Information processing method and information processing device

Abstract

To provide an information processing method capable of easily knowing a BHQ while conducting daily life or the like without attending an inspection agency of a hospital or the like.SOLUTION: An information processing method is a brain health management index estimation method for making a computer estimate a BHQ being a human brain health management index, and includes an acquisition step S10 for acquiring a plurality of vital data from a measuring instrument 21 attached to a body, and an estimation step (a classification step S11, a calculation step S12, an output step S13) for calculating and outputting the BHQ as an estimation value from the plurality of vital data that are acquired.SELECTED DRAWING: Figure 3

Description

[Technical field]

[0001] The present disclosure relates to an information processing method and an information processing device, and more particularly to an information processing method for estimating BHQ, which is a human brain health management index. [Background technology]

[0002] In recent years, attention has been focused on "brain health," which is central to understanding people, and brain information analysis devices and brain health management index calculation devices have been proposed that can convert brain analysis information into easy-to-handle values ​​and use it as an index of health (see, for example, Patent Document 1).

[0003] According to the technology of Patent Document 1, brain image data output by MRI (magnetic resonance imaging) is used to estimate BHQ (Brain Healthcare Quotient), which is a brain health management index. More specifically, BHQ is an index of the "quantity" of the brain's area called gray matter and the "quality" of the brain's area called white matter, which is the degree of organization of nerve fibers, and was internationally standardized in 2018. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2018-33516 A Summary of the Invention [Problem to be solved by the invention]

[0005] However, the technique of Patent Document 1 has the inconvenience that the BHQ cannot be determined unless an MRI examination is performed at a specialized examination facility such as a hospital.

[0006] Therefore, an object of the present disclosure is to provide an information processing method and an information processing device that enable a person to easily find out about the BHQ while going about their daily lives, without having to go to a testing institution such as a hospital. [Means for solving the problem]

[0007] In order to achieve the above object, an information processing method according to one embodiment of the present disclosure is an information processing method in which a computer estimates a human brain health care quotient (BHQ), which is an index for managing the health of the human brain, and includes an acquisition step of acquiring a plurality of vital data that can be measured daily, and an estimation step of calculating and outputting an estimated value of BHQ from the acquired plurality of vital data.

[0008] In addition, in order to achieve the above-mentioned object, an information processing device according to one embodiment of the present disclosure is an information processing device that estimates BHQ (Brain Healthcare Quotient), which is a health management index for a human brain, and is equipped with an acquisition unit including an input circuit that acquires multiple vital data that can be measured on a daily basis, and a control unit including a processor that calculates and outputs an estimated BHQ from the multiple vital data acquired by the acquisition unit. Effect of the Invention

[0009] The present disclosure provides an information processing method and information processing device that enable a person to easily find out about the BHQ while going about their daily life, etc., without having to go to a testing institution such as a hospital. [Brief description of the drawings]

[0010] [Figure 1] FIG. 1 is a block diagram showing a configuration of a brain health management index presumption device according to the first embodiment. [Diagram 2] FIG. 2 is a diagram showing a specific example of vital data. [Diagram 3] FIG. 3 is a flowchart showing the procedure by which the brain health management index estimation device calculates the BHQ as an estimated value using decision tree analysis. [Figure 4] FIG. 4 is a diagram illustrating the decision tree analysis used in the classification step of FIG. [Diagram 5]FIG. 5 is a diagram illustrating the four categories classified by the decision tree analysis shown in FIG. [Figure 6] FIG. 6 is a diagram showing the experimental results regarding the correlation between the BHQ estimated using the decision tree analysis shown in FIG. 4 and the true value. [Figure 7] FIG. 7 is a flowchart showing the procedure by which the brain health management index estimation device calculates the BHQ as an estimated value using a product-sum operation. [Figure 8] FIG. 8 is a diagram showing the experimental results regarding the correlation between the BHQ estimated by the product-sum calculation shown in Equation 2 and Equation 3 and the true value. [Figure 9] FIG. 9 is a flowchart showing the procedure by which the brain-health management index estimation device calculates the region-specific BHQ of the brain and the whole brain BHQ as estimated values. [Figure 10] FIG. 10 shows the results of cluster analysis of 90 brain regions. [Figure 11] FIG. 11 shows the results of an experiment in which a cluster analysis of subjects was performed using the body part-specific BHQ for several types of functional categories shown in FIG. [Figure 12] FIG. 12 is a block diagram showing a configuration of a brain health management index presumption device according to the second embodiment. As shown in FIG. [Figure 13] FIG. 13 is a flowchart showing a procedure for the brain-health care index estimation device to calculate the BHQ as an estimated value by analyzing at least one of the user's facial expression, posture, and voice. [Figure 14] FIG. 14 is a diagram showing a specific example of a process in which the brain health management index estimation device acquires video data of a user's facial expression and audio data of the user's voice through a dialogue with the user via the display unit and the input unit. [Figure 15] FIG. 15 is a diagram illustrating the process of the estimation unit that calculates the BHQ as an estimated value by analyzing the obtained video data of several types of facial expressions. [Figure 16]FIG. 16 is a diagram showing a specific example of a process in which the brain health management index estimation device instructs the user to imitate a sample shown on a display unit, and then acquires and analyzes video data of the user's posture and facial expression, as well as audio data of the user's voice. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] (Insights gained by the inventors) The inventors have studied whether BHQ can be estimated from vital data that can be measured on a daily basis without using brain image data obtained by MRI. Specifically, the inventors analyzed the correlation between BHQ obtained using MRI and multiple vital data that can be measured on a daily basis obtained by familiar measuring devices such as wearable devices and body composition scales for multiple subjects, and found that a correlation exists between specific vital data and BHQ. In other words, it was confirmed that BHQ can be estimated from specific vital data that can be measured on a daily basis without using MRI. Further research has confirmed that a specific relationship exists between BHQ and facial expressions and postures of people contained in video data obtained from a camera, or the voice of a user contained in audio data, instead of vital data that can be measured on a daily basis, and that by using this relationship, BHQ can be estimated from at least one of the video data and audio data obtained from a camera.

[0012] More specifically, the information processing method according to the first embodiment of the present disclosure is an information processing method in which a computer estimates a human brain health care index BHQ (Brain Healthcare Quotient), and includes an acquisition step of acquiring a plurality of vital data measurable on a daily basis, and an estimation step of calculating and outputting an estimated value of BHQ from the acquired plurality of vital data. Here, "vital data measurable on a daily basis" refers to vital data obtained from a measuring instrument attached to the body such as a wearable device, a measuring instrument carried on the body such as a smartphone, and a measuring instrument installed at home such as a body composition scale.

[0013] As a result, the BHQ is calculated as an estimated value from multiple vital data that can be measured daily, so that users can easily know their BHQ while living their daily lives without having to go to a testing institution such as a hospital. In addition, users can easily know their BHQ as an estimated value at low cost. In addition, the information processing method according to the present disclosure is believed to contribute to the prevention of dementia, the development of lifestyle improvement apps for living a healthy life, the development of products and spaces that are good for the brain, and even corporate health management, including employee health management.

[0014] Moreover, an information processing method according to a second embodiment of the present disclosure is the information processing method of the first embodiment, in which the plurality of vital data includes at least one of vital data at rest, vital data related to sleep, and vital data related to exercise. More specifically, an information processing method according to a third embodiment of the present disclosure is the information processing method of the first or second embodiment, in which the plurality of vital data includes a resting heart rate, a deep sleep time, and a number of steps taken in a certain period of time. As a result, vital data having an extremely high correlation with BHQ is used from among a certain type of vital data, and BHQ is estimated with high accuracy.

[0015] Further, an information processing method according to a fourth aspect of the present disclosure is the information processing method according to any one of the first to third aspects, wherein the estimation step includes a classification step of classifying the acquired vital data into one of a plurality of categories using decision tree analysis. As a result, the user is classified into one of a plurality of categories using decision tree analysis, and the range of BHQ divided into stages can be specified.

[0016] In addition, an information processing method according to a fifth aspect of the present disclosure is the information processing method of the fourth aspect, in which the estimation step further includes a calculation step of calculating the BHQ from the category classified in the classification step and the person's age. In this way, a known correlation between a person's age and BHQ is used, and the BHQ is estimated with high accuracy.

[0017] An information processing method according to a sixth aspect of the present disclosure is any of the information processing methods of the first to fifth aspects, wherein in the estimating step, the BHQ is calculated by performing a product-sum operation on the plurality of vital data acquired. This allows the BHQ to be estimated simply and with high accuracy by the product-sum operation on the plurality of vital data.

[0018] Moreover, an information processing method according to a seventh embodiment of the present disclosure is an information processing method in which a computer estimates a BHQ (Brain Healthcare Quotient), which is a health management index for a person's brain, and includes an acquisition step of acquiring at least one of video data of a person and audio data of a person's voice, and an estimation step of calculating and outputting an estimated BHQ from at least one of the acquired video data and audio data. This allows the estimated BHQ to be calculated in a non-contact manner by simply standing in front of the camera without having to wear a measuring device on the body, and therefore allows the person to easily know their BHQ without having to go to a testing institution such as a hospital.

[0019] An information processing method according to an eighth aspect of the present disclosure is the information processing method of the seventh aspect, wherein in the estimating step, the BHQ is calculated using at least one of facial expression, posture, and voice of the person included in at least one of the video data and audio data. As a result, at least one of facial expression, posture, and voice of the person that has a high correlation with BHQ is used from at least one of the video data and audio data of the person, so that the BHQ can be estimated with high accuracy.

[0020] An information processing method according to a ninth embodiment of the present disclosure is the information processing method of any one of the first to eighth embodiments, in which, in the estimation step, a brain region-specific BHQ is calculated as an estimated value from the data acquired in the acquisition step and output. Furthermore, an information processing method according to a tenth embodiment of the present disclosure is the information processing method of the ninth embodiment, in which, in the estimation step, a whole brain BHQ is further calculated as an estimated value from the part-specific BHQ. As a result, the brain region-specific BHQ is estimated, and it is possible to know a brain health index in more detail than when only the whole brain BHQ is estimated.

[0021] An information processing method according to an eleventh aspect of the present disclosure is any of the information processing methods of the first to tenth aspects, further including a prediction step of predicting a future BHQ of the person based on the BHQ estimated in the estimation step. This allows the person's future BHQ to be predicted, making it possible to prepare in advance for deterioration of brain health indexes.

[0022] The information processing method according to a twelfth aspect of the present disclosure is the information processing method of the ninth aspect, further including a classification step of classifying the type of the person's brain by using the region-specific BHQ calculated in the estimation step. This allows the type of the person's brain to be classified, making it possible to take effective measures to improve BHQ according to the type and to give advice leading to behavioral change.

[0023] A program according to a thirteenth aspect of the present disclosure is a program for causing a computer to execute steps included in any of the information processing methods of the first to twelfth aspects. An information processing device according to a fourteenth aspect of the present disclosure is an information processing device for estimating BHQ (Brain Healthcare Quotient), which is a human brain health management index, and includes an acquisition unit including an input circuit for acquiring a plurality of vital data measurable on a daily basis, and a control unit including a processor for calculating and outputting BHQ as an estimated value from the plurality of vital data acquired by the acquisition unit.

[0024] As a result, the BHQ is calculated as an estimated value from multiple vital data that can be measured daily, so that users can easily know their BHQ while living their daily lives without going to a testing institution such as a hospital. In addition, users can easily know their BHQ as an estimated value at low cost. In addition, the program and information processing device disclosed herein can contribute to the prevention of dementia, the development of lifestyle improvement apps for living a healthy life, the development of products and spaces that are good for the brain, and even corporate health management, including employee health management.

[0025] Hereinafter, the embodiments of the present disclosure will be described in detail with reference to the drawings. Each of the embodiments described below shows a specific example of the present disclosure. The numerical values, judgment criteria, display examples, realization forms, components, arrangement and connection forms of components, steps, order of steps, and the like shown in the following embodiments are merely examples and are not intended to limit the present disclosure. In addition, each figure is not necessarily a strict illustration. In each figure, substantially the same configuration is given the same reference numeral, and duplicated explanations are omitted or simplified.

[0026] (Embodiment 1) First, a brain health management index estimation device according to embodiment 1 that can easily estimate BHQ while going about one's daily life or the like using a familiar measuring device that can perform daily measurements will be described.

[0027] 1 is a block diagram showing a configuration of a brain health management index estimation device 30 according to the first embodiment. In this embodiment, the brain health management index estimation device 30 is realized in a form built into a wearable device 10. Note that the realization form of the brain health management index estimation device 30 is not limited to a form built into the wearable device 10, but may be built into a measuring device carried on the body such as a smartphone, or a measuring device installed at home such as a body composition meter, or may be realized in a stand-alone form as a smartphone app or the like without being connected to a measuring device.

[0028] In this embodiment, the wearable device 10 is a computing device (for example, a smart watch, smart glasses, etc.) worn on the body of a user 5, and includes a peripheral device 20, a brain health management index estimation device 30, and a display unit 40.

[0029] The peripheral device 20 is an information source of vital data, environmental data, and attribute data required by the brain health management index estimation device 30, and has a measuring instrument 21, an input unit 22, and a storage unit 23. The vital data is information about the living body of the user 5, and includes more than 20 types of vital data, such as vital data related to exercise (data belonging to "activity" in FIG. 2), vital data related to sleep (data belonging to "sleep" in FIG. 2), and vital data at rest (data belonging to "health index" in FIG. 2), as shown in FIG. 2. The environmental data is information about the environment of the user 5, and includes temperature, humidity, illuminance, etc. The attribute data is information about the attributes of the user 5, and includes age, sex, etc.

[0030] The measuring instrument 21 has sensors such as a heart rate sensor, a blood oxygen concentration sensor, a blood pressure sensor, a bioimpedance sensor, a three-axis acceleration sensor, a gyro sensor, a position information sensor, a magnetic sensor, an ambient light sensor, a temperature and humidity sensor, and an air pressure sensor, as well as a signal processing circuit including an A / D converter and a timer for processing signals obtained by the sensors, and detects the biological condition of the user 5 and stores it in the memory unit 23 as vital data, and detects the environment of the user 5 and stores it in the memory unit 23 as environmental data.

[0031] The input unit 22 is an input device (for example, a touch panel, input buttons, etc.) that accepts input related to the attributes of the user 5 from the user 5, and stores the accepted input related to the attributes in the storage unit 23 as attribute data.

[0032] The storage unit 23 is a memory (e.g., a semiconductor memory or the like) that holds the vital data and environmental data obtained by the measuring instrument 21 and the attribute data obtained by the input unit 22, and provides these data to the brain health management index estimation device 30 in response to a request from the brain health management index estimation device 30. Note that the brain health management index estimation device 30 may obtain the vital data, environmental data, and attribute data directly from the measuring instrument 21 and input unit 22 of the peripheral device 20 without going through the storage unit 23. Furthermore, the brain health management index estimation device 30 may obtain the vital data, environmental data, and attribute data directly by manual input from the user 5 without being connected to the peripheral device 20.

[0033] The brain-health management index estimation device 30 is an example of an information processing device that estimates BHQ, which is a human brain health management index, and includes an acquisition unit 31 and a control unit 32.

[0034] The acquisition unit 31 is an example of a processing unit that acquires a plurality of vital data that can be measured daily, and in this embodiment, acquires vital data, environmental data, and attribute data from the peripheral device 20. The acquisition unit 31 is, for example, an input circuit, a communication interface, etc.

[0035] The control unit 32 is a processing unit that performs various information processing such as calculating BHQ (hereinafter also referred to as "estimated BHQ") as an estimated value using the vital data, environmental data, and attribute data acquired by the acquisition unit 31, and outputs the results to an external device including the display unit 40, and includes a memory that stores programs (i.e., apps) and the like, and a processor that executes the programs. The control unit 32 functionally includes an estimation unit 33, a prediction unit 34, and a classification unit 35. The external device may include a memory, an external device connected via a communication interface, and the like.

[0036] The estimation unit 33 calculates the BHQ as an estimated value from the plurality of vital data acquired by the acquisition unit 31, and outputs it to the display unit 40. The plurality of vital data includes at least one of vital data at rest, vital data related to sleep, and vital data related to exercise. More specifically, the plurality of vital data includes the heart rate at rest, the deep sleep time, and the number of steps in a certain period. The algorithm for calculating the BHQ includes a method using decision tree analysis and a method using product-sum calculation. Which algorithm is to be adopted is set in advance by the user 5 or the like. The estimation unit 33 also has a function of calculating the brain region-specific BHQ as an estimated value from the plurality of vital data acquired by the acquisition unit 31, and outputting it to the display unit 40, and calculating the whole brain BHQ as an estimated value from the region-specific BHQ, and outputting it to the display unit 40. In this specification, when simply described as "BHQ", it means the whole brain BHQ.

[0037] The prediction unit 34 executes a prediction step of predicting the future direction of change in BHQ of the user 5 from the amount of change in the multiple vital data acquired by the acquisition unit 31 over a certain period of time, and outputting the predicted result to the display unit 40. More specifically, the prediction unit 34 predicts the future direction of change in BHQ by adding or subtracting a weight for the amount of change in the multiple vital data over a certain period of time.

[0038] The classification unit 35 classifies the type of the human brain using the region-specific BHQ calculated by the estimation unit 33, and outputs the classification result to the display unit 40.

[0039] The display unit 40 is a device that displays the results of information processing in the control unit 32, and is, for example, a liquid crystal display.

[0040] Fig. 2 is a diagram showing a specific example of vital data. Here, some of more than 20 types of vital data are shown, which are classified into three groups: vital data related to exercise (data belonging to "activity" in Fig. 2), vital data related to sleep (data belonging to "sleep" in Fig. 2), and vital data at rest (data belonging to "health index" in Fig. 2).

[0041] In the "activity" group, "step count" is the average number of steps taken over a certain period of time (e.g., 1 minute). "Restless time" is the average restless time over a certain period of time (e.g., one day) (i.e., the total time during which body movement does not exceed a predetermined threshold). "Somewhat active" is the average time during which a person was somewhat active over a certain period of time (e.g., one day) (i.e., the total time during which body movement was within a predetermined small range). "Very active" is the average time during which a person was very active over a certain period of time (e.g., one day) (i.e., the total time during which body movement was within a predetermined large range). These vital data are obtained using, for example, a three-axis acceleration sensor, a position information sensor, a heart rate sensor, a blood pressure sensor, etc.

[0042] In the "sleep" group, "sleep time" is the average number of hours slept per day. "number of awakenings" is the average number of times awakened per day. "REM sleep" is the average number of REM sleep hours per day. "light sleep" is the average number of light sleep hours per day. "deep sleep" is the average number of deep sleep hours per day. These vital data are obtained using a heart rate sensor, a blood pressure sensor, a 3-axis acceleration sensor, etc.

[0043] In the group of "health indexes", "weight" is the weight of the user 5 inputted via the input unit 22. "BMI" is a value calculated from the height and weight of the user 5 inputted via the input unit 22 by weight (kg) / (height (m)×height (m)). "Body fat percentage" is a value expressed as body fat mass (kg) / body fat mass (kg)×100, and is obtained using an input by the user 5 and a bioimpedance sensor or the like. "Muscle mass" is the weight of muscle tissue, and is a value calculated, for example, by (body weight (kg)-body fat mass (kg))×50%, and is obtained using an input by the user 5 and a bioimpedance sensor or the like. "Visceral fat" is the level of visceral fat, and is inputted by the user 5 via the input unit 22, for example. "Resting heart rate" is the heart rate at rest, and is obtained by a heart rate sensor or the like.

[0044] Next, the operation of the brain health management index estimation device 30 configured as above will be described.

[0045] FIG. 3 is a flowchart showing a procedure (that is, an information processing method) in which the brain health management index estimation device 30 calculates the BHQ as an estimated value using decision tree analysis.

[0046] First, the acquisition unit 31 acquires a plurality of vital data from the measuring device 21 attached to the body of the user 5 (acquisition step S10).

[0047] Next, the estimation unit 33 classifies the user 5 into one of a number of categories using decision tree analysis based on the acquired vital data (classification step S11). A category refers to each division into a number of divisions of the estimated BHQ within a predetermined numerical range.

[0048] Next, the estimation unit 33 calculates the BHQ as an estimated value from the classified category and the age of the user 5 (calculation step S12). In the calculation, a predetermined relationship is used for deriving the BHQ as an estimated value from the category and the age.

[0049] Finally, the estimation unit 33 outputs the BHQ as an estimated value to the display unit 40 (output step S13). The classification step S11, calculation step S12, and output step S13 constitute an estimation step of calculating and outputting the BHQ as an estimated value from the multiple vital data acquired in the acquisition step S10.

[0050] Fig. 4 is a diagram for explaining the decision tree analysis used in the classification step S11 in Fig. 3. Here, a decision tree is shown for determining into which of four categories (Cat 0, Cat 1, Cat 2, Cat 3 in order of decreasing BHQ) a user 5 should be classified based on four vital data ("resting heart rate", "deep sleep", "very active", and "number of steps") obtained from the user 5.

[0051] First, the estimation unit 33 determines whether the vital data "resting heart rate" is below a predetermined threshold (here, 72 beats / minute) (S20), and if not (No in S20), then determines whether the vital data "number of steps" is below a predetermined threshold (here, 11,899 steps) (S23), and if the result is positive (Yes in S23), classifies the user 5 into category Cat2 (S26), whereas if the result is negative (No in S23), classifies the user 5 into category Cat3 (S27).

[0052] On the other hand, if the result at step S20 is positive (Yes at S20), the estimation unit 33 then determines whether the vital data “deep sleep” is below a predetermined threshold (here, 63 minutes / day) (S22), and if the result is negative (No at S22), classifies the user 5 into category Cat0 (S25).

[0053] On the other hand, if the result is positive in step S22 (Yes in S22), the estimation unit 33 then determines whether the vital data "deep sleep" is below a predetermined threshold (here, 47 minutes / day) (S24), and if the result is positive (Yes in S24), the estimation unit 33 then determines whether the vital data "very active" is below a predetermined threshold (here, 27 minutes / day) (S28), and if the result is positive (Yes in S28), the estimation unit 33 classifies the user 5 into category Cat1 (S30), while if the result is negative (No in S28), the estimation unit 33 classifies the user 5 into category Cat0 (S31).

[0054] On the other hand, if the result is negative in step S24 (No in S24), the estimation unit 33 determines whether the vital data "resting heart rate" is below a predetermined threshold value (here, 67 beats / min) (S29), and if the result is positive (Yes in S29), it classifies the user 5 into category Cat2 (S32), while if the result is negative (No in S29), it classifies the user 5 into category Cat1 (S33).

[0055] In this way, the estimation unit 33 uses decision tree analysis to classify the user 5 into one of four categories (Cat0, Cat1, Cat2, Cat3) from the four vital data obtained from the user 5 ("resting heart rate," "deep sleep," "very active," and "number of steps").

[0056] Fig. 5 is a diagram for explaining the four categories classified by the decision tree analysis shown in Fig. 4. In this diagram, a relationship between the age and average BHQ of ordinary people with previously known healthy brains (reference line 50 sloping downward to the right) and areas corresponding to the four categories Cat0 to Cat3 (rectangular areas sloping downward to the right) are shown on a two-dimensional coordinate system consisting of age (horizontal axis) and BHQ (vertical axis).

[0057] The baseline 50 indicates a linear decline in BHQ with increasing age.

[0058] Category Cat0 is a rectangular region of a certain width extending parallel to the baseline 50, and for the same age, this region indicates a BHQ obtained by adding +2.5 to +7.5 to the average BHQ indicated by the baseline 50 (i.e., a "high" BHQ).

[0059] Category Cat1 is a rectangular region of a certain width extending parallel to the reference line 50, and for the same age, this region indicates a BHQ obtained by adding -2.5 to +2.5 to the average BHQ indicated by the reference line 50 (i.e., the "average" BHQ).

[0060] Category Cat2 is a rectangular region of a certain width extending parallel to the baseline 50, and for the same age, this region indicates a BHQ obtained by adding -7.5 to -2.5 to the average BHQ indicated by the baseline 50 (i.e., a "low" BHQ).

[0061] Category Cat3 is a rectangular region of a certain width extending parallel to the baseline 50, and for the same age, this region indicates a BHQ obtained by adding -12.5 to -7.5 to the average BHQ indicated by the baseline 50 (i.e., a "fairly low" BHQ).

[0062] The black dots in FIG. 5 indicate the age and BHQ of the subjects in the experiment described below.

[0063] As shown in Fig. 5, the four categories Cat0 to 3 classified by the decision tree analysis shown in Fig. 4 indicate the degree of offset from the average BHQ of normal people with healthy brains of the same age. Using this, in calculation step S12 in Fig. 3, the estimation unit 33 calculates the BHQ as an estimated value from the category classified by the decision tree analysis and the age of the user 5. Specifically, the estimation unit 33 calculates the BHQ in normal times on the reference line 50 in Fig. 5 from the age of the user 5, and calculates the BHQ as an estimated value by adding an offset corresponding to the category classified by the decision tree analysis to the calculated BHQ (i.e., for categories Cat0, Cat1, Cat2, and Cat3, the offsets are +5, 0, -5, and -10, respectively). The offsets (i.e., +5, 0, -5, -10) are the center values ​​of the ranges of values ​​(i.e., +2.5 to +7.5, -2.5 to +2.5, -7.5 to -2.5, -12.5 to -7.5) to be added to the BHQ indicated by the reference line 50 in each category in FIG.

[0064] FIG. 6 is a diagram showing the experimental results regarding the correlation between the BHQ estimated using the decision tree analysis shown in FIG. 4 and the true value. The type of plot is changed according to the categories Cat0 to 3. More specifically, this diagram is a two-dimensional plot of four vital data ("resting heart rate", "deep sleep", "light sleep", and "very active") obtained for each of 25 subjects whose true BHQ values ​​are known, with the "estimated value" BHQ obtained by the decision tree analysis shown in FIG. 4 and the "true value" BHQ plotted on the horizontal and vertical axes, respectively.

[0065] As shown in this figure, the correlation coefficient was 0.89 and the mean absolute error was 1.59 between the true value of BHQ and the estimated value obtained by the decision tree analysis shown in Figure 4. From these findings, it can be said that the BHQ as an estimated value obtained by the decision tree analysis shown in Figure 4 indicates the true value with a high degree of certainty.

[0066] FIG. 7 is a flowchart showing the procedure by which the brain health management index estimation device 30 calculates the BHQ as an estimated value using a product-sum operation.

[0067] First, the acquisition unit 31 acquires a plurality of vital data V1, V2, . . . , Vn from the measuring device 21 attached to the body of the user 5 (acquisition step S40).

[0068] Next, the estimation unit 33 performs a product-sum calculation shown in the following equation 1 using the acquired multiple vital data to calculate the BHQ as an estimated value (product-sum calculation step S41).

[0069] Estimated BHQ=k1·V1+k2·V2+··+kn·Vn+k(n+1) (Formula 1)

[0070] Finally, the estimation unit 33 outputs the calculated estimated value, BHQ, to the display unit 40 (output step S42).

[0071] The important vital data used in this product-sum calculation are "VO2Max (maximum oxygen intake)" and "duration of very active exercise" for calculating the estimated BHQ for men, and "heart rate during non-REM sleep," "duration of very active exercise," "calories burned during exercise," and "VO2Max (maximum oxygen intake)" for calculating the estimated BHQ for women.

[0072] Therefore, the product-sum calculation formula is specifically expressed as the following formulas 2 and 3.

[0073] Estimated BHQ for men = k1 · VO2Max (maximum oxygen uptake) + k2 · minutes of very active exercise + k3 + constant (average BHQ for men of their age) (Equation 2)

[0074] Here, in equation 2, k1 = 0.3409, k2 = 0.1041, and k3 = -20.3982.

[0075] Estimated BHQ for women = k1 · "HR during non-REM sleep" + k2 · "Time spent on very active exercise" + k3 · "Calories burned during exercise" + k4 · "VO2Max (maximum oxygen intake)" + k5 + constant (average BHQ for women of their age) (Equation 3)

[0076] Here, in equation 3, k1 = -0.4510, k2 = 0.2071, k3 = -0.0069, k4 = -0.2752, and k5 = 39.4118.

[0077] The vital data "VO2Max (maximum oxygen intake)" is a value calculated by 15 x maximum heart rate / resting heart rate, and is obtained by a heart rate sensor or the like. In this case, the maximum heart rate is the maximum heart rate that is reached when the exercise intensity is increased. The vital data "exercise calories burned" is a value that can be easily obtained by using a body movement sensor or the like, or is input by the user 5 via the input unit 22.

[0078] In the above formulas 2 and 3, age, sex, BHQ, and 40 types of vital data for 55 subjects were used, with the difference from the average BHQ for that person's age as the objective variable, and the 40 types of vital data as the explanatory variables.The coefficient k was determined by multiple regression analysis after reducing the dimensionality of the explanatory variables using t-SNE (t-distributed Stochastic Neighbor Embedding).

[0079] Fig. 8 shows the experimental results of the correlation between BHQ estimated by the product-sum calculation shown in the above formulas 2 and 3 and the true value. More specifically, Fig. 8(a) shows the relationship between the estimated value (horizontal axis) and the true value (vertical axis) of the difference from the average BHQ for a person's age, and Fig. 8(b) shows the relationship between the estimated value (horizontal axis) and the true value (vertical axis) of BHQ. The correlation between BHQ estimated by the product-sum calculation shown in the above formulas 2 and 3 and the true value is plotted for each of male and female subjects (55 subjects in total) whose true BHQ values ​​are known.

[0080] The correlation coefficient between the estimated value and the true value for the difference shown in Figure 8(a) is 0.63, and the mean absolute error is 2.77. The correlation coefficient between the estimated value and the true value for BHQ shown in Figure 8(b) is 0.83, and the mean absolute error is 2.77.

[0081] As can be seen from these, the BHQ as an estimated value obtained by the product-sum calculation shown in the above formulas 2 and 3 can be said to indicate the true value with a high degree of certainty.

[0082] FIG. 9 is a flowchart showing the procedure by which the brain-health management index estimation device 30 calculates the region-specific BHQ of the brain and the whole brain BHQ as estimated values.

[0083] First, the acquisition unit 31 acquires a plurality of vital data from the measuring device 21 attached to the body of the user 5 (acquisition step S50).

[0084] Next, the estimation unit 33 uses the acquired multiple vital data to calculate the region-specific BHQ of the brain as an estimated value by decision tree analysis or product-sum calculation (region-specific BHQ calculation step S51). It is known that the human brain is classified into multiple regions (e.g., 90 items), and each region is associated with a different function. By utilizing such correspondence, specific vital data and algorithms (decision tree analysis or product-sum calculation formula) required for calculating each region-specific BHQ are prepared in advance.

[0085] Next, the estimation unit 33 calculates the whole brain BHQ as an estimated value by performing an operation according to a predetermined relational expression using the calculated BHQs of the multiple regions (whole brain BHQ calculation step S52). Note that the relational expression for deriving the whole brain BHQ from the multiple BHQs of the multiple regions is clarified by a prior analysis.

[0086] Finally, the estimation unit 33 outputs the calculated multiple regional BHQs and whole brain BHQ to the display unit 40 (output step S53).

[0087] This allows the BHQ of each part of the brain to be estimated, providing a more detailed indicator of brain health than if only the whole-brain BHQ were estimated.

[0088] Next, the functions of the classification unit 35 of the control unit 32 included in the brain health management index estimation device 30 will be described.

[0089] Figure 10 shows the results of a cluster analysis of 90 brain regions. This shows the results of an analysis of the regions into 10 functional categories using cluster analysis, which analyzes the similarities between regions for the 90 region-specific BHQs obtained from multiple subjects (i.e., grouping together regions that have similar tendencies toward high / low BHQs). The horizontal axis shows multiple subjects, the vertical axis shows regions, and the shading indicates the level of BHQ (the lower the score, the darker the shade).

[0090] As can be seen from Figure 10, based on the similarities of the BHQs for each region, the brain regions can be classified into 10 functional categories ("motivation," "memory," "creativity," "understanding others," "self-understanding," "cognition," "understanding things," "speaking ability," "thinking ability," and "movement").

[0091] FIG. 11 shows the results of an experiment in which a cluster analysis of subjects was performed using the body part BHQs of several functional categories shown in FIG. 10. In other words, the results show the grouping of people with similar body part category characteristics (tendency to have high / low BHQ). Specifically, the results show the classification of brain types into six types shown in six radar charts ((a) to (f) in FIG. 11). Each radar chart is the result of standardizing the body part BHQs of the 10 functional categories shown in FIG. 10 for each type. Note that each radar chart is classified by brain pattern, and does not include the perspective of large or small BHQ.

[0092] The six classified brain types, as shown in Figure 11, are: "high ability to understand things but low self-understanding" (Figure 11 (a)), "high self-understanding but poor memory" (Figure 11 (b)), "high motivation but low creativity" (Figure 11 (c)), "high ability to understand others but poor memory" (Figure 11 (d)), "high ability to think but poor memory" (Figure 11 (e)), and "good ability to speak but poor memory" (Figure 11 (f)).

[0093] As can be seen from Fig. 11, by using the region-specific BHQ, a person's brain type can be classified into one of six types. The classification unit 35 of the brain health management index estimation device 30 classifies the person's brain type using the region-specific BHQ calculated by the estimation unit 33, and outputs the classification result to the display unit 40. As a result, the person's brain type is classified, so that it becomes possible to take effective measures to improve BHQ according to the type and to provide advice that leads to behavioral change.

[0094] As described above, the information processing method according to the first embodiment is an information processing method in which a computer estimates BHQ (Brain Healthcare Quotient), which is a health management index for a person's brain, and includes an acquisition step of acquiring a plurality of vital data measurable on a daily basis, and an estimation step of calculating and outputting BHQ as an estimated value from the acquired plurality of vital data. The program according to the first embodiment is a program that causes a computer to execute the steps included in the information processing method. Furthermore, the information processing device according to the embodiment is an information processing device that estimates BHQ (Brain Healthcare Quotient), which is a health management index for a person's brain, and includes an acquisition unit including an input circuit that acquires a plurality of vital data measurable on a daily basis, and a control unit including a processor that calculates and outputs BHQ as an estimated value from the plurality of vital data acquired by the acquisition unit.

[0095] As a result, the BHQ is calculated as an estimated value from multiple vital data that can be measured daily, so that users can easily know their BHQ while living their daily lives without having to go to a testing institution such as a hospital. In addition, users can easily know their BHQ as an estimated value at low cost. In addition, the information processing method according to the present disclosure is believed to contribute to the prevention of dementia, the development of lifestyle improvement apps for living a healthy life, the development of products and spaces that are good for the brain, and even corporate health management, including employee health management.

[0096] (Embodiment 2) Next, a brain health management index estimation device according to embodiment 2 will be described, which can estimate BHQ simply and in a non-contact manner while a user is working, exercising, going about daily life, etc., by using a camera installed on-site such as an office.

[0097] 12 is a block diagram showing a configuration of a brain health management index estimation device 30a according to embodiment 2. In this embodiment, the brain health management index estimation device 30a is realized as a part of a brain health management index estimation system 11 including a camera 25, a display unit 40a, and an input unit 40b.

[0098] The camera 25 is an imaging device that captures images of the facial expressions and body posture of the user 5 and collects audio and other sounds, thereby providing the obtained video of the user 5 (i.e., video data and audio data) to the brain health management index estimation device 30a, and is, for example, a video camera capable of capturing video.

[0099] The display unit 40a and the input unit 40b are input / output devices for interaction between the user 5 and the brain health management index estimation device 30a, and are, for example, a display similar to the display unit 40 in the first embodiment and a touch panel, respectively.

[0100] The brain health management index estimation device 30a is an example of an information processing device that estimates BHQ, which is a human brain health management index, and includes an acquisition unit 31a and a control unit 32a. The brain health management index estimation device 30a differs from the first embodiment that estimates BHQ using vital data and the like of the user 5 in that the brain health management index estimation device 30a estimates BHQ using at least one of video data and audio data of the user 5, but has the same function as the brain health management index estimation device 30 according to the first embodiment in that it provides the user 5 with BHQ as an estimated value. The following mainly describes the differences from the brain health management index estimation device 30 according to the first embodiment.

[0101] The acquisition unit 31a is a processing unit that acquires at least one of video data and audio data from the camera 25, and is, for example, an input circuit, a communication interface, or the like.

[0102] The control unit 32a is a processing unit that performs various information processing such as calculating BHQ as an estimated value using at least one of the video and audio data acquired by the acquisition unit 31a, and outputs the results to an external device including the display unit 40a, and includes a memory that stores programs and the like, and a processor that executes the programs. The control unit 32a functionally includes an estimation unit 33a, a prediction unit 34a, and a classification unit 35a.

[0103] The estimation unit 33a calculates the BHQ as an estimated value from at least one of the video data and the audio data acquired by the acquisition unit 31a, and outputs it to the display unit 40a. More specifically, the estimation unit 33a has a function of calculating the BHQ as an estimated value by facial expression analysis using the video data of the user 5, a function of calculating the BHQ as an estimated value by posture analysis, or a function of calculating the BHQ as an estimated value by audio analysis using the audio data of the user 5's voice. The estimation unit 33a also has a function of calculating the brain region-specific BHQ as an estimated value from the multiple vital data acquired by the acquisition unit 31a, and outputting it to the display unit 40a, and calculating the whole brain BHQ as an estimated value from the region-specific BHQ, and outputting it to the display unit 40a.

[0104] The prediction unit 34a predicts the person's future BHQ based on the BHQ estimated by the estimation unit 33a, and outputs the prediction result to the display unit 40a.

[0105] The classification unit 35a classifies the type of the human brain using the region-specific BHQ calculated by the estimation unit 33a, and outputs the classification result to the display unit 40a.

[0106] FIG. 13 is a flowchart showing a procedure for the brain-health care index estimation device 30a to calculate the BHQ as an estimated value by analyzing at least one of the facial expression, posture, and voice of the user 5.

[0107] First, the acquisition unit 31a acquires at least one of video data of the facial expression or posture of the user 5 and audio data of the user's voice by dialogue with the user 5 via the display unit 40a and the input unit 40b (acquisition step S60). Note that the "dialogue" includes an interaction in which the user 5 responds in some way to an instruction from the brain health management index estimation device 30a.

[0108] Next, the estimation unit 33a calculates the BHQ as an estimated value by analyzing at least one of the facial expression, posture, and voice of the user 5 from at least one of the acquired video data and audio data (calculation step S61).

[0109] Finally, the estimation unit 33a outputs the calculated BHQ as an estimated value to the display unit 40a (output step S62). The calculation step S61 and the output step S62 constitute an estimation step for calculating and outputting the BHQ as an estimated value from at least one of the video data and the audio data acquired in the acquisition step S60.

[0110] Hereinafter, an algorithm for the estimation unit 33a to calculate the BHQ as an estimated value by analyzing the facial expression of the user 5 will be described with reference to FIGS.

[0111] Fig. 14 is a diagram showing a specific example of a process (acquisition step S60 in Fig. 13) in which the brain health management index estimation device 30a acquires video data of the facial expression of the user 5 and audio data of the user's voice by interacting with the user 5 via the display unit 40a and the input unit 40b. This shows the interaction between the user 5 and the acquisition unit 31a via the display unit 40a and the input unit 40b. First, the acquisition unit 31a displays a guide entitled "Measurement Method" on the display unit 40a, prompts the user 5 to make four types of facial expressions, "smile", "surprise", "anger", and "sadness", in order, and waits for the "Start" button (input unit 40b) to be pressed (Fig. 14(a)). When the "start" button is pressed, the acquisition unit 31a sequentially indicates four types of facial expressions on the display unit 40a, and by checking the video data at that time, displays on the display unit 40a whether or not video data of the indicated four types of facial expressions has been acquired (Figures 14(b) and (c)), and finally acquires video data of the four types of facial expressions.

[0112] FIG. 15 is a diagram illustrating the process of the estimation unit 33a that calculates the BHQ as an estimated value by analyzing the obtained video data of several types of facial expressions.

[0113] The estimation unit 33a acquires basic data including the basic emotions of the user 5 (normal, smiling, sad, surprised, angry) and their position on the Russell circle (pleasant / unpleasant, alert / sleepiness) by analyzing the video data obtained by the dialogue or the like shown in Fig. 14. The Russell circle is a model that represents all emotions on two-dimensional axes of pleasant-unpleasant and alert-sleepiness.

[0114] Then, the estimation unit 33a calculates the BHQs by region as three estimated values ​​shown in FIG. 15 using the basic data. More specifically, the estimation unit 33a calculates the BHQs by region of the "sociality-related region" (104.2 in this example) by analyzing the "expression richness" of the user 5, that is, the "area of ​​the emotion variable region" using the basic data, calculates the BHQs by region of the "cognitive control-related region" (96.5 in this example) by analyzing the "recognition and reaction speed", that is, the "time it takes to make a facial expression", and calculates the BHQs by region of the "monitoring-related region" (102.4 in this example) by analyzing the "match rate and accuracy rate", that is, the "degree of correct facial expression". The estimation unit 33a then calculates the whole brain BHQ as an estimated value from the three calculated BHQs by region using a previously known relational expression.

[0115] As described above, the estimation unit 33a calculates the BHQ (that is, the whole brain BHQ) as an estimated value by analyzing the facial expression of the user 5, according to the procedures shown in FIG. 14 and FIG.

[0116] Next, an algorithm by which the estimation unit 33a calculates the BHQ as an estimated value by analyzing the posture of the user 5 will be described with reference to FIG.

[0117] Fig. 16 is a diagram showing a specific example of a process (acquisition step S60 and calculation step S61 in Fig. 13) in which the brain health management index estimation device 30a instructs the user 5 to imitate a sample displayed on the display unit 40a, and then acquires and analyzes video data of the posture and facial expression of the user 5 and audio data of the user's voice. More specifically, (a) of Fig. 16 shows an example of display on the display unit 40a, and (b) of Fig. 16 shows an overview of the process by the estimation unit 33a and an example of the measurement environment.

[0118] As shown in (a) of Fig. 16, the acquisition unit 31a displays on the display unit 40a the image of the user 5 together with the model posture and smile. At the same time, the estimation unit 33a analyzes the video data of the user 5 imitating the model, and quantifies the posture and facial expression of the user 5 ((b) of Fig. 16), thereby displaying on the display unit 40a, as indices related to BHQ, a "posture" score (44 in this example) indicating the degree of agreement with the model, a time required to match the model movement, a "balance" score (100 in this example) indicating the degree to which the posture is not unsteady, and a "smile" score (100 in this example) obtained by analyzing the facial expression. As shown in “Measurement Environment” in (b) of FIG. 16, as an example of the measurement environment, measurement may be performed using a display, a camera, a Kinect, and a PC, and the user 5 may be photographed at a distance of about 2 m from the screen, with the photographing time being about 2 minutes (10 poses may be photographed during this time).

[0119] Then, the estimation unit 33a calculates the region-specific BHQ of the "social-related area" from the "smile" score, calculates the region-specific BHQ of the "cognitive control-related area" from the "balance" score, and calculates the region-specific BHQ of the "monitoring-related area" from the "posture" score, which is the degree of agreement with the model, and calculates the whole-brain BHQ as an estimated value from these three region-specific BHQs using a previously determined relationship equation.

[0120] As described above, the estimation unit 33a calculates the BHQ (that is, the whole brain BHQ) as an estimated value by analyzing the posture of the user 5 through the process shown in FIG.

[0121] In this embodiment, the function of calculating BHQ as an estimated value by facial expression analysis and the function of calculating BHQ as an estimated value by posture analysis are selectively executed, but the present invention is not limited to this implementation form. It is also possible to perform both facial expression analysis and posture analysis and calculate whole-brain BHQ as a single estimated value by taking into account the results of both analyses.

[0122] As described above, the information processing method according to the second embodiment is an information processing method in which a computer estimates a BHQ (Brain Healthcare Quotient), which is a health management index for a person's brain, and includes an acquisition step of acquiring at least one of video data of a person and audio data of a person's voice, and an estimation step of calculating and outputting an estimated BHQ from at least one of the acquired video data and audio data. This allows the estimated BHQ to be calculated in a non-contact manner by simply standing in front of a camera or speaking into the camera, without the need to wear a measuring device on the body, and therefore allows the user to easily know the BHQ without going to a testing facility such as a hospital.

[0123] More specifically, in the information processing method of the seventh embodiment, the estimation step calculates the BHQ using at least one of facial expression, posture, and voice of the person included in at least one of the video data and audio data of the person. As a result, at least one of facial expression, posture, and voice of the person that has a high correlation with BHQ is used from at least one of the video data and audio data of the person, so that the BHQ can be estimated with high accuracy.

[0124] (Other embodiments) The brain health management index estimation device and method according to the present disclosure have been described above based on the first and second embodiments, but the present disclosure is not limited to these first and second embodiments. As long as they do not deviate from the gist of the present disclosure, various modifications conceivable by those skilled in the art to the first and second embodiments, and other forms constructed by combining some of the components in the first and second embodiments are also included within the scope of the present disclosure.

[0125] For example, in the first embodiment, the peripheral device 20, the brain health management index estimation device 30, and the display unit 40 are integrated into one wearable device 10, but the present disclosure is not limited to this form, and the peripheral device 20, the brain health management index estimation device 30, and the display unit 40 may be in a distributed form connected by a communication network or a communication cable. For example, the peripheral device 20 and the display unit 40 may be integrated into a wearable device, and the wearable device may be connected to the brain health management index estimation device 30 functioning as a server via a communication network including wireless communication.

[0126] Furthermore, the implementation form of the brain health management index estimation device 30 is not limited to being built into the wearable device 10 as in embodiment 1, but may be built into a measuring device carried on the body such as a smartphone, or a measuring device installed in the home such as a body composition scale, or may be implemented in a standalone form as a smartphone app or the like without being connected to a measuring device.

[0127] In addition, in the brain health management index estimation system 11 according to embodiment 2, the camera 25, the display unit 40a and the input unit 40b may be integrated into a mobile terminal such as a smartphone, and the mobile terminal may be connected to the brain health management index estimation device 30a functioning as a server via a communication network including wireless communication.

[0128] Furthermore, the brain health management index estimation device 30a according to the second embodiment may be realized in a stand-alone form as a smartphone app or the like, without being connected to the camera 25, the display unit 40a, and the input unit 40b.

[0129] Also, it may be realized as a brain health management index estimation device / brain health management index estimation system having a function that combines the functions of the first and second embodiments. For example, the peripheral device includes the camera 25, the display unit 40a, and the input unit 40b in the second embodiment in addition to the measuring device 21, the input unit 22, and the storage unit 23 in the first embodiment. And the brain health management index estimation device may include the acquisition unit 31a and the control unit 32a in the second embodiment in addition to the acquisition unit 31 and the control unit 32 in the first embodiment, and may have the BHQ estimation function in the second embodiment in addition to the BHQ estimation function in the first embodiment. [Industrial Applicability]

[0130] The information processing method and information processing device disclosed herein can be used as a brain health management index estimation device that estimates BHQ, which is a human brain health management index, for example, as a wearable device and a body composition scale incorporating the brain health management index estimation device, or as a smartphone app, etc. [Explanation of symbols]

[0131] 5 User 10. Wearable Devices 11 Brain health management index estimation system 20 Peripheral Devices 21 Measuring Instruments 22 Input section 23 Memory section 25 Camera 30, 30a Brain health management index estimation device 31, 31a acquisition part 32, 32a Control section 33, 33a Estimation part 34, 34a Prediction Section 35,35a Classification section 40, 40a Display section 40b Input section

Claims

1. An information processing method for estimating a human brain health management index BHQ (Brain Healthcare Quotient) by a computer, comprising: An acquisition step of acquiring a plurality of vital data measurable on a daily basis; and an estimation step of calculating and outputting an estimated BHQ from the acquired plurality of vital data. Information processing methods.

2. The plurality of vital data include at least one of vital data at rest, vital data related to sleep, and vital data related to exercise. The information processing method according to claim 1 .

3. The plurality of vital data includes a resting heart rate, a deep sleep time, and a number of steps taken in a certain period of time. The information processing method according to claim 2 .

4. The estimation step includes a classification step of classifying the acquired plurality of vital data into one of a plurality of categories using a decision tree analysis. The information processing method according to claim 1 .

5. The estimation step further includes a calculation step of calculating the BHQ from the category classified in the classification step and the person's age. The information processing method according to claim 4.

6. In the estimation step, the BHQ is calculated by performing a product-sum operation on the acquired plurality of vital data. The information processing method according to claim 1 .

7. An information processing method for estimating a human brain health management index BHQ (Brain Healthcare Quotient) by a computer, comprising: An acquisition step of acquiring at least one of video data of a person and audio data of a person's voice; and an estimation step of calculating and outputting a BHQ as an estimated value from at least one of the acquired video data and audio data. Information processing methods.

8. In the estimation step, the BHQ is calculated using at least one of a facial expression, a posture, and a voice of the person included in at least one of the video data and the audio data. The information processing method according to claim 7.

9. In the estimation step, a brain region-specific BHQ is calculated as an estimated value from the data acquired in the acquisition step, and output. The information processing method according to claim 1 or 7.

10. In the estimation step, a whole brain BHQ is further calculated as an estimated value from the site-specific BHQ. The information processing method according to claim 9.

11. Further, the method includes a prediction step of predicting a future BHQ of the person based on the BHQ estimated in the estimation step. The information processing method according to claim 1 or 7.

12. Further, a classification step of classifying a brain type of the person using the site-specific BHQ calculated in the estimation step is included. The information processing method according to claim 9.

13. A program causing a computer to execute the steps included in the information processing method according to claim 1 or 7.

14. An information processing device that estimates a human brain health care index (BHQ), An acquisition unit including an input circuit for acquiring a plurality of vital data that can be measured daily; A control unit including a processor that calculates and outputs a BHQ as an estimated value from the plurality of vital data acquired by the acquisition unit. Information processing device.

Images