WO2025027673A1 - Information providing device, information providing system, information providing method, and recording medium - Google Patents

Abstract

An information providing device according to the present invention comprises: an acquisition unit that acquires sensor data including an acceleration and an angular velocity measured by a measurement device mounted on the footwear of a subject for whom credit information is to be created in order to provide credit-related information according to the mental and physical state of the subject; a risk estimation unit that uses the acquired sensor data to estimate a disease risk for each disease related to the subject; a credit-related information generation unit that generates credit-related information according to the estimated disease risk related to the subject and the status information of the subject registered in advance; and an output unit that outputs the generated credit-related information.

Description

Information providing device, information providing system, information providing method, and recording medium

This disclosure relates to an information providing device, an information providing system, an information providing method, and a recording medium.

Banks and other financial institutions review the loans they offer to their customers (target persons) based on the customer's credit information. When reviewing loans, factors such as the customer's creditworthiness, income, and ability to repay are emphasized. These factors can be affected by the customer's physical and mental state. If the customer's physical and mental state can be estimated based on their daily behavior, the customer's credit information can be reviewed in accordance with the estimated physical and mental state.

Patent Document 1 discloses a pre-credit limit calculation device. The device in Patent Document 1 performs detailed analysis of default risk and loan demand based on the personality and behavioral characteristics of customers inferred through years of data analysis. The device in Patent Document 1 calculates a pre-credit limit and a recommended credit limit based on the analysis results.

JP 2017-054495 A

The method of Patent Document 1 calculates a preliminary credit limit and a recommended credit limit based on the customer's personality and behavioral characteristics. The method of Patent Document 1 infers a customer's personality and behavioral characteristics from information such as ATM (Automatic Teller Machine) usage, card loan amounts used, repayment methods, and smartphone usage. Information such as ATM usage, card loan amounts used, repayment methods, and smartphone usage only reveals a one-sided personality. As a result, the method of Patent Document 1 was unable to accurately infer a customer's physical and mental state, including their personality.

The purpose of this disclosure is to provide an information provision device, an information provision system, an information provision method, and a recording medium that can provide credit-related information according to the subject's physical and mental state.

An information provision device according to one embodiment of the present disclosure includes an acquisition unit that acquires sensor data including acceleration and angular velocity measured by a measuring device mounted on the footwear of a subject for whom credit information is to be created, a risk estimation unit that estimates a disease risk for each disease related to the subject using the acquired sensor data, a credit-related information generation unit that generates credit-related information according to the estimated disease risk related to the subject and pre-registered status information of the subject, and an output unit that outputs the generated credit-related information.

In one aspect of the information provision method disclosed herein, sensor data including acceleration and angular velocity measured by a measuring device mounted on the footwear of a subject for whom credit information is to be created is acquired, the acquired sensor data is used to estimate disease risk for each disease of the subject, credit-related information is generated according to the estimated disease risk of the subject and pre-registered status information of the subject, and the generated credit-related information is output.

The program in one aspect of the present disclosure causes a computer to execute the following processes: acquiring sensor data including acceleration and angular velocity measured by a measuring device mounted on the footwear of a subject for whom credit information is to be created; estimating a disease risk for each disease related to the subject using the acquired sensor data; generating credit-related information based on the estimated disease risk related to the subject and pre-registered status information of the subject; and outputting the generated credit-related information.

This disclosure makes it possible to provide an information provision device, information provision system, information provision method, and recording medium that can provide credit-related information according to the subject's physical and mental state.

1 is a block diagram showing an example of a configuration of an information providing system according to the present disclosure. 1 is a block diagram showing an example of a configuration of a measurement device according to the present disclosure. FIG. 1 is a conceptual diagram showing an example of the arrangement of a measurement device in the present disclosure. 1 is a conceptual diagram showing an example of a coordinate system set in a measurement device according to the present disclosure. FIG. 2 is a conceptual diagram illustrating an example of a human body surface in the present disclosure. 1 is a block diagram showing an example of a configuration of an information providing device according to the present disclosure. FIG. 1 is a conceptual diagram illustrating an example of a walking cycle in the present disclosure. FIG. 1 is a conceptual diagram showing an example of a physical ability estimation model in the present disclosure. FIG. 1 is a conceptual diagram showing an example of estimating a disease risk score using a disease risk estimation model in the present disclosure. FIG. 1 is a conceptual diagram showing an example of estimating a disease risk score using a disease risk estimation model in the present disclosure. FIG. 1 is a conceptual diagram for explaining an example of estimating a credit score in the present disclosure. FIG. 1 is a conceptual diagram for explaining an example of estimating a credit score using a credit score estimation model in the present disclosure. 10 is a flowchart for explaining an example of an operation of an information providing device in the present disclosure. 11 is a flowchart for illustrating an example of a gait index calculation process performed by the information providing device in the present disclosure. FIG. 13 is a conceptual diagram showing a correlation diagram in an application example of the present disclosure. 11 is a conceptual diagram showing an example of displaying credit-related information in an application example of the present disclosure. FIG. 1 is a block diagram showing an example of a configuration of an information providing system according to the present disclosure. 1 is a block diagram showing an example of a configuration of an information providing device according to the present disclosure. 1 is a conceptual diagram for explaining an example of estimating personality information using a personality model in the present disclosure. FIG. 10 is a flowchart for explaining an example of an operation of an information providing device in the present disclosure. FIG. 13 is a conceptual diagram showing a correlation diagram in an application example of the present disclosure. 11 is a conceptual diagram showing an example of displaying credit-related information in an application example of the present disclosure. FIG. 1 is a block diagram showing an example of a configuration of an information providing device according to the present disclosure. 10 is a flowchart for explaining an example of an operation of an information providing device in the present disclosure. FIG. 2 is a block diagram showing an example of a hardware configuration according to the present disclosure.

Below, the embodiments for implementing the present disclosure are described with reference to the drawings. In this disclosure, the drawings used in the description of each embodiment relate to one or more embodiments. Furthermore, elements included in each drawing may apply to one or more embodiments. The embodiments described below are limited in a way that is technically preferable for implementing the present disclosure, but the scope of the disclosure is not limited to the following. In all drawings used in the description of the embodiments below, similar parts are given the same reference numerals unless there is a particular reason. In the embodiments below, repeated description of similar configurations and operations may be omitted.

First Embodiment
First, an example of an information provision system according to the present embodiment will be described with reference to the drawings. The information provision system according to the present embodiment acquires sensor data related to foot movements measured according to the walking of a customer (subject) for whom credit information is to be created to be used by a financial institution in considering loans, etc. The information provision system according to the present embodiment uses the acquired sensor data to estimate credit-related information to be referred to in the examination of a loan to the subject by the financial institution.

(composition)
FIG. 1 is a block diagram showing an example of the configuration of an information providing system 1 in the present disclosure. The information providing system 1 includes a measurement device 10 and an information providing device 12. For example, the measurement device 10 is installed in the footwear of a customer (subject) of a financial institution. For example, the function of the information providing device 12 is implemented in a server or a cloud. The server or cloud is connected via a network to a mobile terminal carried by the subject or a repeater installed inside a building where the subject is staying. For example, the function of the information providing device 12 may be implemented in a mobile terminal carried by the subject. In the following, the configurations of the measurement device 10 and the information providing device 12 will be described individually.

[Measuring equipment]
2 is a block diagram showing an example of the configuration of the measurement device 10. The measurement device 10 has a sensor 110, a control unit 113, a communication unit 115, and a power source 117. The sensor 110 has an acceleration sensor 111 and an angular velocity sensor 112. The sensor 110 may include sensors other than the acceleration sensor 111 and the angular velocity sensor 112. Descriptions of sensors other than the acceleration sensor 111 and the angular velocity sensor 112 that may be included in the sensor 110 will be omitted.

The acceleration sensor 111 is a sensor that measures acceleration in three axial directions. The acceleration in three axial directions is also called spatial acceleration. The acceleration sensor 111 measures acceleration as a physical quantity related to foot movement. The acceleration sensor 111 outputs the measured acceleration to the control unit 113. There are no limitations on the sensor used as the acceleration sensor 111 as long as it can measure acceleration. For example, the acceleration sensor 111 can be a piezoelectric type, a piezo-resistive type, a capacitance type, or other type of sensor.

Angular velocity sensor 112 is a sensor that measures angular velocity around three axes. Angular velocity around three axes is also called spatial angular velocity. Angular velocity sensor 112 measures angular velocity as a physical quantity related to foot movement. Angular velocity sensor 112 outputs the measured angular velocity to control unit 113. There are no limitations on the sensor used as angular velocity sensor 112 as long as it can measure angular velocity. For example, a vibration type, capacitance type, or other type of sensor can be used for angular velocity sensor 112.

The sensor 110 is realized, for example, by an inertial measurement unit that measures acceleration and angular velocity. An example of an inertial measurement unit is an IMU (Inertial Measurement Unit). The IMU includes an acceleration sensor that measures acceleration in three axial directions and an angular velocity sensor that measures angular velocity around three axes. The sensor 110 may be realized by an inertial measurement unit such as a VG (Vertical Gyro) or an AHRS (Attitude Heading Reference System). The sensor 110 may also be realized by a GPS/INS (Global Positioning System/Inertial Navigation System). The sensor 110 may be realized by a device other than an inertial measurement unit as long as it can measure physical quantities related to foot movement. For example, the sensor 110 may include a pressure sensor that measures pressure applied by the sole of the foot.

3 is a conceptual diagram showing an example of the measurement device 10 being placed in the shoes 100 of both feet. In the example of FIG. 3, the measurement device 10 is placed at a position that corresponds to the back side of the arch of the foot. For example, the measurement device 10 is placed in an insole inserted into the shoe 100. For example, the measurement device 10 may be placed on the bottom surface of the shoe 100. For example, the measurement device 10 may be embedded in the body of the shoe 100. The measurement device 10 may be detachable from the shoe 100, or may not be detachable from the shoe 100. The measurement device 10 may be placed at a position other than the back side of the arch of the foot, as long as it can measure sensor data related to foot movement. The measurement device 10 may also be placed in socks worn by the subject or in an accessory such as an anklet worn by the subject. The measurement device 10 may also be attached directly to the foot or embedded in the foot. The measurement device 10 may also be placed in one of the shoes 100, as long as it can measure data that can be used to estimate disease risk.

In the example of FIG. 3, a local coordinate system is set with the measuring device 10 (sensor 110) as the reference, including an x-axis in the left-right direction, a y-axis in the front-back direction, and a z-axis in the up-down direction. FIG. 3 shows an example in which the same coordinate system is set for the left foot and the right foot. For example, when sensors 110 manufactured with the same specifications are placed in the left and right shoes 100, the up-down orientation (Z-axis orientation) of the sensors 110 placed in the left and right shoes 100 is the same. In this case, the three axes of the local coordinate system set for the sensor data derived from the left foot and the three axes of the local coordinate system set for the sensor data derived from the right foot are the same for the left and right. In this disclosure, the x-axis is positive to the left, the y-axis is positive backward, and the z-axis is positive upward.

FIG. 4 is a conceptual diagram for explaining the local coordinate system (x-axis, y-axis, z-axis) set in the measuring device 10 (sensor 110) installed on the back side of the arch, and the world coordinate system (x-axis, y-axis, z-axis) set with respect to the ground. FIG. 4 shows an example in which different coordinate systems are set for the left foot and the right foot. In the world coordinate system (x-axis, y-axis, z-axis), the horizontal direction of the subject is set as the x-axis direction, the front-back direction of the subject is set as the y-axis direction, and the direction of gravity is set as the z-axis direction when the subject is standing upright facing the direction of travel. Note that the example in FIG. 4 conceptually shows the relationship between the local coordinate system (x-axis, y-axis, z-axis) and the world coordinate system (x-axis, y-axis, z-axis), and does not accurately show the relationship between the local coordinate system and the world coordinate system, which changes according to the subject's walking.

FIG. 5 is a conceptual diagram for explaining planes (also called human body planes) set for the human body. The sagittal plane is a plane that divides the body into left and right. The coronal plane is a plane that divides the body into front and back. The horizontal plane is a plane that divides the body horizontally. As shown in FIG. 5, when the user stands upright with the center line of the foot facing the direction of travel, the world coordinate system and the local coordinate system are assumed to match. FIG. 5 shows an example in which the same coordinate system is set for the left and right feet. In this embodiment, the rotation in the sagittal plane around the X-axis (x-axis) as the rotation axis is defined as roll, the rotation in the coronal plane around the Y-axis (y-axis) as the rotation axis is defined as pitch, and the rotation in the horizontal plane around the Z-axis (z-axis) as the rotation axis is defined as yaw. The rotation angle in the sagittal plane around the X-axis (x-axis) as the rotation axis is defined as roll angle, the rotation angle in the coronal plane around the Y-axis (y-axis) as the rotation axis is defined as pitch angle, and the rotation angle in the horizontal plane around the Z-axis (z-axis) as the rotation axis is defined as yaw angle.

The control unit 113 (control means) causes the acceleration sensor 111 and the angular velocity sensor 112 to measure sensor data. For example, the control unit 113 causes the acceleration sensor 111 and the angular velocity sensor 112 to start measurement in response to a measurement start signal transmitted from the information providing device 12. For example, the control unit 113 may cause the acceleration sensor 111 and the angular velocity sensor 112 to start measurement in response to detection of the subject's walking. For example, the control unit 113 starts measuring the step width starting from the point in time when it is detected that either the left or right foot has started to move in the forward direction after both feet have been at the same vertical height for a predetermined period of time. The control unit 113 may also cause the acceleration sensor 111 and the angular velocity sensor 112 to start measurement at a predetermined timing.

The control unit 113 acquires the acceleration in three axial directions from the acceleration sensor 111. The control unit 113 also acquires the angular velocity around three axes from the angular velocity sensor 112. For example, the control unit 113 performs AD (Analog-to-Digital) conversion of the acquired physical quantities (analog data) such as angular velocity and acceleration. The physical quantities (analog data) measured by the acceleration sensor 111 and the angular velocity sensor 112 may be converted to digital data in each of the acceleration sensor 111 and the angular velocity sensor 112. For example, an AD conversion circuit that AD converts the physical quantities (analog data) such as angular velocity and acceleration may be provided. The control unit 113 outputs the converted digital data (also called sensor data) to the communication unit 115. For example, the control unit 113 may temporarily store the sensor data in a storage unit (not shown).

The sensor data includes at least acceleration data converted into digital data and angular velocity data converted into digital data. The acceleration data includes acceleration vectors in three axial directions. The angular velocity data includes angular velocity vectors about three axes. The acceleration data and angular velocity data are linked to the time at which they were acquired. The control unit 113 may also apply corrections such as corrections for mounting errors, temperature corrections, and linearity corrections to the acceleration data and angular velocity data.

For example, the control unit 113 is realized by a microcomputer or microcontroller that performs overall control of the measuring device 10 and performs data processing. For example, the control unit 113 has a CPU (Central Processing Unit), RAM (Random Access Memory), ROM (Read Only Memory), flash memory, etc. For example, the control unit 113 may calculate at least one of the gait indices described below. In that case, the measuring device 10 outputs the calculated gait indices to the information providing device 12. For example, the control unit 113 may calculate features used to estimate physical ability described below. In that case, the measuring device 10 outputs the calculated features to the information providing device 12.

The communication unit 115 (communication means) acquires sensor data from the control unit 113. The communication unit 115 transmits the acquired sensor data to the information providing device 12. There are no particular limitations on the timing of transmitting the sensor data. For example, the communication unit 115 transmits the sensor data at a preset transmission timing. For example, the communication unit 115 transmits the sensor data in real time in response to the measurement of the sensor data. For example, the communication unit 115 may store sensor data measured over a predetermined period of time and transmit the stored sensor data all at once at a preset timing. For example, the communication unit 115 may be configured to receive a measurement start signal from the information providing device 12. In this case, the communication unit 115 outputs the received measurement start signal to the control unit 113.

For example, the communication unit 115 transmits the sensor data to the information providing device 12 via wireless communication. For example, the communication unit 115 transmits the sensor data to the information providing device 12 via a wireless communication function (not shown) that complies with standards such as Bluetooth (registered trademark) or WiFi (registered trademark). The communication function of the communication unit 115 may be based on standards other than Bluetooth (registered trademark) or WiFi (registered trademark). The communication unit 115 may transmit the sensor data to the information providing device 12 via a wired connection such as a cable.

The power source 117 is a battery that supplies power for the measurement device 10 to operate. For example, the power source 117 is realized by a thin battery such as a coin type or button type. For example, the power source 117 is realized by a primary battery such as a lithium primary battery, a silver oxide battery, an alkaline button battery, or an air zinc battery. When realized by a primary battery, the power source 117 is preferably realized by a long-life battery. The power source 117 may also be realized by a rechargeable secondary battery. When realized by a secondary battery, the power source 117 may be a battery that can be charged via a wired connection or a battery that can be wirelessly powered. If the power source 117 is capable of wireless power supply, a wireless power supply device may be placed in a place where footwear is placed, such as an entrance or a shoe cupboard. If footwear equipped with the measurement device 10 is placed on the wireless power supply device, the measurement device 10 can be appropriately charged when not in use.

[Information Providing Device]
6 is a block diagram showing an example of the configuration of the information providing device 12. The information providing device 12 has an acquisition unit 121, a waveform processing unit 122, a gait index calculation unit 123, a storage unit 124, a physical ability estimation unit 125, a disease risk estimation unit 126, a credit-related information generation unit 127, and an output unit 129. The waveform processing unit 122, the gait index calculation unit 123, the physical ability estimation unit 125, and the disease risk estimation unit 126 constitute the risk estimation unit 15. The waveform processing unit 122 and the gait index calculation unit 123 constitute the calculation unit 13. The physical ability estimation unit 125 and the disease risk estimation unit 126 constitute the estimation unit 14.

The acquisition unit 121 (acquisition means) acquires sensor data from the measuring device 10 mounted on the subject's footwear. The acquisition unit 121 receives the sensor data from the measuring device 10 via wireless communication. For example, the sensor data may include location information of a mobile terminal (not shown) that is the source of the sensor data. For example, the location information is measured by a GPS (Global Positioning System) function mounted on the mobile terminal and added to the sensor data. For example, the acquisition unit 121 receives the sensor data from the measuring device 10 via a wireless communication function (not shown) that complies with standards such as Bluetooth (registered trademark) and WiFi (registered trademark). Note that the communication function of the acquisition unit 121 may be in accordance with standards other than Bluetooth (registered trademark) and WiFi (registered trademark) as long as it can communicate with the measuring device 10. The acquisition unit 121 may receive the sensor data from the measuring device 10 via a wired connection such as a cable. For example, the acquisition unit 121 may acquire gait indices and feature amounts calculated by the measurement device 10.

The acquisition unit 121 also acquires attribute data of the subject. The attribute data includes gender, date of birth, height, and weight. The date of birth is converted to age. Age may be included in the attribute data. The gender, date of birth (age), height, and weight included in the attribute data are also called physical information. For example, the attribute data is input via an input device (not shown). For example, the attribute data is input via a terminal device used by the administrator. For example, the attribute data is input via a mobile terminal used by the subject. For example, the attribute data may be stored in advance in the storage unit 124. The attribute data may be updated at any time in response to input by the subject or the administrator.

The acquisition unit 121 also acquires the status information of the subject. The status information is information related to the social attributes of the subject. For example, the status information includes identity information, credit history information, contract fulfilment information, interpersonal relationship information, and behavioral characteristic information. The identity information includes information that guarantees that the subject's name is a real name, and information that indicates the stability of the subject's status. The credit history information includes card repayment history information, loan repayment history information, tax payment history information, insurance premium payment history information, pension payment history information, and fine payment history information. The contract fulfilment information includes fixed asset information, deposit and savings information, and income information. The interpersonal relationship information includes personal connections information and social influence information. The behavioral characteristic information includes consumption behaviour information, travel behaviour information, and health behaviour information. Note that the information included in the status information is not limited to that listed here. Of the status information listed here, the credit history information, contract fulfilment information, interpersonal relationship information, and behavioral characteristic information are affected by the subject's disease risk. The sum of the scores relating to the identification information, credit history information, contract fulfilment ability information, human relationship information, and behavioral characteristic information corresponds to the credit score, which will be described later. As will be described later, the credit history information, contract fulfilment ability information, human relationship information, and behavioral characteristic information are multiplied by a penalty coefficient according to the subject's status information and disease risk. For example, the status information is input via an input device (not shown). For example, the status information is input via a terminal device used by the administrator. For example, the status information is input via a mobile terminal used by the subject. For example, the status information may be registered in advance in the storage unit 124. The attribute data may be updated at any time according to input by the subject or the administrator.

The waveform processing unit 122 (waveform processing means) acquires sensor data from the acquisition unit 121. The waveform processing unit 122 extracts time series data for one walking cycle from the time series data of acceleration in three axial directions and angular velocity around three axes contained in the sensor data. The time series data for one walking cycle is also called walking waveform data. The waveform processing unit 122 extracts walking waveform data based on the timing of walking events detected from the time series data of the sensor data. For example, the waveform processing unit 122 extracts walking waveform data that starts at the timing of a heel strike and ends at the timing of the next heel strike.

Here, the walking cycle will be explained with reference to the drawings. FIG. 7 is a conceptual diagram for explaining the step cycle based on the right foot. The step cycle based on the left foot is similar to the right foot. The horizontal axis of FIG. 7 indicates one walking cycle of the right foot, starting from the point when the heel of the right foot lands on the ground and ending from the point when the heel of the right foot lands on the ground. The horizontal axis of FIG. 7 is normalized with the step cycle set to 100%. Normalizing one walking cycle to 100% is called the first normalization. One walking cycle of one foot is broadly divided into a stance phase in which at least a part of the sole of the foot is in contact with the ground, and a swing phase in which the sole of the foot is off the ground. The stance phase is the period in which at least a part of the sole of the foot is in contact with the ground. The stance phase is further divided into an early stance phase T1, a mid stance phase T2, a final stance phase T3, and an early swing phase T4. The swing phase is the period when the sole of the foot is off the ground. The swing phase is further divided into early swing phase T5, mid swing phase T6, and final swing phase T7. The horizontal axis in FIG. 7 is normalized so that the stance phase is 60% and the swing phase is 40%. Normalizing the gait waveform data so that the stance phase is 60% and the swing phase is 40% is called second normalization. Note that the periods shown in FIG. 7 are merely examples, and do not limit the periods that make up a step cycle or the names of these periods.

As shown in Figure 7, multiple events occur during walking. Multiple events that occur during walking are also called walking events. P1 represents heel strike (HS: Heel Strike). Heel strike is an event in which the heel of the right foot touches the ground. P2 represents opposite toe off (OTO: Opposite Toe Off). Opposite toe off is an event in which the toe of the left foot leaves the ground while the sole of the right foot is on the ground. P3 represents heel rise (HR: Heel Rise). Heel rise is an event in which the right heel rises while the sole of the right foot is on the ground. P4 represents opposite heel strike (OHS: Opposite Heel Strike). Opposite heel strike is an event in which the heel of the left foot touches the ground. P5 represents toe off (TO: Toe Off). Toe off is an event in which the toe of the right foot leaves the ground while the sole of the left foot is on the ground. P6 represents foot adjacent (FA). Foot crossing is an event in which the left and right feet cross while the sole of the left foot is on the ground. P7 represents tibia vertical (TV). Tibia vertical is an event in which the tibia of the right foot becomes nearly perpendicular to the ground while the sole of the left foot is on the ground. P8 represents heel strike. P8 corresponds to the end point of the walking cycle that begins with P1 and corresponds to the starting point of the next walking cycle. Note that the walking events shown in Figure 7 are merely examples, and do not limit the events that occur during walking or the names of these events.

The timing of heel strike is the timing of the minimum peak immediately after the maximum peak that appears in the time series data of forward acceleration (Y-direction acceleration). The maximum peak that marks the timing of heel strike corresponds to the maximum peak of the gait waveform data for one step cycle. The section between successive heel strikes corresponds to one step cycle. The timing of toe off is the timing of the rise of the maximum peak that appears after the stance phase period in which no fluctuations appear in the time series data of forward acceleration (Y-direction acceleration). The midpoint between the timing of the minimum roll angle and the timing of the maximum roll angle corresponds to the mid-stance phase.

The waveform processing unit 122 normalizes (first normalization) the time of the extracted walking waveform data for one step cycle to a walking cycle of 0 to 100% (percent). The timing of 1%, 10%, etc. included in the 0 to 100% walking cycle is also called a walking phase. Furthermore, with respect to the first normalized walking waveform data for one step cycle, the waveform processing unit 122 normalizes (second normalization) the walking waveform data so that the stance phase is 60% and the swing phase is 40%. If the walking waveform data is second normalized, the deviation of the walking phase from which the feature amount is extracted can be reduced. The waveform processing unit 122 outputs the normalized walking waveform data to the gait index calculation unit 123.

For example, the waveform processing unit 122 extracts walking waveform data for one step cycle using the forward acceleration (Y-direction acceleration). For accelerations/angular velocities other than the forward acceleration (Y-direction acceleration), the waveform processing unit 122 extracts walking waveform data for one step cycle in accordance with the walking cycle of the forward acceleration (Y-direction acceleration). The waveform processing unit 122 normalizes the extracted walking waveform data for one step cycle. The waveform processing unit 122 may also generate time series data of angles around three axes by integrating time series data of angular velocities around three axes. In that case, the waveform processing unit 122 extracts walking waveform data for one step cycle in accordance with the walking cycle of the forward acceleration (Y-direction acceleration) for angles around three axes as well.

The waveform processing unit 122 may extract walking waveform data for one step cycle using acceleration/angular velocity other than the forward acceleration (Y-direction acceleration). For example, the waveform processing unit 122 may detect heel strike and toe lift from time series data of vertical acceleration (Z-direction acceleration) (not shown). The timing of heel strike is the timing of a steep minimum peak that appears in the time series data of vertical acceleration (Z-direction acceleration). At the timing of the steep minimum peak, the value of vertical acceleration (Z-direction acceleration) becomes almost 0. The minimum peak that marks the timing of heel strike corresponds to the minimum peak of the walking waveform data for one step cycle. The section between successive heel strikes is the one step cycle. The timing of toe lift is the timing of an inflection point in the middle of the time series data of vertical acceleration (Z-direction acceleration) gradually increasing after a section of small fluctuation following the maximum peak immediately after heel strike. The waveform processing unit 122 may also extract walking waveform data for one step cycle using both the forward acceleration (Y-direction acceleration) and the vertical acceleration (Z-direction acceleration). The waveform processing unit 122 may also extract walking waveform data for one step cycle using acceleration, angular velocity, angle, etc. other than the forward acceleration (Y-direction acceleration) and the vertical acceleration (Z-direction acceleration).

The waveform processing unit 122 extracts features (physical ability features) used to estimate physical abilities from the walking waveform data. The waveform processing unit 122 extracts physical ability features used to estimate at least one physical ability. For example, the waveform processing unit 122 extracts physical ability features used to estimate at least one of physical abilities such as grip strength (total muscle strength of the entire body), dynamic balance, lower limb muscle strength, mobility, and static balance. For example, the waveform processing unit 122 extracts physical ability features for each walking phase cluster according to a preset condition. A walking phase cluster is a cluster that integrates walking phases that are consecutive in time. A walking phase cluster includes at least one walking phase. A walking phase cluster also includes a single walking phase. The waveform processing unit 122 outputs the extracted physical ability features to the physical ability estimation unit 125. Note that if physical ability is not used in estimating disease risk, the extraction of physical ability features can be omitted.

The gait index calculation unit 123 (gait index calculation means) acquires normalized gait waveform data from the waveform processing unit 122. The gait index calculation unit 123 uses the normalized gait waveform data to calculate gait indices used to estimate physical ability. There are no particular limitations on the gait indices to be calculated. For example, the gait index calculation unit 123 calculates gait indices related to distance, height, angle, speed, time, CPEI (Center of Pressure Exclusion Index), frailty level, etc. Representative gait indices are listed below. Specific calculation methods for the following gait indices will be omitted.

For example, the gait index calculation unit 123 calculates indices related to distance and height as gait indices. For example, the gait index calculation unit 123 calculates stride length, turning distance, foot lift height, FTC (Foot Clearance), and MTC (Minimum Toe Clearance). Stride length indicates the distance between the front foot and the rear foot while walking. Turning distance indicates the maximum distance that the foot is moved outward in the direction of travel during the swing phase. Foot lift height indicates the maximum distance between the measuring device 10 (sensor 110) and the ground during the swing phase. FTC indicates the maximum distance between the heel and the ground during the swing phase. MTC indicates the minimum distance between the toe and the ground during the swing phase.

For example, the gait index calculation unit 123 calculates indexes related to angles as gait indices. For example, the gait index calculation unit 123 calculates the contact angle, the take-off angle, the toe direction, the heel contact roll angle, the toe off roll angle, the swing leg peak angular velocity, and the big toe angle. The contact angle indicates the maximum angle between the sole of the foot and the ground at heel contact. The take-off angle indicates the angle between the sole of the foot and the ground during the swing phase. The toe direction indicates the average value of the direction of the toe relative to the direction of travel during the swing phase. The heel contact roll angle is the angle between the ankle and the ground at heel contact as viewed from a rear perspective. The toe off roll angle is the angle between the ankle and the ground at push-off as viewed from a rear perspective. The swing leg peak angular velocity is the angular velocity in the ankle dorsiflexion direction in the section from immediately after push-off until the toe comes closest to the ground. The hallux angle indicates the angle at which the big toe is tilted toward the index toe. Specifically, the hallux angle is the angle between the center line of the first metatarsal bone and the center line of the first proximal phalanx.

For example, the gait index calculation unit 123 calculates an index related to speed as a gait index. For example, the gait index calculation unit 123 calculates walking speed, cadence, and maximum swing speed. Walking speed indicates the walking speed. Cadence indicates the number of steps per minute. Maximum swing speed indicates the speed at which the leg is swung out during the swing phase.

For example, the gait index calculation unit 123 calculates time-related indices as gait indices. For example, the gait index calculation unit 123 calculates stance time, load time, sole contact time, push-off time, swing time, and DST (Double Support Time). Stance time indicates the time that the foot is on the ground while walking. Stance time is the sum of load time, sole contact time, and push-off time. Load time is the time from when the heel touches the ground until the toe touches the ground during the stance phase. Sole contact time is the time during the stance phase when the entire sole of the foot is on the ground and the sole of the foot is horizontal to the ground. Push-off time is the time from when the sole of the foot is on the ground until the toe pushes off the ground during the stance phase. Swing time indicates the time that the foot is off the ground while walking. DST is divided into DST1 and DST2. DST1 indicates the time during which the foot on which the measuring device 10 (sensor 110) is mounted is in front of the other foot during a period when both feet are on the ground at the same time. DST2 indicates the time during which the foot on which the measuring device 10 (sensor 110) is mounted is behind the other foot during a period when both feet are on the ground at the same time.

For example, the gait index calculation unit 123 calculates the Center of Pressure Exclusion Index (CPEI) as a gait index. The CPEI indicates an estimate of the rate of expansion of the movement of the center of foot pressure on the ground during the stance phase.

For example, the gait index calculation unit 123 calculates a frailty level as a gait index. The frailty level is an estimated value of a frailty state according to a walking state. For example, the gait index calculation unit 123 estimates an index indicating a judgment result regarding frailty as the frailty level. If there is no possibility of frailty, the gait index calculation unit 123 estimates an index indicating that there is no frailty. If there is a possibility of frailty, the gait index calculation unit 123 estimates an index indicating that there is a possibility of frailty. Furthermore, if there is a high possibility of frailty, the gait index calculation unit 123 estimates an index indicating that there is a high possibility of frailty.

The memory unit 124 (storage means) stores a physical ability estimation model (described later) that estimates physical ability using physical ability features extracted from the walking waveform data. For example, the physical ability is at least one of grip strength, dynamic balance, lower limb muscle strength, mobility, and static balance. The physical ability may include items other than grip strength, dynamic balance, lower limb muscle strength, mobility, and static balance. The memory unit 124 stores physical ability estimation models trained for multiple subjects. For example, the physical ability estimation model outputs an index of physical ability (physical ability score) in response to input of physical ability features extracted from the walking waveform data. If physical ability is not used in estimating disease risk, the physical ability estimation model can be omitted.

The memory unit 124 also stores a disease risk estimation model (described later). The disease risk estimation model estimates disease risk using attribute data, gait index, and physical ability score. The disease risk indicates the risk of contracting a specific disease. For example, the specific diseases include gout, diabetes, hypertension, nephrolithiasis, liver cirrhosis, arteriosclerosis, thromboembolism, dyslipidemia, hypercholesterolemia, hyperlipidemia, and the like. For example, the specific diseases include lower back pain, sleep apnea syndrome, insomnia, depression, osteoarthritis of the knee, Parkinson's syndrome, and the like. The specific diseases may include diseases other than those mentioned above. The memory unit 124 stores disease risk estimation models learned for multiple subjects. For example, the disease risk estimation model outputs an index related to disease risk (disease risk score) in response to input of attribute data, gait index, and physical ability score. For example, the disease risk estimation model may be a model that outputs a disease risk score in response to input of gait index and attribute data without using a physical ability score. In that case, the physical ability estimation model is omitted.

The memory unit 124 may also store a credit score estimation model (described below). The credit score estimation model estimates a credit score using status information and a disease risk score. The memory unit 124 stores a credit score estimation model trained on a plurality of subjects. For example, the credit score estimation model outputs a credit-related indicator (credit score) in response to input of status information and a disease risk score.

The memory unit 124 stores the physical ability estimation model and disease risk estimation model learned for multiple subjects. For example, the physical ability estimation model and disease risk estimation model may be stored in the memory unit 124 when the product is shipped from the factory. The physical ability estimation model and disease risk estimation model may also be stored in the memory unit 124 at the timing of calibration of the information providing device 12. For example, a physical ability estimation model and disease risk estimation model saved in a storage device (not shown) such as an external server may be used. In that case, it is sufficient if the physical ability estimation model and disease risk estimation model can be accessed via an interface (not shown) connected to the storage device.

The memory unit 124 also stores attribute data and status information of the subject. The attribute data includes gender, date of birth (age), height, and weight. The status information includes identification information, credit history information, contract enforcement ability information, human relationship information, and behavioral characteristic information. The attribute data and status information may be updated at any time. Furthermore, the memory unit 124 may store health check data of the subject. The health check data can be a factor in improving the estimation accuracy of disease risk scores and credit-related information. For example, the health check data of the subject includes diagnosis results regarding statutory items in the health check at the time of employment and regular health checks. The health check data of the subject may also include diagnosis results regarding items other than statutory items in the health check at the time of employment and regular health checks.

The physical ability estimation unit 125 (physical ability estimation means) acquires the physical ability feature extracted from the walking waveform data from the waveform processing unit 122. The physical ability estimation unit 125 also acquires the attribute data stored in the memory unit 124. The physical ability estimation unit 125 estimates a physical ability score using the physical ability feature and the attribute data. The physical ability estimation unit 125 inputs the subject's physical ability feature and attribute data to a physical ability estimation model stored in the memory unit 124. For example, the physical ability estimation unit 125 estimates a physical ability score related to at least one of the physical abilities of grip strength (total muscle strength of the entire body), dynamic balance, lower limb muscle strength, mobility, and static balance. The estimation of the physical ability score by the physical ability estimation unit 125 will be described later. The physical ability estimation unit 125 outputs the physical ability score output from the physical ability estimation model to the disease risk estimation unit 126.

Next, an example of the estimation of the physical ability score by the physical ability estimation unit 125 will be described. Here, an example of the feature values used to estimate grip strength (total muscle strength of the entire body), dynamic balance, lower limb muscle strength, mobility, and static balance will be described. Note that the following example does not limit the physical ability estimated by the physical ability estimation unit 125. The physical ability estimated by the physical ability estimation unit 125 may be appropriately selected depending on the disease for which the disease risk is to be estimated. Note that the disease risk estimation unit 126 may be configured to estimate the disease risk using the gait index and attribute data without using the physical ability score. In that case, the physical ability estimation unit 125 may be omitted from the estimation unit 14.

<Grip strength (total muscle strength of the whole body)>
There is a correlation between grip strength, which is one of the physical abilities, and the total muscle strength of the whole body. Grip strength is also correlated with knee extension strength. For example, an estimated value of grip strength is an index of total muscle strength. For example, a score according to an estimated value of grip strength (also called a total muscle strength score) is an index of total muscle strength. The total muscle strength score is a value obtained by scoring grip strength, which is an index of total muscle strength, according to a preset criterion. Grip strength is affected by attributes such as gender, age, and height. Therefore, the total muscle strength score may be scored according to a criterion for each attribute. In particular, grip strength is affected by gender. Therefore, the total muscle strength score may be scored according to different criteria depending on gender. Note that the index of total muscle strength is not limited to grip strength as long as the total muscle strength can be scored.

The walking phase from which the features used to estimate grip strength are extracted differs depending on gender. For men, there is a correlation between quadriceps activity and grip strength. Therefore, to estimate men's grip strength, features extracted from walking phases in which the characteristics of quadriceps activity are apparent are used. For women, there is a correlation between grip strength and activity of the vastus lateralis, vastus intermedius, and vastus medialis muscles of the quadriceps. Therefore, to estimate women's grip strength, features extracted from walking phases in which the characteristics of vastus lateralis, vastus intermedius, and vastus medialis muscles are apparent are used.

Features AM1, AM2, AM3, and AM4 are used to estimate the grip strength of a man. Feature AM1 is extracted from the 3% walking phase section of the walking waveform data related to the time series data of the acceleration in the forward direction (acceleration in the Y direction). The 3% walking phase is included in the initial stance phase T1. Feature AM1 mainly includes features related to the movement of the vastus lateralis, vastus intermedius, and vastus medialis, which are among the quadriceps muscles. Feature AM2 is extracted from the 59-62% walking phase section of the walking waveform data related to the time series data of the acceleration in the forward direction (acceleration in the Y direction). The 59-62% walking phase is included in the early swing phase T4. Feature AM2 mainly includes features related to the movement of the rectus femoris, which is among the quadriceps muscles. Feature AM3 is extracted from the 59-62% walking phase section of the walking waveform data related to the time series data of the acceleration in the vertical direction (acceleration in the Z direction). 59-62% of the walking phase is included in the early swing phase T4. Feature AM3 mainly includes features related to the movement of the rectus femoris, which is one of the quadriceps muscles. Feature AM4 is the proportion of the period from heel-contact to toe-off of the opposite foot during the period when both feet are simultaneously on the ground (DST1). DST1 is the proportion of the period from heel-contact to toe-off of the opposite foot during one stride cycle. Feature AM4 mainly includes features attributable to the quadriceps muscles.

Feature AF1, feature AF2, and feature AF3 are used to estimate the grip strength of women. Feature AF1 is extracted from a 13% section of the walking phase of the walking waveform data related to the time series data of lateral acceleration (X-direction acceleration). The 13% walking phase is included in the mid-stance phase T2. Feature AF1 mainly includes features related to the movement of the vastus lateralis, vastus intermedius, and vastus medialis of the quadriceps. Feature AF2 is extracted from a 7-10% section of the walking phase of the walking waveform data related to the time series data of the angular velocity (pitch angular velocity) in the coronal plane (around the Y-axis). The 7-10% walking phase is included in the early stance phase T1. Feature AF2 mainly includes features related to the movement of the vastus lateralis, vastus intermedius, and vastus medialis. Feature AF3 is the proportion of the period from heel contact to toe-off of the opposite foot to the period during which both feet are simultaneously on the ground (DST2). DST2 is the ratio of the period from heel contact to toe-off of the opposite foot in a gait cycle. The sum of DST1 and DST2 corresponds to the period during which both feet are simultaneously in contact with the ground in a gait cycle. Feature AF3 mainly includes features related to the movements of the vastus lateralis, vastus intermedius, and vastus medialis.

<Dynamic balance>
Dynamic balance, which is one of the physical abilities, can be evaluated by the results of a Functional Reach Test (FRT). In the present disclosure, the results of the FRT are evaluated by the distance between the fingertips (also called the functional reach distance) when the upper limbs are moved forward as far as possible from a standing position with both hands raised at 90 degrees relative to the horizontal plane. The functional reach distance (hereinafter, called the FR distance) is the FRT performance value. The larger the FR distance, the higher the FRT performance. The dynamic balance may be evaluated by something other than the FRT performed with both hands. For example, the dynamic balance may be evaluated by the performance of the FRT performed with one hand or other variations of the FRT.

The index of dynamic balance is the FR distance. For example, an estimated value of the FR distance is the index of dynamic balance. For example, a score according to the estimated value of the FR distance (also called the dynamic balance score) is the index of dynamic balance. The dynamic balance score is a value obtained by scoring the FR distance, which is an index of dynamic balance, using a preset criterion. Dynamic balance is affected by attributes such as height. Therefore, the dynamic balance score may be scored using a criterion for each attribute. Note that the index of dynamic balance is not limited to the FR distance as long as dynamic balance can be scored. The FR distance is correlated with the activity of the gluteus medius, iliac muscle, hamstrings (long head of biceps femoris), tibialis anterior muscle, etc., and the magnitude of the compensatory movement of turning the toes outward. Therefore, the feature quantity extracted from the walking phase in which these features appear is used to estimate the FR distance.

Features B1, B2, B3, B4, and B5 are used to estimate the FR distance. Feature B1 is extracted from the 75-79% walking phase of the gait waveform data related to the time series data of the acceleration in the forward direction (acceleration in the Y direction). The 75-79% walking phase is included in the mid-swing phase T6. Feature B1 mainly includes features related to the movement of the tibialis anterior and the short head of the biceps femoris. Feature B2 is extracted from the 62% walking phase of the gait waveform data related to the time series data of the acceleration in the vertical direction (acceleration in the Z direction). The 62% walking phase is included in the early swing phase T5. Feature B2 mainly includes features related to the movement of the iliacus. Feature B3 is extracted from the 7-8% walking phase of the gait waveform data related to the time series data of the angular velocity in the coronal plane (around the Y axis). The 7-8% walking phase is included in the early stance phase T1. The feature B3 mainly includes features related to the movement of the gluteus medius. The feature B4 is extracted from the section of the walking phase 57-58% of the walking waveform data related to the time series data of the angle (posture angle) in the horizontal plane (around the Z axis). The walking phase 57-58% is included in the early swing phase T4. The feature B4 mainly includes features related to the compensatory movement. The compensatory movement is a movement to change the foot angle to obtain stability in order to compensate for the deterioration of balance ability and muscle function that occurs with aging. The feature B5 is the average value of the foot angle in the horizontal plane during the swing phase. For example, the feature B5 is the average value in the swing phase of the walking waveform data. In other words, the feature B5 is the integral value of the walking waveform data related to the time series data of the angular velocity in the horizontal plane (around the Z axis). The feature B5 mainly includes features related to the compensatory movement.

<Lower limb strength>
Lower limb muscle strength, which is one of the physical abilities, can be evaluated by the results of a chair stand test. In the present disclosure, the results of the 5-times chair stand test, in which the person stands up and sits down on a chair five times, are evaluated. The 5-times chair stand test is also called the SS-5 (Sit to Stand-5) test. The results of the 5-times chair stand test are evaluated based on the time it takes to stand up and sit down on a chair five times (also called the sit-to-stand time). The sit-to-stand time is the score value of the SS-5 test. The shorter the sit-to-stand time, the higher the score of the SS-5 test. The results may also be evaluated based on the results of a 30-second chair stand (CS-30) test, which measures the number of times the person stands up and sits down on a chair in 30 seconds.

The index of lower limb muscle strength is the sit-stand time. For example, an estimate of the sit-stand time five times is an index of lower limb muscle strength. For example, a score according to the estimate of the sit-stand time (also called the lower limb muscle strength score) is an index of lower limb muscle strength. The lower limb muscle strength score is a value obtained by scoring the sit-stand time, which is an index of lower limb muscle strength, using a preset criterion. Lower limb muscle strength is affected by attributes such as age. Therefore, the lower limb muscle strength score may be scored using a criterion for each attribute. Note that the index of lower limb muscle strength is not limited to the sit-stand time, as long as the lower limb muscle strength can be scored. The sit-stand time is correlated with the quadriceps, hamstrings, tibialis anterior, and gastrocnemius. Therefore, feature values extracted from the walking phase in which these features appear are used to estimate the sit-stand time.

The estimation of lower limb muscle strength includes feature C1, feature C2, feature C3, and feature C4. Feature C1 is extracted from the section of walking phase 42-54% of the walking waveform data related to the time series data of angular velocity in the sagittal plane (around the X-axis). Walking phase 42-54% is the section from the end of stance phase T3 to the early swing phase T4. Feature C1 mainly includes features related to the movement of the gastrocnemius. Feature C2 is extracted from the section of walking phase 99-100% of the walking waveform data related to the time series data of angular velocity in the coronal plane (around the Y-axis). Walking phase 99-100% is the end of the end of swing phase T7. Feature C2 mainly includes features related to the movement of the quadriceps, hamstrings, and tibialis anterior. Feature C3 is extracted from the 10% to 12% walking phase section of the walking waveform data related to the time series data of angular velocity in the coronal plane (around the Y-axis). The 10% to 12% walking phase is the beginning of mid-stance phase T2. Feature C3 mainly includes features related to the movement of the quadriceps, hamstrings, and gastrocnemius. Feature C4 is extracted from the 99% walking phase section of the walking waveform data related to the time series data of angles (posture angles) in the horizontal plane (around the Z-axis). The 99% walking phase is the end of end-swing phase T7. Feature C4 mainly includes features related to the movement of the quadriceps, hamstrings, and tibialis anterior.

<Movement Ability>
Mobility, which is one of the physical abilities, can be evaluated by the results of a TUG (Time Up and Go) test. In the present disclosure, the results of the TUG test are evaluated based on the time it takes to stand up from a chair, walk to a landmark 3 meters away, change direction, and sit back down on the chair (also called the TUG time). The TUG time is the score value of the TUG test. The shorter the TUG time, the higher the score of the TUG test. Mobility may be evaluated by the score of a test related to mobility other than the TUG test.

The index of mobility is the time required for TUG. For example, an estimate of the time required for TUG is an index of mobility. For example, a score according to the estimate of the time required for TUG (also called a mobility score) is an index of mobility. The mobility score is a value obtained by scoring the time required for TUG, which is an index of mobility, using a preset criterion. Mobility is affected by attributes such as age. Therefore, the mobility score may be scored using a criterion for each attribute. Note that the index of mobility is not limited to the time required for TUG, as long as mobility can be scored. The time required for TUG is correlated with the quadriceps, gluteus medius, and tibialis anterior. Therefore, feature quantities extracted from the walking phase in which these features appear are used to estimate the time required for TUG.

Feature amount D1, feature amount D2, feature amount D3, feature amount D4, feature amount D5, and feature amount D6 are used to estimate mobility. Feature amount D1 is extracted from the section of walking phase 64-65% of walking waveform data related to time series data of lateral acceleration (X-direction acceleration). Walking phase 64-65% is included in early swing phase T5. Feature amount D1 mainly includes features related to the movement of the quadriceps in the standing and sitting movements. Feature amount D2 is extracted from the section of walking phase 57-58% of walking waveform data related to time series data of angular velocity in the sagittal plane (around the X-axis). Walking phase 57-58% is included in early swing phase T4. Feature amount D2 mainly includes features related to the movement of the quadriceps related to the kicking speed of the foot. The feature amount D3 is extracted from a section of the walking phase 19-20% of the walking waveform data related to the time series data of the angular velocity in the coronal plane (around the Y axis). The walking phase 19-20% is included in the mid-stance phase T2. The feature amount D3 mainly includes features related to the movement of the gluteus medius muscle in the change of direction. The feature amount D4 is extracted from a section of the walking phase 12-13% of the walking waveform data related to the time series data of the angular velocity in the horizontal plane (around the Z axis). The walking phase 12-13% is the beginning of the mid-stance phase T2. The feature amount D4 mainly includes features related to the movement of the gluteus medius muscle in the change of direction. The feature amount D5 is extracted from a section of the walking phase 74-75% of the walking waveform data related to the time series data of the angular velocity in the horizontal plane (around the Z axis). The walking phase 74-75% is the beginning of the mid-swing phase T6. Feature D5 mainly includes features related to the movement of the tibialis anterior muscle when standing up, sitting down, and changing direction. Feature D6 is extracted from the section of the walking phase 76-80% of the walking waveform data related to the time series data of the angle (posture angle) in the coronal plane (around the Y axis). The walking phase 76-80% is included in the mid-swing phase T6. Feature D6 mainly includes features related to the movement of the tibialis anterior muscle when standing up, sitting down, and changing direction.

<Static balance>
Static balance, which is one of the physical abilities, can be evaluated by the performance of a one-leg standing test. In the present disclosure, the performance of the one-leg standing test is evaluated based on the time (also called the one-leg standing time) during which the eyes are closed and one leg is raised 5 centimeters (cm) from the ground. The one-leg standing time is a performance value of static balance. The longer the one-leg standing time, the higher the performance of static balance. Static balance may be evaluated by a performance other than the one-leg standing test with eyes closed. For example, static balance may be evaluated by a one-leg standing test with eyes open (one-leg standing test with eyes open) or other variations of the one-leg standing test.

The static balance index is the single leg standing time. For example, an estimate of the single leg standing time is an index of static balance. For example, a score according to the estimate of the single leg standing time (also called the static balance score) is an index of static balance. The static balance score is a value obtained by scoring the single leg standing time, which is an index of static balance, using a preset criterion. Static balance is affected by attributes such as age and height. Therefore, the static balance score may be scored using a criterion for each attribute. Note that the static balance index is not limited to the single leg standing time as long as the static balance can be scored. The single leg standing time is correlated with the gluteus medius, adductor longus, sartorius, and abductor and adductor muscles. Therefore, the feature values extracted from the walking phase in which these features appear are used to estimate the single leg standing time.

Features E1, E2, E3, E4, E5, E6, and E7 are used to estimate static balance. Feature E1 is extracted from the 13-19% gait phase section of the gait waveform data related to the time series data of lateral acceleration (X-direction acceleration). The 13-19% gait phase is included in the mid-stance phase T2. Feature E1 mainly includes features related to the movement of the gluteus medius. Feature E2 is extracted from the 95% gait phase section of the gait waveform data related to the time series data of vertical acceleration (Z-direction acceleration). The 95% gait phase is the end of the end-swing phase T7. Feature E2 mainly includes features related to the movement of the gluteus medius. Feature E3 is extracted from the 64-65% gait phase section of the gait waveform data related to the time series data of angular velocity in the coronal plane (around the Y-axis). The walking phase 64-65% is included in the early swing phase T5. The feature amount E3 mainly includes features related to the movement of the adductor longus and sartorius. The feature amount E4 is extracted from the section of the walking phase 11-16% of the walking waveform data related to the time series data of the angular velocity in the horizontal plane (around the Z axis). The walking phase 11-16% is included in the mid-stance phase T2. The feature amount E4 mainly includes features related to the movement of the gluteus medius. The feature amount E5 is extracted from the section of the walking phase 57-58% of the walking waveform data related to the time series data of the angular velocity in the horizontal plane (around the Z axis). The walking phase 57-58% is included in the early swing phase T4. The feature amount E5 mainly includes features related to the movement of the adductor longus and sartorius. The feature amount E6 is extracted from the section of the walking phase 100% of the walking waveform data related to the time series data of the angle (posture angle) in the horizontal plane (around the Z axis). The 100% walking phase corresponds to the timing of heel contact when switching from the final swing phase T7 to the initial stance phase T1. The feature value of the walking waveform data in the 100% walking phase corresponds to the foot angle when the sole of the foot is in contact with the ground. Feature value E6 mainly includes features related to the movement of the gluteus medius. Feature value E7 is the distance between the axis of motion and the foot (circumflex over). Feature value E7 is the amount of circular motion normalized by the subject's height. Feature value E7 mainly includes features related to the movement of the abductor and adductor muscles.

8 is a conceptual diagram showing an example of a physical ability estimation model 150 that estimates physical ability. The feature values extracted from the walking waveform data are input to the physical ability estimation model 150 that estimates physical ability. In addition to the feature value data extracted from the walking waveform data, the attributes of the subject are input. In FIG. 8, the attributes input to the physical ability estimation model 150 are omitted. In response to the input of the physical ability feature values extracted from the walking waveform data, the physical ability estimation model 150 outputs a physical ability score related to the physical ability. In the example of FIG. 8, the physical ability estimation model 150 includes a grip strength estimation model 151, a dynamic balance estimation model 152, a lower limb muscle strength estimation model 153, a mobility estimation model 154, and a static balance estimation model 155. Each of the grip strength estimation model 151, the dynamic balance estimation model 152, the lower limb muscle strength estimation model 153, the mobility estimation model 154, and the static balance estimation model 155 outputs a score for each estimation target of the model. The physical ability estimation model 150 may be configured by a single model, not by a model for each physical ability. Also, the physical ability estimation model 150 may be a physical ability value such as grip strength, FR distance, standing and sitting time, TUG time, and one-legged standing time, instead of a physical ability score.

The grip strength estimation model 151 outputs a grip strength score S1 related to grip strength (total muscle strength of the whole body) in response to the input of the feature amounts AM1 to AM4 or the feature amounts AF1 to AF3. For example, the grip strength estimation model 151 may be a model that outputs grip strength in response to the input of the feature amounts AM1 to AM4 or the feature amounts AF1 to AF3. For example, the grip strength estimation model 151 may be a different model for men and women. There are no limitations on the estimation result of the grip strength estimation model 151 as long as an estimation result related to a grip strength index is output in response to the input of a physical ability feature amount for estimating total muscle strength. For example, the grip strength estimation model 151 may be a model that outputs grip strength in response to the input of the feature amounts AM1 to AM4 or the feature amounts AF1 to AF3. For example, the grip strength estimation model 151 may be a model that estimates grip strength using attribute data such as age and height in addition to the feature amounts AM1 to AM4 or the feature amounts AF1 to AF3.

The dynamic balance estimation model 152 outputs a dynamic balance score S2 related to dynamic balance in response to the input of the features B1 to B5. There are no limitations on the estimation results of the dynamic balance estimation model 152, so long as an estimation result related to a dynamic balance index is output in response to the input of the physical ability features for estimating dynamic balance. For example, the dynamic balance estimation model 152 may be a model that outputs the FR distance in response to the input of the features B1 to B5. For example, the dynamic balance estimation model 152 may be a model that estimates dynamic balance using attribute data such as height in addition to the features B1 to B5.

The lower limb muscle strength estimation model 153 outputs a lower limb muscle strength score S3 related to lower limb muscle strength in response to input of the features C1 to C4. There are no limitations on the estimation result of the lower limb muscle strength estimation model 153, so long as an estimation result related to an index of lower limb muscle strength is output in response to input of the physical ability features for estimating lower limb muscle strength. For example, the lower limb muscle strength estimation model 153 may be a model that outputs a lower limb muscle strength score S3 related to lower limb muscle strength in response to input of the features C1 to C4. For example, the lower limb muscle strength estimation model 153 may be a model that estimates dynamic balance using attribute data such as age in addition to the features C1 to C4.

The mobility estimation model 154 outputs a mobility score S4 related to mobility in response to the input of the features D1 to D6. There are no limitations on the estimation results of the mobility estimation model 154, so long as an estimation result related to a mobility index is output in response to the input of the physical ability features for estimating mobility. For example, the mobility estimation model 154 may be a model that outputs the TUG required time in response to the input of the features D1 to D6. For example, the mobility estimation model 154 may be a model that estimates mobility using attribute data such as age in addition to the features D1 to D6.

The static balance estimation model 155 outputs a static balance score S5 related to static balance in response to the input of the features E1 to E7. There are no limitations on the estimation results of the static balance estimation model 155, so long as an estimation result related to a static balance index is output in response to the input of the physical ability features for estimating static balance. For example, the static balance estimation model 155 may be a model that outputs one-leg standing time in response to the input of the features E1 to E7. For example, the static balance estimation model 155 may be a model that estimates static balance using attribute data such as age and height in addition to the features E1 to E7.

The physical ability estimation model 150 may be stored in an external storage device constructed in a cloud or a server. In this case, the physical ability estimation unit 125 uses the physical ability estimation model 150 via an interface (not shown) connected to the storage device. The physical ability estimation model 150 is a machine learning model. For example, the physical ability estimation model 150 is a model trained on a data set using the attributes and gait indices of multiple subjects as explanatory variables and the physical ability score as the objective variable as teacher data. The physical ability estimation model 150 may be a model trained on a data set using the attributes and gait waveform data of multiple subjects as explanatory variables and the physical ability score as the objective variable as teacher data. For example, the physical ability estimation model 150 may be a model trained on teacher data including gait waveform data of acceleration in three axial directions, angular velocity around three axes, and angle (posture angle) around three axes as explanatory variables.

For example, the physical ability estimation model 150 may be generated by learning using a linear regression algorithm. For example, the physical ability estimation model 150 may be generated by learning using a support vector machine (SVM) algorithm. For example, the physical ability estimation model 150 may be generated by learning using a Gaussian process regression (GPR) algorithm. For example, the physical ability estimation model 150 may be generated by learning using a random forest (RF) algorithm. For example, the physical ability estimation model 150 may be generated by unsupervised learning that classifies the physical ability of a subject according to physical ability features. There are no particular limitations on the algorithm used to train the physical ability estimation model 150.

The disease risk estimation unit 126 (disease risk estimation means) acquires the estimation result of the physical ability (physical ability score) estimated by the physical ability estimation unit 125. The disease risk estimation unit 126 also acquires the gait index from the gait index calculation unit 123. Furthermore, the disease risk estimation unit 126 acquires the attribute data of the subject from the storage unit 124. The disease risk estimation unit 126 estimates the disease risk for each disease using the physical ability score, the gait index, and the attribute data. The disease risk estimation unit 126 may be configured to estimate the disease risk for each disease including the health check data. For example, the disease risk estimation unit 126 may be configured to estimate the disease risk for each disease using at least the gait index. The disease risk estimation unit 126 associates the estimated disease risk for each disease with the subject and stores it in the storage unit 124. The disease risk for each disease of the subject may be accumulated in a dedicated database (not shown).

9 is a conceptual diagram showing an example of disease risk estimation by the disease risk estimation unit 126. The disease risk estimation unit 126 inputs attribute data, gait index, and physical ability score used to estimate the disease risk for a specific disease to the disease risk estimation model 160. The disease risk estimation model 160 receives the attribute data, gait index, and physical ability score used to estimate the disease risk for a specific disease. In response to the input of the attribute data, gait index, and physical ability score, the disease risk estimation model 160 outputs a disease risk score for a specific disease. In the example of FIG. 9, a disease risk score is estimated for each of a plurality of diseases. The disease risk estimation model 160 may be configured as a model for each disease, or as a single model. When a physical ability score is not used, the disease risk estimation model 160 may be configured to output a disease risk score for a specific disease in response to the input of the attribute data and gait index.

For example, the disease risk estimation model 160 outputs a disease risk score for a specific disease such as a lifestyle-related disease. For example, the disease risk estimation model 160 outputs a disease risk score for a specific disease such as gout, diabetes, hypertension, nephrolithiasis, liver cirrhosis, arteriosclerosis, thromboembolism, dyslipidemia, hypercholesterolemia, and hyperlipidemia. For example, the disease risk estimation model 160 includes lower back pain, sleep apnea syndrome, insomnia, depression, osteoarthritis of the knee, and Parkinson's syndrome. The disease risk estimation model 160 may be configured to output a disease risk score for diseases other than those mentioned above.

As the amount of data used for estimation increases, the accuracy of the disease risk score estimation by the disease risk estimation model 160 improves. For example, the disease risk estimation model 160 is configured to output a disease risk score for a specific disease in response to inputs of health check data, attribute data, gait index, and physical ability score. When attribute data is included in the health check data items, the disease risk estimation model 160 may be configured to output a disease risk score for a specific disease in response to inputs of health check data, gait index, and physical ability score.

The disease risk estimation model 160 may be stored in an external storage device (not shown) constructed in a cloud or a server. In this case, the disease risk estimation unit 126 uses the disease risk estimation model 160 via an interface (not shown) connected to the storage device. The disease risk estimation model 160 is a machine learning model. For example, the disease risk estimation model 160 is a model trained using a data set in which attribute data, gait index, and physical ability score for multiple subjects are used as explanatory variables, and a disease risk score for a specific disease is used as a target variable as training data. For example, the disease risk estimation model 160 may be a model trained using training data in which gait waveform data of acceleration in three axial directions, angular velocity around three axes, and angle (posture angle) around three axes are included as explanatory variables.

For example, the disease risk estimation model 160 is generated by learning using a linear regression algorithm. For example, the disease risk estimation model 160 is generated by learning using a support vector machine (SVM) algorithm. For example, the disease risk estimation model 160 is generated by learning using a Gaussian process regression (GPR) algorithm. For example, the disease risk estimation model 160 is generated by learning using a random forest (RF) algorithm. For example, the disease risk estimation model 160 may be generated by unsupervised learning that classifies the disease risk of a subject according to attribute data, gait index, and physical ability score. There are no particular limitations on the algorithm used to train the disease risk estimation model 160.

For example, the disease risk estimation model 160 may be a machine learning model such as an incomplete heterogeneous variational autoencoder or a random forest. If an incomplete heterogeneous variational autoencoder is used, the disease risk of a subject can be estimated even if there are some missing data in the attribute data, gait index, physical ability score, etc.

10 is a conceptual diagram showing an example of a disease risk estimation model 165 that estimates the annual average number of receipts issued. The disease risk estimation unit 126 inputs attribute data, gait index, and physical ability score to the disease risk estimation model 165. The disease risk estimation model 165 receives attribute data, gait index, and physical ability score used to estimate the disease risk for a specific disease. In response to the input of the attribute data, gait index, and physical ability score, the disease risk estimation model 165 outputs the annual average number of receipts issued for a specific disease. In the example of FIG. 10, the annual average number of receipts issued is estimated for each of a plurality of diseases. The disease risk estimation unit 126 calculates a disease risk score using the annual average number of receipts issued output from the disease risk estimation model 165. The annual average number of receipts issued may be used as the disease risk score.

Here, an example will be described in which the disease risk estimation unit 126 calculates a disease risk score using the average annual number of receipts issued. Three calculation examples will be given below. It is assumed that the average annual number of receipts issued for a standard person μ ₀ has been obtained in advance. The disease risk estimation model 165 outputs the average annual number of receipts issued μ for a specific disease in response to input of attribute data, gait index, and physical ability score for the subject.

In the first method, the disease risk estimation unit 126 calculates, as the disease risk score, the ratio of the average annual number of medical receipts issued for a standard person μ ₀ to the average annual number of medical receipts issued for the subject μ. The disease risk estimation unit 126 calculates the disease risk score RS ₁ using the following formula 1.

第２の手法において、疾病リスク推定部１２６は、特定疾病に関する年平均レセプト発行数がポアソン分布に従うという仮定の下で、疾病リスクスコアを計算する。第２の手法において、疾病リスク推定部１２６は、標準的な人の年平均レセプト発行数の確率質量関数Ｐ₀（Ｘ＝ｋ）と、対象者に関して推定された年平均レセプト発行数の確率質量関数Ｐ（Ｘ＝ｋ）との比を、疾病リスクスコアとして計算する（ｋは自然数）。疾病リスク推定部１２６は、以下の式２を用いて、疾病リスクスコアＲＳ₂を計算する。

In the second method, the disease risk estimation unit 126 calculates the disease risk score under the assumption that the annual average number of receipts issued for a specific disease follows a Poisson distribution. In the second method, the disease risk estimation unit 126 calculates the disease risk score as the ratio of the probability mass function _P0 (X=k) of the annual average number of receipts issued for a standard person to the probability mass function P(X=k) of the annual average number of receipts issued estimated for the subject (k is a natural number). The disease risk estimation unit 126 calculates the disease risk score _RS2 using the following formula 2.

第３の手法において、疾病リスク推定部１２６は、特定疾病に関する年平均レセプト発行数のオッズ比を計算する。疾病リスク推定部１２６は、以下の式３を用いて、疾病リスクスコアＲＳ₃を計算する。

In the third method, the disease risk estimation unit 126 calculates the odds ratio of the annual average number of receipts issued for a specific disease. The disease risk estimation unit 126 calculates a disease risk score _RS3 using the following formula 3.

なお、上記の３通りの計算例は、一例であって、年平均レセプト発行数を用いた疾病リスクスコアの計算方法を限定するものではない。疾病リスク推定部１２６は、年平均レセプト発行数以外の指標を用いて、疾病リスクスコアを計算するように構成されてもよい。

The above three calculation examples are merely examples, and do not limit the method of calculating the disease risk score using the annual average number of medical receipts issued. The disease risk estimation unit 126 may be configured to calculate the disease risk score using an index other than the annual average number of medical receipts issued.

The credit-related information generation unit 127 acquires the disease risk score and status information of the subject. The credit-related information generation unit 127 adjusts the penalty coefficients of the credit score for the identity information, credit history information, contract fulfillment information, human relationship information, and behavioral characteristic information included in the status information according to the disease risk score and status information of the subject. The credit-related information generation unit 127 adjusts the penalty coefficients of the credit score for each of the identity information, credit history information, contract fulfillment information, human relationship information, and behavioral characteristic information according to preset standards. The penalty coefficients are adjusted within the range of 0 to 1. A weight is set for each of the identity information, credit history information, contract fulfillment information, human relationship information, and behavioral characteristic information. The sum of the weights for each of the identity information, credit history information, contract fulfillment information, human relationship information, and behavioral characteristic information is set to 1. The credit-related information generation unit 127 calculates the credit score as the sum of the products of the penalty coefficients and weights for each of the identification information, credit history information, contract enforcement ability information, human relationship information, and behavioral characteristic information.

FIG. 11 is a conceptual diagram for explaining an example of calculation of the credit score CS by the credit-related information generating unit 127. The status information IS includes identity verification information IS ₁ , credit history information IS ₂ , contract performance information IS ₃ , human relationship information IS ₄ , and behavioral characteristic information IS _5. The identity verification information IS ₁ includes information that guarantees that the subject's name is a real name and information that indicates the stability of the subject's status. The credit history information IS ₂ includes card repayment history information, loan repayment history information, tax payment history information, insurance premium payment history information, pension payment history information, and penalty payment history information. The contract performance information IS ₃ includes fixed asset information, deposit and savings information, and income information. The human relationship information IS ₄ includes personal connections information and social influence information. The behavioral characteristic information IS ₅ includes consumption behavior information, travel behavior information, and health behavior information. The credit score of the identity verification information IS ₁ is cs ₁ . The credit score of the credit history information IS ₂ is cs _2. The credit score of the contract performance information IS ₃ is cs _3. The credit score of the human relationship information IS ₄ is cs _4. The credit score of the behavioral characteristic information IS ₅ is cs ₅ .

In the example of FIG. 11, the weight of the identification information _IS1 is 0.15. The weight of the credit history information _IS2 is 0.35. The weight of the contract fulfillment ability information _IS3 is 0.20. The weight of the human relationship information _IS4 is 0.05. The weight of the behavioral characteristic information _IS5 is 0.25. Note that the weights of the identification information _IS1 , credit history information _IS2 , contract fulfillment ability information _IS3 , human relationship information _IS4 , and behavioral characteristic information _IS5 are merely examples and are not intended to limit the values.

In addition, a penalty coefficient p is set for each of the identification information _IS1 , credit history information _IS2 , contract fulfilment ability information _IS3 , human relationship information _IS4 , and behavioral characteristic information _IS5 according to the status information IS and disease risk score RS. The penalty coefficient for the identification information _IS1 is _p1 . The penalty coefficient for the credit history information _IS2 is _p2 . The penalty coefficient for the contract fulfilment ability information _IS3 is _p3 . The penalty coefficient for the human relationship information _IS4 is _p4 . The penalty coefficient for the behavioral characteristic information _IS5 is _p5 .

The sum of the credit scores relating to the identification information IS ₁ , the credit history information IS ₂ , the contract fulfilment ability information IS ₃ , the human relationship information IS ₄ , and the behavioral characteristic information IS ₅ corresponds to the credit score CS. For example, the credit-related information generating unit 127 calculates the credit score CS using the following formula 4.

　与信関連情報生成部１２７は、信用スコア推定モデルを用いて、対象者の信用スコアを推定してもよい。信用スコア推定モデルは、疾病リスクスコアおよびステータス情報の入力に応じて、信用スコアを出力する。信用スコア推定モデルは、複数の被験者のデータを用いて学習されたモデルである。例えば、信用スコア推定モデルは、記憶部１２４に記憶させておく。

The credit-related information generating unit 127 may estimate the credit score of the subject using a credit score estimation model. The credit score estimation model outputs a credit score in response to input of a disease risk score and status information. The credit score estimation model is a model trained using data of multiple subjects. For example, the credit score estimation model is stored in the memory unit 124.

Fig. 12 is a conceptual diagram showing an example of a credit score estimation model (credit score estimation model 170). Fig. 12 is an example in which the credit score estimation model 170 includes a neural network. The credit score estimation model 170 includes an input layer, a first hidden layer, a second hidden layer, and an output layer. The input layer includes a plurality of nodes I. The first hidden layer includes a plurality of nodes _H1 . The second hidden layer includes a plurality of nodes _H2 . The output layer includes a plurality of nodes O. The credit score estimation model 170 may include an hidden layer other than the first hidden layer and the second hidden layer.

The status information IS and the disease risk score RS are input to the input layer. The input layer includes nodes _I1 , _I2 , _I3 , _I4 , _I5 , and _IRS . The identity information _IS1 is input to the node _I1 . The information included in the identity information _IS1 is distributed to a plurality of nodes ( _H11 , ..., _H1a ) included in the first intermediate layer subsequent to the node _I1 (a is a natural number). The credit history information _IS2 is input to the node I2. The information included in the credit history _{information IS2} is distributed to a plurality of nodes ( _H21 , ..., _H2b ) included in the first intermediate layer subsequent to the node _I2 (b is a natural number). The contract performance information _IS3 is input to the node _I3 . The information included in the contract fulfillment ability information _IS3 is distributed to a plurality of nodes ( _H31 , ..., _H3c ) included in the first hidden layer behind node _I3 (c is a natural number). Human relationship information _IS4 is input to node _I4 . The information included in the human relationship information _IS4 is distributed to a plurality of nodes ( _H41 , ..., _H4d ) included in the first hidden layer behind node _I4 (d is a natural number). Behavioral characteristic information IS5 is input to node _I5 . The information included in the behavioral characteristic information _IS5 is distributed to a plurality of nodes ( _H51 , ... _{, H5e} ) included in the first hidden layer behind node _I5 (e is a natural number).

In addition, a disease risk score RS is input to node I _RS . The disease risk score RS is distributed to a plurality of nodes included in the first intermediate layer behind node I _RS . In this embodiment, among the status information IS, credit history information IS ₂ , contract performance information IS ₃ , human relationship information IS ₄ , and behavioral characteristic information IS ₅ are affected by the disease risk of the subject. Therefore, the disease risk score RS is distributed to nodes H ₂ , H ₃ , H ₄ , and H ₅ to which credit history information IS ₂ , contract performance information IS ₃ , human relationship information IS ₄ , and behavioral characteristic information IS ₅ are input, respectively.

The information included in the identification information IS ₁ is distributed to each of the nodes H ₁₁ to H _1a included in the first hidden layer. Each of the nodes H ₁₁ to H _1a outputs a penalty coefficient p ₁₁ to p _1a for the distributed information. The sum of the penalty coefficients p ₁₁ to p _1a is equal to or greater than 0 and equal to or less than 1. The penalty coefficients p ₁₁ to p _1a are input to the node H ₂₁ included in the second hidden layer. The node H ₂₁ calculates the sum of the input penalty coefficients p ₁₁ to p _1a . The node H ₂₁ calculates the credit score cs ₁ by multiplying the calculated sum of the penalty coefficients p ₁₁ to p _1a by a weight of 0.15. The node H ₂₁ outputs the calculated credit score cs ₁ to the node O ₁ included in the output layer. The node O ₁ outputs the credit score cs ₁ .

The information included in the credit history information _IS2 is distributed to each of the nodes _H21 to _H2b included in the first hidden layer. In addition, a disease risk score RS is input to each of the nodes _H21 to _H2b . The disease risk score RS may be input only to the nodes affected by the disease risk. Each of the nodes _H21 to _H2b outputs a penalty coefficient _p21 to _p2b according to the distributed information and the input of the disease risk score. The sum of the penalty coefficient _p21 to _p2b is 0 to 1. The penalty coefficient _p21 to _p2b are input to the node _H22 included in the second hidden layer. The node _H22 calculates the sum of the input penalty coefficient _p21 to _p2b . The node _H22 calculates the credit score _cs2 by multiplying the calculated sum of the penalty coefficient _p21 to _p2b by a weight of 0.35. Node _H22 outputs the calculated credit score _cs2 to node _O2 included in the output layer. Node _O2 outputs the credit score _cs2 .

The information included in the contract performance information _IS3 is distributed to each of the nodes _H31 to _H3c included in the first intermediate layer. In addition, a disease risk score RS is input to each of the nodes _H31 to _H3c . The disease risk score RS may be input only to the nodes affected by the disease risk. Each of the nodes _H31 to _H3c outputs a penalty coefficient _p31 to _p3c according to the distributed information and the input of the disease risk score. The sum of the penalty coefficient _p31 to _p3c is 0 to 1. The penalty coefficient _p31 to _p3c are input to the node _H23 included in the second intermediate layer. The node _H23 calculates the sum of the input penalty coefficient _p31 to _{p3c. The node H23 calculates the credit score cs3 by multiplying the calculated sum of the penalty coefficient p31 to p3c by a weight of} 0.20. The node _H23 outputs the calculated credit score _cs3 to a node _O3 included in the output layer. The node _O3 outputs the credit score _cs3 .

The information included in the human relationship information _IS4 is distributed to each of the nodes _H41 to _H4d included in the first intermediate layer. In addition, a disease risk score RS is input to each of the nodes _H41 to _H4d . The disease risk score RS may be input only to the nodes affected by the disease risk. Each of the nodes _H41 to _H4d outputs a penalty coefficient _p41 to _p4d according to the input of the distributed information and the disease risk score. The sum of the penalty coefficient _p41 to _p4d is 0 to 1. The penalty coefficient _p41 to _p4d are input to the node _H24 included in the second intermediate layer. The node _H24 calculates the sum of the input penalty coefficient _p41 to _{p4d. The node H24 calculates the credit score cs4 by multiplying the calculated sum of the penalty coefficient p41 to p4d by a weight of} 0.05. The node _H24 outputs the calculated credit score _cs4 to a node _O5 included in the output layer. The node _O5 outputs the credit score _cs4 .

The information included in the behavioral characteristic information _IS5 is distributed to each of the nodes _H51 to _H5e included in the first hidden layer. In addition, a disease risk score RS is input to each of the nodes _H51 to _H5e . The disease risk score RS may be input only to the nodes affected by the disease risk. Each of the nodes _H51 to _H5e outputs a penalty coefficient _p51 to _p5e according to the distributed information and the input of the disease risk score. The sum of the penalty coefficient _p51 to _p5e is 0 to 1. The penalty coefficient _p51 to _p5e are input to the node _H25 included in the second hidden layer. The node _H25 calculates the sum of the input penalty coefficient _p51 to _p5e . The node _H25 calculates the credit score _cs5 by multiplying the calculated sum of the penalty coefficient _p51 to _p5e by a weight of 0.25. The node _H25 outputs the calculated credit score _cs5 to a node _O5 included in the output layer. The node _O5 outputs the credit score _cs5 .

In the example of FIG. 12, the credit-related information generation unit 127 calculates the sum of all credit scores ( _cs1 , _cs2 , _cs3 , _cs4 , _cs5 ) output from the credit score estimation model 170. The sum of credit scores _cs1 , _cs2 , _cs3 , _cs4 , and cs5 corresponds to the credit score CS. The credit score CS is a numerical value between 0 and _1. The higher the creditworthiness of the subject, the higher the credit score CS. The lower the creditworthiness of the subject, the lower the credit score CS. The credit-related information generation unit 127 generates credit-related information including the value of the credit score CS.

The credit score estimation model 170 may be stored in an external storage device (not shown) constructed on a cloud or a server, etc. In this case, the credit-related information generation unit 127 uses the credit score estimation model 170 via an interface (not shown) connected to the storage device. The credit score estimation model 170 is a machine learning model. For example, the credit score estimation model 170 is a model trained on a data set using as training data a data set in which status information and disease risk scores relating to multiple subjects are explanatory variables and the credit score is the objective variable.

For example, the credit score estimation model 170 is generated by learning using a linear regression algorithm. For example, the credit score estimation model 170 is generated by learning using a support vector machine (SVM) algorithm. For example, the credit score estimation model 170 is generated by learning using a Gaussian process regression (GPR) algorithm. For example, the credit score estimation model 170 is generated by learning using a random forest (RF) algorithm. For example, the credit score estimation model 170 may be generated by unsupervised learning that classifies the subject's credit-related tendencies according to input status information and disease risk score. There are no particular limitations on the algorithm used to train the credit score estimation model 170.

For example, the credit score estimation model 170 may be a machine learning model such as an incomplete heterogeneous variational autoencoder or a random forest. If an incomplete heterogeneous variational autoencoder is used, the subject's credit score can be estimated even if there is some loss in the status information, gait index, physical ability score, etc.

For example, the credit-related information generating unit 127 generates credit-related information including a determination result indicating whether or not a loan can be provided to the target person, depending on the value of the credit score CS. In this case, if the credit score CS exceeds a preset threshold, the credit-related information generating unit 127 determines that a loan can be provided to the target person. On the other hand, if the credit score CS falls below the preset threshold, the credit-related information generating unit 127 determines that a loan cannot be provided to the target person.

For example, the credit-related information generating unit 127 calculates preferential treatment in loans to the target person depending on the difference between the credit score CS and a preset threshold. In this case, the more the credit score CS exceeds the preset threshold and the greater the difference between the credit score CS and the threshold, the greater the degree of preferential treatment the credit-related information generating unit 127 will give to the target person. On the other hand, if the credit score CS exceeds the preset threshold but the difference between the credit score CS and the threshold becomes smaller, the credit-related information generating unit 127 will reduce the degree of preferential treatment the target person will receive.

For example, the credit-related information generating unit 127 calculates preferential treatment in loans to the subject depending on changes in the credit score over time. In this case, if the credit score CS exceeds a preset threshold and there is a tendency for the credit score CS to increase over time, the credit-related information generating unit 127 increases the degree of preferential treatment for the subject. On the other hand, if the credit score CS exceeds the preset threshold but there is a tendency for the credit score CS to decrease over time, the credit-related information generating unit 127 decreases the degree of preferential treatment for the subject.

The output unit 129 (output means) outputs credit-related information including the credit score estimated by the credit-related information generation unit 127. For example, the output unit 129 outputs the credit-related information to a terminal device or server managed by a financial institution with which the subject is going to enter into a contract. For example, the output unit 129 outputs the credit-related information to a terminal device or server managed by a credit investigation company commissioned by the financial institution with which the subject is going to enter into a contract. For example, the output unit 129 may display the credit-related information on the screen of the subject's mobile terminal. For example, the output unit 129 may output the credit-related information to an external system or the like that uses the credit-related information. Since the credit-related information includes personal information, the output destination is limited.

For example, the information providing device 12 is connected to an external system built on a cloud or a server via a mobile terminal (not shown) carried by the subject. The mobile terminal is a portable communication device. For example, the mobile terminal is a portable communication device having a communication function such as a smartphone, a smart watch, or a mobile phone. For example, the information providing device 12 is connected to the mobile terminal via wireless communication. For example, the information providing device 12 is connected to the mobile terminal via a wireless communication function (not shown) conforming to a standard such as Bluetooth (registered trademark) or WiFi (registered trademark). Note that the communication function of the information providing device 12 may conform to a standard other than Bluetooth (registered trademark) or WiFi (registered trademark). For example, the information providing device 12 may be connected to the mobile terminal via a wire such as a cable. The credit-related information may be used by an application installed on the mobile terminal. For example, the mobile terminal executes a process using the credit-related information by application software installed on the mobile terminal.

(Operation)
Next, the operation of the information providing system 1 will be described with reference to the drawings. The operation of the information providing device 12 included in the information providing system 1 will be described below. Fig. 13 is a flowchart for explaining an example of the operation of the information providing device 12. In the explanation of the process according to the flowchart of Fig. 13, the components of the information providing device 12 will be described as the subject of the operation. The subject of the process according to the flowchart of Fig. 13 may be the information providing device 12.

In FIG. 13, first, the acquisition unit 121 acquires time series data of sensor data measured by the measurement device 10 mounted on the subject's footwear (step S11). The sensor data includes acceleration in three axial directions and angular velocity around three axes.

Next, the calculation unit 13 executes a gait index calculation process using the acquired sensor data (step S12). In the gait index calculation process, the calculation unit 13 calculates a gait index used to estimate physical ability. Details of the gait index calculation process in step S12 will be described later ( FIG. 14 ).

Next, the physical ability estimation unit 125 estimates physical ability using the attribute data and gait index (step S13). For example, the physical ability estimation unit 125 estimates physical ability scores such as grip strength (total muscle strength of the entire body), dynamic balance, lower limb muscle strength, mobility, and static balance. If disease risk is estimated without using physical ability, step S13 can be omitted.

Next, the disease risk estimation unit 126 estimates the disease risk of the subject using the attribute data, gait index, and physical ability (step S14). When the disease risk is estimated without using the physical ability, the disease risk estimation unit 126 estimates the disease risk of the subject using the attribute data and gait index. The disease risk estimation unit 126 estimates the disease risk score of the subject. For example, the disease risk estimation unit 126 estimates the disease risk score for each disease, such as gout, diabetes, hypertension, nephrolithiasis, liver cirrhosis, arteriosclerosis, thromboembolism, dyslipidemia, hypercholesterolemia, and hyperlipidemia. For example, the disease risk estimation unit 126 estimates the disease risk score for each disease, such as lower back pain, sleep apnea syndrome, insomnia, depression, osteoarthritis of the knee, and Parkinson's syndrome.

Next, the credit-related information generating unit 127 calculates a credit score for the subject using the estimated disease risk (step S15). The credit-related information generating unit 127 generates credit-related information including the calculated credit score.

Next, the output unit 129 outputs the credit-related information including the generated credit score (step S16). For example, the output unit 129 outputs the credit-related information to a terminal device or server managed by the financial institution with which the subject is going to enter into a contract. For example, the output unit 129 outputs the credit-related information to an external system or the like that uses the credit-related information. For example, the output unit 129 may display the credit-related information on the screen of the subject's mobile terminal.

[Gait index calculation process]
Next, the gait index calculation process (step S12 in FIG. 13 ) by the calculation unit 13 of the information providing device 12 will be described with reference to the drawings. FIG. 14 is a flowchart for explaining an example of the operation of the calculation unit 13. In explaining the process according to the flowchart in FIG. 14 , the components of the calculation unit 13 will be described as the subject of the operation. The subject of the operation of the process according to the flowchart in FIG. 14 may be the information providing device 12 or the calculation unit 13.

In FIG. 14, first, the waveform processing unit 122 extracts walking waveform data from the time series data of the sensor data (step S121). The walking waveform data corresponds to the time series data of the sensor data for one walking cycle.

Next, the waveform processing unit 122 normalizes the extracted walking waveform data (step S122). The waveform processing unit 122 performs first normalization on the walking waveform data so that the step period is 100%. The waveform processing unit 122 also performs second normalization on the walking waveform data so that the stance phase is 60% and the swing phase is 40%.

Next, the gait index calculation unit 123 uses the normalized walking waveform data to calculate gait indices used to estimate physical ability (step S123). For example, the gait index calculation unit 123 calculates gait indices related to distance, height, angle, speed, time, frailty level, CPEI, etc.

(Examples of application)
Next, an application example according to the present embodiment will be described with reference to the drawings. In this application example, the relationship between a business operator, a financial institution, a credit investigation company, a financial institution, and a target is shown. FIG. 15 is a correlation diagram showing the relationship between a business operator, a financial institution, a credit investigation company, and a target in this disclosure. The business operator is a business entity that provides a service using the information provision system 1. The financial institution is an institution that provides financial services according to a contract. The financial institution uses a service using the information provision system 1. The credit investigation company is an organization that creates credit information of the target under commission from the financial institution. In this application example, the credit investigation company also uses a service using the information provision system 1. The target is an entity that is about to enter into a contract with the financial institution. In this application example, an example in which the target is an individual is given. The target may be a corporation.

Below, an example is given in which the credit-related information estimation model is used to estimate credit-related information. Credit-related information is used to create credit information used by financial institutions. For example, the credit-related information estimation model is optimized according to the industry of the financial institution. For example, financial institutions include industries such as banks, securities companies, insurance companies, and credit card companies. The credit-related information generated by the information providing device 12 is not limited to the following example, so long as it includes the credit-related information of the subject.

The business provides a service using the information provision system 1 to a financial institution or a credit investigation company. Based on a contract concluded with the financial institution or the credit investigation company, the business provides the financial institution or the credit investigation company with credit-related information corresponding to the disease risk of the subject. The credit-related information includes a credit score estimated according to the disease risk of the subject. The financial institution pays the business a fee for the service using the information provision system 1. If the subject's health check-up data is used to estimate the credit score, the financial institution obtains the health check-up data from the subject. The financial institution provides the business with the obtained health check-up data of the subject. In the contract between the financial institution or credit investigation company and the business, rules regarding the handling of personal information and appropriate data management are clarified. The business clearly explains that the credit-related information is for reference only and does not guarantee medical accuracy or completeness.

The financial institution is an institution with which the subject is about to enter into a contract. The financial institution fully explains the personal information protection policy and the contents of data management to the subject, and then obtains the subject's consent to the use of personal information and data. Furthermore, if there are any changes to the personal information protection policy or the contents of data management, the financial institution explains the changes to the subject and obtains the subject's consent. For example, the subject's consent is obtained electronically. The financial institution enters into a contract with the business operator regarding the use of services using the information provision system 1. The financial institution pays the business operator a fee for using the information provision system 1. The financial institution receives credit-related information on the subject from the business operator. The financial institution creates credit information on the subject according to the content of the credit-related information provided by the business operator. The financial institution refers to the content of the created credit information and considers loans, etc. to the subject. If the creation of credit information is entrusted to a credit investigation company, the financial institution does not need to be provided with credit-related information.

　A credit investigation company is commissioned to create credit information and provides a service of conducting a credit investigation of the subject. In response to a commission from a financial institution, the credit investigation company handles personal information and data related to the subject. The credit investigation company obtains consent from the subject regarding the use of the personal information and data through the financial institution. The credit investigation company may obtain consent directly from the subject regarding the use of the personal information and data. For example, consent from the subject is obtained electronically. The credit investigation company enters into a contract with the business operator regarding the use of a service using the information provision system 1. The credit investigation company pays the business operator a fee for using the information provision system 1. The credit investigation company is provided with credit-related information of the subject from the business operator. The credit investigation company may obtain the credit-related information via the financial institution. The credit investigation company creates credit information of the subject by referring to the content of the credit-related information provided by the business operator. The credit investigation company provides the created credit information to the financial institution.

The subject is an entity that is about to enter into a contract with a financial institution. The subject is loaned or provided with a special insole equipped with the measuring device 10 by a business that has a contract with the financial institution. The subject wears shoes equipped with the special insole and carries a mobile terminal (not shown) capable of communicating with the measuring device 10 while performing work. The mobile terminal uploads sensor data measured by the measuring device 10 to the business's cloud server. The sensor data uploaded to the cloud server is used to estimate disease risk and credit score. The sensor data measured as the subject walks is used to estimate the subject's credit score. The subject is provided with financial products and preferential interest rate loans depending on the credit score.

Terminal devices (not shown) used by financial institutions and credit bureaus download credit-related information, including credit scores, from the operator's cloud server. Administrators at the financial institutions and credit bureaus refer to the credit-related information to create credit information on the subject. Financial institutions refer to the created credit information when considering loans, etc., to the subject. For example, administrators at financial institutions may periodically refer to the credit-related information to consider countermeasures in response to changes in credit practice information.

FIG. 16 shows an example in which credit-related information for Person A, generated by the information providing device 12, is displayed on the screen of a terminal device 180 used by a financial institution with which the subject is about to enter into a contract. The screen of the terminal device 180 displays credit-related information including a credit score CS optimized for the financial institution. In the example of FIG. 16, credit-related information including a credit score for each status information is displayed on the screen of the terminal device 180.

The screen of the terminal device 180 displays the value of the credit score CS. The value of the credit score CS displayed on the screen of the terminal device 180 is 0.73. The screen of the terminal device 180 also displays the credit score for each information status. The credit score cs ₁ of the identification information IS ₁ is 0.15. The credit score cs ₂ of the credit history information IS ₂ is 0.25. The credit score cs ₃ of the contract performance information IS 3 is 0.10. The credit score cs ₄ of the human relationship information IS ₄ is 0.03. The credit score _{cs 5 of} the behavioral characteristic information IS ₅ is 0.20. Furthermore, the screen of the terminal device 180 displays credit-related information according to the value of the credit score CS. The screen of the terminal device 180 displays credit-related information indicating whether or not a loan can be granted according to the credit score, such as "The credit score exceeds the loanable threshold (0.6 or more) so a loan is available." Furthermore, the screen of the terminal device 180 displays credit-related information regarding the loan amount according to the credit score, such as "The loan limit according to the credit score is XXX million yen." A loan officer at the financial institution can refer to the credit-related information displayed on the screen of the terminal device 180 and consider loaning to the target person.

As described above, the information provision system of this embodiment includes a measuring device and an information provision device. The measuring device is installed on the subject's footwear. The measuring device measures acceleration and angular velocity. The measuring device generates sensor data using the measured acceleration and angular velocity. The measuring device transmits the generated sensor data to the information provision device. The information provision device includes an acquisition unit, a risk estimation unit, a credit-related information generation unit, and an output unit. The acquisition unit acquires sensor data including acceleration and angular velocity measured by a measuring device mounted on the footwear of the subject for whom credit information is to be created. The risk estimation unit estimates a disease risk for each disease related to the subject using the acquired sensor data. The credit-related information generation unit generates credit-related information according to the estimated disease risk related to the subject and pre-registered status information of the subject. The output unit outputs the generated credit-related information.

The information providing device of this embodiment estimates disease risk using sensor data measured by a measuring device mounted on the footwear of the subject for whom credit information is to be created. The information providing device of this embodiment generates credit-related information according to the disease risk and status information related to the subject. Therefore, according to this embodiment, it is possible to provide credit-related information according to the subject's physical and mental condition.

In one aspect of this embodiment, the risk estimation unit has a calculation unit and an estimation unit. The calculation unit calculates a gait index using sensor data. The estimation unit inputs data including the gait index calculated using the sensor data to a disease risk estimation model that outputs a disease risk score indicating the degree of disease risk for each disease in response to input of data including the gait index. The estimation unit estimates disease risk information corresponding to the disease risk score output from the disease risk estimation model. According to this aspect, disease risk information corresponding to the disease risk score can be estimated by inputting data including the gait index calculated using sensor data to the disease risk estimation model.

In one aspect of this embodiment, the credit-related information generation unit estimates a credit score for each of the identity, credit history, contract fulfilment, interpersonal relationships, and behavioral characteristics included in the status information. The credit-related information generation unit generates credit-related information including a credit score for each of the estimated identity, credit history, contract fulfilment, interpersonal relationships, and behavioral characteristics. According to this aspect, it is possible to provide credit-related information including a credit score for each of the identity, credit history, contract fulfilment, interpersonal relationships, and behavioral characteristics included in the status information.

In one aspect of this embodiment, the credit-related information generation unit calculates the sum of values obtained by multiplying the weights for each of the identification, credit history, ability to fulfill contracts, human relationships, and behavioral characteristics by a penalty coefficient as the credit score for the subject. The penalty coefficient is a coefficient that depends on at least one of the status information and the disease risk score. According to this aspect, it is possible to calculate a credit score whose value is adjusted according to the status information or the disease risk score.

In one aspect of this embodiment, the credit-related information generation unit uses a credit score estimation model to estimate a credit score for each of identification, credit history, contract enforcement ability, interpersonal relationships, and behavioral characteristics. The credit score estimation model outputs a credit score in response to input of a disease risk score and status information. According to this aspect, a credit score can be calculated in response to status information or a disease risk score.

In one aspect of this embodiment, the disease risk estimation model and the credit score estimation model are models trained using machine learning techniques. The disease risk estimation model and the credit score estimation model include an incomplete heterogeneous variational autoencoder. According to this aspect, even if there is some loss of data such as gait indicators, the subject's credit-related information can be estimated.

In one aspect of this embodiment, the information providing device displays credit-related information optimized for the financial institution on the screen of a terminal device used by the financial institution that reviews the credit information for the subject. According to this aspect, credit-related information estimated according to the subject's disease risk can be provided in an optimized manner for the financial institution.

In this embodiment, an example is given in which credit-related information including a credit score calculated using the subject's status information and disease risk score is provided. The credit-related information may be updated according to changes in disease risk over time. For example, the credit-related information may be updated according to the trend or amount of change in disease risk in a specific period such as one month, three months, six months, or one year. For example, if the disease risk of a specific disease in a specific period is on the decline, it is estimated that the subject's health condition is improving. In such a case, information indicating that the subject's health condition is improving may be added to the credit-related information. For example, if the disease risk of a specific disease in a specific period is on the increase, it is estimated that the subject's health condition is worsening. In such a case, information indicating that the subject's health condition is worsening may be added to the credit-related information. For example, by accumulating the timing of updates to credit-related information for multiple subjects and applying machine learning to the accumulated update timing, it is possible to estimate the timing of reviewing credit information. Financial institutions and credit investigation companies can review the credit information of a subject in response to updates to the credit-related information of the subject.

In loan screening, factors such as creditworthiness, income, and repayment ability are emphasized. For example, income is affected by health status. Even if your current income is sufficient, if you have health risks, your income may decrease in the future. Also, even if your current income is insufficient, if you have no health risks and good healthy habits, you may be able to earn a sufficient income in the future. Therefore, if future health risks can be estimated, financial institutions can properly screen you for loan provision.

With growing interest in healthcare, attention is being focused on services that provide information based on gait. Gait can be analyzed using sensor data measured by sensors mounted on footwear such as shoes, as in this embodiment. Time-series data of sensor data contains characteristics associated with walking events related to physical conditions. If the subject's future disease risk can be estimated based on the characteristics associated with walking events, as in this embodiment, useful information can be provided for loan screening.

In addition, even if a person's current income is sufficient, if they have health risks, their income may decrease in the future. On the other hand, even if their current income is insufficient, if they have no health risks and have good healthy habits, they may be able to earn a sufficient income in the future. According to this embodiment, credit-related information that reflects future health risks is provided, allowing financial institutions to appropriately review the provision of loans.

Second Embodiment
Next, an information provision system according to a second embodiment will be described with reference to the drawings. The information provision system according to this embodiment estimates the personality of a subject using a personality estimation model. Credit-related information including information on the estimated personality of the subject is provided to financial institutions and the like.

(composition)
17 is a block diagram showing an example of the configuration of the information providing system 2 in the present disclosure. The information providing system 2 includes a measurement device 20 and an information providing device 22. For example, the measurement device 20 is installed on the footwear of a subject who is the subject of estimation of credit-related information. The measurement device 20 has the same configuration as the measurement device 10 of the first embodiment. In the following, a description of the measurement device 20 will be omitted, and only the information providing device 22 will be described. Note that the main configuration of the information providing device 22 is similar to the configuration of the information providing device 12 of the first embodiment, and therefore the description may be omitted.

[Information Providing Device]
18 is a block diagram showing an example of the configuration of the information providing device 22. The information providing device 22 has an acquisition unit 221, a calculation unit 23, an estimation unit 24, a storage unit 224, a credit-related information generation unit 227, and an output unit 229. The calculation unit 23 and the estimation unit 24 constitute a risk estimation unit 25.

The acquisition unit 221 (acquisition means) has a configuration similar to that of the acquisition unit 121 of the first embodiment. The acquisition unit 221 acquires sensor data from the measurement device 20 mounted on the footwear of the subject who uses the information provision system 2. The acquisition unit 221 receives the sensor data from the measurement device 20 via wireless communication. The sensor data includes location information of the subject's mobile terminal (not shown) that is the source of the sensor data. For example, the acquisition unit 221 receives the sensor data from the measurement device 20 via a wireless communication function (not shown) that complies with standards such as Bluetooth (registered trademark) and WiFi (registered trademark). Note that the communication function of the acquisition unit 221 may be in accordance with standards other than Bluetooth (registered trademark) and WiFi (registered trademark) as long as it can communicate with the measurement device 20. The acquisition unit 221 may receive the sensor data from the measurement device 20 via a wired connection such as a cable. For example, the acquisition unit 221 may acquire gait indices and feature amounts calculated by the measurement device 20.

The acquisition unit 221 also acquires attributes of the subject. The attribute data includes gender, date of birth, height, and weight. The date of birth is converted to age. The attribute data also includes the subject's residential address (location information). The subject's residential address (location information) is used to generate a risk map of the target area. Typically, the subject's residential address (location information) is not used to estimate physical ability or disease risk. For example, the attribute data is input via an input device (not shown). For example, the attribute data is input via a mobile terminal used by the subject. For example, the attribute data may be stored in advance in the storage unit 224. The attribute data may be updated at any time in response to input by the subject.

The acquisition unit 221 also acquires the status information of the subject. The status information includes identity verification information, credit history information, contract fulfilment information, interpersonal relationship information, and behavioral characteristic information. The identity verification information includes information that guarantees that the name of the subject is real and information that indicates the stability of the subject's status. Note that the information included in the status information is not limited to that given here. Among the status information given here, the credit history information, contract fulfilment information, interpersonal relationship information, and behavioral characteristic information are affected by the subject's disease risk. The sum of the scores related to the identity verification information, credit history information, contract fulfilment information, interpersonal relationship information, and behavioral characteristic information corresponds to the credit score described below. The credit history information, contract fulfilment information, interpersonal relationship information, and behavioral characteristic information are multiplied by a penalty coefficient according to the subject's status information and disease risk. For example, the status information is input via an input device (not shown). For example, the status information is input via a terminal device used by the administrator. For example, the status information is input via a mobile terminal used by the subject. For example, the status information may be stored in advance in the storage unit 224. Attribute data may be updated at any time based on input from the subject or administrator.

The calculation unit 23 (calculation means) has the same configuration as the calculation unit 13 of the first embodiment. The calculation unit 23 has the functions of the waveform processing unit 122 and gait index calculation unit 123 of the first embodiment. The calculation unit 23 acquires sensor data from the acquisition unit 221. The calculation unit 23 extracts time series data for one walking cycle (gait waveform data) from the time series data of acceleration in three axial directions and angular velocity about three axes included in the sensor data. The calculation unit 23 extracts gait waveform data based on the timing of walking events detected from the time series data of the sensor data. For example, the calculation unit 23 extracts gait waveform data that starts from the timing of a heel strike and ends with the timing of the next heel strike.

The calculation unit 23 normalizes (first normalization) the time of the extracted walking waveform data for one step cycle to a walking cycle of 0 to 100% (percent). The calculation unit 23 also normalizes (second normalization) the first normalized walking waveform data for one step cycle so that the stance phase is 60% and the swing phase is 40%.

The calculation unit 23 extracts features (physical ability features) used to estimate physical abilities from the walking waveform data. The calculation unit 23 extracts physical ability features used to estimate at least one physical ability. For example, the calculation unit 23 extracts physical ability features used to estimate at least one of physical abilities such as grip strength (total muscle strength of the entire body), dynamic balance, lower limb muscle strength, mobility, and static balance. For example, the calculation unit 23 extracts physical ability features for each walking phase cluster according to preset conditions.

The calculation unit 23 uses the normalized walking waveform data to calculate gait indices used to estimate physical ability. For example, the calculation unit 23 calculates gait indices related to distance, height, angle, speed, time, frailty level, CPEI (Center of Pressure Exclusion Index), etc.

The storage unit 224 (storage means) has the same configuration as the storage unit 124 of the first embodiment. The storage unit 224 stores a physical ability estimation model. The physical ability estimation model estimates physical ability using physical ability features extracted from the walking waveform data. For example, the physical ability estimation model outputs an index related to physical ability (physical ability score) in response to input of the physical ability features extracted from the walking waveform data.

The memory unit 224 also stores a disease risk estimation model. The disease risk estimation model estimates disease risk using attribute data, gait index, and physical ability score. For example, the disease risk estimation model outputs an index related to disease risk (disease risk score) in response to input of attribute data, gait index, and physical ability score. For example, the disease risk estimation model may be a model that outputs a disease risk score in response to input of gait index and attribute data, without using a physical ability score. In that case, the physical ability estimation model does not need to be used.

Furthermore, the storage unit 224 stores a personality estimation model. The personality estimation model outputs personality information of the subject in response to input of attribute data, gait index, and disease risk score. The personality estimation model may be a model that estimates personality information of the subject using physical information and status information in addition to attribute data, gait index, and disease risk score. Details of the personality estimation model will be described later.

The storage unit 224 stores the physical ability estimation model, disease risk estimation model, and personality estimation model learned for multiple subjects (subjects). For example, the physical ability estimation model, disease risk estimation model, and personality estimation model may be stored in the storage unit 224 when the product is shipped from the factory. The physical ability estimation model, disease risk estimation model, and personality estimation model may also be stored in the storage unit 224 at a timing such as at the time of calibration before the subject uses the information providing device 22. For example, the physical ability estimation model, disease risk estimation model, and personality estimation model stored in a storage device (not shown) such as an external server may be used. In that case, it is sufficient if the physical ability estimation model, disease risk estimation model, and personality estimation model can be accessed via an interface (not shown) connected to the storage device.

The memory unit 224 also stores attribute data and status information of the subject. The attribute data includes gender, date of birth (age), height, and weight. The status information includes identification information, credit history information, contract enforcement ability information, human relationship information, and behavioral characteristic information. The attribute data and status information may be updated at any time. Furthermore, the memory unit 224 may store health checkup data of the subject.

The estimation unit 24 (estimation means) has the same configuration as the estimation unit 14 of the first embodiment. The estimation unit 24 includes the functions of the physical ability estimation unit 125 and the disease risk estimation unit 126 of the first embodiment. The estimation unit 24 acquires the physical ability feature extracted from the walking waveform data from the calculation unit 23. The estimation unit 24 also acquires the attributes stored in the memory unit 224. The estimation unit 24 estimates a physical ability score using the physical ability feature and the attributes. The estimation unit 24 inputs the physical ability feature and the attributes of the subject to a physical ability estimation model stored in the memory unit 224. For example, the estimation unit 24 estimates a physical ability score related to at least one of the physical abilities of grip strength (total muscle strength of the entire body), dynamic balance, lower limb muscle strength, mobility, and static balance. The estimation unit 24 estimates a disease risk score for each disease using the physical ability score, gait index, and attributes. The estimation unit 24 inputs the physical ability score, gait index, and attributes into a disease risk model to estimate a disease risk score. The estimation unit 24 outputs the estimated disease risk score.

The credit-related information generating unit 227 acquires attribute data, gait index, disease risk score, and status information related to the subject. Similar to the credit-related information generating unit 127 of the first embodiment, the credit-related information generating unit 227 calculates the subject's credit score using the subject's disease risk score and status information. Explanation of the calculation of the credit score by the credit-related information generating unit 227 is omitted.

The credit-related information generating unit 227 also estimates personality information of the subject using the attribute data, gait index, and disease risk score. The credit-related information generating unit 227 inputs the subject's attribute data, gait index, and disease risk score into a personality estimation model. The credit-related information generating unit 227 estimates the subject's personality using the personality scores output from the personality estimation model in response to the input of the subject's attribute data, gait index, and disease risk score.

FIG. 19 is a conceptual diagram showing an example of estimating personality information using the personality estimation model 275. The example in FIG. 19 shows five personality elements. The five personality elements include an openness element, a conscientiousness element, an extraversion element, an agreeableness element, and a neuroticism element. Note that the personality elements are not limited to the five shown in FIG. 19 and may include other elements.

The openness factor is an element that indicates a tendency to be open to new experiences. The openness score P _O is a score that indicates the degree of the openness factor. The larger the openness score P _O , the more open the person tends to be. On the other hand, the smaller the openness score P _O , the more closed the person tends to be. People with a large openness score P _O are curious, have a good eye for aesthetics, and are good at coming up with ideas.

The Conscientiousness element is an element that indicates a tendency to be responsible and serious. The Conscientiousness score P _C is a score that indicates the degree of the Conscientiousness element. The higher the Conscientiousness score P _C , the more responsible and serious a person tends to be. On the other hand, the lower the Conscientiousness score P _C , the less responsible and careless a person tends to be. People with a high Conscientiousness score P _C are autonomous, conscientious, and tend to proceed with things carefully.

The extroversion element is an element that indicates that interests and concerns are directed toward the outside world. The extroversion score P _E is a score that indicates the degree of the extroversion element. The higher the extroversion score P _E , the more interests and concerns tend to be directed toward the outside world. On the other hand, the lower the extroversion score P _E , the less interest and concern one has toward the outside world. People with a high extroversion score P _E are proactive, sociable, and cheerful.

The agreeableness element is an element that indicates a person's tendency to value harmony with those around them and to be cooperative. The agreeableness score P _A is a score that indicates the degree of the agreeableness element. The higher the agreeableness score P _A , the more one values harmony with those around them and tends to be cooperative. On the other hand, the lower the agreeableness score P _A , the more one disregards harmony with those around them and tends to be confrontational. People with a high agreeableness score P _A are considerate, kind, and devoted.

Neuroticism is an element that indicates the tendency to self-control emotions and feelings. Neuroticism score P _N is a score that indicates the degree of neuroticism. The higher the neuroticism score P _N , the more likely one is to be able to self-control emotions and feelings. On the other hand, the lower the neuroticism score P _N , the more likely one is to be able to self-control emotions and feelings. People with a high neuroticism score P _N have high stress resistance, are less likely to become anxious, and can maintain a stable mental state.

The personality estimation model 275 may be stored in an external storage device (not shown) constructed on a cloud or a server. In this case, the credit-related information generation unit 227 uses the personality estimation model 275 via an interface (not shown) connected to the storage device. The personality estimation model 275 is a machine learning model. For example, the personality estimation model 275 is a model trained on a data set using as training data a personality-related score as a response variable and attribute data, gait index, and disease risk score, related to multiple subjects, as explanatory variables. The personality-related scores include an openness score, a conscientiousness score, an extroversion score, an agreeableness score, and a neuroticism score. The explanatory variables may include a physical ability score and status information.

For example, the personality estimation model 275 is generated by learning using a linear regression algorithm. For example, the personality estimation model 275 is generated by learning using a support vector machine (SVM) algorithm. For example, the personality estimation model 275 is generated by learning using a Gaussian process regression (GPR) algorithm. For example, the personality estimation model 275 is generated by learning using a random forest (RF) algorithm. For example, the personality estimation model 275 may be generated by unsupervised learning that classifies tendencies related to the personality of a subject according to input attribute data, gait index, and disease risk score. There are no particular limitations on the algorithm for training the personality estimation model 275.

For example, the personality estimation model 275 may be a machine learning model such as an incomplete heterogeneous variational autoencoder or a random forest. If an incomplete heterogeneous variational autoencoder is used, personality information of a subject can be estimated even if there are some missing data in attribute data, gait indices, and disease risk scores.

The credit-related information generating unit 227 generates credit-related information including a credit score and personality information. The credit-related information may not include a credit score. For example, the credit-related information generating unit 227 adds each of the openness score P _O , the conscientiousness score P _C , the extraversion score P _E , the agreeableness score P _A , and the neuroticism score P _N to the credit-related information. For example, the credit-related information generating unit 227 may add the sum of the openness score P _O , the conscientiousness score P _C , the extraversion score P _E , the agreeableness score P _A , and the neuroticism score P _N to the credit-related information. For example, the credit-related information generating unit 227 applies the personality information to a preset document format to generate the credit-related information. For example, the credit-related information generating unit 227 may generate the credit-related information using a large-scale language model.

The output unit 229 (output means) has the same configuration as the output unit 129 of the first embodiment. The output unit 229 outputs credit-related information including personality information generated by the credit-related information generation unit 227. For example, the output unit 229 outputs credit-related information including personality information to an external system that uses the personality information. For example, the output unit 229 outputs credit-related information including personality information to a terminal device (not shown) used by a financial institution. There are no particular limitations on the use of the output credit-related information including personality information. For example, the credit-related information including personality information is used by the financial institution in considering financing, etc. for the subject. For example, the financial institution can select a financial product that matches the subject's personality information in response to the acquisition of credit-related information including personality information. In other words, the credit-related information generation unit 227 generates credit-related information that supports the decision-making of the financial institution.

(Operation)
Next, the operation of the information providing system 2 will be described with reference to the drawings. The operation of the information providing device 22 included in the information providing system 2 will be described below. Fig. 20 is a flowchart for explaining an example of the operation of the information providing device 22. In explaining the process according to the flowchart of Fig. 20, the components of the information providing device 22 will be described as the subject of the operation. The subject of the process according to the flowchart of Fig. 20 may be the information providing device 22.

In FIG. 20, first, the acquisition unit 221 acquires time series data of sensor data measured by the measurement device 20 mounted on the footwear (step S21). The sensor data includes acceleration in three axial directions and angular velocity around three axes.

Next, the calculation unit 23 executes a gait index calculation process using the acquired sensor data (step S22). In the gait index calculation process, the calculation unit 23 calculates a gait index used to estimate physical ability. The gait index calculation process in step S22 is similar to the gait index calculation process in the first embodiment ( FIG. 13 ).

Next, the estimation unit 24 estimates physical ability using the attribute data and gait index (step S23). For example, the estimation unit 24 estimates physical ability scores such as grip strength (total muscle strength of the entire body), dynamic balance, lower limb muscle strength, mobility, and static balance. If disease risk is estimated without using physical ability, step S23 can be omitted.

Next, the estimation unit 24 estimates the disease risk for each disease using the attribute data, gait index, and physical ability (step S24). When the disease risk is estimated without using physical ability, the estimation unit 24 estimates the disease risk for each disease using the attribute data and gait index. The estimation unit 24 estimates a disease risk score for each disease. For example, the estimation unit 24 estimates a disease risk score for each disease, such as gout, diabetes, hypertension, nephrolithiasis, liver cirrhosis, arteriosclerosis, thromboembolism, dyslipidemia, hypercholesterolemia, and hyperlipidemia. For example, the estimation unit 24 estimates a disease risk score for each disease, such as lower back pain, sleep apnea syndrome, insomnia, depression, osteoarthritis of the knee, and Parkinson's syndrome.

Next, the credit-related information generating unit 227 calculates a credit score for the subject using the estimated disease risk (step S25). The credit-related information generating unit 227 generates credit-related information including the calculated credit score.

Next, the estimation unit 24 estimates personality information of the subject using the attribute data, gait index, and disease risk (step S26). The estimation unit 24 estimates personality information of the subject according to the personality score output from the personality estimation model 275 in response to the input of the attribute data, gait index, and disease risk.

Next, the output unit 229 outputs the credit-related information including the generated credit score (step S27). For example, the output unit 229 outputs the credit-related information to a terminal device or server managed by the financial institution with which the subject is going to enter into a contract. For example, the output unit 229 outputs the credit-related information to an external system or the like that uses the credit-related information. For example, the output unit 229 may display the credit-related information on the screen of the subject's mobile terminal.

(Examples of application)
Next, an application example according to the present embodiment will be described with reference to the drawings. In this application example, the relationship between a business operator, a financial institution, a credit investigation company, a financial institution, and a target is shown. FIG. 21 is a correlation diagram showing the relationship between a business operator, a financial institution, a credit investigation company, and a target in this disclosure. The business operator is a business entity that provides a service using the information provision system 2. The financial institution is an institution that provides financial services according to a contract. The financial institution uses a service using the information provision system 2. The credit investigation company is an organization that creates credit information of the target under commission from the financial institution. In this application example, the credit investigation company also uses a service using the information provision system 2. The target is an entity that is about to enter into a contract with the financial institution. In this application example, an example in which the target is an individual is given. The target may be a corporation.

Below, an example will be given in which a personality estimation model is used to estimate personality information. For example, personality information is used to select financial products that a financial institution recommends to a subject. For example, the personality estimation model is optimized according to the type of financial product provided by the financial institution. For example, financial products include investment trusts, stocks, corporate bonds, government bonds, insurance, and other products. The credit-related information generated by the information providing device 22 is not limited to the following example, so long as it includes the personality information of the subject.

The business provides a service using the information provision system 2 to a financial institution or a credit investigation company. Based on a contract concluded with the financial institution or the credit investigation company, the business provides the financial institution or the credit investigation company with credit-related information corresponding to the disease risk of the subject. The credit-related information includes a credit score estimated according to the disease risk of the subject. The credit-related information provided to the financial institution also includes personality information of the subject. The financial institution pays the business a fee for the service using the information provision system 2. If the subject's health check-up data is used to estimate the credit score, the financial institution obtains the health check-up data from the subject. The financial institution provides the business with the obtained health check-up data of the subject. In the contract between the financial institution or credit investigation company and the business, rules regarding the handling of personal information and appropriate data management are clarified. The business clearly explains that the credit-related information is for reference only and does not guarantee medical accuracy or completeness.

The financial institution is an institution with which the subject is about to enter into a contract. The financial institution fully explains the personal information protection policy and the contents of data management to the subject, and then obtains the subject's consent to the use of personal information and data. Furthermore, if there are any changes to the personal information protection policy or the contents of data management, the financial institution explains the changes to the subject and obtains the subject's consent. For example, the subject's consent is obtained electronically. The financial institution enters into a contract with the business operator regarding the use of services using the information provision system 2. The financial institution pays the business operator a fee for using the information provision system 2. The financial institution receives credit-related information on the subject from the business operator. The financial institution creates credit information on the subject according to the content of the credit-related information provided by the business operator. The financial institution refers to the content of the created credit information and considers loans, etc. to the subject. If the creation of credit information is entrusted to a credit investigation company, the financial institution does not need to be provided with credit-related information.

The credit investigation company is commissioned to create credit information and provides a service of conducting a credit investigation of the subject. The credit investigation company handles personal information and data related to the subject in response to the commission from the financial institution. The credit investigation company obtains consent from the subject regarding the use of the personal information and data through the financial institution. The credit investigation company may obtain consent directly from the subject regarding the use of the personal information and data. For example, consent from the subject is obtained electronically. The credit investigation company enters into a contract with the business operator regarding the use of a service using the information provision system 2. The credit investigation company pays the business operator a fee for using the information provision system 2. The credit investigation company is provided with the subject's credit-related information from the business operator. The credit investigation company may obtain the credit-related information via the financial institution. The credit investigation company creates credit information for the subject by referring to the content of the credit-related information provided by the business operator. The credit investigation company provides the created credit information to the financial institution.

The subject is an entity that is about to enter into a contract with a financial institution. The subject is loaned or provided with a special insole equipped with a measuring device 20 by a business that has a contract with the financial institution. The subject wears shoes equipped with the special insole and carries a mobile terminal (not shown) capable of communicating with the measuring device 20 while performing work. The mobile terminal uploads sensor data measured by the measuring device 20 to the business's cloud server. The sensor data uploaded to the cloud server is used to estimate disease risk and credit score. The sensor data measured as the subject walks is used to estimate the subject's credit score. The subject is provided with financial products and preferential interest rate loans depending on the credit score.

Terminal devices (not shown) used by financial institutions and credit bureaus download credit-related information, including credit scores, from the operator's cloud server. Administrators at the financial institutions and credit bureaus refer to the credit-related information to create credit information on the subject. Financial institutions refer to the created credit information when considering loans, etc., to the subject. For example, administrators at financial institutions may periodically refer to the credit-related information to consider countermeasures in response to changes in credit practice information.

FIG. 22 shows an example in which credit-related information for Person B, generated by information providing device 22, is displayed on the screen of a terminal device 280 used at a financial institution with which the subject is planning to enter into a contract. The screen of terminal device 280 displays credit-related information including personality information optimized for the financial institution's selection of financial products. In the example of FIG. 22, estimated personality information for Person B is displayed on the screen of terminal device 280.

A radar chart of five personality elements is displayed on the screen of the terminal device 280. In the radar chart, the openness score P _O and the extraversion score P _E are high. Therefore, the screen of the terminal device 280 displays information according to the personality score, such as "Your openness score P _O and extraversion score P _E are high." People with a high openness score P _O are expected to be able to tolerate the risks of financial products. In addition, people with a high extraversion score P _E tend to be sociable, so it is expected that even if they do not have funds, they will be able to get loans from acquaintances or have many people who will act as guarantors. Therefore, the screen of the terminal device 280 displays information about financial products according to the personality information, such as "We recommend financial product Z, which has a higher risk." A financial institution's financial product selection staff can consider financial products to recommend to the target person by referring to the information displayed on the screen of the terminal device 280.

As described above, the information provision system of this embodiment includes a measuring device and an information provision device. The measuring device is installed on the subject's footwear. The measuring device measures acceleration and angular velocity. The measuring device generates sensor data using the measured acceleration and angular velocity. The measuring device transmits the generated sensor data to the information provision device. The information provision device includes an acquisition unit, a risk estimation unit, a credit-related information generation unit, and an output unit. The acquisition unit acquires sensor data including acceleration and angular velocity measured by a measuring device mounted on the footwear of the subject for which credit information is to be created. The risk estimation unit estimates a disease risk for each disease related to the subject using the acquired sensor data. The credit-related information generation unit generates credit-related information according to the estimated disease risk related to the subject and pre-registered status information of the subject. In addition, the credit-related information generation unit estimates personality information of the subject using a personality estimation model. The personality estimation model outputs a personality score according to input of a disease risk score, a gait index, and attribute data. The credit-related information generation unit adds the estimated personality information of the subject to the credit-related information. The output unit outputs the generated credit-related information.

The information providing device of this embodiment estimates disease risk using sensor data measured by a measuring device mounted on the footwear of the subject for whom credit information is to be created. The information providing device of this embodiment generates credit-related information according to the disease risk and status information related to the subject. The information providing device of this embodiment also estimates personality information of the subject. Therefore, according to this embodiment, it is possible to provide credit-related information according to the personality information of the subject.

In one aspect of this embodiment, the personality estimation model is a model trained using a machine learning technique. The personality estimation model includes an incomplete heterogeneous variational autoencoder. According to this aspect, even if there is some loss of data such as gait indicators, it is possible to estimate credit-related information including personality information of the subject.

Third Embodiment
Next, an information providing device according to a third embodiment will be described with reference to the drawings. The information providing device according to this embodiment has a simplified configuration of the information providing device included in the information providing system according to the first and second embodiments.

(composition)
23 is a block diagram showing an example of a configuration of the information providing device 30 in the present disclosure. The information providing device 30 includes an acquisition unit 31, a risk estimation unit 35, a credit-related information generation unit 37, and an output unit 39.

The acquisition unit 31 acquires sensor data including acceleration and angular velocity measured by a measuring device mounted on the footwear of the subject for whom credit information is to be created. The risk estimation unit 35 uses the acquired sensor data to estimate the disease risk for each disease related to the subject. The credit-related information generation unit 37 generates credit-related information according to the estimated disease risk related to the subject and pre-registered status information of the subject. The output unit 39 outputs the generated credit-related information.

(Operation)
Next, the operation of the information providing device 30 will be described with reference to the drawings. Fig. 24 is a flowchart for explaining an example of the operation of the information providing device 30. In the explanation of the process according to the flowchart of Fig. 24, the components of the information providing device 30 will be described as the subject of the operation. The subject of the process according to the flowchart of Fig. 24 may be the information providing device 30.

In FIG. 24, first, the acquisition unit 31 acquires sensor data including acceleration and angular velocity measured by a measuring device mounted on the footwear of the subject for whom credit information is to be created (step S31).

Next, the risk estimation unit 35 uses the acquired sensor data to estimate the disease risk for each disease for the subject (step S32).

Next, the credit-related information generating unit 37 generates credit-related information according to the estimated disease risk of the subject and the subject's pre-registered status information (step S33).

Next, the output unit 39 outputs the generated credit-related information (step S34).

As described above, the information providing device of this embodiment estimates disease risk using sensor data measured by a measuring device mounted on the footwear of the subject for whom credit information is to be created. The information providing device of this embodiment generates credit-related information according to the disease risk and status information related to the subject. Therefore, according to this embodiment, it is possible to provide credit-related information according to the subject's physical and mental state.

(Hardware)
Next, a hardware configuration for executing the control and processing in the present disclosure will be described with reference to the drawings. Here, an information processing device 90 (computer) in Fig. 25 is given as an example of such a hardware configuration. The information processing device 90 in Fig. 25 is an example of a configuration for executing the control and processing in the present disclosure, and does not limit the scope of the present disclosure.

As shown in FIG. 25, the information processing device 90 includes a processor 91, a main memory device 92, an auxiliary memory device 93, an input/output interface 95, and a communication interface 96. In FIG. 25, the interface is abbreviated as I/F (Interface). The processor 91, the main memory device 92, the auxiliary memory device 93, the input/output interface 95, and the communication interface 96 are connected to each other via a bus 98 so as to be able to communicate data with each other. In addition, the processor 91, the main memory device 92, the auxiliary memory device 93, and the input/output interface 95 are connected to a network such as the Internet or an intranet via the communication interface 96.

The processor 91 expands a program (instructions) stored in the auxiliary storage device 93 or the like into the main storage device 92. For example, the program is a software program for executing the control and processing in this disclosure. The processor 91 executes the program expanded into the main storage device 92. The processor 91 executes the program to execute the control and processing in this disclosure.

The main memory 92 has an area in which programs are expanded. Programs stored in the auxiliary memory 93 or the like are expanded in the main memory 92 by the processor 91. The main memory 92 is realized by a volatile memory such as a DRAM (Dynamic Random Access Memory). In addition, a non-volatile memory such as an MRAM (Magneto-resistive Random Access Memory) may be configured/added to the main memory 92.

The auxiliary storage device 93 stores various data such as programs. The auxiliary storage device 93 is realized by a local disk such as a hard disk or flash memory. Note that it is also possible to omit the auxiliary storage device 93 by configuring the various data to be stored in the main storage device 92.

The input/output interface 95 is an interface for connecting the information processing device 90 to peripheral devices based on standards and specifications. The communication interface 96 is an interface for connecting to external systems and devices via a network such as the Internet or an intranet based on standards and specifications. The input/output interface 95 and the communication interface 96 may be a common interface for connecting to external devices.

If necessary, input devices such as a keyboard, mouse, or touch panel may be connected to the information processing device 90. These input devices are used to input information and settings. When a touch panel is used as the input device, a screen having the function of a touch panel becomes the interface. The processor 91 and the input devices are connected via an input/output interface 95.

The information processing device 90 may be equipped with a display device for displaying information. If a display device is equipped, the information processing device 90 is equipped with a display control device (not shown) for controlling the display of the display device. The information processing device 90 and the display device are connected via an input/output interface 95.

The information processing device 90 may be equipped with a drive device. The drive device acts as an intermediary between the processor 91 and a recording medium (program recording medium) to read data and programs stored on the recording medium and to write the processing results of the information processing device 90 to the recording medium. The information processing device 90 and the drive device are connected via an input/output interface 95.

The above is an example of a hardware configuration for enabling the control and processing in this disclosure. The hardware configuration in FIG. 25 is an example of a hardware configuration for executing the control and processing in this disclosure, and does not limit the scope of this disclosure. Programs that cause a computer to execute the control and processing in this disclosure are also included in the scope of the present invention.

The scope of the present invention also includes a program recording medium on which a program for executing the processing in this embodiment is recorded. For example, the program recording medium is a computer-readable, non-transient recording medium. The recording medium can be realized, for example, as an optical recording medium such as a CD (Compact Disc) or a DVD (Digital Versatile Disc). The recording medium may also be realized as a semiconductor recording medium such as a USB (Universal Serial Bus) memory or an SD (Secure Digital) card. The recording medium may also be realized as a magnetic recording medium such as a flexible disk, or other recording medium.

The components in this disclosure may be combined in any manner. The components in this disclosure may be implemented by software. The components in this disclosure may be implemented by circuits.

The present disclosure has been described above with reference to the embodiments, but the present disclosure is not limited to the above-mentioned embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate.

A part or all of the above-described embodiments can be described as, but is not limited to, the following supplementary notes.
(Appendix 1)
An acquisition unit that acquires sensor data including acceleration and angular velocity measured by a measuring device mounted on the footwear of a subject for whom credit information is to be created;
A risk estimation unit that estimates a disease risk for each disease of the subject using the acquired sensor data;
a credit-related information generating unit that generates credit-related information according to the estimated disease risk of the subject and pre-registered status information of the subject;
and an output unit that outputs the generated credit-related information.
(Appendix 2)
The risk estimation unit is
a calculation unit that calculates a gait index using the sensor data;
an estimation unit that inputs data including the gait index calculated using the sensor data into a disease risk estimation model that outputs a disease risk score indicating the degree of disease risk for each disease in response to input of data including the gait index, and estimates disease risk information according to the disease risk score output from the disease risk estimation model.
(Appendix 3)
The credit-related information generating unit
estimating a credit score for each of the identity, credit history, contractual ability, interpersonal relationships, and behavioral characteristics included in the status information;
3. The information providing device of claim 2, which generates the credit-related information including the credit score for each of the estimated identity, credit history, contractual ability, interpersonal relationships, and behavioral characteristics.
(Appendix 4)
The credit-related information generating unit
The information providing device described in Appendix 3 calculates the credit score for the subject by multiplying the weights for each of the identification, credit history, ability to fulfill contracts, human relationships, and behavioral characteristics by a penalty coefficient corresponding to at least one of the status information and the disease risk score.
(Appendix 5)
The credit-related information generating unit
An information providing device as described in Appendix 3, which estimates the credit score for each of the identification, the credit history, the ability to fulfill contracts, the interpersonal relationships, and the behavioral characteristics using a credit score estimation model that outputs the credit score in response to input of the disease risk score and the status information.
(Appendix 6)
The credit-related information generating unit
estimating personality information of the subject using a personality estimation model that outputs a score related to personality in response to input of the disease risk score, the gait index, and attribute data;
An information providing device as described in Appendix 5, which generates credit-related information including the estimated personality information of the subject.
(Appendix 7)
The disease risk estimation model, the credit score estimation model, and the personality estimation model,
This is a model trained using machine learning techniques.
The disease risk estimation model and the personality estimation model are
7. The information providing apparatus of claim 6, comprising an incomplete heterogeneous variational autoencoder.
(Appendix 8)
An information providing device according to any one of appendix 1 to 6;
The measuring device,
The measuring device includes:
a sensor device that is installed in the footwear of the subject, measures acceleration and angular velocity, generates the sensor data using the measured acceleration and angular velocity, and transmits the generated sensor data to the information providing device;
The information providing device includes:
An information providing system that displays the credit-related information optimized for a financial institution on a screen of a terminal device used by the financial institution that reviews the credit information regarding the subject.
(Appendix 9)
The computer
Acquire sensor data including acceleration and angular velocity measured by a measuring device mounted on the footwear of a subject for whom credit information is to be created;
Using the acquired sensor data, a disease risk for each disease of the subject is estimated;
generating credit-related information according to the estimated disease risk of the subject and pre-registered status information of the subject;
An information providing method for outputting the generated credit-related information.
(Appendix 10)
The computer
Calculating a gait index using the sensor data;
inputting data including the gait index calculated using the sensor data into a disease risk estimation model that outputs a disease risk score indicating a degree of disease risk for each disease in response to input of data including the gait index;
An information providing method according to claim 9, which estimates disease risk information according to the disease risk score output from the disease risk estimation model.
(Appendix 11)
The computer
estimating a credit score for each of the identity, credit history, contractual ability, interpersonal relationships, and behavioral characteristics included in the status information;
11. The information providing method of claim 10, which generates the credit-related information including the credit score for each of the estimated identity, credit history, contractual ability, interpersonal relationships, and behavioral characteristics.
(Appendix 12)
The computer
The information provision method described in Appendix 11, in which the credit score for the subject is calculated as the sum of values obtained by multiplying the weights for each of the identification, credit history, ability to fulfill contracts, human relationships, and behavioral characteristics by a penalty coefficient corresponding to at least one of the status information and the disease risk score.
(Appendix 13)
The computer
An information provision method as described in Appendix 11, in which the credit score for each of the identification, the credit history, the ability to fulfill contracts, the interpersonal relationships, and the behavioral characteristics is estimated using a credit score estimation model that outputs the credit score in response to the input of the disease risk score and the status information.
(Appendix 14)
The computer
estimating personality information of the subject using a personality estimation model that outputs a score related to personality in response to input of the disease risk score, the gait index, and attribute data;
An information providing method as described in Appendix 10, which generates credit-related information including the estimated personality information of the subject.
(Appendix 15)
A process of acquiring sensor data including acceleration and angular velocity measured by a measuring device mounted on the footwear of a subject for whom credit information is to be created;
A process of estimating a disease risk for each disease of the subject using the acquired sensor data;
A process of generating credit-related information according to the estimated disease risk of the subject and pre-registered status information of the subject;
and a process of outputting the generated credit-related information.
(Appendix 16)
A process of calculating a gait index using the sensor data;
A process of inputting data including the gait index calculated using the sensor data into a disease risk estimation model that outputs a disease risk score indicating a degree of disease risk for each disease in response to input of data including the gait index;
A non-transitory computer-readable recording medium as described in Appendix 15, having a program recorded thereon to cause a computer to execute the process of estimating disease risk information according to the disease risk score output from the disease risk estimation model.
(Appendix 17)
A process of estimating a credit score for each of the identity, credit history, contractual ability, interpersonal relationships, and behavioral characteristics included in the status information;
A non-transitory computer-readable recording medium as described in Appendix 16, having recorded thereon a program for causing a computer to execute the steps of: generating the credit-related information including the credit scores for each of the estimated identity, credit history, ability to fulfill contracts, interpersonal relationships, and behavioral characteristics.
(Appendix 18)
A non-transitory computer-readable recording medium as described in Appendix 17, having recorded thereon a program that causes a computer to execute a process of calculating the credit score for the subject by multiplying the weights for each of the identification, credit history, ability to fulfill contracts, human relationships, and behavioral characteristics by a penalty coefficient corresponding to at least one of the status information and the disease risk score.
(Appendix 19)
A non-transitory computer-readable recording medium as described in Appendix 17, having recorded thereon a program that causes a computer to execute a process of estimating the credit score for each of the identification, the credit history, the ability to fulfill contracts, the interpersonal relationships, and the behavioral characteristics using a credit score estimation model that outputs the credit score in response to input of the disease risk score and the status information.
(Appendix 20)
A process of estimating personality information of the subject using a personality estimation model that outputs a score related to personality in response to input of the disease risk score, the gait index, and attribute data;
A non-transitory computer-readable recording medium as described in Appendix 16, having recorded thereon a program for causing a computer to execute the process of generating credit-related information including the estimated personality information of the subject.

LIST OF SYMBOLS 1, 2 INFORMATION PROVIDING SYSTEM 10, 20 MEASURING DEVICE 12, 22 INFORMATION PROVIDING DEVICE 13, 23 CALCULATOR 14, 24 ESTIMATION DEVICE 15, 25 RISK ESTIMATION DEVICE 30 INFORMATION PROVIDING DEVICE 31 ACQUISITION DEVICE 35 RISK ESTIMATION DEVICE 37 CREDIT-RELATED INFORMATION GENERATOR 39 OUTPUT DEVICE 110 SENSOR 111 ACCELERATION SENSOR 112 ANGULAR VELOCITY SENSOR 113 CONTROL DEVICE 115 COMMUNICATION DEVICE 117 POWER SOURCE 121, 221 ACQUISITION DEVICE 122 WAVEFORM PROCESSING DEVICE 123 GAIT INDEX COMPUTING DEVICE 124, 224 MEMORY DEVICE 125 PHYSICAL ABILITY ESTIMATION DEVICE 126 DISEASE RISK ESTIMATION DEVICE 127, 227 CREDIT-RELATED INFORMATION GENERATOR 129, 229 OUTPUT DEVICE

Claims (20)

An acquisition unit that acquires sensor data including acceleration and angular velocity measured by a measuring device mounted on the footwear of a subject for whom credit information is to be created;
A risk estimation unit that estimates a disease risk for each disease of the subject using the acquired sensor data;
a credit-related information generating unit that generates credit-related information according to the estimated disease risk of the subject and pre-registered status information of the subject;
and an output unit that outputs the generated credit-related information. The risk estimation unit is
a calculation unit that calculates a gait index using the sensor data;
an estimation unit that inputs data including the gait index calculated using the sensor data into a disease risk estimation model that outputs a disease risk score indicating a degree of disease risk for each disease in response to input of data including the gait index, and estimates disease risk information according to the disease risk score output from the disease risk estimation model. The credit-related information generating unit
estimating a credit score for each of the identity, credit history, contractual ability, interpersonal relationships, and behavioral characteristics included in the status information;
The information providing apparatus of claim 2 , further comprising: a credit score for each of the estimated identity, credit history, contractual ability, interpersonal relationships, and behavioral characteristics. The credit-related information generating unit
The information providing device of claim 3, wherein the credit score for the subject is calculated as the sum of values obtained by multiplying weights for each of the identification, credit history, ability to fulfill contracts, human relationships, and behavioral characteristics by a penalty coefficient corresponding to at least one of the status information and the disease risk score. The credit-related information generating unit
The information providing device of claim 3 , wherein the credit scores for each of the identification, the credit history, the ability to fulfill contracts, the interpersonal relationships, and the behavioral characteristics are estimated using a credit score estimation model that outputs the credit score in response to input of the disease risk score and the status information. The credit-related information generating unit
estimating personality information of the subject using a personality estimation model that outputs a score related to personality in response to input of the disease risk score, the gait index, and attribute data;
The information providing device according to claim 5 , wherein the credit-related information is generated including the estimated personality information of the subject. The disease risk estimation model, the credit score estimation model, and the personality estimation model,
This is a model trained using machine learning techniques.
The disease risk estimation model, the credit score estimation model, and the personality estimation model,
7. The information providing apparatus of claim 6, comprising an incomplete heterogeneous variational autoencoder. An information providing device according to any one of claims 1 to 6;
The measuring device,
The measuring device includes:
a sensor device that is installed in the footwear of the subject, measures acceleration and angular velocity, generates the sensor data using the measured acceleration and angular velocity, and transmits the generated sensor data to the information providing device;
The information providing device includes:
An information providing system that displays the credit-related information optimized for a financial institution on a screen of a terminal device used by the financial institution that reviews the credit information regarding the subject. The computer
Acquire sensor data including acceleration and angular velocity measured by a measuring device mounted on the footwear of a subject for whom credit information is to be created;
Using the acquired sensor data, a disease risk for each disease of the subject is estimated;
generating credit-related information according to the estimated disease risk of the subject and pre-registered status information of the subject;
An information providing method for outputting the generated credit-related information. The computer
Calculating a gait index using the sensor data;
inputting data including the gait index calculated using the sensor data into a disease risk estimation model that outputs a disease risk score indicating a degree of disease risk for each disease in response to input of data including the gait index;
The information providing method according to claim 9 , further comprising estimating disease risk information according to the disease risk score output from the disease risk estimation model. The computer
estimating a credit score for each of the identity, credit history, contractual ability, interpersonal relationships, and behavioral characteristics included in the status information;
The method of claim 10 , further comprising generating the credit-related information including a credit score for each of the estimated identity, credit history, ability to honor contracts, interpersonal relationships, and behavioral characteristics. The computer
The information providing method of claim 11, wherein the credit score for the subject is calculated as the sum of values obtained by multiplying weights for each of the identification, credit history, ability to fulfill contracts, human relationships, and behavioral characteristics by a penalty coefficient corresponding to at least one of the status information and the disease risk score. The computer
The information providing method of claim 11, wherein the credit scores for each of the identification, the credit history, the ability to fulfill contracts, the interpersonal relationships, and the behavioral characteristics are estimated using a credit score estimation model that outputs the credit score in response to input of the disease risk score and the status information. The computer
estimating personality information of the subject using a personality estimation model that outputs a score related to personality in response to input of the disease risk score, the gait index, and attribute data;
The information providing method according to claim 10 , further comprising generating the credit-related information including the estimated personality information of the subject. A process of acquiring sensor data including acceleration and angular velocity measured by a measuring device mounted on the footwear of a subject for whom credit information is to be created;
A process of estimating a disease risk for each disease of the subject using the acquired sensor data;
A process of generating credit-related information according to the estimated disease risk of the subject and pre-registered status information of the subject;
and a process of outputting the generated credit-related information. A process of calculating a gait index using the sensor data;
A process of inputting data including the gait index calculated using the sensor data into a disease risk estimation model that outputs a disease risk score indicating a degree of disease risk for each disease in response to input of data including the gait index;
A non-transitory computer-readable recording medium as described in claim 15, having a program recorded thereon to cause a computer to execute the process of estimating disease risk information according to the disease risk score output from the disease risk estimation model. A process of estimating a credit score for each of the identity, credit history, contractual ability, interpersonal relationships, and behavioral characteristics included in the status information;
The non-transitory computer-readable recording medium of claim 16, having recorded thereon a program for causing a computer to execute the steps of: generating the credit-related information including the credit scores for each of the estimated identity, credit history, contractual ability, interpersonal relationships, and behavioral characteristics. The non-transitory computer-readable recording medium according to claim 17, which has recorded thereon a program for causing a computer to execute a process of calculating the credit score for the subject as the sum of values obtained by multiplying the weights for the identity proof, the credit history, the ability to enforce the contract, the human relationships, and the behavioral characteristics by a penalty coefficient corresponding to at least one of the status information and the disease risk score. The non-transitory computer-readable recording medium according to claim 17, which has recorded thereon a program for causing a computer to execute a process of estimating the credit scores for each of the identification, the credit history, the ability to enforce a contract, the human relationships, and the behavioral characteristics, using a credit score estimation model that outputs the credit score in response to input of the disease risk score and the status information. A process of estimating personality information of the subject using a personality estimation model that outputs a score related to personality in response to input of the disease risk score, the gait index, and attribute data;
A non-transitory computer-readable recording medium as described in claim 16, having a program recorded thereon to cause a computer to execute the steps of: generating the credit-related information including the estimated personality information of the subject.

Images