WO2024261997A1 - Information generating device, information providing system, information providing method, and recording medium - Google Patents

Abstract

The present invention provides, in order to provide a health measure according to a disease risk of a management target person engaged in daily work, an information generating device comprising: an acquisition unit that acquires sensor data including an acceleration and an angular velocity measured by a measurement device installed in a footwear of at least one management target person; a risk estimation unit that uses the acquired sensor data to estimate a disease risk for each disease concerning the at least one management target person; a proposal information generation unit that generates proposal information including a health measure according to the disease risk concerning the at least one management target person; and an output unit that outputs the generated proposal information.

Description

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

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

As interest in healthcare grows, attention is being focused on services that provide information based on gait. For example, technology is being developed that analyzes gait using sensor data measured by sensors mounted in footwear such as shoes. Time-series sensor data contains characteristics associated with walking events that are related to physical conditions. If the disease risk of a subject can be estimated based on the characteristics associated with walking events, it will be possible to provide information based on disease risk to companies with many employees.

Patent Document 1 discloses a member health status management system that manages the health status of members such as employees belonging to a company. The system of Patent Document 1 acquires primary analysis data based on the health status analyzed by a health service provider. The system of Patent Document 1 generates evaluation criteria based on the acquired primary analysis data. The system of Patent Document 1 generates secondary analysis data for a member based on the member's health status information relating to the same items as the health status information related to the primary analysis data used to generate the evaluation criteria, and the evaluation criteria. The system of Patent Document 1 notifies the member of the generated secondary analysis data.

JP 2020-013230 A

The method of Patent Document 1 required obtaining health status information of members from multiple health service providers. Therefore, the method of Patent Document 1 could not manage the health status of members unless the health status information of members was obtained from multiple health service providers. In other words, the method of Patent Document 1 could not provide health measures according to the disease risk of members engaged in daily work.

The purpose of this disclosure is to provide an information generating device, an information providing system, an information providing method, and a recording medium that can provide health measures according to the disease risk of managed individuals engaged in daily work.

An information generating 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 at least one managed person, a risk estimation unit that estimates a disease risk for each disease for at least one managed person using the acquired sensor data, a proposed information generating unit that generates proposed information including health measures according to the disease risk for at least one managed person, and an output unit that outputs the generated proposed information.

In one embodiment of the information generation method disclosed herein, sensor data including acceleration and angular velocity measured by a measuring device mounted on the footwear of at least one managed person is acquired, the acquired sensor data is used to estimate a disease risk for each disease for the at least one managed person, suggested information including health measures according to the disease risk for the at least one managed person is generated, and the generated suggested information is output.

A program according to one embodiment 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 at least one managed person; estimating a disease risk for each disease for at least one managed person using the acquired sensor data; generating suggested information including health measures according to the disease risk for at least one managed person; and outputting the generated suggested information.

This disclosure makes it possible to provide an information generating device, an information providing system, an information providing method, and a recording medium that can provide health measures according to the disease risk of managed individuals engaged in daily work.

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 included in an information providing system according to the present disclosure. 1 is a conceptual diagram showing an example of the arrangement of measuring devices provided in an information providing system according to the present disclosure. 1 is a conceptual diagram for explaining a coordinate system set in a measurement device included in an information provision system in the present disclosure. FIG. FIG. 2 is a conceptual diagram for explaining a human body surface used in the description of the present disclosure. 2 is a block diagram showing an example of a configuration of an information generating device included in the information providing system in the present disclosure. FIG. FIG. 1 is a conceptual diagram for explaining a walking cycle used in the explanation of the present disclosure. 1 is a conceptual diagram for explaining a physical ability estimation model used by an information generating device included in an information providing system in the present disclosure. FIG. 1 is a conceptual diagram for explaining an example of estimating disease risk by the information providing system in the present disclosure. 1 is a conceptual diagram for explaining an example of estimating disease risk by the information providing system in the present disclosure. FIG. 11 is a conceptual diagram for explaining an example of an estimation of a health measure by the information provision system in the present disclosure. 10 is a flowchart for explaining an example of an operation of an information generating device included in the information providing system in the present disclosure. 10 is a flowchart for illustrating an example of a gait index calculation process performed by an information generating device included in the information provision system in the present disclosure. FIG. 1 is a conceptual diagram for explaining a service that uses an information providing system in the present disclosure. 1 is a conceptual diagram showing a display example of suggested information including health measures provided from an information providing system in the present disclosure. FIG. 1 is a conceptual diagram for explaining a service that uses an information providing system in the present disclosure. 1 is a conceptual diagram showing a display example of suggested information including health measures provided from an information providing system in the present disclosure. FIG. 1 is a conceptual diagram for explaining a service that uses an information providing system in the present disclosure. 1 is a conceptual diagram showing a display example of suggested information including health measures provided from an information providing system in the present disclosure. 1 is a block diagram showing an example of a configuration of an information generating device according to the present disclosure. 11 is a flowchart for explaining an example of an operation of the information generating device in the present disclosure. FIG. 2 is a conceptual diagram illustrating 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 estimates health measures customized for each company using sensor data related to foot movements measured according to the walking of employees (subjects of management) belonging to the company. The method according to the present embodiment can be applied not only to companies but also to any organization having multiple members (subjects of management). For example, the method according to the present embodiment can be applied to organizations such as local governments.

(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 measuring device 10 and an information generating device 12. For example, the measuring device 10 is installed in the footwear of an employee (managed person) belonging to a company. For example, the function of the information generating device 12 is implemented in a server or cloud connected via a network to a mobile terminal carried by the managed person or a repeater installed inside the building where the managed person works. For example, the function of the information generating device 12 may be implemented in a mobile terminal carried by the subject. In the following, the configurations of the measuring device 10 and the information generating 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 (also called spatial acceleration). The acceleration sensor 111 measures acceleration (also called spatial acceleration) as a physical quantity related to foot movement. The acceleration sensor 111 outputs the measured acceleration to the control unit 113. For example, the acceleration sensor 111 can be a piezoelectric type, a piezo-resistive type, a capacitance type, or other type of sensor. There are no limitations on the sensor used as the acceleration sensor 111 as long as it can measure acceleration.

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

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 111 that measures acceleration in three axial directions and an angular velocity sensor 112 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.

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 person to be managed, or in an accessory such as an anklet worn by the person to be managed. 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 lateral direction of the managed person is set as the x-axis direction, the direction of the back of the managed person is set as the y-axis direction, and the direction of gravity is set as the z-axis direction when the managed person stands 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 walking of the managed person.

FIG. 5 is a conceptual diagram for explaining the planes (also called human body planes) set for the human body. In this embodiment, a sagittal plane that divides the body into left and right, a coronal plane that divides the body into front and back, and a horizontal plane that divides the body horizontally are defined. 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 different coordinate systems are 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. In addition, 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 generating 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 walking of the managed person. 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 be configured to start measuring the step width 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 may calculate at least one of the gait indices described below. In that case, the measurement device 10 outputs the calculated gait indices to the information generating device 12. For example, the control unit 113 may calculate a feature amount used to estimate physical ability described below. In that case, the measurement device 10 outputs the calculated feature amount to the information generating device 12.

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.

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 generating 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 according 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 generating 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 generating device 12 via wireless communication. For example, the communication unit 115 transmits the sensor data to the information generating 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 compliant with standards other than Bluetooth (registered trademark) or WiFi (registered trademark). The communication unit 115 may transmit the sensor data to the information generating 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 generating device]
6 is a block diagram showing an example of the configuration of the information generating device 12. The information generating device 12 has an acquiring unit 121, a waveform processing unit 122, a gait index calculating unit 123, a storage unit 124, a physical ability estimating unit 125, a disease risk estimating unit 126, a proposed information generating unit 127, and an output unit 129. The waveform processing unit 122, the gait index calculating unit 123, the physical ability estimating unit 125, and the disease risk estimating unit 126 constitute the risk estimating unit 15. The waveform processing unit 122 and the gait index calculating unit 123 constitute the calculating unit 13. The physical ability estimating unit 125 and the disease risk estimating unit 126 constitute the estimating unit 14.

The acquisition unit 121 (acquisition means) acquires sensor data from the measurement device 10 mounted on the footwear of the managed person. The acquisition unit 121 receives the sensor data from the measurement device 10 via wireless communication. For example, the sensor data may include location information of the managed person's mobile terminal (not shown), which 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 measurement device 10 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 acquisition unit 121 may conform to a standard other than Bluetooth (registered trademark) or WiFi (registered trademark) as long as it can communicate with the measurement device 10. The acquisition unit 121 may receive the sensor data from the measurement 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 managed person. The attribute data includes gender, date of birth, height, and weight. The date of birth is converted to age. The gender, date of birth (age), height, and weight contained 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 managed person. 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 managed person 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.

Figure 7 is a conceptual diagram for explaining a step cycle based on the right foot. The step cycle based on the left foot is the same as that of the right foot. The horizontal axis of Figure 7 shows one walking cycle of the right foot, starting from the point when the heel of the right foot lands on the ground and ending at the point when the heel of the right foot lands on the ground. The horizontal axis of Figure 7 is normalized with the step cycle as 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 a 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 a period in which the sole of the foot is off the ground. The swing phase is further divided into early swing T5, mid swing T6, and final swing 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 during walking are also called walking events. P1 represents the event of the heel of the right foot touching the ground (heel strike) (HS: Heel Strike). P2 represents the event of the toe of the left foot lifting off the ground (opposite toe off) while the sole of the right foot is on the ground (OTO: Opposite Toe Off). P3 represents the event of the right heel lifting off the ground (heel rise) while the sole of the right foot is on the ground (HR: Heel Rise). P4 represents the event of the left heel touching the ground (opposite heel strike) (OHS: Opposite Heel Strike). P5 represents the event of the right toe lifting off the ground (toe off) while the sole of the left foot is on the ground (TO: Toe Off). P6 represents an event in which the left and right feet cross (foot crossing) with the sole of the left foot touching the ground (FA: Foot Adjacent). P7 represents an event in which the tibia of the right foot is nearly perpendicular to the ground with the sole of the left foot touching the ground (TV: Tibia Vertical). P8 represents an event in which the heel of the right foot touches the ground (heel strike) (HS: Heel Strike). P8 corresponds to the end 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 those 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. The waveform processing unit 122 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%. By second normalizing the walking waveform data, it is possible to reduce the deviation of the walking phase from which the feature is extracted. 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 and normalizes 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 and normalizes 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 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 and normalizes 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/normalize the 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 the 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 the 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/normalize the 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/normalize the 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. 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, so long as they can be calculated using normalized gait waveform data. For example, the gait index calculation unit 123 calculates gait indices related to distance, height, angle, speed, time, frailty level, CPEI (Center of Pressure Exclusion Index), 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 a frailty level and a center of pressure exclusion index (CPEI) as the 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 such as a judgment result _R1 indicating health, a judgment result _R2 indicating a possibility of frailty, and a judgment result _R3 indicating a high possibility of frailty as the frailty level. The CPEI indicates an estimated value of a swelling rate of the movement of the center of foot pressure applied to the ground during the stance phase.

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 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 storage unit 124 also stores a disease risk estimation model (described later) that 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, and hyperlipidemia. For example, the specific diseases include lower back pain, sleep apnea syndrome, insomnia, depression, osteoarthritis of the knee, and Parkinson's syndrome. The specific diseases may include diseases other than those mentioned above. The storage 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 may not be used.

The storage unit 124 also stores a health measure estimation model that outputs health measures for a managed person in response to an input of a disease risk related to the managed person. For example, the health measure estimation model is a model that has been trained using a disease risk score and a data set of health measures as teacher data. For example, the health measure estimation model is a model that has been trained to output information including advice and comments from experts such as industrial physicians, public health nurses, physical therapists, doctors, and nurses in response to an input of a disease risk score. The health measures may be health measures directed at individual disease risks, or health measures directed at disease risks of multiple managed persons. For example, the health measure estimation model may be a model that outputs corporate health measures for multiple managed persons in response to an input of disease risks related to the multiple managed persons. For example, the health measure estimation model may be a model customized for each company. For example, the corporate health measures may include health measures according to the working style of the company. For example, the health measure estimation model may be a model customized according to the working style of the company. For example, the health measure estimation model may include a large-scale language model that outputs sentences including corporate health measures in response to an input of disease risks related to multiple managed persons.

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

The storage unit 124 also stores attributes of the managed persons. The attribute data includes gender, date of birth (age), height, and weight. The attribute data may be updated at any time. Furthermore, the storage unit 124 may store health check data of the managed persons. The health check data can be a factor in improving the accuracy of estimating disease risk scores and health measures. For example, the health check data of the managed persons includes diagnostic results for statutory items in the health check at the time of employment and regular health checks. The health check data of the managed persons may also include diagnostic results for 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 physical ability features extracted from the walking waveform data from the waveform processing unit 122. The physical ability estimation unit 125 also acquires attributes stored in the memory unit 124. The physical ability estimation unit 125 estimates a physical ability score using the physical ability features and attributes. The physical ability estimation unit 125 inputs the physical ability features and attributes of the managed person 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 walking phase of 100% corresponds to the timing of heel contact when switching from the end of swing phase T7 to the beginning of stance phase T1. The feature value of the walking waveform data at the walking phase of 100% 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) at the timing when the central axis of the foot is farthest from the axis of motion during the swing phase. Feature value E7 is the amount of circular motion normalized by the height of the person to be managed. 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 managed person 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 abilities of the managed person 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 managed person 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 managed person and stores it in the storage unit 124. The disease risk for each disease of the managed person 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 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 that uses attribute data, gait indices, and physical ability scores related to multiple managed persons as explanatory variables and a disease risk score related to a specific disease 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 angles around three axes (posture angles) 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 the managed person 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 the managed individual 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 on the managed person, gait index, and physical ability score.

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 _μ0 to the average annual number of medical receipts issued for the managed person μ. The disease risk estimation unit 126 calculates the disease risk score _RS1 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、管理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 managed person (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 proposed information generating unit 127 acquires disease risk scores for the managed persons. For example, the proposed information generating unit 127 acquires disease risk scores for specific diseases for multiple managed persons. For example, the proposed information generating unit 127 acquires disease risk scores for multiple specific diseases for multiple managed persons. The proposed information generating unit 127 inputs the acquired disease risk scores for the multiple managed persons into a health measure estimation model. The proposed information generating unit 127 generates proposed information according to health measures that are output from the health measure estimation model in response to the input of disease risk scores for the multiple managed persons.

The health measure estimation model 170 may be stored in an external storage device constructed in a cloud, a server, or the like. In this case, the proposal information generation unit 127 uses the health measure estimation model 170 via an interface (not shown) connected to the storage device. The health measure estimation model 170 is a machine learning model. For example, the health measure estimation model 170 is a model trained on a data set using disease risk scores for multiple subjects as explanatory variables and health measures as objective variables as training data.

For example, the health policy estimation model 170 is generated by learning using a linear regression algorithm. For example, the health policy estimation model 170 is generated by learning using a support vector machine (SVM) algorithm. For example, the health policy estimation model 170 is generated by learning using a Gaussian process regression (GPR) algorithm. For example, the health policy estimation model 170 is generated by learning using a random forest (RF) algorithm. For example, the health policy estimation model 170 may be generated by unsupervised learning that classifies the health measures of the managed individuals according to their disease risk scores. There are no particular limitations on the algorithm used to train the health policy estimation model 170.

For example, the health measure 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, it is possible to estimate the health measures of the managed individual even if there are some gaps in the disease risk score.

11 is a conceptual diagram showing an example of estimating a health measure using the health measure estimation model 170. The proposal information generation unit 127 inputs disease risk scores for multiple managed persons 1 to M to the health measure estimation model 170 (M is a natural number). In response to the input of disease risk scores for multiple managed persons 1 to M, the health measure estimation model 170 outputs at least one health measure 1 to N (N is a natural number). In the example of FIG. 11, the health measure estimation model 170 outputs at least one health measure 1 to N in response to the input of a disease risk score for a specific disease. The health measure estimation model 170 may be configured to output at least one health measure 1 to N in response to the input of disease risk scores for multiple specific diseases. The health measure estimation model 170 may also be configured to output at least one health measure 1 to N in response to the input of a disease risk score for at least one specific disease for a managed person.

For example, the proposed information generation unit 127 generates proposed information including at least one health measure for the company to which the managed person belongs. For example, the proposed information generation unit 127 applies the measure to a preset document format to generate the proposed information. For example, the proposed information generation unit 127 may generate the proposed information using a large-scale language model. Upon obtaining the proposed information, the company's health management officer can take action according to the proposed information.

For example, the proposal information generating unit 127 generates proposal information including a health measure such as periodically broadcasting music for exercises or broadcasting a voice encouraging employees to go home when it is time to finish work. For example, the proposal information generating unit 127 generates proposal information including a health measure such as turning off the lights on the work floor when it is time to finish work. For example, the proposal information generating unit 127 generates proposal information including a proposal to the company to reduce the salt content of food at the convenience store. For example, the proposal information generating unit 127 generates proposal information including health measures related to cafeteria menus and opening and closing times of smoking areas. For example, the proposal information generating unit 127 generates proposal information including a proposal to reduce cup noodles and increase salads for employees who are subject to management. For example, the proposal information generating unit 127 generates proposal information including a proposal to limit the use of elevators in order to encourage employees who are subject to management to exercise. For example, the proposal information generating unit 127 may generate health measures at a level related to corporate management. For example, the proposal information generating unit 127 may generate information in which the financial indicators of the company are visualized according to changes in the disease risk of employees who are subject to management.

The output unit 129 (output means) outputs the proposed information including the health measures estimated by the proposed information generation unit 127. For example, the output unit 129 outputs the proposed information to a terminal device or a server managed by the company to which the managed person belongs. For example, the output unit 129 may display the proposed information on the screen of the managed person's mobile terminal. For example, the output unit 129 may output the proposed information to an external system or the like that uses the proposed information. There are no particular limitations on the use of the output proposed information. For example, the proposed information may be used for statistical analysis, research on disease prevention, and the like.

For example, the information generating device 12 is connected to an external system built on a cloud or a server via a mobile terminal (not shown) carried by the person to be managed. 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 generating device 12 is connected to the mobile terminal via wireless communication. For example, the information generating 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 generating device 12 may conform to a standard other than Bluetooth (registered trademark) or WiFi (registered trademark). For example, the information generating device 12 may be connected to the mobile terminal via a wire such as a cable. The proposed information may be used by an application installed on the mobile terminal. In that case, the mobile terminal executes a process using the proposed information by application software or the like 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 generating device 12 included in the information providing system 1 will be described below. Fig. 12 is a flowchart for explaining an example of the operation of the information generating device 12. In the explanation of the process according to the flowchart of Fig. 12, the components of the information generating device 12 will be explained as the subject of the operation. The subject of the process according to the flowchart of Fig. 12 may be the information generating device 12.

In FIG. 12, first, the acquisition unit 121 acquires time series data of sensor data measured by the measurement device 10 mounted on the footwear of the person to be managed (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. 13 ).

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 managed person using the attribute data, gait index, and physical ability (step S14). When the disease risk is estimated without using physical ability, the disease risk estimation unit 126 estimates the disease risk of the managed person using the attribute data and gait index. The disease risk estimation unit 126 estimates the disease risk score of the managed person. 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 memory unit 124 accumulates the disease risk estimated for the managed individual (step S15). The disease risk accumulated in the memory unit 124 is used to estimate health measures. The disease risk may be accumulated in a database (not shown) connected to the information generating device 12.

Next, the proposed information generation unit 127 estimates health measures for at least one of the managed individuals using the disease risks stored in the storage unit 124 (step S16). The proposed information generation unit 127 generates proposed information including the estimated health measures.

Next, the output unit 129 outputs the proposed information including the generated health measures (step S17). For example, the output unit 129 outputs the proposed information to a terminal device or a server managed by the company to which the managed person belongs. For example, the output unit 129 outputs the proposed information to an external system or the like that uses the proposed information. For example, the output unit 129 may display the proposed information on the screen of the managed person's mobile terminal.

Note that attribute data of the managed persons does not necessarily have to be acquired. If attribute data is not acquired from the managed persons, a model can be used that estimates disease risk without using attribute data. Also, the managed persons may be asked in advance for consent to acquiring the attribute data. At that time, the benefits of acquiring the attribute data may be communicated to the managed persons, and consent to acquiring the attribute data may be encouraged. An example of a benefit here is that more accurate risk estimation results can be obtained.

[Gait index calculation process]
Next, the gait index calculation process (step S12 in FIG. 12 ) by the calculation unit 13 of the information generating device 12 will be described with reference to the drawings. FIG. 13 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. 13 , 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. 13 may be the information generating device 12 or the calculation unit 13.

In FIG. 13, 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.

(Application example)
Next, application examples according to the present embodiment will be described with reference to the drawings. In the following application examples, the relationship between a business providing a service using the information provision system 1, a company using the service, and employees corresponding to the managed persons of the company will be described. In the following, application examples 1 to 3 relating to three types of business forms will be described. The following business forms are examples, and do not limit the application of the information provision system 1. In addition, in the following, an example will be given in which a health measure estimation model customized to the working style of an employee who is a managed person is used. The health measure estimation model may be customized to the industry of the company (organization) to which the employee who is a managed person belongs. The proposed information generated by the information generation device 12 is not limited to the following examples, as long as it includes health measures for the employees who are managed.

The business provides the company with a service using the information provision system 1. Based on a contract concluded with the company, the business provides the company with proposed information including estimated health measures according to the employee's disease risk. The company pays the business a fee for the service using the information provision system 1. When employee health checkup data is used to estimate the health measures, the company provides the business with the employee health checkup data. In the contract between the business and the company, rules regarding the handling of personal information and appropriate data management are clarified. The business clearly explains that the proposed information is for reference only and does not guarantee medical accuracy or completeness.

Companies will fully explain to employees the details of their personal information protection policies and data management, and obtain consent from employees regarding the use of personal information and data. Furthermore, if there are any changes to the details of their personal information protection policies and data management, companies will explain the changes to their employees and obtain consent from them. For example, consent from employees will be obtained electronically. Companies will consider what health measures to provide to employees based on the content of the proposed information provided by business operators, and provide appropriate health measures to employees.

An employee is a person employed by a company. The employee is loaned or provided with a special insole equipped with the measuring device 10 by a business operator who has a contract with the company. The employee performs work while wearing shoes equipped with the special insoles and carrying a mobile terminal (not shown) capable of communicating with the measuring device 10. The mobile terminal uploads the sensor data measured by the measuring device 10 to the business operator's cloud server. The sensor data uploaded to the cloud server is used to estimate disease risks and health measures.

A terminal device (not shown) used by a company downloads proposed information including health measures from the business operator's cloud server. The company's manager refers to the health measures included in the proposed information and considers health measures for employees. For example, the company's manager periodically refers to the health measures included in the proposed information and considers countermeasures in response to changes in the health measures. For example, the company holds health consultation sessions and events and incorporates employees' opinions and requests regarding countermeasures in response to changes in health measures.

[Application Example 1]
FIG. 14 is a correlation diagram showing the relationship between the business operator, company A, and employees (managed persons) in the present disclosure. Company A is an industry in which many employees engage in desk work. In industries with a lot of desk work, employees often sit in the same position for long periods of time, and there is a risk that they will develop back pain. In addition, in industries with a lot of desk work, there are fewer opportunities to walk, which weakens leg muscles, and there is a risk that employees will develop lifestyle-related diseases such as obesity, diabetes, and high blood pressure.

FIG. 15 shows an example in which proposed information generated by the information generating device 12 is displayed on the screen of a terminal device 180A used by a manager who manages the health status of employees. The proposed information including health measures optimized for company A is displayed on the screen of the terminal device 180A. In the example of FIG. 15, proposed information including multiple health measures is displayed on the screen.

The first health measure is a suggestion that "We have a department with many employees who are at high risk of developing back pain. We suggest that you regularly do health exercises." For Company A, where most of the work is done at a desk, the risk of back pain tends to increase due to sitting for long periods of time. For example, for Company A, health measures that include the keyword "health exercises," which involves standing up and moving the body regularly, are inferred. For example, text other than the keyword "health exercises" is generated using templates or large-scale language models. The address of the link related to "health exercises" is displayed on the screen of terminal device 180A. The administrator can refer to the information at the link and consider whether to adopt "health exercises" as a health measure.

The second health measure is a proposal that reads, "There is a department with many employees who are at high risk of lifestyle-related diseases. We suggest that you increase the number of walking events." For Company A, where most of the work is done at a desk, there is a tendency for the risk of lifestyle-related diseases to increase due to weakened leg muscles. For example, for Company A, health measures that include the keyword "walking," which refers to walking long distances, are estimated. For example, text other than the keyword "walking" is generated using templates or large-scale language models. The address of the link related to "walking" is displayed on the screen of terminal device 180A. The administrator can refer to the information at the link and consider whether to adopt "walking" as a health measure.

[Application Example 2]
FIG. 16 is a correlation diagram showing the relationship between the business operator, company B, and employees (managed persons) in the present disclosure. Company B is a delivery company. Employees of the delivery company often perform physical labor such as carrying luggage stored in warehouses and luggage loaded on cargo vehicles. For example, employees are at risk of developing back pain due to repeated unnatural postures to lift heavy luggage. In addition, employees of the delivery company may repeatedly drink and eat excessively to satisfy hunger after work. Repeated overeating and drinking may cause the risk of developing various diseases such as diabetes, high blood pressure, nephrolithiasis, liver cirrhosis, arteriosclerosis, thromboembolism, dyslipidemia, hypercholesterolemia, and hyperlipidemia.

FIG. 17 shows an example in which proposed information generated by the information generating device 12 is displayed on the screen of a terminal device 180B used by a manager who manages the health status of employees. The proposed information including health measures optimized for company B is displayed on the screen of the terminal device 180B. In the example of FIG. 17, proposed information including multiple health measures optimized for company B is displayed on the screen.

The first health measure is a proposal that reads, "There is a department with many employees who are at high risk of back pain. We suggest that you hire a masseuse." For Company B, which has a lot of physical labor, the risk of back pain tends to increase due to repeated awkward postures when lifting heavy loads. For example, for Company B, health measures that include the keyword "massage therapist," who cares for employees' bodies at appropriate times, are estimated. For example, text other than the keyword "massage therapist" is generated using templates and large-scale language models. The address of the link related to "massage therapist" is displayed on the screen of terminal device 180B. The administrator can refer to the information at the link and consider whether to hire "massage therapist" as a health measure.

The second health measure is a proposal that reads, "There is a department with many employees who are at high risk for various diseases. We suggest that you regularly meet with a registered dietitian." For Company B, which has a lot of physical labor, there is a tendency for the risk of various diseases to increase due to repeated overeating and drinking to satisfy hunger after work. For example, for Company B, health measures that include the keyword "registered dietitian" who cares for employees' eating habits are estimated. For example, text other than the keyword "registered dietitian" is generated using templates and large-scale language models. The screen of terminal device 180B displays the address of the link related to "registered dietitian." The administrator can refer to the information at the link and consider whether to employ a "registered dietitian" as a health measure.

[Application Example 3]
FIG. 18 is a correlation diagram showing the relationship between the business operator, company C, and employees (managed persons) in the present disclosure. Company C is a retailer such as a supermarket. Employees who work as cashiers at supermarket stores often work for long periods of time while standing. Such a posture puts strain on the knees, and there is a risk of developing osteoarthritis in the future. In addition, in cashier work, since cashiers must deal with a variety of customers in succession, the mental burden accumulates, and there is a risk of developing mental illnesses such as insomnia and depression.

FIG. 19 shows an example in which proposed information generated by the information generating device 12 is displayed on the screen of a terminal device 180C used by a manager who manages the health status of employees. The proposed information including health measures optimized for company C is displayed on the screen of the terminal device 180C. In the example of FIG. 19, proposed information including multiple health measures optimized for company C is displayed on the screen.

The first health measure is a proposal that reads, "There is a department with many employees who are at high risk of osteoarthritis of the knee. I suggest that you install a training machine in the break room." For company C, the risk of osteoarthritis of the knee tends to increase due to working for long periods of time while standing. For example, for company C, health measures that include the keyword "training machine" that allows employees to train their legs during breaks are estimated. For example, text other than the keyword "training machine" is generated using a template or a large-scale language model. The address of the link related to "training machine" is displayed on the screen of terminal device 180C. The administrator can refer to the information at the link and consider whether to adopt "training machine" as a health measure.

The second health measure is a proposal that "There is a department with many employees who are at high risk of mental illness. We suggest that employees have regular interviews with a counselor." For company C, the risk of mental illness tends to increase due to continuously dealing with a variety of customers. For example, for company C, health measures including the keyword "counselor" who cares for the mental health of employees are estimated. For example, text other than the keyword "counselor" is generated using a template or a large-scale language model. The address of the link related to "counselor" is displayed on the screen of terminal device 180C. The administrator can refer to the information at the link and consider whether to adopt "counselor" as a health measure.

As described above, the information provision system of this embodiment includes a measurement device and an information generating device. The measurement device is installed in the footwear of at least one of the subjects. The measurement device measures acceleration and angular velocity. The measurement device generates sensor data using the measured acceleration and angular velocity. The measurement device transmits the generated sensor data to the information generating device. The information generating device includes an acquisition unit, a risk estimation unit, a proposed information generating 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 at least one managed person. The risk estimation unit estimates a disease risk for each disease for the at least one managed person using the acquired sensor data. The proposed information generation unit generates proposed information including health measures according to the disease risk for the at least one managed person. The output unit outputs the generated proposed information.

The information generating device of this embodiment estimates disease risk using sensor data including acceleration and angular velocity measured by a measuring device mounted on the footwear of the managed person. The information generating device of this embodiment generates suggested information including health measures according to the estimated disease risk. Therefore, according to this embodiment, it is possible to provide health measures according to the disease risk of the managed person engaged in daily work.

In order to maintain the health of people under management who belong to a company or other organization, it is preferable to continually implement health measures to improve lifestyle problems such as diet, exercise, and work. To achieve this, it is important for employees to feel the effects of taking actions in response to health measures and to have external motivation to continue the actions. In recent years, as part of health management, companies have been required to implement health measures that encourage employees to improve and maintain their lifestyle habits. However, it is difficult for a company to continually implement measures related to employees' lifestyle habits on its own.

The method of this embodiment can promote health management to improve the health awareness and lifestyle habits of the managed persons belonging to an organization and reduce the risk of diseases such as diabetes and high blood pressure. For example, the method of this embodiment can reduce the effort required to improve lifestyle habits in an organization by automatically suggesting and motivating actions that are tailored to various factors such as the attributes, industry, and working hours of the managed persons in multiple organizations.

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 proposed information generation unit estimates health measures corresponding to the disease risk score of at least one managed person using a health measure estimation model that outputs health measures in response to an input of a disease risk score. According to this aspect, by inputting a disease risk score into the health measure estimation model, it is possible to estimate health measures corresponding to the disease risk score of the managed person.

In one aspect of this embodiment, the proposal information generation unit estimates health measures according to the disease risk score of at least one managed person using a health measure estimation model customized to the working style of the managed person. According to this aspect, by using a health measure estimation model customized to the working style of the managed person, it is possible to estimate health measures optimized for the working style of the managed person.

In one aspect of this embodiment, the proposal information generation unit estimates health measures according to the disease risk score of at least one managed person using a health measure estimation model customized to the industry of the organization to which the managed person belongs. According to this aspect, by using a health measure estimation model customized to the industry of the organization to which the managed person belongs, it is possible to estimate health measures optimized for the industry of the organization.

In one aspect of this embodiment, the health measure estimation model and the disease risk estimation model are models trained using machine learning techniques. The disease risk 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 health measures according to the disease risk of the managed individual.

In one aspect of this embodiment, the information generating device displays proposed information including health measures optimized for the organization on the screen of a terminal device used in the organization to which the managed person belongs. According to this aspect, proposed information including health measures estimated according to the disease risk of the managed person can be provided in an optimized manner for the organization to which the managed person belongs.

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

(composition)
20 is a block diagram showing an example of a configuration of an information generating device 20 in the present disclosure. The information generating device 20 includes an acquiring unit 21, a risk estimating unit 25, a proposed information generating unit 27, and an output unit 29.

The acquisition unit 21 acquires sensor data including acceleration and angular velocity measured by a measuring device mounted on the footwear of at least one managed person. The risk estimation unit 25 uses the acquired sensor data to estimate a disease risk for each disease for at least one managed person. The proposed information generation unit 27 generates proposed information including health measures according to the disease risk for at least one managed person. The output unit 29 outputs the generated proposed information.

(Operation)
Next, the operation of the information generating device 20 will be described with reference to the drawings. Fig. 21 is a flowchart for explaining an example of the operation of the information generating device 20. In the explanation of the process according to the flowchart of Fig. 21, the components of the information generating device 20 will be explained as the subject of the operation. The subject of the process according to the flowchart of Fig. 21 may be the information generating device 20.

In FIG. 21, first, the acquisition unit 21 acquires sensor data including acceleration and angular velocity measured by a measuring device mounted on the footwear of at least one of the managed persons (step S21).

Next, the risk estimation unit 25 uses the acquired sensor data to estimate the disease risk for at least one managed person (step S22).

Next, the proposed information generation unit 27 generates proposed information including health measures according to the disease risk for at least one managed person (step S23).

Next, the output unit 29 outputs the generated proposal information (step S24).

As described above, the information generating device of this embodiment estimates disease risk using sensor data including acceleration and angular velocity measured by a measuring device mounted on the footwear of the managed person. The information generating device of this embodiment generates suggested information including health measures according to the estimated disease risk. Therefore, according to this embodiment, it is possible to provide health measures according to the disease risk of the managed person engaged in daily work.

(Hardware)
Next, a hardware configuration for executing control and processing according to each embodiment of the present disclosure will be described with reference to the drawings. Here, an information processing device 90 (computer) in Fig. 22 is given as an example of such a hardware configuration. The information processing device 90 in Fig. 22 is an example of a configuration for executing the control and processing according to each embodiment, and does not limit the scope of the present disclosure.

As shown in FIG. 22, 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. 22, 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 of each embodiment. 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 of each embodiment.

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 according to each embodiment of the present invention. The hardware configuration in FIG. 22 is an example of a hardware configuration for executing the control and processing according to each embodiment, and does not limit the scope of the present invention. Programs that cause a computer to execute the control and processing according to each embodiment are also included in the scope of the present invention.

The scope of the present invention also includes a program recording medium on which the program according to each embodiment is recorded. 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. When the program executed by the processor is recorded on a recording medium, the recording medium corresponds to a program recording medium.

The components of each embodiment may be combined in any manner. The components of each embodiment may be realized by software. The components of each embodiment may be realized by circuitry.

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 measurement device mounted on the footwear of at least one of the managed persons;
A risk estimation unit that estimates a disease risk for each disease of at least one of the managed individuals using the acquired sensor data;
a proposal information generating unit configured to generate proposal information including health measures according to a disease risk of at least one of the management subjects;
and an output unit that outputs the generated proposal 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 corresponding to the disease risk score output from the disease risk estimation model.
(Appendix 3)
The proposal information generation unit,
An information generating device as described in Appendix 2, which estimates the health measure according to the disease risk score of at least one of the managed persons using a health measure estimation model that outputs the health measure according to the input of the disease risk score.
(Appendix 4)
The proposal information generation unit,
4. The information generating device described in claim 3, which estimates the health measure according to the disease risk score of at least one of the managed persons using the health measure estimation model customized to suit the working style of the managed persons.
(Appendix 5)
The proposal information generation unit,
4. An information generation device as described in Appendix 3, which estimates the health measures according to the disease risk score of at least one of the managed persons using the health measure estimation model customized to the industry of the organization to which the managed persons belong.
(Appendix 6)
the health measure estimation model and the disease risk estimation model are models trained using a machine learning technique,
The disease risk estimation model is
4. The information generating apparatus of claim 3, comprising an incomplete heterogeneous variational autoencoder.
(Appendix 7)
An information generating device according to any one of Supplementary Notes 1 to 6;
The measuring device,
The measuring device includes:
An information provision system that is installed on the footwear of at least one of the managed persons, measures spatial acceleration and spatial angular velocity, generates sensor data using the measured spatial acceleration and spatial angular velocity, and transmits the generated sensor data to the information generation device.
(Appendix 8)
The information generating device includes:
An information providing system as described in Appendix 7, which displays the proposed information including the health measures optimized for the organization on a screen of a terminal device used in the organization to which the managed person belongs.
(Appendix 9)
The computer
Acquire sensor data including acceleration and angular velocity measured by a measuring device mounted on the footwear of at least one of the managed persons;
Using the acquired sensor data, estimate a disease risk for each disease for at least one of the managed individuals;
Generate proposal information including health measures according to a disease risk for at least one of the managed persons;
The information generating method outputs the generated proposal information.
(Appendix 10)
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 generating method described in Appendix 9, which estimates disease risk information according to the disease risk score output from the disease risk estimation model.
(Appendix 11)
An information generation method described in Appendix 10, which estimates the health measure corresponding to the disease risk score of at least one of the managed persons using a health measure estimation model that outputs the health measure in response to the input of the disease risk score.
(Appendix 12)
12. The information generation method described in claim 11, which estimates the health measure according to the disease risk score of at least one of the managed persons using the health measure estimation model customized to suit the working style of the managed persons.
(Appendix 13)
12. An information generation method as described in claim 11, which estimates the health measures according to the disease risk score of at least one of the managed persons using the health measure estimation model customized to the industry of the organization to which the managed persons belong.
(Appendix 14)
the health measure estimation model and the disease risk estimation model are models trained using a machine learning technique,
The disease risk estimation model is
12. The information generation method of claim 11, comprising an incomplete heterogeneous variational autoencoder.
(Appendix 15)
A process of acquiring sensor data including acceleration and angular velocity measured by a measuring device mounted on the footwear of at least one person to be managed;
A process of estimating a disease risk for each disease for at least one of the managed individuals using the acquired sensor data;
A process of generating proposal information including health measures according to a disease risk for at least one of the managed persons;
and a computer-readable non-transitory recording medium having recorded thereon a program for causing a computer to execute a process of outputting the generated proposal 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 described in Appendix 15, having a program recorded thereon to cause a computer to execute the following steps: estimating disease risk information according to the disease risk score output from the disease risk estimation model.
(Appendix 17)
A non-transitory computer-readable recording medium as described in Appendix 16, having recorded thereon a program for causing a computer to execute a process of estimating the health measure according to the disease risk score of at least one of the managed persons using a health measure estimation model that outputs the health measure according to the input of the disease risk score.
(Appendix 18)
18. A non-transitory computer-readable recording medium according to claim 17, having recorded thereon a program for causing a computer to execute a process of estimating the health measure according to the disease risk score of at least one of the managed persons, using the health measure estimation model customized to suit the working style of the managed persons.
(Appendix 19)
18. A non-transitory computer-readable recording medium according to claim 17, having recorded thereon a program for causing a computer to execute a process of estimating the health measure according to the disease risk score of at least one of the managed persons, using the health measure estimation model customized to the industry of the organization to which the managed persons belong.
(Appendix 20)
the health measure estimation model and the disease risk estimation model are models trained using a machine learning technique,
The disease risk estimation model is
20. The non-transitory computer-readable storage medium of claim 17, comprising an incomplete heterogeneous variational autoencoder.

REFERENCE SIGNS LIST 1 Information provision system 10 Measurement device 12 Information generation device 13 Calculation unit 14 Estimation unit 15 Risk estimation unit 20 Information generation device 21 Acquisition unit 25 Risk estimation unit 27 Proposed information generation unit 29 Output unit 110 Sensor 111 Acceleration sensor 112 Angular velocity sensor 113 Control unit 115 Communication unit 117 Power supply 121 Acquisition unit 122 Waveform processing unit 123 Gait index calculation unit 124 Memory unit 125 Physical ability estimation unit 126 Disease risk estimation unit 127 Proposed information generation unit 129 Output unit

Claims (20)

An acquisition unit that acquires sensor data including acceleration and angular velocity measured by a measurement device mounted on the footwear of at least one of the managed persons;
A risk estimation unit that estimates a disease risk for each disease of at least one of the managed individuals using the acquired sensor data;
a proposal information generating unit configured to generate proposal information including health measures according to a disease risk of at least one of the management subjects;
and an output unit that outputs the generated proposal information. The risk estimation unit is
a calculation unit that calculates a gait index using the sensor data;
2. The information generating device according to claim 1, further comprising: 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. The proposal information generation unit,
The information generating device according to claim 2 , wherein the health measure corresponding to the disease risk score of at least one of the managed persons is estimated using a health measure estimation model that outputs the health measure in response to an input of the disease risk score. The proposal information generation unit,
The information generating device according to claim 3 , wherein the health measure estimation model is customized to match the working style of the managed persons, and the health measure is estimated according to the disease risk score of at least one of the managed persons. The proposal information generation unit,
The information generating device according to claim 3 , wherein the health measure estimation model is customized to suit the industry of the organization to which the managed persons belong, and the health measure is estimated according to the disease risk score of at least one of the managed persons. the health measure estimation model and the disease risk estimation model are models trained using a machine learning technique,
The disease risk estimation model is
4. The information generating apparatus of claim 3, comprising an incomplete heterogeneous variational autoencoder. An information generating device according to any one of claims 1 to 6;
The measuring device,
The measuring device includes:
An information provision system that is installed on the footwear of at least one of the managed persons, 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 generation device. The information generating device includes:
8. The information providing system according to claim 7, wherein the proposed information including the health measure optimized for the organization is displayed on a screen of a terminal device used in an organization to which the person to be managed belongs. The computer
Acquire sensor data including acceleration and angular velocity measured by a measuring device mounted on the footwear of at least one of the managed persons;
Using the acquired sensor data, estimate a disease risk for each disease for at least one of the managed individuals;
Generate proposal information including health measures according to a disease risk for at least one of the managed persons;
The information generating method outputs the generated proposal information. 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 generating 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 information generation method according to claim 10, wherein the health measure corresponding to the disease risk score of at least one of the managed persons is estimated using a health measure estimation model that outputs the health measure according to the input of the disease risk score. The information generation method according to claim 11, wherein the health measure estimation model is customized to match the working style of the managed persons, and the health measure is estimated according to the disease risk score of at least one of the managed persons. The information generation method according to claim 11, in which the health measures according to the disease risk score of at least one of the managed persons are estimated using the health measure estimation model customized to the industry of the organization to which the managed persons belong. the health measure estimation model and the disease risk estimation model are models trained using a machine learning technique,
The disease risk estimation model is
The method of claim 11 comprising an incomplete heterogeneous variational autoencoder. A process of acquiring sensor data including acceleration and angular velocity measured by a measuring device mounted on the footwear of at least one person to be managed;
A process of estimating a disease risk for each disease for at least one of the managed individuals using the acquired sensor data;
A process of generating proposal information including health measures according to a disease risk for at least one of the managed persons;
and a computer-readable non-transitory recording medium having recorded thereon a program for causing a computer to execute a process of outputting the generated proposal 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 following steps: estimating disease risk information according to the disease risk score output from the disease risk estimation model. The non-transitory computer-readable recording medium according to claim 16, which has recorded thereon a program for causing a computer to execute a process of estimating the health measures according to the disease risk score of at least one of the managed persons, using a health measure estimation model that outputs the health measures according to the input of 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 health measures according to the disease risk score of at least one of the managed persons, using the health measure estimation model customized to the working style of the managed persons. The non-transitory computer-readable recording medium according to claim 17, which stores a program for causing a computer to execute a process of estimating the health measures according to the disease risk score of at least one of the managed persons, using the health measure estimation model customized to the industry of the organization to which the managed persons belong. the health measure estimation model and the disease risk estimation model are models trained using a machine learning technique,
The disease risk estimation model is
20. The non-transitory computer readable storage medium of claim 17, comprising an incomplete heterogeneous variational autoencoder.

Images