a plurality of subjects. The acquisition means 121 can, for example, receive data for a plurality of subjects stored in the database unit 200 via the interface unit 110 and acquire the received data. The acquisition means 121 can, for example, receive data for a plurality of subjects stored in the database unit 200 from the computer system of an inspection facility (e.g., a hospital, a research institute, etc.) via the interface unit 110 and acquire the received data.

[0235] In step S502, the processing means 122 of the processor unit 120 processes the first dataset obtained in step S501 to obtain first data. The processing by the processing means 122 may include, for example, at least one of the following: dimensionality reduction processing, standardization processing, and weighting processing for the first dataset.

[0236] Preferably, the processing by the processing means 122 includes dimensionality reduction processing for the first dataset. This reduces the dimensionality of the multidimensional and complex first dataset, making it possible to create more understandable data and, consequently, a health positioning map. In this case, it is preferable that the dimensionality reduction processing reduces the first dataset to 2D or 3D data. This is because a health positioning map created from 2D or 3D data becomes a map in 2D or 3D space, making it easier to understand visually. Through dimensionality reduction processing, (1) the contribution of each measurement item to the values ​​of each axis of the health positioning map can be determined, and furthermore, (2) by removing data of measurement items that do not significantly affect the values ​​of each axis of the health positioning map, the data on the health positioning map can be understood more clearly.

[0237] More preferably, the processing by the processing means 122 includes a standardization process for the first dataset and a dimensionality reduction process for the standardized dataset. This eliminates scale differences between parameters in the first dataset, ensuring that the influence of each parameter in the first dataset on the health positioning map is considered equally, and enabling the creation of a highly accurate and easy-to-understand health positioning map. In particular, by performing a standardization process on parameters that result from gender differences, for example, both data obtained from male subjects and data obtained from female subjects can be evaluated on the same health positioning map.

[0238] More preferably, the processing by the processing means 122 includes weighting the first dataset, standardization of the weighted dataset, and dimensionality reduction of the standardized dataset. This is because it is possible to highlight the magnitude of the influence of each parameter in the first dataset on the health positioning map, thereby creating a health positioning map that is more accurate and easier to understand.

[0239] The standardization process by the processing means 122 may be performed, for example, on all parameters in the first parameter set, or on specific parameters. The weighting process by the processing means 122 may be performed, for example, on the entire first dataset of multiple subjects, or on the first dataset of a specific population of multiple subjects.

[0240] In step S503, the mapping means 123 of the processor unit 120 maps the first data obtained in step S502 to each of the multiple subjects. The mapping means 123 maps the n-dimensional first data onto an n-dimensional space. By mapping the first data for each of the multiple subjects, the mapping means 123 can output a map in which the first data of each of the multiple subjects is mapped. For example, if the first data is two-dimensional, the mapping means 123 can output a two-dimensional map by mapping the first data to a two-dimensional space, i.e., a position on a plane.

[0241] In step S504, the clustering means 124 of the processor unit 120 identifies multiple regions by clustering the first data mapped in step S503. The clustering means 124 can identify any number of regions by dividing the mapped first data into any number of clusters.

[0242] In step S505, the characterization means 125 of the processor unit 120 characterizes at least a portion of the multiple regions identified in step S504. The characterization means 125 may, for example, characterize at least a portion of the multiple regions based on information input to the server device 100, or it may automatically characterize at least a portion of the multiple regions without relying on input. For example, the characterization means 125 may characterize at least a portion of the multiple regions based on relative position in the health positioning map, or it may characterize at least a portion of the multiple regions based on machine learning.

[0243] The process 500 described above creates a health positioning map characterized by at least some of the multiple regions. The created health positioning map can be used in processes 510, 600, and 700 described later.

[0244] Figure 5B shows another example of processing in the server device 100. Process 510 is the process of creating a health positioning map for data included in a portion of the health positioning map created in process 500. Process 510 is executed in the processor unit 120 of the server device 100.

[0245] In step S511, the processor unit 120 receives an input to select a portion of the multiple regions of the health positioning map created in process 500. The input to select a portion of the multiple regions is received, for example, from outside the server device 100 via the interface unit 110.

[0246] In step S512, the acquisition means 121 of the processor unit 120 acquires the first data mapped to the selected region. The acquired first data may be called sub-first data.

[0247] In step S513, the clustering means 124 of the processor unit 120 identifies multiple regions by clustering the sub-first data acquired in step S512. The processing in step S513 may be the same as the processing in step S504.

[0248] In step S514, the characterization means 125 of the processor unit 120 characterizes at least a portion of the multiple regions identified in step S513. The processing in step S514 may be similar to the processing in step S505.

[0249] The process 510 described above creates a health positioning map for some of the subjects among the multiple subjects. This health positioning map for some of the subjects may be a health positioning map focused on a specific group of subjects, such as a male subject group, a female subject group, a young adult group (under 40 years old), a middle-aged group (40 to under 60 years old), or an elderly group (60 years and older). Multiple regions in a health positioning map focused on a specific group may have different characteristics from multiple regions in the overall health positioning map of the multiple subjects, and can be used to analyze health status from different perspectives.

[0250] Figure 6 shows another example of processing in the server device 100. Process 600 is the process of creating a health function. Process 600 is executed in the processor unit 130 of the server device 100.

[0251] In step S601, the processor unit 130 prepares a health positioning map. For example, the processor unit 130 can prepare a health positioning map by acquiring the health positioning map by means of the first acquisition means of the processor unit 130. The health positioning map is created based on a first dataset for the above-described first parameter set for a plurality of subjects. The prepared health positioning map may be a health positioning map created by process 500 or process 510 as long as it is created using the first parameter set, or may be a health positioning map created in another manner.

[0252] In step S602, the second acquisition means 132 of the processor unit 130 acquires a second dataset for a second parameter set for at least a part of a plurality of subjects. The second parameter set is a part of the first parameter set. The second acquisition means 132 can acquire, for example, data for a part of a plurality of subjects stored in the database unit 200 via the interface unit 110.

[0253] In step S603, the derivation means 133 of the processor unit 130 derives a health function that correlates the second dataset of at least a part of the subjects acquired in step S602 with the positions on the health positioning map of at least a part of the subjects among the plurality of subjects. The derivation means 133 can derive the health function, for example, by machine learning. The health function can be derived, for example, for each axis of an n-dimensional health positioning map.

[0254] The health function may be, for example, a regression model or a neural network model. If the health function is a regression model, the derivation means 133 can derive each coefficient of the regression model by machine learning for at least some of the subjects among the multiple subjects, using the second dataset as the independent variable and the coordinates on the health positioning map of that subject as the dependent variable. If the health function is a neural network model, the derivation means 133 can derive the weight coefficient of each node by machine learning for at least some of the subjects among the multiple subjects, using the second dataset as input training data and the position on the health positioning map of that subject as output training data.

[0255] The process 600 described above creates a health function for mapping the subject's health status onto a health positioning map. The created health function can be used in process 700, which will be described later. By excluding invasive test results from the second parameter set when creating the health function, the resulting health function can determine the position on the health positioning map from the data of the parameter set that does not include invasive test results, and estimate the user's health status. Estimating the user's health status from such a parameter set that does not include invasive test results makes it possible for users to know their health status regardless of the location of the test. For example, users can find out their health status from simple tests not only in hospitals, but also in places like their company, pharmacy, community center, cafe, or home.

[0256] Figure 7A shows another example of processing in the server device 100. Process 700 is a process that estimates the user's health status. Process 700 is executed in the processor unit 140 of the server device 100.

[0257] In step S701, the processor unit 140 prepares a health function. For example, the processor unit 140 can prepare a health function by obtaining it using the third acquisition means 141 of the processor unit 140. The health function is a function that correlates the dataset for the second parameter set with the position on the health positioning map. The acquired health function may be a health function created by process 600 or a health function created in a different way, as long as it can correlate the user dataset with the position on the health positioning map. The health positioning map may be a health positioning map created by process 500 or process 510 or a health positioning map created in a different way, as long as it is created using the first parameter set.

[0258] In step S702, the fourth acquisition means 142 of the processor unit 140 acquires the first user dataset for the user's second parameter set. The fourth acquisition means 142 can, for example, acquire the first user dataset stored in the database unit 200 via the interface unit 110. Alternatively, the fourth acquisition means 142 can, for example, acquire the first user dataset from the user's terminal device via the interface unit 110.

[0259] In step S703, the output generation means 143 of the processor unit 140 obtains a first output by inputting the first user dataset into the health function. For example, if the health function is a regression model, the coordinates on the health positioning map are output as the first output by inputting the first user dataset into the independent variables of the regression model. For example, if the health function is a neural network model, the coordinates on the health positioning map are output as the first output by inputting the first user dataset into the input layer of the neural network model.

[0260] In step S704, the output mapping means 144 of the processor unit 140 maps the first output onto the health positioning map. Since the output obtained in step S703 is a coordinate on the health positioning map, the output mapping means 144 can map that coordinate within the n-dimensional space of the health positioning map.

[0261] The process 700 described above maps the user's health status onto a health positioning map, allowing us to estimate the user's health status from the characteristics of the mapped area. For example, by using a health function that does not include invasive test results in the second parameter set, the user's position on the health positioning map can be identified from the data in the parameter set that does not include invasive test results, and the user's health status can be estimated. Estimating the user's health status from such a parameter set that does not include invasive test results makes it possible for users to know their own health status regardless of the location of the test. For example, users can find out their health status through simple tests not only in hospitals, but also in places like their company, pharmacy, community center, cafe, or home.

[0262] For example, estimated health status can be used to correct other data. Other data may include, for example, data that can vary depending on health status. Other data may include, but are not limited to, test results, including cognitive ability tests, physical fitness tests, and academic ability tests. For example, a user whose test results are poor due to a worse-than-normal health status can be corrected by adding points to their test results. For example, to minimize the impact of a user's health status, a user with relatively poor health among multiple users can be corrected by adding points to their test results.

[0263] Figure 7B shows an example of a process that follows process 700 shown in Figure 7A. The process shown in Figure 7B is for estimating the user's health status after a predetermined period of time has elapsed.

[0264] In step S705, the fourth acquisition means 142 of the processor unit 140 acquires a second user data set for the user's second parameter set. Step S705 is performed at least after a predetermined period of time has elapsed since step S702. The fourth acquisition means 142 can, for example, acquire the second user data set stored in the database unit 200 via the interface unit 110. Alternatively, the fourth acquisition means 142 can, for example, acquire the second user data set from the user's terminal device via the interface unit 110.

[0265] In step S706, the output generation means 143 of the processor unit 140 obtains a second output by inputting the second user dataset into the health function. For example, if the health function is a regression model, the coordinates on the health positioning map are output as the second output by inputting the second user dataset into the independent variables of the regression model. For example, if the health function is a neural network model, the coordinates on the health positioning map are output as the second output by inputting the second user dataset into the input layer of the neural network model.

[0266] In step S707, the output mapping means 144 of the processor unit 140 maps the second output onto the health positioning map. Since the output obtained in step S706 is a coordinate on the health positioning map, the output mapping means 144 can map that coordinate within the n-dimensional space of the health positioning map.

[0267] Steps S705 to S707 allow us to estimate the user's health status after a predetermined period. For example, by comparing the health status estimated in steps S701 to S704 with the health status estimated in steps S705 to S707, we can identify changes in the health status over time.

[0268] Furthermore, it is possible to predict future health status based on the direction of time-series changes on the health positioning map. For example, if the first output is mapped and the health status belongs to the region characterized as a healthy individual on the health positioning map, and the second output is mapped after a predetermined period of time and the health status still belongs to the region characterized as a healthy individual but is approaching the region characterized as a lifestyle-related disease risk group, then it can be predicted that the health status is moving towards a lifestyle-related disease risk.

[0269] In one embodiment, the process 700 can be used to evaluate items for improving health status (e.g., pharmaceuticals, food and beverages, health equipment, etc.). For example, by having a user use an item for improving health status for a predetermined period and comparing a first output before the predetermined period with a second output after the predetermined period has elapsed, it is possible to identify time-series changes on the health status positioning map. The time-series changes on the health status positioning map due to the use of an item for improving health status reflect the effect of the item, and by comparing this with the time-series changes on the health status positioning map when the item for improving health status is not used, it is possible to evaluate the effectiveness of the item for improving health status.

[0270] Furthermore, based on the direction of time-series changes on the health positioning map resulting from the use of items to improve health, it is also possible to recommend items to improve health to the user. For example, items to improve health are generally effective for users whose time-series changes on the health positioning map are in the opposite direction to the direction of time-series changes on the health positioning map resulting from the use of items to improve health. Therefore, it is possible to recommend items to the user that have time-series changes in the opposite direction to the time-series changes on the health positioning map of the user identified by the processing in steps S701 to S707.

[0271] Furthermore, it is possible to predict future health status based on the trajectory of time-series changes on the health positioning map. For example, the health status of a subject can be evaluated by pattern matching the trajectory, which includes the first position resulting from mapping the first output and the second position resulting from mapping the second output after a predetermined period of time. This can be achieved, for example, by learning the trajectory patterns of healthy individuals and subjects with specific disease risks.

[0272] In one embodiment, the process 700 can be used to evaluate the effect of a stimulus on health status. For example, by applying a stimulus to the user for a predetermined period and comparing a first output before the predetermined period with a second output after the predetermined period has elapsed, time-series changes on the health status positioning map can be identified. The time-series changes on the health status positioning map due to the application of the stimulus reflect the effect of the stimulus on health status, and by comparing this with the time-series changes on the health status positioning map when no stimulus is applied, the effect of the stimulus on health status can be evaluated.

[0273] Here, stimuli include, but are not limited to, tactile stimuli, olfactory stimuli, visual stimuli, gustatory stimuli, auditory stimuli, and stimuli from the external environment. Tactile stimuli may include, for example, massage, acupressure, and vibration. Olfactory stimuli may include, for example, smelling a specific odor. Gustatory stimuli may include, for example, eating sweet foods, sour foods, salty foods, bitter foods, and umami foods. Visual stimuli may include, for example, viewing a specific still image, watching a specific video, seeing a specific color, or viewing an object under lighting of a specific brightness. Auditory stimuli may include, for example, listening to specific music, listening to noise, listening to high-pitched sounds (e.g., sounds above approximately 1000 Hz), or listening to low-pitched sounds (e.g., sounds below approximately 100 Hz). External environmental stimuli may include, for example, changes in the external environment, the presence of substances in the external environment (e.g., viruses, allergens, NOx, etc.).

[0274] Furthermore, based on the direction of time-series changes on the health positioning map resulting from the stimulus, it is possible to recommend stimuli to improve the user's health status. For example, stimuli to improve health status are generally effective for users whose time-series changes on the health positioning map are in the opposite direction to the direction of time-series changes on the health positioning map resulting from the stimulus. Therefore, it is possible to recommend stimuli to users that have time-series changes in the opposite direction to the time-series changes on the health positioning map of the user identified by the processing in steps S701 to S707.

[0275] In one embodiment, the process 700 may be used to evaluate the impact of an event on health status. For example, by comparing a first output before the event with a second output after the event, time-series changes on the health status positioning map can be identified. The time-series changes on the health status positioning map due to experiencing the event reflect the impact of the event on health status, and by comparing this with the time-series changes on the health status positioning map when the event was not experienced, the impact of the event on health status can be evaluated. Here, events include, but are not limited to, infectious disease outbreaks (such as Covid-19), natural disasters (e.g., damage caused by storms, heavy rain, heavy snow, floods, storm surges, earthquakes, tsunamis, volcanic eruptions, and other unusual natural phenomena), overtime work, experiences (direct experiences or simulated experiences (e.g., experiences via VR (virtual reality), AR (augmented reality), etc.)), and communication with other people or animals.

[0276] Figure 8 shows an example of data flow in a method implemented in the computer system 10 of the present invention. Figure 8 shows the data flow between a measuring instrument, a terminal device 300, and a server device 100 in a method for measuring the health status of a subject.

[0277] In step S801, the measuring instrument acquires a dataset for the parameter set. Here, the parameter set corresponds to the second parameter set described above. The parameter set may include autonomic nervous system parameters, body composition parameters, and questionnaire parameters.

[0278] In one embodiment, step S801 is, I. To acquire data on autonomic nerve parameters using an autonomic nerve measuring device, II. Obtaining data on body composition parameters using a body composition analyzer. III. Obtaining data for questionnaire parameters using questionnaire processing equipment. It can include...

[0279] In this case, the autonomic nervous system measuring device, body composition analyzer, and questionnaire processing device may each be separate devices, each may be implemented by the same device, or at least two of them may be implemented by the same device. Alternatively, at least two of the autonomic nervous system measuring device, body composition analyzer, and questionnaire processing device may be implemented by the terminal device 300. In this embodiment, in step S801, a dataset is acquired using at most three measuring devices, for example, a dataset is acquired using two measuring devices, or for example, a dataset is acquired using one measuring device. The fewer measuring devices used, the less burden it places on the user for measurement.

[0280] In another embodiment, step S801 is, I. To acquire data on autonomic nerve parameters using an autonomic nerve measuring device, II. Obtaining data on body composition parameters using a body composition analyzer. III. Obtaining data for questionnaire parameters using questionnaire processing equipment, IV. Obtaining data on blood pressure parameters using a blood pressure monitor and It can include...

[0281] In this case, the autonomic nervous system measuring device, body composition analyzer, questionnaire processing device, and blood pressure monitor may each be separate devices, each may be implemented by the same device, or at least two of them may be implemented by the same device. Alternatively, at least two of the autonomic nervous system measuring device, body composition analyzer, questionnaire processing device, and blood pressure monitor may be implemented by the terminal device 300. In this embodiment, in step S801, a dataset is acquired using at most four measuring devices, for example, a dataset is acquired using three measuring devices, for example, a dataset is acquired using two measuring devices, or for example, a dataset is acquired using one measuring device. The fewer measuring devices used, the less burden it is on the user for measurement.

[0282] The acquisition of a dataset for a parameter set may be done consciously or unconsciously by the subject. For example, the acquisition of a dataset for a parameter set can be done without the subject's awareness by automatically taking measurements when predetermined conditions are met. These predetermined conditions include, for example, temporal conditions (e.g., between 6:00 AM and 8:00 AM, between 11:00 AM and 1:00 PM, between 4:00 PM and 6:00 PM, between 9:00 PM and 12:00 AM, or at 6:00 AM, 12:00 PM, 6:00 PM, 12:00 AM, or every hour, every three hours, every six hours, every twelve hours, etc.), geographical conditions (e.g., when leaving work, when entering home), and behavioral conditions (e.g., sitting in a chair, lying in bed, being within the camera's field of view for a certain period of time).

[0283] In step S802, the measuring instrument transmits the data set acquired in step S801 to the terminal device 300, and the terminal device 300 receives the data set. The processor unit 350 of the terminal device 300 acquires the data set via the interface unit 310.

[0284] In one embodiment, the processor unit 350 is I. Obtaining data on autonomic nerve parameters from an autonomic nerve measuring device, II. Obtaining data on body composition parameters from a body composition analyzer, III. Obtaining data for questionnaire parameters from questionnaire processing equipment and The dataset can be obtained by doing this.

[0285] In another embodiment, the processor unit 350 is I. Obtaining data on autonomic nerve parameters from an autonomic nerve measuring device, II. Obtaining data on body composition parameters from a body composition analyzer, III. Obtaining data for questionnaire parameters from questionnaire processing equipment, IV. Obtaining data on blood pressure parameters from a blood pressure monitor and The dataset can be obtained by doing this.

[0286] The timing of step S802 following step S801 is irrelevant. For example, in step S802, the processor unit 350 of the terminal device 300 may acquire a dataset each time a dataset of one parameter from the parameter set is acquired in step S801, or in step S802, the processor unit 350 of the terminal device 300 may acquire a dataset after a dataset of all parameters in the parameter set has been acquired in step S801.

[0287] In embodiments where the measuring instrument is implemented by the terminal device 300, step S802 may be omitted.

[0288] In step S803, the processor unit 350 of the terminal device 300 sends the dataset to the server device 100 via the interface unit 310, and the server device 100 receives the dataset. The processor unit 140 of the server device 100 acquires the dataset via the interface unit 100.

[0289] The timing of step S803 following step S802 does not matter. For example, each time a dataset of one parameter from the parameter set is acquired in step S802, the processor unit 350 of the terminal device 300 may transmit the dataset in step S803, or after the datasets of all parameters in the parameter set have been acquired in step S802, the processor unit 350 of the terminal device 300 may transmit the dataset in step S803.

[0290] For example, when transmitting images acquired for analysis to derive autonomic nervous system parameters to the server device 100, it is preferable to transmit the images to the server device 100 each time they are acquired, or separately from other parameter datasets. This is because images have a large data size, which can lead to communication delays.

[0291] In step S804, the processor unit 140 of the server device 100 derives health information using a health function that correlates the dataset with the subject's position on the health positioning map. The health information includes coordinates on the health positioning map (e.g., X-axis values, Y-axis values). The processor unit 140 can derive health information, for example, by processing steps S701 to S703 of process 700.

[0292] In step S805, the processor unit 140 of the server device 100 transmits health status information to the terminal device 300 via the interface unit 110, and the terminal device 300 receives the health status information. The processor unit 350 of the terminal device 300 receives the health status information via the interface unit 310. In the embodiment in which the above-described measuring instrument is implemented by the terminal device 300, the processor unit 140 of the server device 100 transmits health status information to the measuring instrument that performed the measurement in step S801 via the interface unit 110, and the measuring instrument receives the health status information (for example, coordinates on the health status positioning map (for example, X-axis values, Y-axis values)).

[0293] In step S806, the processor unit 350 of the terminal device 300 represents the subject's health status as a position on a health status positioning map of health status information. Based on the X-axis and Y-axis values ​​included in the health status information, the health status information can be displayed on the health status positioning map. For example, the processor unit 350 can display the health status positioning map on the display unit 330 and plot the coordinates indicated by the health status information on the displayed health status positioning map. In the embodiment in which the above-described measuring instrument is implemented by the terminal device 300, the measuring instrument that performed the measurement in step S801 will display the health status information on the health status positioning map based on the X-axis and Y-axis values ​​included in the health status information.

[0294] Since the data obtained from the measurement in step S801 does not require time for analysis, the process from when the terminal device 300 receives the dataset (or when the terminal device 300 sends the dataset to the server device 100 in step S803) until the subject's health status is represented as a position on the health status positioning map in step S806 can be completed within a predetermined time. The predetermined time can be, for example, 0.01 seconds, 0.02 seconds, 0.05 seconds, 0.1 seconds, 0.2 seconds, 0.5 seconds, within 1 second, within 3 seconds, within 5 seconds, within 10 seconds, within 20 seconds, within 30 seconds, within 45 seconds, within 1 minute, within 5 minutes, within 10 minutes, within 1 hour, within 2 hours, within 12 hours, within 24 hours, etc. This allows the user to immediately know their health status. This high responsiveness reduces the psychological burden on the user regarding measurement and prevents a decrease in the user's motivation to take measurements.

[0295] Furthermore, in steps S805 and S806, the predetermined time can be further shortened by ensuring that the health status information transmitted from the server device 100 includes at least coordinates on the health status positioning map (e.g., X-axis values, Y-axis values). For example, the processor unit 350 of the terminal device 300 that receives the health status information can display the health status information on the health status positioning map simply by plotting the coordinates on the positioning map. This simplifies processing in the terminal device 300 and shortens the time from receiving to displaying the health status information. For example, the amount of data transferred for the transmitted health status information can be reduced, thus preventing a decrease in communication speed. As a result, health status information can be transmitted at high speed, reducing data transfer time and shortening the time required to transmit health status information.

[0296] The health status information received in step S805 and / or the position on the health status positioning map represented in step S806 can be stored in the memory unit 340 of the terminal device 300.

[0297] In one embodiment, the health information received in step S805 and / or the position on the health positioning map represented in step S806 can be used, for example, to correct other data. Other data may be, for example, data that can vary depending on the health status. Other data may include, but are not limited to, test results, including cognitive ability tests, physical fitness tests, academic ability tests, etc. For example, the test results can be corrected by adding points to those of subjects whose test results are poor because their health status is worse than normal. For example, in order to minimize the influence of a subject's health status, the test results can be corrected by adding points to those of subjects with relatively poor health status among a group of subjects.

[0298] In one embodiment, the position on the health positioning map represented in step S806 can be used, for example, to control other network-connectable devices. Here, the other devices may be network-connectable electrical products (so-called "IoT devices").

[0299] For example, the processor unit 350 of the terminal device 300 can generate commands to control the device based on its position on the health positioning map. Then, the processor unit 350 of the terminal device 300 can control the device according to those commands by transmitting them to the device via the network.

[0300] Alternatively, the processor unit 350 of the terminal device 300 transmits the position on the health positioning map to the device via the network. The device can then control its operation according to the instructions by generating commands to control the device based on the position on the health positioning map.

[0301] Here, the device is, for example, an air conditioner. The air conditioner can be controlled to maintain an appropriate indoor temperature and / or humidity according to the location on the health positioning map. The device is, for example, lighting. The lighting can be controlled to maintain an appropriate brightness according to the location on the health positioning map. The device is, for example, a music player. The music player can be controlled to play appropriate music (e.g., music to relax the mind and body, music to boost motivation, etc.) according to the location on the health positioning map. The device is, for example, a video player. The video player can be controlled to play appropriate videos (e.g., videos to relax the mind and body, videos to boost motivation, etc.) according to the location on the health positioning map.

[0302] Controlling other devices in this manner becomes even more useful if, as described above, the process from when the terminal device 300 receives the dataset (or when the terminal device 300 sends the dataset to the server device 100 in step S803) until the subject's health status is represented as a position on the health status positioning map in step S806 is performed within a predetermined time. In other words, by acquiring the position on the health status positioning map used for control within a predetermined time, particularly in near real-time, it becomes possible to achieve real-time control that corresponds to the subject's current health status.

[0303] In one embodiment, if the user of the terminal device 300 gives their consent, the health information derived in step S804 is stored in the database unit 200 and made available for research use by other users.

[0304] By repeating steps S801 to SS805 at least twice, at least two positions on the health positioning map can be obtained.

[0305] In step S806, the subject's health status can be evaluated based on the trajectory containing at least two obtained positions. For example, the subject's health status can be evaluated by pattern matching the trajectory containing the first position obtained in the first steps S801 to S805 and the second position obtained in the second steps S801 to S805 after a predetermined period of time has elapsed. This can be achieved, for example, by learning the trajectory patterns of healthy individuals and the trajectory patterns of subjects with a specific disease risk.

[0306] Here, the specified period is any period. For example, the specified period could be half a day, one day, one week, two weeks, one month, three months, six months, one year, etc. For example, if the specified period is half a day, the health status of the subject will be evaluated from the diurnal variation in their health status. This can provide an indicator of, for example, how much fatigue accumulated due to a day's activities. For example, if the specified period is sleep time, the health status of the subject will be evaluated from the nocturnal variation in their health status. This can provide an indicator of, for example, how much recovery occurred due to sleep at night.

[0307] In the example described above, in step S802, the measuring instrument transmits the data set acquired in step S801 to the terminal device 300, and in step S803, the processor unit 350 of the terminal device 300 transmits the data set to the server device 100 via the interface unit 310. However, the present invention is not limited to this. For example, if the measuring instrument is server-linked, the measuring instrument can transmit the data set directly to the server device 100. Therefore, step S802 can be omitted.

[0308] In one embodiment, step S806 allows for the evaluation of items for improving health status (e.g., pharmaceuticals, food and beverages, health equipment, etc.) based on a trajectory that includes at least two obtained positions. For example, by comparing the first position obtained in the first step S801 to S805 with the second position obtained in the second step S801 to S805 after the user has used the items for improving health status for a predetermined period, the time-series change on the health status positioning map can be identified. The time-series change on the health status positioning map due to the use of the items for improving health status reflects the effect of the items for improving health status, and by comparing this with the time-series change on the health status positioning map when the items for improving health status are not used, the superiority or inferiority of the effect of the items for improving health status can be evaluated.

[0309] Furthermore, based on the direction of time-series changes on the health positioning map resulting from the use of items to improve health, it is also possible to recommend items to improve health to the user. For example, items to improve health are generally effective for users whose time-series changes on the health positioning map are in the opposite direction to the direction of time-series changes on the health positioning map resulting from the use of items to improve health. Therefore, items that have time-series changes in the opposite direction to the time-series changes on the health positioning map of the user identified by the processing in step S806 can be recommended to the user.

[0310] In one embodiment, step S806 may be used to evaluate the effect of stimulation on health status. For example, by comparing the first position obtained in the first step S801 to S805 with the second position obtained in the second step S801 to S805 after the user has been stimulated for a predetermined period, the time-series change on the health status positioning map can be identified. The time-series change on the health status positioning map due to stimulation reflects the effect of stimulation on health status, and by comparing this with the time-series change on the health status positioning map when no stimulation is applied, the effect of stimulation on health status can be evaluated.

[0311] Here, stimuli include, but are not limited to, tactile stimuli, olfactory stimuli, visual stimuli, gustatory stimuli, and auditory stimuli. Tactile stimuli may include, for example, massage, acupressure, vibration, etc. Olfactory stimuli may include, for example, smelling a particular odor. Gustatory stimuli may include, for example, eating sweet foods, sour foods, salty foods, bitter foods, umami foods, etc. Visual stimuli may include, for example, viewing a particular still image, viewing a particular video, viewing a particular color, viewing an object under lighting of a particular brightness, etc. Auditory stimuli may include, for example, listening to a particular piece of music, listening to noise, listening to high-pitched sounds (e.g., sounds above approximately 1000 Hz), listening to low-pitched sounds (e.g., sounds below approximately 100 Hz), etc.

[0312] Furthermore, based on the direction of time-series changes on the health positioning map resulting from the stimulus, it is possible to recommend stimuli to improve the user's health status. For example, stimuli to improve health status are generally effective for users whose time-series changes on the health positioning map are in the opposite direction to the direction of time-series changes on the health positioning map resulting from the stimulus. Therefore, it is possible to recommend stimuli to users that have time-series changes in the opposite direction to the time-series changes on the health positioning map of the user identified by the processing in steps S701 to S707.

[0313] In one embodiment, step S806 may be used to evaluate the impact of an event on health status. For example, by comparing a first position obtained in the first set of steps S801 to S805 before the event with a second position obtained in the second set of steps S801 to S805 after the event, time-series changes on the health status positioning map can be identified. The time-series changes on the health status positioning map due to experiencing an event reflect the impact of the event on health status, and by comparing this with the time-series changes on the health status positioning map when the event was not experienced, the impact of the event on health status can be evaluated. Here, events include, but are not limited to, infectious disease outbreaks (such as Covid-19), natural disasters (e.g., damage caused by storms, heavy rain, heavy snow, floods, storm surges, earthquakes, tsunamis, volcanic eruptions, and other unusual natural phenomena), overtime work, experiences (direct experiences or simulated experiences (e.g., experiences via VR (virtual reality), AR (augmented reality), etc.)), and communication with other people or animals.

[0314] In the embodiment for controlling the device described above, step S806 may be used to evaluate the impact of controlling the device on the health state and to further control the device taking that evaluation into consideration. For example, a second command to control the device can be generated based on a first position obtained in the first steps S801 to S805 and a second position obtained in the second steps S801 to S805 after the device has been controlled according to the first position. For example, by comparing the first position and the second position, a time-series change on the health positioning map can be identified. The time-series change on the health positioning map due to controlling the device reflects the impact of controlling the device on the health state. For example, if the impact of controlling the device on the health state is positive, a second command can be generated to continue controlling the device, and the device can be controlled according to the second command. For example, if the impact of controlling the device on the health state is negative, a second command can be generated to stop controlling the device or to control it in the reverse direction, and the device can be controlled according to the second command.

[0315] For example, if the device is an air conditioner, after the air conditioner is controlled to maintain an appropriate room temperature according to the first position obtained in the first steps S801 to S805, if the second position obtained in the second steps S801 to S805 is (1) a position indicating a worse health condition than the first position, the air conditioner can be controlled to raise or lower the room temperature, or (2) a position indicating a better health condition than the first position, the air conditioner can be controlled to maintain the room temperature.

[0316] For example, if the device is a light fixture, after the light fixture is controlled to maintain an appropriate brightness according to the first position obtained in the first steps S801 to S805, the light fixture can be controlled to increase or decrease its brightness if the second position obtained in the second steps S801 to S805 is (1) a position indicating a worse health condition than the first position, or (2) a position indicating a better health condition than the first position, the light fixture can be controlled to maintain its brightness.

[0317] Referring to Figures 5A, 5B, 6, 7A, 7B, and 8, the above examples illustrate that the processes are carried out in a specific order. However, the order of each process is not limited to those described and can be carried out in any logically possible order.

[0318] In the examples described above with reference to Figures 5A, 5B, 6, 7A, and 7B, the processing of each step shown in Figures 5A, 5B, 6, 7A, and 7B was explained to be realized by a processor unit 120, a processor unit 130, or a processor unit 140 and a program stored in a memory unit 150, but the present invention is not limited thereto. At least one of the processing of each step shown in Figures 5A, 5B, 6, 7A, and 7B may be realized by a hardware configuration such as a control circuit. Alternatively, at least one of the steps shown in Figures 5A, 5B, 6, 7A, and 7B may be performed by a person using a computer system or measuring instruments.

[0319] In the example described above with reference to Figure 8, it was explained that some of the processing steps shown in Figure 8 are implemented by programs stored in the processor unit 350 and memory unit 340 of the terminal device 300, but the present invention is not limited thereto. At least one of the processing steps shown in Figure 8 may be implemented by hardware configurations such as control circuits.

[0320] The present invention is not limited to the embodiments described above, and various modifications are possible within the scope of the claims. Embodiments obtained by appropriately combining the technical means disclosed in different embodiments are also included in the technical scope of the present invention. [Examples]

[0321] (Example 1: Creation of a health positioning map) In this embodiment, initial data on 232 health-related items were first obtained from 720 subjects. This initial data acquisition was carried out at RIKEN Building IIB in Kobe. These 232 items included both invasive and non-invasive tests. Next, the values ​​of the acquired initial data were corrected so that the mean was 0 and the standard deviation was 1. Then, from the corrected data, some data was extracted using a method in which only one data point was extracted if there was data with a correlation coefficient higher than a predetermined value (specifically, a correlation coefficient of 0.9). This extracted data included data on the four basic parameters. In this embodiment, one data point was extracted if there was data with a correlation coefficient higher than 0.9, but the present invention is not limited to this, and the value of the correlation coefficient can be changed as appropriate. By setting the correlation coefficient to 0.9 or higher, it is possible to create a health function that can calculate the health status of subjects more comprehensively.

[0322] As a result of the extraction, 81 items were extracted. These 81 items correspond to the "first parameter set" in the present invention. These 81 items included four basic parameters, basic parameters, cognitive function parameters, subjective parameters, blood parameters, vascular and skin parameters, and lifestyle parameters.

[0323] Next, multidimensional scaling was used to reduce the multidimensional data (i.e., 81-dimensional data) to 2 dimensions, and the data for 692 individuals out of 720 for whom complete data was available was plotted on the 2-dimensional plane. Clustering was performed on the plot distribution patterns of the 692 plots plotted on the 2-dimensional plane using the k-means method, resulting in 10 clusters (Figure 9B). Health-related information was characterized for each cluster, and the health positioning map of the present invention was created. Figure 10 shows the health positioning map created in this embodiment. Note that although Figure 10 also shows the actual plots, the health positioning map of the present invention does not need to include the underlying plots; it is sufficient to include the regions identified by the clustering of the plots and the health-related information associated with those regions.

[0324] (Example 2. Creation of an alternative health positioning map) In this embodiment, initial data on 242 health-related items were first obtained from 1000 subjects. These 242 items included both invasive and non-invasive tests. Next, machine learning was used with a pre-trained model that learned the impact of the 242 data items on the health positioning map to extract items that had a relatively high impact on the health positioning map.

[0325] As a result of the extraction, 69 items were extracted. These 69 items correspond to the "first parameter set" in the present invention. These 69 items included 30 blood parameters and SOS. These 69 items were items that could be measured through 7 measurements. Next, using the extracted 69 items, a health positioning map of the present invention was created using the same method as in Example 1.

[0326] (Example 3. Creating a health function) Using machine learning, we identified a function (health function) that allows for appropriate placement on the health positioning map created in Example 1, with fewer test items (second parameter set) than the first parameter set.

[0327] As shown above, Figure 10 is a health positioning map in this embodiment. When the subjects corresponding to each plot were analyzed, as shown in Figure 10, the plots on the left side (i.e., the -X axis side) of Figure 10 were plots of subjects who were relatively younger, and the plots on the right side (i.e., the +X axis side) were plots of subjects who were relatively older. The group of subjects included in Group G1 in Figure 10 were young, had high levels of depression and anxiety, low autonomic nervous system regulation ability, and a high number of errors in cognitive tasks. Therefore, if a subject whose data has been newly measured belongs to Group G1, it can be seen that the subject is likely to be in a pre-disease state of mental health disorder.

[0328] Furthermore, the subjects included in Group G2 were older and had high levels of serum γ-GTP, serum ALT, serum triglycerides, serum HbA1c, and serum high-sensitivity CRP. Therefore, if a newly measured subject belongs to Group G2, it can be concluded that that subject is likely to be in a pre-disease state of lifestyle-related disease.

[0329] Furthermore, the subjects included in Group G3 were older and had higher blood glucose levels. Therefore, if a newly measured subject belongs to Group G3, it can be concluded that that subject is likely to be in a pre-diabetic state. The region where the first function X ≤ approximately 4 and the second function Y ≤ approximately 2 generally represents a healthy group with no health problems.

[0330] The above groups G1 to G3 are just a few examples of health risks that can be evaluated by the health evaluation device of the present invention; various other health risks can also be evaluated.

[0331] (Example 4. Observation of changes in health status using a health positioning map) We investigated whether changes in the subjects' health status could be observed using the health positioning map created in Example 1. We compared the mapping position on the health positioning map before and after 3 months of reduced CoQ10 intake. The results are shown in Figure 11.

[0332] As is clear from Figure 11, in the subjects compared, a shift was observed from Group G1, the mental health risk group, to the healthy group. Upon closer examination of each test item in these subjects, it was found that the total blood CoQ10 level increased, and parameters related to fatigue and depression, such as fatigue VAS, depression VAS, ChaTF11G, and PS, decreased (Figure 12). These results suggest that reduced CoQ10 may be effective in relieving fatigue and improving mental health, and it was confirmed that the health status of subjects can be tracked using the health positioning map and health assessment method based on the present invention.

[0333] (Example 5. Examination of a second parameter set for simplified measurement) We attempted to use machine learning to identify a function that allows for appropriate placement on a health positioning map using a second set of parameters measured by measuring devices available at home.

[0334] A health positioning map was created using a first parameter set of 76 items from data of 965 subjects. Data from half of the subjects was used as training data, and data from the other half was used to evaluate the resulting function. A health function was created using a second parameter set of 19 items based on four measurements (body composition measurement, blood pressure measurement, autonomic nervous system function measurement, and questionnaire measurement), and a health function was created using a second parameter set of 18 items based on three measurements (body composition measurement, autonomic nervous system function measurement, and questionnaire measurement), and the prediction accuracy was verified.

[0335] The second parameter set, consisting of 19 items based on four measurements, included two body composition parameters, one blood pressure parameter, five autonomic nervous system parameters, and eleven questionnaire parameters.

[0336] The second parameter set, consisting of 18 items from three measurements, included two body composition parameters, five autonomic nervous system parameters, and eleven questionnaire parameters.

[0337] As a result, the health function using a second parameter set of 19 items from four measurements yielded a predictive accuracy of R=0.9778 on the X axis and R=0.9556 on the Y axis (Figure 13). Furthermore, the health function using a second parameter set of 18 items from three measurements yielded a predictive accuracy of R=0.9774 on the X axis and R=0.9532 on the Y axis (Figure 13). It was unexpected that health status could be evaluated with high accuracy even with measurement items from simple measuring instruments.

[0338] Furthermore, these measurement items do not include bone density parameters or cognitive function parameters, and are items that can be measured with at most four measuring devices, preferably at most three measuring devices, and even more preferably one measuring device (e.g., a smartphone). In other words, by using these measurement items, the burden of measurement on the subject can be reduced, and easy measurement can be performed at any time and place, including places other than testing facilities such as the home.

[0339] (Example 6. Analysis using the WH ratio) Similar to Example 5, a health positioning map was created using a first parameter set of 76 items from data of 965 subjects. Under the same conditions as in Example 5, clustering was performed using the k-means method on the plot distribution patterns of the 965 plots plotted in 2D, resulting in 10 clusters.

[0340] Figure 14(a) shows data from 965 individuals plotted and clustered on a health positioning map. The horizontal axis is associated with physical health, with higher values ​​indicating poorer physical health, while the vertical axis is associated with mental health, with higher values ​​indicating poorer mental health. Of the 10 clusters, the third cluster was assessed as a mental health disorder risk group, the tenth cluster was assessed as a lifestyle-related disease risk group, and the sixth and ninth clusters were assessed as both lifestyle-related disease and mental health disorder risk groups.

[0341] The data from the 965 subjects included WH ratio and BMI. In particular, WH ratio and BMI were calculated from data obtained from a body composition analyzer (InBody Japan Co., Ltd.). Using these WH ratio and BMI, subjects with a BMI of 25 or higher and a WH ratio of 1.0 or higher (male) or 0.9 or higher (female) were identified from the data of the 965 subjects. Obese individuals with a BMI of 25 or higher and a WH ratio of 1.0 or higher (male) or 0.9 or higher (female) are known to have apple-shaped obesity (abdominal obesity) and are known to be prone to various complications. Figure 14(b) highlights the data of subjects with a BMI of 25 or higher and a WH ratio of 1.0 or higher (male) or 0.9 or higher (female) on a health positioning map. In Figure 14(b), data for subjects with a BMI of 25 or higher and a WH ratio of 1.0 or higher (male) or 0.9 or higher (female) are represented by black squares, while data for other subjects are represented by white circles. Note that the first parameter set used to create the health positioning map in this example included BMI but not the WH ratio.

[0342] Figure 14(c) shows the results of an analysis of which of the clusters (1st to 10th) shown in Figure 14(a) each subject with a BMI of 25 or higher and a WH-to-Waist ratio of 1.0 or higher (male) or 0.9 or higher (female) belongs to. The proportion of subjects with a BMI of 25 or higher and a WH-to-Waist ratio of 1.0 or higher (male) or 0.9 or higher (female) is shown in black, and the proportion of other subjects is shown in diagonal lines. Subjects with a BMI of 25 or higher and a WH-to-Waist ratio of 1.0 or higher (male) or 0.9 or higher (female) were most frequently classified into cluster 9, with nearly 40% of subjects having a BMI of 25 or higher and a WH-to-Waist ratio of 1.0 or higher (male) or 0.9 or higher (female). As mentioned above, cluster 9 is the cluster evaluated as a risk group for lifestyle-related diseases and mental health disorders. Next, clusters 10 and 8 had a high proportion of individuals with a BMI of 25 or higher and a WH ratio of 1.0 or higher (males) or 0.9 or higher (females), followed by cluster 6.

[0343] It is already known that the more obese a person is (i.e., with an apple-shaped obesity, or abdominal obesity) (i.e., a BMI of 25 or higher and a WH ratio of 1.0 or higher for men or 0.9 or higher for women), the worse their physical health. The results shown in Figure 14(c) were consistent with this finding. This is because subjects with a BMI of 25 or higher and a WH ratio of 1.0 or higher for men or 0.9 or higher for women were more frequently distributed in clusters where subjects with poor physical health were classified (e.g., clusters 6-10) than in clusters where subjects with good physical health were classified (e.g., clusters 1-5). Thus, since the results obtained from the health positioning map created in this embodiment are consistent with the facts regarding obese individuals with apple-shaped obesity (abdominal obesity), it can be considered that the health positioning map created in this embodiment can appropriately represent the health status of subjects.

[0344] Furthermore, the health positioning map created in this embodiment could be used for analysis using parameters (WH ratio) that were not used as part of the first parameter set for creating the health positioning map. This suggests that the second parameter for simplified measurement does not necessarily have to be part of the first parameter, and that analysis is possible even if the second parameter for simplified measurement is not part of the first parameter.

[0345] Furthermore, as shown in Figure 14(c), a tendency was observed for a large number of subjects with poor physical and mental health to have a BMI of 25 or higher and a WH ratio of 1.0 or higher (male) or 0.9 or higher (female). The finding that apple-shaped obesity (abdominal obesity) can be associated not only with physical health but also with mental health was a new and unexpected finding. Based on this new finding, for example, subjects with apple-shaped obesity (abdominal obesity) can be made aware that they may have poor mental health as well as physical health, based solely on their physical appearance or the results of body composition measurements, and can be encouraged to improve their mental health as well. [Explanation of symbols]

[0346] 100 Computer Systems 110 Interface section 120, 130, 140 Processor section 150 memory section 200 Database Department 300 User terminal devices 400 Networks

Claims

1. A method for measuring the health status of a subject, wherein the method is performed in a computer device equipped with a processor, Step (1): The processor obtains a dataset for the parameter set, Step (2): The processor transmits the dataset to the server device, Step (3): The processor receives health information derived from the dataset from the server device, Step (4): The processor represents the health status as a position on the health status positioning map of the health status information. A method comprising, wherein step (1) automatically retrieves other data from the dataset in response to having retrieved at least one data from the dataset.

2. A method for measuring the health status of a subject, wherein the method is performed in a computer device equipped with a processor, Step (1): The processor obtains a dataset for the parameter set, Step (2): The processor transmits the dataset to the server device, Step (3): The processor receives health information derived from the dataset from the server device, Step (4): The processor represents the health status as a position on the health status positioning map of the health status information, Step (5): The processor generates instructions for controlling the device based on the position of the health information on the health positioning map, Step (6): The processor controls the device in accordance with the instructions. A method that includes this.

3. The method according to claim 1 or 2, wherein step (1) includes obtaining the dataset from at least four measuring instruments.

4. The method according to claim 3, wherein each of the four measuring instruments is portable or handheld.

5. The method according to claim 1 or 2, wherein step (1) includes obtaining the dataset from one measuring instrument.

6. The method according to any one of claims 1 to 5, wherein the health information includes the values ​​of the X axis and the Y axis in the health positioning map, and step (4) includes displaying the health information on the health positioning map based on the values ​​of the X axis and the Y axis.

7. The method according to claim 1 or 2, wherein step (1) includes obtaining the dataset by the computer device performing measurements.

8. Step (5): The processor determines a first position and a second position on the health positioning map by repeating steps (1) to (4) at least twice, Step (6): The processor evaluates the health status of the subject based on the trajectory including the first position and the second position. The method according to any one of claims 1 to 7, further comprising:

9. The method according to claim 8, wherein step (5) comprises repeating steps (1) to (4) at least twice in one day.

10. The method according to any one of claims 1 to 9, wherein the server device is configured to derive the health information using a health function that correlates the dataset with the position of the subject on the health positioning map.

11. The method according to any one of claims 1 to 10, wherein steps (2) to (4) are performed within a predetermined time.

12. The method according to claim 11, wherein the predetermined time is approximately 1 minute.

13. The health positioning map is created using a parameter set for creating a health positioning map, The method according to any one of claims 1 to 12, wherein the parameter set is part of the parameter set for creating the health positioning map.

14. After controlling the device, The processor determines a second position on the health positioning map by repeating steps (1) to (4), The processor generates a second instruction for controlling the device based on the position and the second position. The method according to claim 2, further comprising:

15. A device for measuring the health status of a subject, A means for obtaining a dataset for a parameter set, A transmission means for transmitting the aforementioned dataset to a server device, A receiving means for receiving health information derived from the aforementioned dataset from the server device, A means for representing the health status as a position on a health status positioning map of the health status information, A device comprising, wherein the acquisition means is configured to automatically acquire other data from the dataset in response to acquiring at least one data from the dataset.

16. A program for measuring the health status of a subject, wherein the program is executed on a computer device, and the program Step (1): Obtain a dataset for the parameter set, Step (2): Send the dataset to the server device, Step (3): Receiving health status information derived from the dataset from the server device, Step (4): Represent the health status as a position on the health status positioning map of the health status information. A program that causes the computer device to perform a process including the acquisition of at least one data from the dataset, wherein step (1) includes automatically acquiring other data from the dataset in response to acquiring at least one data from the dataset.

17. A device for measuring the health status of a subject, A means for obtaining a dataset for a parameter set, A transmission means for transmitting the aforementioned dataset to a server device, A receiving means for receiving health information derived from the aforementioned dataset from the server device, A means for representing the health status as a position on a health status positioning map of the health status information, Based on the position of the health information on the health positioning map, a control means generates a command to control the device, and controls the device according to the command. A device equipped with the following features.

18. A program for measuring the health status of a subject, wherein the program is executed on a computer device, and the program Step (1): Obtain a dataset for the parameter set, Step (2): Send the dataset to the server device, Step (3): Receiving health status information derived from the dataset from the server device, Step (4): Represent the health status as a position on the health status positioning map of the health status information, Step (5): Based on the position of the health information on the health positioning map, generate commands to control the device, Step (6): Controlling the device in accordance with the command and A program that causes the computer device to perform a process including the following.

Images