Information processing system, server, information processing method, and program

Abstract

To provide an information processing system, a server, an information processing method, and a program for providing frail index information for showing especially a frail state on the basis of measurement data via a frail index information generation part.SOLUTION: In an information management system, a management server 100 includes a frail index information generation part for generating at least one of responsiveness index information for showing how biological data respond to occurrence of predetermined or more exercise intensity on the basis of change information of biological data within a determination period with a time when the predetermined or more exercise intensity occurs as reference time information, and recoverability index information for showing how biological data recover from a response due to occurrence of the predetermined or more exercise intensity on the basis of change information of biological data from a response state or an operation state to a rest state, and for generating frail index information for showing a user's frail state on the basis of at least one of the responsiveness index information and the recoverability index information and previously stored correspondence relation information.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to an information processing system, a server, an information processing method, and a program that generate frailty index information based on measurement data acquired from a measurement device. [Background technology]

[0002] It is said that increasing muscle strength helps prevent diseases associated with aging, such as dementia, and it is important to prevent frailty by actively exercising on a daily basis.

[0003] The assessment of frailty is also important. For example, Patent Document 1 discloses a method of assessing frailty by asking questions to subjects and calculating the total score of their answers. Patent Document 2 discloses a frailty health check system that outputs the results of a frailty health check based on the results of a medical interview with the recipient and the results of a balance measurement test in a standing position. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent Publication No. 2021-177282 [Patent Document 2] Patent No. 6943395 Summary of the Invention [Problem to be solved by the invention]

[0005] However, with the recent advances in wearable device technology, there is a demand for methods to assess frailty based on everyday movements.

[0006] Therefore, the present disclosure describes an information processing system, a server, an information processing method, and a program that generate frailty index information based on measurement data acquired from a measurement device worn by a user. [Means for solving the problem]

[0007] An information processing system according to one aspect of the present disclosure is an information processing system that receives measurement data from a measurement device worn by a user via a network and generates biometric data and frailty index information from the measurement data, and includes a frailty index information generation unit that generates at least one of responsiveness index information indicating how the biometric data is responding to the occurrence of an exercise intensity of a predetermined level or more, based on change information in the biometric data within a determination period, the reference time being a time when the exercise intensity of a predetermined level or more occurred, or resilience index information indicating how the user is recovering from the response due to the occurrence of an exercise intensity of a predetermined level or more, based on change information in the biometric data from a responsive state or an active state to a resting state, and generates frailty index information to indicate the user's frailty state, based on correspondence information stored in advance between the responsiveness index information or the resilience index information.

[0008] A server in one aspect of the present disclosure receives measurement data from a measurement device worn by a user via a network, and generates biometric data and frailty index information from the measurement data. The server is equipped with a frailty index information generation unit that generates at least one of responsiveness index information indicating how the biometric data is responding to the occurrence of an exercise intensity of a predetermined level or more, based on change information in the biometric data within a determination period, the reference time being a time when the exercise intensity of a predetermined level or more occurred, or recovery index information indicating how the user is recovering from the response due to the occurrence of an exercise intensity of a predetermined level or more, based on change information in the biometric data from a responsive state or an active state to a resting state, and generates frailty index information to indicate the user's frailty state, based on correspondence information stored in advance between the responsiveness index information or the recovery index information.

[0009] An information processing method according to one aspect of the present disclosure is an information processing method for receiving measurement data from a measurement device worn by a user via a network, and generating biological data and frailty index information from the measurement data, the information including: a frailty index information generating unit generating at least one of responsiveness index information indicating how the biological data is responding to the occurrence of an exercise intensity of a predetermined level or more, based on change information in the biological data within a determination period, the reference time being a time when the exercise intensity of a predetermined level or more occurred, or resilience index information indicating how the user is recovering from the response to the occurrence of an exercise intensity of a predetermined level or more, based on change information in the biological data from a responsive state or an active state to a resting state; and generating frailty index information for indicating the frailty state of the user, based on correspondence information stored in advance with at least one of the responsiveness index information or the resilience index information.

[0010] A program according to one aspect of the present disclosure is a program that causes an information processing system to execute an information processing method that receives measurement data from a measurement device worn by a user via a network and generates biological data and frailty index information from the measurement data, the information processing method including the steps of: generating, by a frailty index information generation unit, at least one of responsiveness index information indicating how the biological data is responding to the occurrence of an exercise intensity of a predetermined level or more, based on change information in the biological data within a determination period, the reference time being a time when the exercise intensity of a predetermined level or more occurred; or resilience index information indicating how the user is recovering from the response to the occurrence of an exercise intensity of a predetermined level or more, based on change information in the biological data from a responsive state or an active state to a resting state; and generating frailty index information to indicate the frailty state of the user, based on correspondence information stored in advance with at least one of the responsiveness index information or the resilience index information. [Effects of the Invention]

[0011] According to the present disclosure, the information processing system according to the present embodiment generates frailty index information, particularly relating to the frailty state of the user, based on the measurement data or biological data via the frailty index information generating unit 133. This makes it possible to grasp the frailty state of, for example, the subject. [Brief explanation of the drawings]

[0012] [Figure 1] 1 is a block diagram illustrating an information processing system according to an embodiment of the present disclosure. [Figure 2] FIG. 2 is a diagram illustrating a hardware configuration of a management server 100 in FIG. [Figure 3] 3 is a block diagram illustrating the functions of a storage unit 120 and a control unit 130 of FIG. 2. FIG. [Figure 4] 4 is a schematic diagram showing an example of tag information associated with the measurement data of FIG. 3. FIG. [Figure 5] 1. FIG. 3 is a diagram for explaining an example of an electrocardiogram waveform and a pulse waveform measured by the measurement device 300 of FIG. [Figure 6] 2 is a flowchart showing an example of processing by the information processing system 1 of FIG. DETAILED DESCRIPTION OF THE INVENTION

[0013] The contents of the embodiment of the present invention will be described below. The system according to the embodiment of the present invention has the following configuration.

[0014] [Item 1] An information processing system that receives measurement data from a measurement device worn by a user via a network and generates biological data and frailty index information from the measurement data, a frailty index information generating unit that generates at least one of responsiveness index information indicating how the biological data is responding to the occurrence of an exercise intensity of a predetermined level or more, based on change information on the biological data within a determination period having a time when the exercise intensity of a predetermined level or more as reference time information, or recovery index information indicating how the user is recovering from the response due to the occurrence of the exercise intensity of a predetermined level or more, based on change information on the biological data from a responsive state or an active state to a resting state, and generates frailty index information for indicating the frailty state of the user, based on correspondence relationship information stored in advance with at least one of the responsiveness index information or the recovery index information. An information processing system comprising: [Item 2] the frailty index information generation unit uses circulatory organ-related information including at least one of heart rate information and blood pressure information as the biological data within the determination period; 2. The information processing system according to item 1, [Item 3] the frailty index information generation unit performs clustering based on exercise intensity information indicating exercise intensity associated with at least one of the responsiveness index information or the recovery index information, and generates the frailty index information based on correspondence relationship information for each clustered exercise intensity information. 3. The information processing system according to item 1 or 2. [Item 4] The exercise intensity is an index based on data obtained from an inertial sensor of the measuring device. 4. The information processing system according to any one of items 1 to 3. [Item 5] A server that receives measurement data from a measurement device worn by a user via a network and generates biological data and frailty index information from the measurement data, a frailty index information generating unit that generates at least one of responsiveness index information indicating how the biological data is responding to the occurrence of an exercise intensity of a predetermined level or more, based on change information on the biological data within a determination period having a time when the exercise intensity of a predetermined level or more as reference time information, or recovery index information indicating how the user is recovering from the response due to the occurrence of the exercise intensity of a predetermined level or more, based on change information on the biological data from a responsive state or an active state to a resting state, and generates frailty index information for indicating the frailty state of the user, based on correspondence relationship information stored in advance with at least one of the responsiveness index information or the recovery index information. A server characterized by: [Item 6] An information processing method for receiving measurement data from a measurement device worn by a user via a network and generating biological data and frailty index information from the measurement data, and generating, by a frailty index information generating unit, at least one of responsiveness index information indicating how the biological data is responding to the occurrence of an exercise intensity of a predetermined level or more, based on change information on the biological data within a determination period having a time when the exercise intensity of a predetermined level or more is generated as reference time information, or recovery index information indicating how the user is recovering from the response due to the occurrence of the exercise intensity of a predetermined level or more, based on change information on the biological data from a responsive state or an active state to a resting state, and generating frailty index information for indicating the frailty state of the user, based on correspondence relationship information stored in advance with at least one of the responsiveness index information or the recovery index information. An information processing method comprising: [Item 7] A program that causes an information processing system to execute an information processing method that receives measurement data from a measurement device worn by a user via a network and generates biological data and frailty index information from the measurement data, The information processing method includes: and generating, by a frailty index information generating unit, at least one of responsiveness index information indicating how the biological data is responding to the occurrence of an exercise intensity of a predetermined level or more, based on change information on the biological data within a determination period having a time when the exercise intensity of a predetermined level or more is generated as reference time information, or recovery index information indicating how the user is recovering from the response due to the occurrence of the exercise intensity of a predetermined level or more, based on change information on the biological data from a responsive state or an active state to a resting state, and generating frailty index information for indicating the frailty state of the user, based on correspondence relationship information stored in advance with at least one of the responsiveness index information or the recovery index information. A program characterized by:

[0015] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. Note that the embodiments described below do not unduly limit the content of the present disclosure described in the claims. Furthermore, not all of the components shown in the embodiments are necessarily essential components of the present disclosure. Furthermore, features shown in each embodiment can be applied to other embodiments as long as they are not mutually inconsistent.

[0016] (Embodiment 1) <Configuration> 1 is a block diagram illustrating an information processing system 1 according to a first embodiment of the present disclosure. The information processing system 1 is a system in which, for example, a management server 100 receives measurement data of a user from a measurement device 300 via a network NW, generates biometric data by performing a predetermined calculation on the measurement data, and generates frailty index information based on the biometric data.

[0017] The information processing system 1 includes a management server 100, a user terminal device 200, a measurement device 300, and a network NW. The management server 100 and the user terminal device 200 are connected via the network NW. The network NW is configured by the Internet, an intranet, a blockchain network, a wireless LAN (Local Area Network), a WAN (Wide Area Network), or the like.

[0018] The management server 100 is, for example, a device that receives user measurement data from a measurement device 300 via a network, via a user terminal device 200, and performs calculations to convert the measurement data into biometric data, and is composed of, for example, a server device that provides various web services.

[0019] The user terminal device 200 is an information processing device owned by the user, such as a personal computer, tablet terminal, smartphone, smartwatch, mobile phone, PHS, PDA, etc., and is used, for example, to display the biometric data calculated by the management server 100 as a waveform graph or to display data generated based on the biometric data (details will be described later). User information such as the user's identification number, date of birth, sex, height, weight, etc. is registered in advance in the user terminal device 200, and the user information, including age calculated from the date of birth, etc., is associated with the measurement data and transmitted to the management server 100 via the network NW.

[0020] Furthermore, the user terminal device 200 may be configured to allow the user to input the state in which the user is acquiring data using the measuring device 300 using a touch panel or the like. The user terminal device 200 may input the "state in which data is acquired" as tag information, such as "running" if the user is running, or "eating" if the user is eating. In this case, the user terminal device 200 associates the measurement data received from the measuring device 300 at predetermined periodic intervals with the tag information and transmits the data to the management server 100 via the network NW.

[0021] The measuring device 300 is a device that measures the user's measurement data, and is a device for measuring, for example, the user's electrocardiogram, pulse wave, skin temperature (body temperature), acceleration, and angular velocity data at a predetermined periodic timing using a known method. The predetermined period may be set in advance or may be arbitrarily set by the user. More specifically, a time period may be set in seconds, for example, or may be set similarly based on a frequency. The user of the user terminal device 200 and the user (subject) of the measuring device 300 may be the same or different.

[0022] As a specific example of the configuration of the measuring device 300, it may be configured as a device that contacts two electrodes with the skin and acquires electrocardiogram data from the time change in the difference in detected potential, and the electrocardiogram waveform data may be acquired by galvanic skin reaction. Alternatively, it may be configured as a device that irradiates the skin with green, red, and infrared light from LEDs and acquires pulse waveform data from the volume changes in blood vessels caused by the user's heartbeat based on the time change in the intensity of the light received by a photodiode. The pulse waveform that can be detected using this method is a photoelectric volume pulse waveform. Alternatively, it may be configured as a device that acquires the user's skin temperature data using a temperature sensor that contacts the user's skin. It may also be configured as a triaxial acceleration sensor that detects the state of variation in each of the orthogonal X, Y, and Z axes, and acquires the user's movements as acceleration data. For example, when the measuring device 300 is worn on the user's wrist or arm, the measuring device 300 acquires acceleration data as the acceleration resulting from the swing of the wrist or arm and the movement of the entire body. Furthermore, it may be configured with a gyro sensor (angular velocity sensor) that detects the rotational angular velocity in each of the orthogonal X, Y and Z axes, and acquires the user's movements as angular velocity data. For example, when the measuring device 300 is attached to the user's wrist, arm, etc., the measuring device 300 acquires angular velocity data as the angular velocity resulting from the rotation of the wrist, arm, etc. and the movement of the entire body combined.

[0023] The user terminal device 200 and the measurement device 300 are connected using Bluetooth (registered trademark), Near Field radio Communication (NFC), Afero (registered trademark), Zigbee (registered trademark), Z-Wave (registered trademark), wireless LAN, or the like. Instead of such wireless connection, a wired connection may also be used. The user terminal device 200 and the measurement device 300 may be integrated into one device, and for example, the measurement device 300 may be equipped with a SIM card or other communication function to enable direct communication with the management server 100.

[0024] There is one or more user terminal devices 200, and each of them is connected to the network NW as many times as the number of users who use the measurement devices 300. There is one or more measurement devices 300, and each of them is connected to the same number of user terminal devices 200 used by one user. When one user uses multiple measurement devices 300, multiple measurement devices 300 are connected to one user terminal device 200.

[0025] <Management Server 100> Fig. 2 is a diagram showing the hardware configuration of the management server 100. Fig. 3 is a block diagram showing an example of the functions of the storage unit 120 and the control unit 130. Note that the configuration shown in the figure is an example, and other configurations may also be used.

[0026] The management server 100 includes a communication unit 110, a storage unit 120, a control unit 130, and an input / output unit 140. These functional units are realized by executing a predetermined program for the management server 100.

[0027] The communication unit 110 is a communication interface for communicating with the user terminal device 200, and communication is performed according to a communication protocol such as TCP / IP (Transmission Control Protocol / Internet Protocol).

[0028] The storage unit 120 stores input data and programs for executing various control processes and functions in the control unit 130, and is configured with RAM (Random Access Memory), ROM (Read Only Memory), and the like. As shown in FIG. 3 , the storage unit 120 stores a measurement data DB 121 that stores measurement data obtained by the measurement device 300 in association with user information, a biological data DB 122 that stores biometric data calculated from the measurement data in association with user information, a frailty index information DB 123 that stores frailty index information generated based on the measurement data or biometric data in association with user information, and a user information DB 124 that stores user information including user identification information. The user identification information may be account information generated by the data management unit 131, application identification information of an application downloaded to the user terminal device 200, or user terminal identification information of the user terminal device. The storage unit 120 also temporarily stores data communicated with the user terminal device 200. The data structure of the DB is not limited to this, and part of the DB described above may be stored in the user terminal device 200 or the measurement device 300.

[0029] The control unit 130 controls the overall operation of the management server 100 and is configured with a CPU (Central Processing Unit) etc. As shown in Fig. 3 , the control unit 130 includes functional units such as a data management unit 131, a biological data generation unit 132, a frailty index information generation unit 133, and a data output unit 134.

[0030] The data management unit 131 sets user identification information for each user who uses the measurement device 300. For example, if the user identification information is account information, the account information is generated when the user who uses the measurement device 300 registers the account information in the user terminal device 200. Therefore, the data management unit 131 controls whether or not the user terminal device 200 of each user is allowed to access various DBs in the storage unit 120 for each account. The data management unit 131 stores various data such as measurement data, biological data, and frailty index information in the corresponding DBs in association with user information including user identification information. At this time, the data management unit 131 may also store the measurement data by associating it with predetermined tag information.

[0031] FIG. 4 is a schematic diagram illustrating an example of tag information associated with the measurement data of FIG. 3. Data D1 shown in FIG. 4 is measurement data from the measurement device 300. Tag T1 is tag information associated with data D1, and stores, as time-series data, the time information when the measurement device 300 measured data D1 or the time information when data D1 was transmitted from the measurement device 300 to the user terminal device 200. Alternatively, both the measurement time information and the transmitted time information may be associated. For example, the first line of tag T1 shown in FIG. 4 stores "20180620120746144," which indicates 12:07:46:144 on June 20, 2018. This time information can be obtained from the communication log. This makes it possible to determine the time period for the measurement data.

[0032] The association of measurement data with such tag information is not limited to time information. Physical information and behavioral information indicating the user's physical condition and behavioral details may be freely entered by the user and stored as tag information. Alternatively, the user may be prompted to select from a predetermined list of options (e.g., "How is your current physical condition?" may be prompted to select "1: good, 2: normal, 3: bad"), and the selected answer may be stored. Furthermore, based on other measurement data and biometric data (e.g., walking speed information, stride length information, movement information of the attachment site, posture information, center of gravity position information, heart rate information, etc.), a predetermined behavior (e.g., sitting, standing, lying down, walking, running, sleeping, waking up, sleeping, eating, driving, resting, etc.) may be estimated using a known method and associated with the biometric data as tag information (behavior type information). In this case, the estimation may be performed using a learning model trained based on the training measurement data. Furthermore, the learning model may be personalized by additional learning based on the results of the user's recording. As a result, when generating biometric data such as blood pressure information in the control unit 150, by associating the tag information with the biometric data, it becomes possible to generate more accurate biometric data, and the frailty index information generated based on this can also become more personalized data.

[0033] The biometric data generation unit 132 performs predetermined calculations on the measurement data stored in the measurement data DB 121 to generate biometric data. The generation of biometric data is not limited to direct calculations on the measurement data, but may also generate new biometric data based on one or more previously generated biometric data. The biometric data may include, for example, the user's blood pressure information, heart rate information, blood oxygen content information, maximum oxygen intake information, electrocardiogram information, respiratory rate, body temperature information, blood glucose level information, step count information, stride length information, center of gravity position information, posture information, activity type information, stress information, exercise amount information, exercise load information, travel distance information, walking speed information, activity amount information, and hand or leg movement information. The biometric data generated by calculations is stored in the biometric data DB 122.

[0034] Furthermore, a learning model may be created in advance based on teacher data that matches measurement data with biological data (e.g., heart rate information, blood pressure information, etc.) generated based on the measurement data and correct biological data (e.g., heart rate information, blood pressure information, etc. based on known medical equipment, etc.) based on a correspondence relationship (which may include, for example, information indicating the degree or range of error) using a known learning device, etc., and the biological data generation unit 132 may generate biological data by making a judgment using the learning model as the above-mentioned specified calculation (analysis).

[0035] Here, we will explain an example of a method for calculating systolic and diastolic blood pressure, which are biological data, from measurement data. Figure 5 is a diagram for explaining an example of an electrocardiogram waveform and pulse wave measured by the measurement device 300 of Figure 1. It shows the user's electrocardiogram waveform and photoelectric volume pulse waveform measured by the measurement device 300 and stored in the memory unit 120, as well as a velocity pulse waveform obtained by first-order time differentiation of the photoelectric volume pulse waveform by the app, and an acceleration pulse waveform obtained by second-order time differentiation of the photoelectric volume pulse waveform. Figure 5 shows, from top to bottom, the electrocardiogram waveform, the photoelectric volume pulse waveform, the velocity pulse waveform, and the acceleration pulse waveform. The vertical axis indicates the intensity of each waveform, and the electrocardiogram waveform and the photoelectric volume pulse waveform are expressed in mV, which indicates potential. The horizontal axis indicates the passage of time, with time elapsed from left to right.

[0036] An electrocardiogram waveform is a waveform that shows the periodic changes in the electrical signal that causes the human heart to beat. The inflection points of the electrocardiogram are assigned the names P wave, Q wave, R wave, S wave, and T wave, which represent one cycle of the heartbeat. The P wave represents atrial contraction, the Q wave, R wave, and S wave represent ventricular contraction, and the T wave represents the start of ventricular expansion.

[0037] The photoplethysmography waveform is a waveform that shows changes in blood pressure and volume in the peripheral vascular system as the human heart beats. The inflection points of the photoplethysmography waveform are assigned the names A, P, V, and D waves, and represent one cycle of the heartbeat. The A wave is the reference point for the time when the arterial pulse wave is generated, and the P wave is a percussion wave (shock wave) generated by left ventricular ejection, the V wave is a valley wave (wave caused by dicrotic prominence) generated when the aortic valve closes, and the D wave is a dicrotic wave (dicrotic wave), which is a reflected vibration wave.

[0038] The velocity pulse waveform is the first time derivative of the photoelectric volume pulse waveform. The acceleration pulse waveform is the first time derivative of the velocity pulse waveform, i.e., the second time derivative of the photoelectric volume pulse waveform. As shown in Figure 5, the peaks of the acceleration pulse waveform are assigned the names a wave (early systolic positive wave), b wave (early systolic negative wave), c wave (mid-systolic re-upward wave), d wave (late systolic re-downward wave), e wave (early diastolic positive wave), and f wave (early diastolic negative wave).

[0039] The ratio of b-wave intensity to a-wave intensity, and the ratio of f-wave intensity to e-wave intensity, are parameters that indicate the elasticity of blood vessels. The main components of blood vessels are endothelium, elastic fiber (elastin), collagen, and smooth muscle. Each of these components has different properties, with collagen and elastin having a strong influence on vascular elasticity at systolic and diastolic blood pressure, respectively. Therefore, the elasticity that varies depending on blood pressure can be expressed by the parameters (b / a), which is the ratio of b-wave intensity to a-wave intensity, and (f / e), which is the ratio of f-wave intensity to e-wave intensity. These values ​​also vary depending on age, gender, and environmental variables. Therefore, the values ​​(b / a) and (f / e) can be calculated as characteristic information of the acceleration pulse waveform.

[0040] As shown in Figure 5, the difference between the time Tr when the R wave occurs and the time Tp when the P wave occurs is the ventricular systolic pulse wave transit time PTT_SYS. The difference between the time Tt when the T wave occurs and the time Td when the D wave occurs is the ventricular diastolic pulse wave transit time PTT_DIA. In other words, the ventricular systolic pulse wave transit time PTT_SYS and the ventricular diastolic pulse wave transit time PTT_DIA can be calculated from the time Tr of the R wave and the time Tt of the T wave in the electrocardiogram waveform, and the time Tp of the T wave and the time Td of the D wave in the photoelectric volume pulse waveform, as shown in equations (1) and (2).

[0041] PTT_SYS=Tp-Tr (1)

[0042] PTT_DIA=Td-Tt (2)

[0043] The first and second electrodes for measuring the electrocardiogram waveform and the optical sensor module for measuring the photoelectric volume pulse waveform are placed opposite each other across the wrist, and by separating them, the detection site of the electrocardiogram waveform and the measurement site of the photoelectric volume pulse waveform are separated. This creates a time lag between the generation of each characteristic waveform, allowing for a longer absolute calculation time for the ventricular systolic pulse wave transit time PTT_SYS and the ventricular diastolic pulse wave transit time PTT_DIA. This improves the accuracy of the change information when obtaining the change information for the ventricular systolic pulse wave transit time PTT_SYS and the ventricular diastolic pulse wave transit time PTT_DIA.

[0044] Here, the blood pressure calculation formula will be explained.

[0045] The relationship between pulse wave velocity and the longitudinal elastic modulus of the arterial wall is shown by the Moens-Korteweg equation (3) below.

[0046] L / T_PTT=√(E·h / (2·r·ρ)) ···(3)

[0047] The parameters in equation (3) are L: distance between measurements, T_PTT: pulse wave transit time, r: inner diameter of blood vessel, E: longitudinal elastic modulus of blood vessel, h: thickness of blood vessel, and ρ: blood density.

[0048] It is known that there is a correlation between the longitudinal elastic modulus and blood pressure.

[0049] E = E0 exp(α P) (4)

[0050] Here, P is the blood pressure value, α is a constant, and E0 is the initial value.

[0051] From equations (3) and (4),

[0052] P=(-2·ln(T_PTT)+ln(2·r·ρ·L 2 / (E0·h))) / α (5)

[0053] where ln indicates the natural logarithm. In this case, "r·ρ" is proportional to the blood volume at the measurement site, so it can be expressed as the high values ​​(Vp, Vd) shown on the photoelectric volume pulse waveform. Furthermore, "E0·h" is a value proportional to the elasticity of the blood vessels, so it can be replaced with the parameters (b / a) and (f / e) that indicate elasticity.

[0054] Therefore, the systolic blood pressure BP_SYS (Blood Pressure_Systolic) and the diastolic blood pressure BP_DIA (Blood Pressure_Diastolic) can be expressed by the following equations (6) and (7).

[0055] BP_SYS=A1·ln(PTT_SYS)+A2·ln(Vp)+A3·ln(b / a)+A4 ···(6)

[0056] BP_DIA=A5·ln(PTT_DIA)+A6·ln(Vd)+A7·ln(f / e)+A8 ···(7)

[0057] A1 to A8 are constants determined by conditions. The systolic blood pressure (BP_SYS) calculated using equation (6) can be calculated by multiplying the natural logarithm of the ventricular systolic pulse wave transit time (PTT_SYS) by a constant A1, multiplying the natural logarithm of the P-wave intensity (Vp) by a constant A2, multiplying the natural logarithm of (b / a) by a constant A3, and adding up the constant A4. The diastolic blood pressure (BP_SYS) calculated using equation (7) can be calculated by multiplying the natural logarithm of the ventricular systolic pulse wave transit time (PTT_DIA) by a constant A5, multiplying the natural logarithm of the D-wave intensity (Vd) by a constant A6, multiplying the natural logarithm of (f / e) by a constant A7, and adding up the constant A8. The systolic blood pressure (BP_SYS) and the diastolic blood pressure (BP_DIA) can be calculated by determining each constant based on the characteristics of the device and the person being measured. However, when checking the changes in systolic blood pressure BP_SYS and diastolic blood pressure BP_DIA, it is not necessary to determine all constants; it is possible to obtain values ​​related to systolic blood pressure BP_SYS and diastolic blood pressure BP_DIA by substituting provisional values. The natural logarithm of P-wave intensity Vp and the natural logarithm of D-wave intensity Vd are terms that take into account the influence of blood density. Furthermore, the natural logarithm of (b / a) and the natural logarithm of (f / e) are terms that take into account the influence of the longitudinal elastic modulus of the arterial wall. Therefore, depending on the measurement conditions, it is possible to calculate information related to systolic blood pressure BP_SYS and diastolic blood pressure BP_DIA by selecting one term and constantizing the other terms.

[0058] Furthermore, the biological data generating section 132 can obtain temperature information as biological data from skin temperature information of the subject measured by a temperature sensor (such as a thermistor) of the measuring device 300 worn by the subject.

[0059] Also, a method for calculating walking speed information, which is biometric data, from measurement data is illustrated. For example, walking speed information can be obtained from waveform data of acceleration data measured by a measurement device 300 worn on the user's wrist by using known calculation methods alone or in combination (e.g., averaging, weighting, etc.). For example, walking speed information is calculated by integrating the acceleration data at predetermined intervals. In addition, the user terminal device 200 or the measurement device 300 may be equipped with a GPS function, and more accurate walking speed information may be obtained by referring to walking speed information calculated from GPS location information and time information related to the location information. However, GPS accuracy generally decreases, especially indoors or underground, or when the travel distance is relatively short (e.g., within a few meters). Therefore, for example, the user may operate the user terminal device 200 to select whether to use GPS information in combination with (or instead of) calculation by an acceleration sensor. Alternatively, the user terminal device 200 may select whether to use GPS information based on GPS reception sensitivity information or distance information calculated by the GPS or acceleration sensor. By calculating walking speed information in this way, it is possible to easily measure (especially on a daily basis) "walking speed," which is one of the known indices for measuring human muscle mass that needs to be understood in preventing frailty, etc. Also, although smartphones and mobile phones have acceleration sensors, they are devices that make it difficult to identify which part of the body is moving, so by using a measurement device 300 that the user wears on the wrist, etc., as a wearable device, it is possible to easily track behavioral information.

[0060] We will also illustrate a method for calculating stride information, which is biometric data, from measurement data. For example, stride information can be obtained from waveform data of acceleration data measured by the measurement device 300 worn on the user's wrist by using known calculation methods, either alone or in combination (e.g., averaging, weighting, etc.). For example, because a person swings their hand like a pendulum when walking, the interval between steps can be determined based on information from the acceleration sensor (e.g., the timing when the acceleration component in the forward direction is smallest or when it switches to the opposite direction, the timing when the acceleration component in the direction perpendicular to the forward direction is smallest or when it switches from up to down, etc.). Therefore, stride information can be obtained by further using time information. Another example is when a person pushes off the ground, since the acceleration component in the direction of pushing off is synthesized, so the interval between steps can also be determined based on the timing of the acceleration component in that direction. Calculating stride information in this manner makes it possible to accurately determine the timing at which stride length begins to shorten and the degree of stride length variation, which are considered useful for estimating the progression of dementia. Furthermore, the deterioration of the sense of balance may be calculated by calculating the amount of lateral swaying (for example, sway amplitude or sway speed) during walking from the acceleration data described above.

[0061] Furthermore, exercise amount information calculated based on distance information calculated by the above-mentioned GPS or acceleration sensor, the above-mentioned stride length information and step count information (which can be obtained using known methods based on information from an acceleration sensor, for example) may also be calculated as biometric data.

[0062] In addition, the biometric data generating unit 132 can obtain, as biometric data, motion information, such as the speed and angle at which the part of the body (e.g., the wrist or ankle) wearing the measuring device 300 is moving, from acceleration data and angular velocity data measured by the measuring device 300 worn by the subject.

[0063] Furthermore, the biometric data generating unit 132 performs frequency analysis on acceleration data measured by, for example, the measuring device 300 worn by the subject, and calculates, based on predetermined conditions, for example, how many percent of a day is occupied by activities with a predetermined frequency or higher, thereby obtaining activity amount information as biometric data.

[0064] Furthermore, since the biometric data generating unit 132 can identify acceleration data during exercise, including walking, from acceleration data measured by the measuring device 300 worn by the subject using a known calculation method, it can obtain information on the amount of exercise as biometric data by calculating the data under predetermined conditions using, for example, frequency analysis, etc. Furthermore, by further using additional information such as angular velocity information, it is possible to obtain more accurate information on the amount of exercise.

[0065] Furthermore, the biological data generating unit 132 can obtain exercise stress information as biological data by weighting the activity amount information and the exercise amount information derived from acceleration data measured by the measuring device 300 worn by the subject, for example, with heart rate information, which increases with exercise stress. Furthermore, by adding vector information from the acceleration data, for example, it is possible to identify status information such as the walking environment (slope, stairs, etc.) and posture (standing, sitting, etc.), and this status information may also be used. Furthermore, by using additional information such as angular velocity information, more accurate exercise stress information can be obtained.

[0066] In addition, the biological data generation unit 132 can obtain maximum oxygen uptake information as biological data using, for example, heart rate information using a known formula such as VO2max=15×(220−age)÷heart rate (particularly resting heart rate).

[0067] Furthermore, a machine learning model may be created in advance based on training data that is associated with measurement data, biological data (e.g., heart rate information, blood pressure information, etc.) generated based on the measurement data, and positive biological information (e.g., heart rate information, blood pressure information, etc. based on a known medical device) based on a correspondence relationship (which may include, for example, information indicating the degree or range of error) using a known learning device, and the biological data generation unit 132 may generate biological data by making a judgment using the machine learning model as the above-mentioned specified calculation (analysis).

[0068] The frailty index information generating unit 133 generates responsiveness index information indicating how the biological data is responding to the occurrence of an exercise intensity of a predetermined level or higher, based on change information on the biological data (particularly, circulatory system-related information such as heart rate information and / or blood pressure information) within a determination period, the reference time being the time when the exercise intensity of a predetermined level or higher occurred, and / or generates recovery index information indicating how the biological data is recovering from the response due to the occurrence of an exercise intensity of a predetermined level or higher, based on change information on the biological data (particularly, circulatory system-related information such as heart rate information and / or blood pressure information) from a responsive state or an active state to a resting state.The frailty index information generating unit 133 then performs clustering based on exercise intensity information indicating the exercise intensity associated with at least either the responsiveness index information or the recovery index information. Then, for each clustered exercise intensity information, the frailty index information generating unit 133 refers to correspondence relationship information that has been stored in advance (including information generated by machine learning) that describes the correspondence between at least one of the responsiveness index information or the recovery index information and reference frailty index information (which may be, for example, at least two or more categories, and may include, for example, at least a healthy subject group and a frail subject group), and determines frailty index information for indicating the user's frailty state based on at least one of the responsiveness index information or the recovery index information of the subject. The frailty index information may, for example, indicate a probability value indicating which category of the reference frailty index information is most likely to belong, or may be information indicating one category finally determined based on the probability value or the like.

[0069] The frailty index information generation unit 133 may evaluate the user's frailty state according to the determined frailty index information and generate evaluation information (for example, frailty symptom evaluation information (healthy or frail, etc.) or frailty symptom reference evaluation information indicating whether the evaluation is positive or negative as reference information to assist in determining the frailty symptom, which may correspond to the above-mentioned reference frailty index information). For example, the determined frailty index information may be used as is to evaluate the user's frailty state for each exercise corresponding to each exercise intensity. Alternatively, or in addition, the frailty index information determined for each exercise within a predetermined period may be used as is (particularly when it is a probability value), or may be scored (for example, 0 for the healthy subject group and 1 for the frail subject group), and an aggregate value such as the average value or total value within the predetermined period may be compared with a corresponding reference value (for example, half the value such as 0.5 for the average value, or half the total value when all values ​​are 1 for the total value, or the median or mode of reference data collected before the comparison), and the user's frailty state for the predetermined period may be evaluated according to the comparison result to generate evaluation information. In this case, the aggregated value of the scoring data of all frailty index information within a specified period may be used for comparison with the reference value, or the aggregated value of the scoring data from which at least either values ​​smaller than the first quartile or values ​​larger than the third quartile have been excluded, or from which outliers have been excluded, may be used.

[0070] The exercise intensity may be clustered (classified) based on, for example, change information (particularly transition information) of acceleration data or angular velocity data obtained from the inertial sensors (acceleration sensor, gyro sensor) of the measurement device 300, or may be clustered (classified) based on at least one of walking speed information, stride information, exercise amount information, movement information of the attachment part, activity amount information, and exercise load information generated using the acceleration data or angular velocity data. Alternatively, after clustering, an index expressed as a numerical value, classification, or rank according to the degree of exercise may be set. For example, the behavior information estimated from the above-mentioned behavior information may be associated with an index of exercise intensity, or may be converted into a known index (e.g., METS).

[0071] A more specific example of a clustering method for exercise intensity may be, for example, a method of clustering using signal feature information of at least one of amplitude, frequency components, and stationarity of measurement data (particularly data obtained from an inertial sensor) or biological data signals for a predetermined time period. Alternatively, for example, a method of clustering measurement data (particularly data obtained from an inertial sensor) or biological data signals for which correlation values ​​or correlation values ​​between power spectral densities are equal to or greater than a predetermined value within a certain time window width (which may be the above-mentioned determination period). Alternatively, a method of calculating exercise intensity may be used using a learning model that has been machine-learned using the entire signal waveform of measurement data (particularly data obtained from an inertial sensor) or biological data or each predetermined time window as features.

[0072] The judgment period is, for example, a period set at least either before or after the reference time, and may be arbitrarily set in advance, for example, by several minutes, several tens of seconds, or several seconds before or after the reference time, or the periods set before and after may be set differently, or may be set to several minutes, several tens of seconds, or several seconds after the reference time.

[0073] A responsive state is a state in which exercise intensity is greater than or equal to a predetermined level, or in which biometric data (especially circulatory system-related information such as heart rate information and / or blood pressure information) is greater than or equal to a predetermined value, or in which the fluctuation indicated by the fluctuation information is greater than or equal to a predetermined value.

[0074] The behavior state is a state in which the behavior type information indicates some kind of action.

[0075] A resting state is a state in which exercise intensity is below a predetermined value, or in which biometric data (especially circulatory system-related information such as heart rate information and / or blood pressure information) is below a predetermined value, or in which the fluctuation indicated by the fluctuation information is below a predetermined value.

[0076] As the correspondence information, for example, a correspondence relationship between at least one of responsiveness index information or recovery index information and frailty index information may be stored for each clustered exercise intensity information, depending on the results of a prior experiment, etc. As a more specific example, subjects may be classified based on known reference frailty indices such as the J-CHS criteria or the Rockwood frailty index, and the correspondence relationship between the exercise intensity information and at least one of responsiveness index information or recovery index information and the reference frailty index of the subject, based on measurement data from the measuring device 300 worn by the subject or biological data calculated from the measurement data (particularly, the correspondence relationship for each clustered exercise intensity information) may be stored in the storage unit 120, or may be trained as a learning model by machine learning.

[0077] When storing correspondence information as a learning model, a binary classification model can be created using known learning methods such as SVM, decision tree, gradient boosting, and logistic regression. When using this model, the determined frailty index information (frailty assessment information) can be frailty symptom information (healthy or frail) or two estimated values, such as positive or negative, as reference information to assist in determining frailty symptoms. Furthermore, when storing correspondence information as a learning model, a Transformer model using self-attention can be created. This learning model improves the efficiency of learning non-sequential sample information and overall learning performance by improving the RNN architecture and using the same Tensor for the input (query) and memory (key, value) in the attention structure. Self-attention makes it possible to acquire sequence structure and correspondence relationships, enabling efficient learning of non-sequential sample information. This Transformer structure extracts summary information from the input information in the encoder and replaces the summary information with sequence information in the decoder. By constructing a model architecture that uses only the encoder, such as BERT for language understanding and BEiT for image understanding, the model is trained to understand sequence information. When using a learning model (encoder model) created using this method, the sequence information of measurement data (particularly data obtained from inertial sensors) is processed, and the vector information derived from the leading limb tokens can be treated as summary information of the sequence information, and frailty index information (frailty assessment information) that indicates the progression of frailty symptoms is determined from the vector information derived here.

[0078] The data output unit 134 outputs the measurement data, biological data, frailty index information, etc. to the user terminal device 200 (the user here may be the subject or another person (for example, a close relative, a doctor, a caregiver, a researcher, etc.)). In the user terminal device 200, the output data may be displayed on a screen via a dedicated application, for example, so that the user can easily check it.

[0079] The input / output unit 140 is an information input device such as a keyboard and a mouse, and an output device such as a display.

[0080] <Processing flow> The flow of processing of the data assistance method executed by the information processing system 1 will be described with reference to Fig. 6. Fig. 6 is a flowchart showing an example of processing by the information processing system 1 of Fig. 1.

[0081] In the processing of step S101, data management unit 131 generates account information for each user who uses measurement device 300, and acquires predetermined user information from user terminal device 200, etc. The registered user information is stored in user information DB 124 by data management unit 131. The processing of step S101 may be performed as preprocessing before a user uses measurement device 300, or may be performed when a user uses measurement device 300 for the first time.

[0082] In step S102, when a user uses the measuring device 300, measurement data is transmitted from the measuring device 300 to the management server 100 via the user terminal device 200, and is received via the communication unit 110. The data management unit 131 stores the measurement data in association with the user information in the measurement data DB 121 of the storage unit 120.

[0083] In the process of step S103, the measurement data is read by the biometric data generation unit 132, and biometric data is generated by a predetermined calculation, etc. The generated biometric data is stored in the biometric data DB 122 by the data management unit 131.

[0084] In the process of step S104, the measurement data or biological data is read by the frailty index information generation unit 133, and frailty index information is generated by referring to the correspondence relationship information. The generated frailty index information is stored in the frailty index information DB 123 by the data management unit 131.

[0085] In the process of step S105, the data output unit 134 reads at least one of the measurement data, the biological data, and the frailty index information, and outputs it to the user terminal device 200.

[0086] <Effects> As described above, the information processing system according to this embodiment generates frailty index information particularly relating to the frailty state of the user based on the measurement data or biological data via the frailty index information generating unit 133. This makes it possible to grasp the frailty state of, for example, the subject.

[0087] Although the embodiments of the present disclosure have been described above, they can be implemented in various other forms, and various omissions, substitutions, and modifications can be made. These embodiments, modifications, and omissions, substitutions, and modifications are included in the technical scope of the claims and their equivalents. [Explanation of symbols]

[0088] 1. Information Processing Systems 100 Management Server 200 User terminal device 300 Measuring Equipment NW Network

Claims

1. An information processing system that receives measurement data from a measurement device worn by a user via a network and generates responsiveness index information based on biological data from the measurement data, A generator generates responsiveness index information indicating how the biological data responds to the occurrence of an exercise intensity equal to or greater than a predetermined level, based on change information of the biological data within a determination period, the change information being set as reference time information at a time when the exercise intensity equal to or greater than a predetermined level occurs. An information processing system comprising:

2. An information processing system that receives measurement data from a measurement device worn by a user via a network and generates recovery indicator information based on biological data from the measurement data, A generator that generates recovery index information indicating recovery from a response caused by the occurrence of the exercise intensity equal to or greater than the predetermined level based on change information of biological data from a response state or an action state to a resting state. An information processing system comprising:

3. Further comprising a data output unit that outputs the responsiveness index information to a predetermined terminal via the network.

2. The information processing system according to claim 1 .

4. Further comprising a data output unit that outputs the recovery index information to a predetermined terminal via the network.

3. The information processing system according to claim 2.

5. The generating unit uses circulatory system-related information including at least one of heart rate information and blood pressure information as the biological data during the determination period.

3. The information processing system according to claim 1, wherein the information processing system is a data processing system.

6. The exercise intensity is an index based on data obtained from an inertial sensor of the measuring device.

3. The information processing system according to claim 1, wherein the information processing system is a data processing system.

7. A server that receives measurement data from a measurement device worn by a user via a network and generates responsiveness index information based on biological data from the measurement data, A generator generates responsiveness index information indicating how the biological data responds to the occurrence of an exercise intensity equal to or greater than a predetermined level, based on change information of the biological data within a determination period, the change information being set as reference time information at a time when the exercise intensity equal to or greater than a predetermined level occurs. A server comprising:

8. A server that receives measurement data from a measurement device worn by a user via a network and generates index information based on biological data from the measurement data, A generator that generates recovery index information indicating recovery from a response caused by the occurrence of the exercise intensity equal to or greater than the predetermined level based on change information of biological data from a response state or an action state to a resting state. A server comprising:

9. An information processing method for receiving measurement data from a measurement device worn by a user via a network, and generating responsiveness index information based on biological data from the measurement data by a computer, comprising: and generating, by the generating unit, responsiveness index information indicating how the biological data responds to the occurrence of an exercise intensity equal to or greater than a predetermined level, based on change information of the biological data within a determination period, the reference time information being set to a time when the exercise intensity equal to or greater than a predetermined level occurs.

23. An information processing method comprising:

10. An information processing system that receives measurement data from a measurement device worn by a user via a network and generates recovery index information based on biological data from the measurement data by a computer, A step of generating, by a generating unit, recovery index information indicating recovery from the response due to the occurrence of the predetermined or higher exercise intensity based on change information of biological data from a response state or an action state to a resting state, 23. An information processing method comprising:

11. A program for causing a computer to receive measurement data from a measurement device worn by a user via a network and generate responsiveness index information based on biological data from the measurement data, comprising: causing the computer to execute a step of generating responsiveness index information showing how the biological data is responding to the occurrence of an exercise intensity equal to or greater than a predetermined level, based on change information of the biological data within a determination period, the reference time being set to a time when the exercise intensity equal to or greater than a predetermined level occurs; A program characterized by:

12. A program for receiving measurement data from a measurement device worn by a user via a network and causing a computer to execute recovery index information based on biological data from the measurement data, causing the computer to execute a step of generating recovery index information indicating recovery from a response caused by the occurrence of the exercise intensity equal to or greater than the predetermined level, based on change information of biological data from a response state or an active state to a resting state; A program characterized by:

Images