Map updating device, map generation system, map updating method, and recording medium

Abstract

The present invention provides a map updating device comprising: an acquisition unit that acquires sensor data measured by a measurement device attached to a user's footwear and position data corresponding to the position where the sensor data was acquired; a gait data generation unit that uses the sensor data to generate gait data; a path surface determination unit that uses the gait data to determine the path surface condition of a walking path; and an updating unit that associates the determined path surface condition with the position data, and updates a path surface map in which a display indicating the path surface condition at each position is set.

Description

Map update device, map generation system, map update method, and recording medium

[0001] The present disclosure relates to a map update device, a map generation system, a map update method, and a recording medium.

[0002] With growing interest in healthcare, services that provide information tailored to a user's health condition are gaining attention. For example, providing appropriate training advice is required to prevent users from becoming frail. In daily life, users walk on footpaths in a variety of walking environments. The surface conditions of the footpaths can vary widely, from asphalt to grass to sand. Different surface conditions affect the gait data measured during walking. Understanding the walking environment, including the surface conditions of the footpaths, will enable the provision of more appropriate training advice to elderly people.

[0003] Patent Literature 1 discloses a technology for recognizing road surface conditions based on a user's walking state. The technology disclosed in Patent Literature 1 recognizes road surface conditions using output values ​​of a sensor attached to a portable device carried by the user.

[0004] Japanese Patent Application Laid-Open No. 2020-140743

[0005] According to the method of Patent Document 1, the presence or absence of steps on a walkway can be determined using the output value of a sensor attached to a portable device. However, in the method of Patent Document 1, factors other than walking are added to the output value of the sensor attached to the portable device. Therefore, the method of Patent Document 1 does not necessarily determine the actual road surface condition of the walkway.

[0006] An object of the present disclosure is to provide a map update device, a map generation system, a map update method, and a recording medium that can provide a road surface map that makes it possible to grasp the road surface conditions of actual walking paths.

[0007] A map update device according to one aspect of the present disclosure includes an acquisition unit that acquires sensor data measured by a measuring device mounted on a user's footwear and position data corresponding to the position at which the sensor data was acquired, a gait data generation unit that generates gait data using the sensor data, a road surface determination unit that determines the road surface condition of the walking path using the gait data, and an update unit that associates the determined road surface condition with the position data and updates a road surface map that is set to show the road surface condition for each position.

[0008] In one aspect of the map generation method of the present disclosure, sensor data measured by a measuring device mounted on a user's footwear and position data corresponding to the position where the sensor data was acquired are acquired, gait data is generated using the acquired sensor data, the generated gait data is used to determine the road surface condition of the walkway, the determined road surface condition is associated with the position data, and a road surface map is updated that displays the road surface condition for each position.

[0009] A recording medium according to one embodiment of the present disclosure has recorded thereon a program that causes a computer to execute the following processes: acquiring sensor data measured by a measuring device mounted on a user's footwear and position data corresponding to the position at which the sensor data was acquired; generating gait data using the acquired sensor data; determining the road surface condition of the walking path using the generated gait data; and associating the determined road surface condition with the position data and updating a road surface map that is set to display the road surface condition for each position.

[0010] According to the present disclosure, it is possible to provide a map update device, a map generation system, a map update method, and a recording medium that can provide a road surface map that allows the actual road surface conditions of a walking path to be understood.

[0011] 1 is a block diagram showing an example of the configuration of a map generation system according to the present disclosure. FIG. 1 is a block diagram showing an example of the configuration of a measurement device according to the present disclosure. FIG. 2 is a conceptual diagram showing an example of the arrangement of a measurement device according to the present disclosure. FIG. 3 is a conceptual diagram for explaining a coordinate system set in the measurement device according to the present disclosure. FIG. 4 is a conceptual diagram for explaining an example of a human body surface. FIG. 5 is a conceptual diagram for explaining an example of a gait cycle. FIG. 6 is a block diagram showing an example of the configuration of a map update device according to the present disclosure. FIG. 7 is a conceptual diagram for explaining an example of the flow of sensor data and position data according to the present disclosure. FIG. 8 is a graph showing an example of a gait waveform in which features according to the road surface category of a walkway are expressed. FIG. 9 is a graph showing an example of a gait waveform in which features according to the road surface category of a walkway are expressed. FIG. 10 is a conceptual diagram for explaining an example of training of a road surface discrimination model according to the present disclosure. FIG. 11 is a conceptual diagram showing an example of estimating a road surface category using a road surface discrimination model according to the present disclosure. FIG. 12 is a conceptual diagram for explaining an example of training of a road surface discrimination model according to the present disclosure. FIG. 13 is a conceptual diagram for explaining an example of estimating a road surface category using a road surface discrimination model according to the present disclosure. FIG. 1 is a conceptual diagram showing an example of a road surface map according to the present disclosure. FIG. 2 is a table showing an example of updating a road surface category table according to the present disclosure. FIG. 3 is a conceptual diagram showing an example of updating a road surface map according to the present disclosure. FIG. 4 is a flowchart for explaining an example of operation of a map generation device according to the present disclosure. FIG. 5 is a conceptual diagram for explaining generation of a road surface map by a map generation device according to the present disclosure. FIG. 6 is a flowchart for explaining an example of operation of a map update device according to the present disclosure. FIG. 7 is a conceptual diagram showing an example of display of a road surface map updated by a map update device according to the present disclosure. FIG. 8 is a conceptual diagram showing an example of display of information including a road surface map updated by a map update device according to the present disclosure. FIG. 9 is a block diagram showing an example of the configuration of a map generation system according to the present disclosure. FIG. 10 is a block diagram showing an example of the configuration of a map update device according to the present disclosure.FIG. 1 is a conceptual diagram for explaining an example of collection of sensor data and position data in the present disclosure. FIG. 2 is a graph showing an example in which features according to the road surface category of a walkway appear in difference data of gait waveforms. FIG. 3 is a graph showing an example in which features according to the road surface category of a walkway appear in difference data of gait waveforms. FIG. 4 is a conceptual diagram for explaining an example of learning of a road surface discrimination model according to the present disclosure. FIG. 5 is a conceptual diagram showing an example of estimation of a road surface category using a road surface discrimination model according to the present disclosure. FIG. 6 is a flowchart for explaining an example of operation of a map updating device according to the present disclosure. FIG. 7 is a conceptual diagram showing an example of display of information including a road surface map updated by a map updating device according to the present disclosure. FIG. 8 is a conceptual diagram showing an example of display of information including a road surface map updated by a map updating device according to the present disclosure. FIG. 9 is a conceptual diagram showing an example of road surface category for each pixel included in a measurement accuracy range having a center of gravity at a position specified by position data. FIG. 10 is a conceptual diagram showing an example of change in road surface category for each pixel included in a measurement accuracy range having a center of gravity at a position specified by position data. FIG. 11 is a block diagram showing an example of the configuration of a map updating device according to the present disclosure. FIG. 12 is a flowchart for explaining an example of the operation of a map updating device according to the present disclosure. FIG. 13 is a block diagram showing an example of the configuration of hardware that executes control and processing according to the present disclosure.

[0012] Hereinafter, embodiments for carrying out the present disclosure will be described with reference to the drawings. In this disclosure, the drawings used in describing 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 manner that is technically preferable for carrying out the present disclosure, but the scope of the disclosure is not limited to the following. In all drawings used in describing the following embodiments, similar parts are designated by the same reference numerals unless otherwise specified. In the following embodiments, repeated description of similar configurations and operations may be omitted.

[0013] First Embodiment First, a map generation system according to this embodiment will be described with reference to the drawings. The map generation system of this embodiment acquires sensor data related to foot movements measured in accordance with the walking of a user who is the user of gait data measurement. The map generation system of this embodiment uses the acquired sensor data to determine the road surface condition of the walkway along which the user is walking. The map generation system of this embodiment updates a road surface map onto which the road surface condition of the walkway is mapped, according to the determined road surface condition.

[0014] In this embodiment, the road surface map is generated using image data such as satellite photographs, aerial photographs, and land parcel maps. Photographs taken from the sky, such as satellite photographs and aerial photographs, cannot determine the road surface condition of areas below obstacles such as roadside trees and footbridges. In this embodiment, the road surface condition of areas below obstacles such as roadside trees and footbridges is determined based on features appearing in the gait data of pedestrians walking in such areas. In this embodiment, the road surface condition of areas that could not be determined using photographs taken from the sky is interpolated using the pedestrian's gait data.

[0015] (Configuration) FIG. 1 is a block diagram showing an example of the configuration of a map generation system according to the present disclosure. The map generation system 1 includes a measurement device 10, a map update device 12, and a map generation device 14. For example, the measurement device 10 is attached to the footwear of a user whose gait is to be measured. The measurement device 10 is capable of communicating with a mobile device carried by the user. The mobile device carried by the user is connected to a server or a cloud via a network such as the Internet. For example, the map update device 12 and the map generation device 14 are installed on a server or a cloud. For example, the functions of the map update device 12 may be implemented in the mobile device carried by the user. When a pre-generated road surface map is used, the map generation system 1 may be composed of the measurement device 10 and the map update device 12. Below, the configurations of the measurement device 10, the map update device 12, and the map generation device 14 will be described individually.

[0016] [Measurement Device] Fig. 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 supply 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. Description 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.

[0017] The acceleration sensor 111 is a sensor that measures acceleration in three axial directions. The acceleration in three axial directions is also called spatial acceleration. The acceleration sensor 111 measures acceleration as a physical quantity related to foot movement. The acceleration sensor 111 outputs the measured acceleration to the control unit 113. There are no limitations on the sensor used as the acceleration sensor 111 as long as it can measure acceleration. For example, the acceleration sensor 111 may be a piezoelectric, piezo-resistive, or capacitive sensor.

[0018] The angular velocity sensor 112 is a sensor that measures angular velocity around three axes. The angular velocity around three axes is also called spatial angular velocity. The angular velocity sensor 112 measures angular velocity as a physical quantity related to foot movement. The angular velocity sensor 112 outputs the measured angular velocity to the control unit 113. There are no limitations on the sensor used as the angular velocity sensor 112 as long as it can measure angular velocity. For example, a vibration type, a capacitance type, or other type of sensor can be used as the angular velocity sensor 112.

[0019] The sensor 110 is realized, for example, by an inertial measurement unit (IMU) that measures acceleration and angular velocity. An example of an IMU is an inertial measurement unit (IMU). The IMU includes an acceleration sensor that measures acceleration in three axes and an angular velocity sensor that measures angular velocity around three axes. The sensor 110 may be realized by an inertial measurement unit such as a vertical gyro (VG) or an attitude heading reference system (AHRS). The sensor 110 may also be realized by a global positioning system (GPS) / inertial navigation system (INS). The sensor 110 may be realized by a device other than an inertial measurement unit as long as it can measure physical quantities related to foot movement. For example, the sensor 110 may include a pressure sensor that measures pressure applied by the sole of the foot.

[0020] FIG. 3 is a conceptual diagram showing an example in which the measurement device 10 is placed inside the shoes 100 of both feet. In the example of FIG. 3 , the measurement device 10 is placed at a position corresponding to the back 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 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 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 user or in an accessory such as an anklet worn by the user. 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 inside one of the shoes 100 as long as it can measure sensor data from which gait data can be generated.

[0021] In the example of FIG. 3 , a local coordinate system is set with the measurement device 10 (sensor 110) as the reference, and includes 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. In the present disclosure, the x-axis is positive to the left, the y-axis is positive to the rear, and the z-axis is positive to the up. FIG. 3 shows an example in which the same coordinate system is set for the left foot and the right foot. For example, if sensors 110 manufactured to the same specifications are placed in left and right shoes 100, the up-down orientations (Z-axis directions) of the sensors 110 placed in the left and right shoes 100 are the same. In this case, the three axes of the local coordinate system set for the sensor data originating from the left foot and the three axes of the local coordinate system set for the sensor data originating from the right foot are the same for the left and right.

[0022] FIG. 4 is a conceptual diagram illustrating the relationship between a local coordinate system (x-axis, y-axis, z-axis) set in the measurement device 10 (sensor 110) installed on the backside of the arch of the foot and a world coordinate system (x-axis, y-axis, z-axis) set relative to the ground. FIG. 4 shows the coordinate system set for the right foot. In the world coordinate system (x-axis, y-axis, z-axis), when the user is standing upright facing the direction of travel, the x-axis corresponds to the user's lateral direction, the y-axis corresponds to the user's front-to-back direction, and the z-axis corresponds to the direction of gravity. Note that the example in FIG. 4 conceptually illustrates the relationship between the local coordinate system (x-axis, y-axis, z-axis) and the world coordinate system (x-axis, y-axis, z-axis). The example in FIG. 4 does not accurately illustrate the relationship between the local coordinate system and the world coordinate system, which changes depending on the user's walking.

[0023] FIG. 5 is a conceptual diagram illustrating planes (also called human body planes) set for the human body. The sagittal plane is a plane that divides the body into left and right halves. The coronal plane is a plane that divides the body into front and back halves. The horizontal plane is a plane that divides the body horizontally. As shown in FIG. 5 , when the user is standing upright with the center lines of the feet pointing in the direction of travel, the world coordinate system and the local coordinate system are assumed to coincide. FIG. 5 shows an example in which the same coordinate system is set for the left and right feet. In this embodiment, rotation in the sagittal plane around the X-axis (x-axis) as the rotation axis is defined as roll, rotation in the coronal plane around the Y-axis (y-axis) as the rotation axis is defined as pitch, and rotation in the horizontal plane around the Z-axis (z-axis) as the rotation axis is defined as yaw. Furthermore, 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.

[0024] The control unit 113 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 detection of the user walking. For example, the control unit 113 starts measuring sensor data when it detects that either the left or right foot has started to move in the direction of travel after both feet have been at the same vertical height for a predetermined period of time. For example, the control unit 113 may cause the acceleration sensor 111 and the angular velocity sensor 112 to start measurement at a predetermined timing. For example, the control unit 113 may be configured to cause the acceleration sensor 111 and the angular velocity sensor 112 to start measurement in response to a measurement start signal transmitted from the map update device 12.

[0025] The control unit 113 acquires acceleration in three axial directions from the acceleration sensor 111. The control unit 113 also acquires angular velocities around three axes from the angular velocity sensor 112. For example, the control unit 113 performs analog-to-digital (AD) conversion on 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 referred to as 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 to digital data and angular velocity data converted to digital data. The acceleration data includes acceleration vectors in the three axial directions. The angular velocity data includes angular velocity vectors around three axes. The acceleration data and angular velocity data are associated with the time at which they were acquired. The control unit 113 may also apply corrections to the acceleration data and angular velocity data, such as correction for mounting errors, temperature correction, and linearity correction.

[0026] For example, the control unit 113 is realized by a microcomputer or microcontroller that performs overall control of the measurement device 10 and performs data processing. For example, the control unit 113 includes a CPU (Central Processing Unit), RAM (Random Access Memory), ROM (Read Only Memory), flash memory, etc. For example, the control unit 113 may calculate gait data (described later) using sensor data. In this case, the measurement device 10 outputs the calculated gait data to the map update device 12. For example, the control unit 113 may calculate gait indices (described later) using sensor data. In this case, the measurement device 10 outputs the calculated gait indices to the map update device 12. For example, the control unit 113 may calculate feature amounts used to estimate physical abilities (described later). In this case, the measurement device 10 outputs the calculated feature amounts to the map update device 12.

[0027] The communication unit 115 acquires sensor data from the control unit 113. The communication unit 115 transmits the acquired sensor data to the map update device 12. The timing of transmitting the sensor data is not particularly limited. For example, the communication unit 115 transmits the sensor data in real time in response to measurement of the sensor data. For example, the communication unit 115 transmits the sensor data at a predetermined transmission timing. For example, the communication unit 115 may store sensor data measured over a predetermined period and transmit the stored sensor data all at once at a predetermined timing. For example, the communication unit 115 may be configured to receive a measurement start signal from the map update device 12. In this case, the communication unit 115 outputs the received measurement start signal to the control unit 113.

[0028] For example, the communication unit 115 transmits the sensor data to the map update device 12 via wireless communication. For example, the communication unit 115 transmits the sensor data to the map update device 12 via a wireless communication function (not shown) conforming to standards such as Bluetooth (registered trademark) or Wi-Fi (registered trademark). The communication function of the communication unit 115 may also conform to standards other than Bluetooth (registered trademark) or Wi-Fi (registered trademark). The communication unit 115 may also transmit the sensor data to the map update device 12 via a wired connection such as a cable.

[0029] The power supply 117 is a battery that supplies power for operating the measuring device 10. For example, the power supply 117 may be a thin battery, such as a coin or button type. For example, the power supply 117 may be a primary battery, such as a lithium primary battery, a silver oxide battery, an alkaline button battery, or a zinc-air battery. When the power supply 117 is a primary battery, it is preferable that the power supply 117 be a long-life battery. The power supply 117 may also be a rechargeable secondary battery. When the power supply 117 is a secondary battery, the power supply 117 may be a battery that can be charged via a wired connection or a battery that can be powered wirelessly. If the power supply 117 is capable of wireless power supply, a wireless power supply device may be placed in a location where footwear is kept, such as an entrance or a shoe locker. In this case, by placing footwear equipped with the measuring device 10 on the wireless power supply device, the measuring device 10 can be appropriately charged when not in use.

[0030] Here, a gait cycle will be described with reference to the drawings. FIG. 6 is a conceptual diagram for explaining a step cycle based on the right foot. A step cycle based on the left foot is similar to that of the right foot. The horizontal axis of FIG. 6 indicates one step cycle of the right foot, starting from the point when the heel of the right foot hits the ground and ending from the point when the heel of the right foot hits the ground again. The horizontal axis of FIG. 6 is normalized with the step cycle set to 100%. Normalizing one gait cycle to 100% is called first normalization. One gait cycle of one leg is broadly divided into a stance phase, in which at least a portion of the sole of the foot is in contact with the ground, and a swing phase, in which the sole of the foot is off the ground. The stance phase is the period during which at least a portion of the sole of the foot is in contact with the ground. The stance phase is further divided into an early stance phase T1, a mid-stance phase T2, a final stance phase T3, and an early swing phase T4. The swing phase is the period during which the sole of the foot is off the ground. The swing phase is further divided into an early swing phase T5, a mid-swing phase T6, and a final swing phase T7. The horizontal axis in Figure 6 is normalized so that the stance phase is 60% and the swing phase is 40%. Normalizing 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 Figure 6 are merely examples and do not limit the periods that make up a gait cycle or the names of those periods.

[0031] As shown in FIG. 6 , multiple events occur during walking. Multiple events that occur during walking are also called walking events. P1 represents heel strike (HS). Heel strike is an event in which the heel of the right foot touches the ground. P2 represents opposite toe off (OTO). Opposite toe off is an event in which the toe of the left foot leaves the ground while the sole of the right foot is in contact with the ground. P3 represents heel rise (HR). Heel rise is an event in which the heel of the right foot lifts while the sole of the right foot is in contact with the ground. P4 represents opposite heel strike (OHS). Opposite heel strike is an event in which the heel of the left foot touches the ground. P5 represents toe off (TO). Toe-off is an event in which the toe of the right foot leaves the ground while the sole of the left foot is in contact with the ground. P6 represents foot adjacent (FA). Foot crossing is an event in which the left and right feet cross while the sole of the left foot is in contact with the ground. P7 represents tibia vertical (TV). Tibia vertical is an event in which the tibia of the right foot becomes approximately perpendicular to the ground while the sole of the left foot is in contact with the ground. P8 represents heel strike. P8 corresponds to the end point of the gait cycle that begins with P1 and the start point of the next gait cycle. Note that the gait events shown in FIG. 6 are merely examples and do not limit the events that occur during walking or the names of these events.

[0032] 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 heel strike timing corresponds to the maximum peak of the walking waveform data for one step cycle. The section between consecutive heel strikes corresponds to one step cycle. The timing of toe lift 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 timing midway between the timing of the minimum roll angle and the timing of the maximum roll angle corresponds to the mid-stance phase.

[0033] [Map Update Device] Fig. 7 is a block diagram showing an example of the configuration of a map update device according to the present disclosure. The map update device 12 includes an acquisition unit 121, a determination unit 122, a gait data generation unit 123, a road surface determination unit 125, an update unit 126, and an output unit 127. For example, the map update device 12 is built on a server or a cloud. For example, the functions of the map update device 12 may be implemented in a mobile terminal carried by a user.

[0034] The map updating device 12 also stores a road surface category table 132 and a road surface map 136. The road surface category table 132 is a table showing the correspondence between road surface categories, which indicate road surface conditions, and location data. The road surface map 136 is a map in which road surface categories are mapped for each location indicated by location data. In this embodiment, the road surface category table 132 and the road surface map 136 are generated in advance by the map generating device 14. For example, the road surface category table 132 and the road surface map 136 are stored in the storage unit 130. The road surface category table 132 and the road surface map 136 may also be stored in a storage device (not shown) accessible from the map updating device 12. In this case, the map updating device 12 accesses the road surface category table 132 and the road surface map 136 via an interface (not shown) connected via a network. For example, such an interface is realized by an API (Application Programming Interface).

[0035] The road surface category includes a reference road surface that serves as a reference. The reference road surface is a road surface that serves as a reference for the road surface condition of a walkway. For example, the reference road surface is a walkway with a vinyl-coated surface that is easy to walk on, such as an indoor corridor. For example, road surface categories are classified according to road surfaces that exhibit walking characteristics, such as asphalt, grass, and sand. For example, road surface categories may be classified according to the slope, unevenness, or steps of the road surface. Furthermore, road surface categories may be classified according to the slipperiness of the road surface, such as the degree of wetness or dryness of the road surface. Depending on the road surface category of the walkway, the characteristics of walking on that walkway are reflected in the gait waveform. In other words, by using gait data measured according to the user's walking, the road surface category of the road surface on which the user walked can be determined.

[0036] The map updating device 12 also has a road surface discrimination model 152. For example, the road surface discrimination model 152 may be stored in the storage unit 130. The road surface discrimination model 152 may also be stored in a storage device (not shown) accessible from the map updating device 12. In this case, the map updating device 12 uses the road surface discrimination model 152 via an interface (not shown), such as an API, connected via a network.

[0037] The acquisition unit 121 acquires sensor data from the measurement device 10 mounted on the user's footwear. The acquisition unit 121 receives the sensor data measured by the measurement device 10 from a mobile device (not shown) used by the user via wireless communication. The sensor data includes location information of the mobile device that is the sender of the sensor data. The location data includes latitude and longitude measured by a location measurement means such as a GPS (Global Positioning System). For example, the location information is measured using the GPS function mounted on the mobile device and added to the sensor data.

[0038] For example, the acquisition unit 121 receives sensor data from a mobile terminal via a wireless communication function (not shown) conforming to standards such as Bluetooth (registered trademark) or Wi-Fi (registered trademark). As long as the acquisition unit 121 can communicate with the mobile terminal, the communication function may conform to standards other than Bluetooth (registered trademark) or Wi-Fi (registered trademark). The acquisition unit 121 may receive sensor data from the mobile terminal via a wired connection such as a cable. For example, the acquisition unit 121 may acquire gait data, gait indices, and feature amounts calculated by the measurement device 10.

[0039] FIG. 8 is a conceptual diagram for explaining an example of the flow of sensor data and position data in the present disclosure. A measurement device 10 is disposed in a shoe 100 worn by a user. In the example of FIG. 8, the measurement device 10 is disposed at a position that contacts the sole of the user's arch. Sensor data measured by the measurement device 10 as the user walks is transmitted to a mobile terminal 170 carried by the user. The mobile terminal 170 receives the sensor data transmitted from the measurement device 10. The mobile terminal 170 adds position data to the received sensor data. The position data includes longitude information and latitude information corresponding to the position where the sensor data was measured. The mobile terminal 170 transmits the sensor data with the added position data to the map update device 12.

[0040] The determination unit 122 acquires position data from the acquisition unit 121. The determination unit 122 references the road surface category table 132 and determines whether the road surface category corresponding to the acquired position data is registered in the road surface category table 132. If the road surface category corresponding to the acquired position data is not registered in the road surface category table 132, the determination unit 122 outputs a data generation instruction to the gait data generation unit 123 to determine the road surface category of the position data. Furthermore, the determination unit 122 outputs position data corresponding to the position for which the road surface category is being determined to the update unit 126.

[0041] If the road surface category corresponding to the acquired position data is registered in the road surface category table 132, the determination unit 122 does not execute processing. For example, the determination unit 122 may be configured to output a data generation instruction to the gait data generation unit 123 to determine the road surface category of the acquired position data depending on the amount of time that has elapsed since the road surface category corresponding to the position data was updated. If the determination unit 122 is configured in this manner, it can also handle situations where the registered road surface category changes. The timing for updating the road surface category can be set arbitrarily. For example, the timing for updating the road surface category may be set every three months in accordance with the changing seasons. For example, the timing for updating the road surface category may be set in accordance with changes in weather such as rain or snow.

[0042] The gait data generation unit 123 acquires a data generation instruction from the determination unit 122. In response to the data generation instruction, the gait data generation unit 123 acquires sensor data from the acquisition unit 121. The gait data generation unit 123 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 included in the sensor data. The time series data for one walking cycle is also referred to as gait waveform data. The gait data generation unit 123 extracts gait waveform data based on the timing of walking events detected from the time series data of the sensor data. For example, the gait data generation unit 123 extracts gait waveform data that starts at the timing of a heel strike and ends at the timing of the next heel strike.

[0043] The gait data generation unit 123 normalizes (first normalization) the time of the extracted walking waveform data for one step cycle to a walking cycle of 0 to 100% (percent). The timing of 1%, 10%, etc. included in the 0 to 100% walking cycle is also called a walking phase. Furthermore, with respect to the first-normalized walking waveform data for one step cycle, the gait data generation unit 123 normalizes (second normalization) the data so that the stance phase is 60% and the swing phase is 40%. By subjecting the walking waveform data to second normalization, it is possible to reduce the discrepancy in the walking phases from which feature values ​​are extracted.

[0044] For example, the gait data generation unit 123 extracts gait waveform data for one step gait cycle using the traveling acceleration (Y-direction acceleration). The gait data generation unit 123 extracts gait waveform data for one step gait cycle with respect to accelerations / angular velocities / angles other than the traveling acceleration (Y-direction acceleration) in accordance with the gait cycle of the traveling acceleration (Y-direction acceleration). The gait data generation unit 123 extracts gait waveform data related to accelerations in three axial directions, gait waveform data related to angular velocities around three axes, and gait waveform data related to angles around three axes. The gait data generation unit 123 normalizes the extracted gait waveform data for one step gait cycle. The gait data generation unit 123 may generate time series data of angles around three axes by integrating time series data of angular velocities around three axes.

[0045] The gait data generation unit 123 may extract gait waveform data for one step cycle using acceleration / angular velocity other than forward acceleration (Y-direction acceleration). For example, the gait data generation unit 123 may detect heel strike and toe lift from time-series data of vertical acceleration (Z-direction acceleration). The timing of heel strike is the timing of a steep minimum peak that appears in the time-series data of vertical acceleration (Z-direction acceleration). At the timing of the steep minimum peak, the value of vertical acceleration (Z-direction acceleration) becomes approximately zero. The minimum peak that marks the timing of heel strike corresponds to the minimum peak of the gait waveform data for one step cycle. The section between consecutive heel strikes constitutes a step cycle. The timing of toe lift is the timing of an inflection point in the time-series data of vertical acceleration (Z-direction acceleration) that gradually increases after passing through a section of small fluctuation following the maximum peak immediately after heel strike. The gait data generator 123 may also extract gait waveform data for one step cycle using both the forward acceleration (Y-direction acceleration) and the vertical acceleration (Z-direction acceleration).The gait data generator 123 may also extract gait waveform data for one step cycle using accelerations, angular velocities, angles, etc. other than the forward acceleration (Y-direction acceleration) and the vertical acceleration (Z-direction acceleration).

[0046] For example, the gait data generation unit 123 calculates gait indices using normalized walking waveform data. For example, the gait indices are used to estimate physical ability, etc. There are no particular limitations on the gait indices calculated by the gait data generation unit 123. For example, the gait data generation unit 123 calculates gait indices related to distance, height, angle, speed, time, CPEI (Center of Pressure Exclusion Index), frailty level, etc. Representative gait indices are listed below. Specific methods for calculating the following gait indices will be omitted.

[0047] For example, the gait data generation unit 123 calculates indices related to distance and height as gait indices. For example, the gait data generation 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 separated outward in the direction of travel during the swing phase. Foot lift height indicates the maximum distance between the measurement 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.

[0048] For example, the gait data generation unit 123 calculates angle-related indices as gait indices. For example, the gait data generation unit 123 calculates the contact angle, the takeoff angle, the toe direction, the heel-strike roll angle, the toe-off roll angle, the swing leg peak angular velocity, and the hallux angle. The contact angle indicates the maximum value of the angle between the sole of the foot and the ground at heel-strike. The takeoff 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 orientation of the toe relative to the direction of forward motion during the swing phase. The heel-strike roll angle is the angle between the ankle and the ground at heel-strike, 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 during the period 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 and the center line of the first proximal phalanx.

[0049] For example, the gait data generation unit 123 calculates indices related to speed as gait indices. For example, the gait data generation 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.

[0050] For example, the gait data generation unit 123 calculates time-related indices as gait indices. For example, the gait data generation unit 123 calculates stance time, load-bearing time, sole contact time, push-off time, swing time, and DST (Double Support Time). Stance time indicates the time during which the foot is in contact with the ground during walking. Stance time is the sum of load-bearing time, sole contact time, and push-off time. Load-bearing time is the time during the stance phase from when the heel contacts the ground to when the toe contacts the ground. Sole contact time is the time during the stance phase when the entire sole of the foot is in contact with the ground and is horizontal to the ground. Push-off time is the time during the stance phase from when the sole is in contact with the ground to when the toe pushes off the ground. Swing time indicates the time during which the foot is off the ground during walking. DST is divided into DST1 and DST2. DST1 indicates the time during which the foot equipped with the measuring device 10 (sensor 110) is in front of the other foot during a period when both feet are in contact with the ground at the same time, and DST2 indicates the time during which the foot equipped with the measuring device 10 (sensor 110) is behind the other foot during a period when both feet are in contact with the ground at the same time.

[0051] For example, the gait data generator 123 calculates a center of pressure exclusion index (CPEI) as a gait index. The CPEI indicates an estimated rate of expansion of the center of foot pressure applied to the ground during the stance phase.

[0052] For example, the gait data generation unit 123 calculates a frailty level as a gait index. The frailty level is an estimated value of a frailty state according to a walking state. For example, the gait data generation unit 123 estimates an index indicating a determination result regarding frailty as the frailty level. If there is no possibility of frailty, the gait data generation unit 123 estimates an index indicating that the subject is not frail. If there is a possibility of frailty, the gait data generation unit 123 estimates an index indicating that the subject is likely to be frail. Furthermore, if there is a high possibility of frailty, the gait data generation unit 123 estimates an index indicating that there is a high possibility of frailty.

[0053] The gait data generation unit 123 may extract feature amounts used to calculate or estimate gait indices from the walking waveform data. For example, the gait data generation unit 123 extracts feature amounts for each walking phase cluster according to preset conditions. A walking phase cluster is a cluster that integrates temporally consecutive walking phases. A walking phase cluster includes at least one walking phase. A walking phase cluster may also include a single walking phase. The gait data generation unit 123 may extract physical ability feature amounts used to estimate physical abilities. For example, the physical ability feature amounts are 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 ability, and static balance.

[0054] The gait data generation unit 123 outputs gait data including normalized gait waveform data, gait indices, and feature amounts to the road surface discrimination unit 125. The gait data generation unit 123 outputs gait data including at least any one of the normalized gait waveform data, gait indices, and feature amounts to the road surface discrimination unit 125.

[0055] The road surface determination unit 125 acquires gait data from the gait data generation unit 123. The road surface determination unit 125 uses the acquired gait data to determine the road surface condition of the walkway along which the user is walking. The road surface determination unit 125 uses the road surface determination model 152 to determine a road surface category that indicates the road surface condition of the walkway along which the user is walking. The road surface determination unit 125 outputs the determined road surface category to the update unit 126.

[0056] The road surface discrimination model 152 is a machine learning model. For example, the road surface discrimination model 152 is a model trained using a dataset in which gait data is used as an explanatory variable and road surface categories are used as objective variables (labels) as training data. For example, the road surface discrimination model 152 is a learning model trained using a convolutional neural network (CNN) technique. For example, the road surface discrimination model 152 is a model trained using a principal component analysis (PCA) technique. For example, the road surface discrimination model 152 is a learning model trained using a variational autoencoder (VAE). For example, the road surface discrimination model 152 is a learning model trained using a conditional generative adversarial network (GAN) technique. The above techniques are merely examples and do not limit the techniques for training the road surface discrimination model 152.

[0057] In response to input gait data, road surface discrimination model 152 outputs a road surface category corresponding to the gait data. Road surface discrimination model 152 may be stored in an external storage device constructed in the cloud, a server, or the like. In this case, road surface discrimination unit 125 uses road surface discrimination model 152 via an interface (not shown) connected to the storage device.

[0058] 9 and 10 are graphs showing an example of gait waveforms that reflect characteristics according to the surface category of a walkway. In FIGS. 9 and 10, the reference surface is a vinyl-coated floor. FIGS. 9 and 10 show gait waveforms that are graphs of the average of two 10-meter walking tests conducted by nine subjects. FIG. 9 shows a gait waveform (dashed line) measured while walking on a walkway with a reference surface and a gait waveform (solid line) measured while walking on a grass walkway, superimposed on each other. FIG. 10 shows a gait waveform (dashed line) measured while walking on a walkway with a reference surface and a gait waveform (solid line) measured while walking on a sand walkway, superimposed on each other. By comparing the gait waveforms with the reference surface, as shown within the dashed-dotted circles in FIGS. 9 and 10, it is possible to understand that characteristics according to the walkway are present. The surface condition of a walkway can be estimated using a machine learning model that has learned characteristics according to the walkway.

[0059] Fig. 11 is a conceptual diagram for explaining an example of learning a road surface discrimination model according to the present disclosure. In the example of Fig. 11, a dataset in which gait data is used as an explanatory variable and road surface category is used as a target variable (label) is used as training data to train a road surface discrimination model 152. A description of a learning device (not shown) that trains the road surface discrimination model 152 will be omitted. The road surface condition of the walkway corresponding to gait data 1 is road surface category a. The road surface condition of the walkway corresponding to gait data 2 is road surface category b. The road surface condition of the walkway corresponding to gait data K is road surface category k.

[0060] 12 is a conceptual diagram showing an example of estimation of a road surface category using the road surface discrimination model according to the present disclosure. In response to input gait data, road surface discrimination model 152 outputs a road surface category corresponding to the gait data.

[0061] FIG. 13 is a conceptual diagram illustrating an example of learning a road surface discrimination model according to the present disclosure. FIG. 13 illustrates an example of discriminating a road surface category using gait data affected by weather. Weather is identified by weather conditions that may affect walking, such as sunny, rainy, or snowy. For example, when it is raining or snowing, the characteristics expressed in gait data differ between an asphalt walkway and a sandy walkway. For example, when the road surface is wet even on a sunny day, the road surface category may be discriminated based on the elapsed time since the rain stopped. FIG. 13 illustrates an example of training a model that discriminates road surface conditions using gait data measured under various weather conditions. In the example of FIG. 13 , training data is a dataset containing weather data indicating the weather, gait data measured under that weather (explanatory variables), and the road surface category of the walkway at the time the gait data was measured (objective variable). Gait characteristics corresponding to the road surface category of the walkway vary among individuals. Therefore, it is preferable that the training data be a dataset measured for each of multiple subjects. In the example of Figure 13, road surface discrimination model 152-1 is trained using a data set of weather data and gait data (explanatory variables) and the road surface category of the walkway at the time the gait data was measured (objective variable) as training data.

[0062] FIG. 14 is a conceptual diagram illustrating an example of gait data correction using a road surface discrimination model according to the present disclosure. FIG. 14 illustrates an example in which the road surface discrimination model 152-1 of FIG. 13 is used. Gait data and weather data are input to the road surface discrimination model 152-1. For example, the weather data is acquired from an application that provides weather forecast data or weather information. The road surface discrimination model 152-1 outputs a road surface category in response to the input gait data and weather data. Even if gait data affected by the weather is input, the road surface discrimination model 152-1 can discriminate the road surface category without being affected by the weather. In other words, the road surface discrimination model 152-1 can accurately discriminate the road surface category using a variety of gait data that changes depending on the weather.

[0063] FIG. 15 is a conceptual diagram illustrating an example of learning a road surface discrimination model according to the present disclosure. FIG. 15 illustrates an example of discriminating road surface categories using gait data influenced by seasons. A person's walking state may change depending on environmental factors such as seasonal temperature and humidity. Therefore, seasons are identified by seasons that may affect walking state, such as spring, summer, autumn, and winter. For example, seasons may include rainy seasons such as the rainy season and autumn rains. FIG. 15 illustrates an example of training a model that discriminates road surface conditions using gait data measured in various seasons. In the example of FIG. 15 , training data is a dataset of seasonal data indicating the season, gait data (explanatory variables) measured in that season, and the road surface category (objective variable) of the walkway at the time the gait data was measured. Gait characteristics according to the road surface category of the walkway vary among individuals. Therefore, it is preferable that the training data be a dataset measured for each of multiple subjects. In the example of Figure 15, a road surface discrimination model 152-2 is trained using a data set of seasonal data and gait data (explanatory variables) and the road surface category of the walkway at the time the gait data was measured (objective variable) as training data.

[0064] FIG. 16 is a conceptual diagram illustrating an example of gait data correction using a road surface discrimination model according to the present disclosure. FIG. 16 illustrates an example in which the road surface discrimination model 152-2 of FIG. 15 is used. Gait data and seasonal data are input to the road surface discrimination model 152-2. For example, the seasonal data is identified by the date and month on which the sensor data was measured. For example, location data may be used to identify the seasonal data. Using location data makes it possible to more accurately identify the season for each location. The road surface discrimination model 152-2 outputs a road surface category in response to input gait data and seasonal data. Even if gait data influenced by the season is input, the road surface discrimination model 152-2 can discriminate the road surface category regardless of the influence of the season. In other words, the road surface discrimination model 152-2 can accurately discriminate the road surface category using a variety of gait data that changes with the season.

[0065] The road surface discriminator 125 may be configured to determine the road surface condition of the walkway along which the user is walking based on the similarity. For example, the road surface discriminator 125 calculates the similarity between gait data measured on road surfaces of various road surface categories and gait data measured in response to the user's walking. For example, the road surface discriminator 125 calculates, as the similarity, the cosine similarity between gait waveforms measured on road surfaces of various road surface categories and gait waveforms measured in response to the user's walking. The road surface discriminator 125 determines that the road surface category of the road surface along which the user is walking is the road surface category with the largest similarity. For example, the road surface discriminator 125 may be configured to determine that the road surface category of the road surface along which the user is walking includes multiple road surface categories whose similarity exceeds a predetermined threshold.

[0066] The road surface discriminator 125 may be configured to determine the road surface condition of the walkway on which the user is walking based on a correlation coefficient. For example, the road surface discriminator 125 calculates the similarity between gait data measured on road surfaces of various road surface categories and gait data measured in response to the user's walking. For example, the road surface discriminator 125 calculates, as the correlation coefficient, a correlation coefficient between gait waveforms measured on road surfaces of various road surface categories and gait waveforms measured in response to the user's walking. The road surface discriminator 125 determines that the road surface category of the road surface on which the user is walking is the road surface category with the largest correlation coefficient. For example, the road surface discriminator 125 may be configured to determine that the road surface category of the road surface on which the user is walking includes multiple road surface categories whose correlation coefficients exceed a predetermined threshold.

[0067] The update unit 126 acquires position data from the determination unit 122. The update unit 126 also acquires a road surface category from the road surface determination unit 125. The update unit 126 associates the position data with the road surface category and registers the association in the road surface category table 132. The update unit 126 also reflects the road surface category at the position of the position data in the road surface map 136. That is, the update unit 126 associates the position data with the road surface category and updates the road surface category table 132 and the road surface map 136. For example, the update unit 126 may be configured to update the road surface map 136 using a machine learning model. For example, such a machine learning model outputs the road surface map 136, in which the road surface category has been updated to a position on the map data, in response to input of the position data, the road surface category, and the road surface map 136.

[0068] 17 is a table showing an example of a road surface category table in the present disclosure. In the road surface category table 132, position data A is associated with road surface category a. Position data B is associated with road surface category b. Position data C is associated with road surface category c. However, position data P is not associated with a road surface category. In other words, in the example of FIG. 17 , the road surface category at the position of position data P is unknown.

[0069] Fig. 18 is a conceptual diagram showing an example of a road surface map in the present disclosure. The road surface map in Fig. 18 reflects the road surface categories registered in the road surface category table in Fig. 17. Different hatching is set in the road surface map 136 according to the road surface category. In the road surface map 136, the area R whose road surface category is asphalt is shown. A , the area R where the road surface category is grass G , area R where the road surface category is sand S In addition, the road surface map 136 displays nA, where the road surface category has not been determined. M is displayed.

[0070] Fig. 19 is a table showing an example of a road surface category table in the present disclosure. Fig. 19 shows an example in which the road surface category at the position of position data P is determined in the examples of Figs. 17 and 18. The position data P is associated with a road surface category p. That is, in the example of Fig. 19, the road surface category at the position of position data P is identified.

[0071] Fig. 20 is a conceptual diagram showing an example of a road surface map in the present disclosure. The road surface map in Fig. 20 reflects the road surface categories registered in the road surface category table in Fig. 19. That is, in the example of Fig. 20, the missing area A in the example of Fig. 18 is M In the example of FIG. 18, the road surface category of the missing area A is specified. M The area that was U is displayed as:

[0072] The output unit 127 outputs the road surface map 136 that has been updated by the update unit 126. For example, the output unit 127 outputs the road surface map 136 to a mobile terminal 170 carried by the user. For example, the road surface map 136 output to the mobile terminal 170 is displayed on the screen of the mobile terminal 170. Information about the road surface map 136 may be displayed on the screen of the mobile terminal 170. For example, the information about the road surface map 136 includes advice according to the road surface conditions in the range included in the road surface map 136. For example, the information about the road surface map 136 includes requests according to the road surface conditions in the range included in the road surface map 136. Note that the information about the road surface map 136 may include information that is not advice or requests, as long as it is related to the road surface map 136. For example, the output unit 127 may be configured to output the road surface map 136 to a terminal device or a server that uses the road surface map 136. For example, the output unit 127 may be configured to output the road surface map 136 to an external system that uses the road surface map 136. There are no particular limitations on how the road surface map 136 is used.

[0073] For example, the output unit 127 is constructed in a cloud or a server connected to a mobile terminal 170 carried by a user via a communication network. The mobile terminal 170 is a portable communication device. For example, the mobile terminal 170 is a portable communication device having a communication function, such as a smartphone, a smart watch, or a mobile phone. For example, the output unit 127 is connected to the mobile terminal 170 via wireless communication. For example, the output unit 127 is connected to the mobile terminal 170 via a wireless communication device (not shown) conforming to standards such as Bluetooth (registered trademark) or Wi-Fi (registered trademark). Note that the wireless communication device may conform to standards other than Bluetooth (registered trademark) or Wi-Fi (registered trademark). The road surface map 136 may be used by an application installed on the mobile terminal 170. For example, the mobile terminal 170 executes processing using the road surface map 136 using an application installed on the mobile terminal 170.

[0074] [Map Generation Device] Fig. 21 is a block diagram illustrating an example of the configuration of a map generation device according to the present disclosure. Fig. 22 is a conceptual diagram showing an example of the flow of data during map generation by the map generation device according to the present disclosure. The map generation device 14 includes an image acquisition unit 141, a road surface identification unit 142, a map generation unit 146, and an output unit 147. The map generation device 14 also includes a road surface identification model 154.

[0075] The image acquisition unit 141 acquires map data for a target area for generating a road surface map. The image acquisition unit 141 outputs the acquired map data to the road surface identification unit 142. For example, the map data is image data including photographs taken from above, such as satellite photographs or aerial photographs. For example, the map data may be a map such as a land parcel map. A position in the map data can be specified by longitude and latitude. That is, a position included in the map data is associated with position data including longitude and latitude. For example, a configuration may be adopted in which position data (longitude and latitude) in a global coordinate system is associated with a reference position in the map data, and the position data of any position is specified using the relative coordinate system of the map data.

[0076] The road surface identification model 154 is a machine learning model that has been trained in advance by machine learning. In response to input image data, the road surface identification model 145 identifies a road surface category based on features contained in the image data. The road surface identification model 145 identifies a road surface category for each position in the image data. The road surface identification model 154 is a model trained using a data set that uses image data as an explanatory variable and the road surface category for each position contained in the image data as a target variable (label), as training data. The position data includes latitude and longitude measured by GPS or the like. A description of a learning device (not shown) that trains the road surface identification model 154 will be omitted.

[0077] For example, the road surface identification model 154 may be generated by learning using a linear regression algorithm. For example, the road surface identification model 154 may be generated by learning using a support vector machine (SVM) algorithm. For example, the road surface identification model 154 may be generated by learning using a Gaussian process regression (GPR) algorithm. For example, the road surface identification model 154 may be generated by learning using a random forest (RF) algorithm. For example, the road surface identification model 154 is a learning model trained using a convolutional neural network (CNN) method. For example, the road surface identification model 154 is a model trained using a principal component analysis (PCA) method. For example, the road surface identification model 154 is a learning model trained using a variational autoencoder (VAE). For example, the road surface identification model 154 is a learning model trained using a conditional generative adversarial network (GAN) method. The algorithm for training the road surface discrimination model 154 is not limited to the example given here.

[0078] The road surface identification unit 142 acquires map data of a target area for generating a road surface map from the image acquisition unit 141. The road surface identification unit 142 uses the road surface identification model 145 to identify road surface categories included in the map data. The road surface identification unit 142 inputs the acquired image data to the road surface identification model 145. The road surface identification unit 142 acquires road surface categories for each position output from the road surface identification model 145 in response to the input from the road surface identification model 145. The road surface identification unit 142 generates a dataset in which position data is associated with a road surface category. The road surface identification unit 142 outputs the generated dataset to the map generation unit 146. The road surface identification unit 142 may be configured to generate a road surface category table 132 in which road surface categories are associated with positions identified by the position data. In this case, the road surface identification unit 142 outputs the generated road surface category table 132 to the map generation unit 146.

[0079] The map generation unit 146 acquires a data set in which position data and road surface categories are associated with each other from the road surface identification unit 142. The map generation unit 146 generates a road surface map 136 in which a display indicating a road surface category is associated with each location identified by the position data. For example, the road surface categories are distinguished by the color, pattern, etc. of each category at the time of refueling. For example, the map generation unit 146 generates the road surface map 136 in which a display indicating a road surface category is superimposed on each location included in the map data. For example, the map generation unit 146 may be configured to generate the road surface map 136 using a machine learning model. For example, such a machine learning model outputs the road surface map 136 in which road surface categories are associated with positions on the map data in response to input of position data, road surface categories, and map data.

[0080] The road surface map 136 generated by the map generation unit 146 may include locations where the road surface category could not be identified. For example, the road surface category at a location under an obstruction such as a roadside tree or a footbridge cannot be determined from the air. No road surface category is associated with such a location. For example, a flag may be set to indicate that no road surface category is associated with such a location. The map generation unit 146 outputs the generated road surface map 136 to the output unit 147.

[0081] The output unit 147 acquires the road surface map 136 from the map generation unit 146. The output unit 147 outputs the acquired road surface map 136 to the map update device 12. The output unit 147 may output the road surface map 136 to a server or the like used by a provider that provides a service using the road surface map 136. A description of the service using the road surface map 136 will be omitted.

[0082] (Operation) Next, the operation of the map generation system 1 will be described with reference to the drawings. The operation of the map update device 12 included in the map generation system 1 will be described below. FIG. 23 is a flowchart for explaining an example of the operation of the map generation device according to the present disclosure. In describing the processing according to the flowchart of FIG. 23, the components of the map update device 12 will be described as the subject of the operations. The subject of the processing according to the flowchart of FIG. 23 may be the map update device 12.

[0083] 23 , first, the acquisition unit 121 acquires sensor data and position data transmitted from the mobile terminal 170 carried by the user (step S11). The sensor data includes acceleration in three axial directions and angular velocity around three axes. The position data corresponds to the position where the sensor data was measured.

[0084] Next, the determination unit 122 determines whether a road surface category corresponding to the acquired position data is registered (step S12). If the road surface category of the acquired position data is not registered (No in step S12), the determination unit 122 outputs a data generation instruction to the gait data generation unit 123. The data generation instruction is a signal instructing the generation of gait data using sensor data measured at the timing when the position data was measured. In response to the data generation instruction, the gait data generation unit 123 generates gait data using the sensor data measured at the timing when the position data was measured (step S13). For example, the gait data includes walking waveform data, gait indices, feature amounts, etc. On the other hand, if the road surface category of the acquired position data is registered (Yes in step S12), the processing according to the flowchart in FIG. 23 ends.

[0085] Following step S13, the road surface discrimination unit 125 uses the road surface discrimination model 152 to discriminate a road surface category corresponding to the gait data (step S14). Using the generated gait data, the road surface discrimination unit 125 discriminates the road surface category of the walkway on which the user was walking at the time when the sensor data used to generate the gait data was measured. The road surface discrimination unit 125 discriminates the road surface category output from the road surface discrimination model 152 in response to the input gait data as the road surface category corresponding to the position data.

[0086] Next, the update unit 126 associates the determined road surface category with the position data and registers it in the road surface category table 132 (step S15).

[0087] Next, the update unit 126 associates the determined road surface category with the position data and updates the road surface map 136 (step S16). The order of steps S15 and S16 may be reversed. For example, the output unit 127 may be configured to output the updated road surface map 136. For example, the output unit 127 outputs the road surface map 136 to a mobile terminal 170 carried by a user. For example, the output unit 127 outputs the road surface map 136 to a terminal device or a server that uses the road surface map 136. For example, the output unit 127 outputs the road surface map 136 to an external system or the like that uses the road surface map 136.

[0088] (Application Example) Next, an application example according to this embodiment will be described with reference to the drawings. FIGS. 24 to 26 are conceptual diagrams illustrating an example of displaying information including a road surface map updated by a map update device according to the present disclosure. FIGS. 24 to 26 are examples in which information including a road surface map is displayed on the screen of a mobile terminal 170 carried by a user walking while wearing shoes 100 in which a measuring device 10 is placed. In the example using FIGS. 24 to 26 , information including a road surface map is generated by an information processing device (not shown) that generates information including a road surface map updated by the map update device 12. For example, the information processing device is configured in the map generation system 1. For example, the information processing device may be configured in an external system.

[0089] Fig. 24 is a display example of a road surface map updated by a map updating device according to the present disclosure. In the example of Fig. 24, a road surface map of the user's surroundings is displayed on the screen of mobile terminal 170. In the example of Fig. 24, road surface categories at locations around the user are displayed with different hatching for each road surface category. After checking the road surface map displayed on the screen of mobile terminal 170, a user can walk while referring to the road surface categories displayed on the road surface map, thereby avoiding walkways with surfaces that are prone to tripping or moving to walkways with surfaces that are easy to walk on.

[0090] FIG. 25 illustrates an example of a display of information including a road surface map updated by a map updating device according to the present disclosure. In the example of FIG. 25, information including a road surface map updated by the map updating device 12 and advice according to the road surface category in the user's vicinity is displayed on the screen of the mobile terminal 170. In the example of FIG. 25, a road surface map in the user's vicinity is displayed on the screen of the mobile terminal 170. In the example of FIG. 25, road surface categories in the user's vicinity are displayed with different hatching for each road surface category. In addition, in the example of FIG. 25, a recommended route recommended for the user to walk is superimposed on the road surface map. Furthermore, in the example of FIG. 25, recommendation information including advice such as "We recommend walking along the recommended route" is displayed on the screen of the mobile terminal 170 according to the road surface category in the user's vicinity. The recommendation information is optimized according to the road surface condition of the path along which the user is walking. The recommendation information also prompts the user to make a decision. A user who checks the information displayed on the screen of the mobile terminal 170 can avoid falling and walk along an easy-to-walk road surface by walking along the recommended route according to the recommendation information.

[0091] Fig. 26 is a display example of information including a road surface map updated by a map update device according to the present disclosure. In the example of Fig. 26, information including a road surface map updated by the map update device 12 and requests according to road surface categories in the user's vicinity is displayed on the screen of a mobile terminal 170. In the example of Fig. 26, a road surface map in the user's vicinity is displayed on the screen of the mobile terminal 170. In the example of Fig. 26, road surface categories in positions in the user's vicinity are displayed with different hatching for each road surface category. In addition, in the example of Fig. 26, a missing area A where the road surface category has not been determined is displayed. M is included in the road surface map. In the example of FIG. 26, a recommended route that the user is recommended to walk is superimposed on the road surface map. The recommended route is M Furthermore, in the example of FIG. 26, it is possible to "walk along the recommended route and find the missing area A MThe recommendation information including the request "Please obtain the data of..." is displayed on the screen of the mobile terminal 170. The recommendation information is optimized according to the road surface conditions of the walking path the user is walking on. The recommendation information also encourages the user to make a decision. The user who has checked the information displayed on the screen of the mobile terminal 170 can walk along the recommended route in accordance with the request, thereby filling the missing area A. M By using the sensor data measured in this way, it is possible to obtain the missing area A M It is possible to distinguish the road surface category.

[0092] Defective area A M The data complementation may be linked to a specific event. For example, it may be linked to a game that uses position data in the world coordinate system, M If the data of the missing area A is complemented, M For example, it is possible to efficiently collect data on the missing area A. M If we recruit part-time workers to supplement the data in the missing area A M This may allow for efficient collection of data.

[0093] As described above, the map generation system of this embodiment includes a measurement device, a map generation device, and a map update device. The measurement device is attached to a user's footwear. The measurement device has a sensor that measures acceleration and angular velocity. The measurement device generates sensor data using the acceleration and angular velocity measured by the sensor. The measurement device transmits the generated sensor data to the map generation device. The map generation device generates a road surface map on which road surface conditions are mapped. The map update device includes an acquisition unit, a determination unit, a gait data generation unit, a road surface discrimination unit, an update unit, and an output unit. The acquisition unit acquires sensor data measured by a measurement device attached to the user's footwear and position data corresponding to the position at which the sensor data was acquired. The determination unit references a road surface category table to determine whether or not a road surface category is associated with the acquired position data. The road surface category table is a table in which road surface categories are associated with position data corresponding to positions included in the road surface map. If the road surface category associated with the acquired position data is not registered in the road surface category table, the determination unit outputs an instruction to generate gait data to the gait data generation unit. The gait data generation unit generates gait data using the sensor data in response to instructions from the determination unit. The road surface determination unit uses the gait data to determine the road surface condition of the walkway at a position corresponding to the position data. The update unit associates the determined road surface condition with the position data and updates a road surface map on which an indication of the road surface condition for each position is set. The output unit outputs the updated road surface map.

[0094] The map updating device of this embodiment determines the road surface condition of a walkway using gait data generated in response to the user's walking. The map updating device of this embodiment associates the determined road surface condition of the walkway with position data and updates a road surface map in which a display showing the road surface condition for each position is set. Therefore, the road surface condition determined in response to actual walking is reflected in the road surface map. In other words, this embodiment can provide a road surface map that makes it possible to grasp the road surface condition of the actual walkway.

[0095] Using remote sensing data and aerial photographs, it is possible to generate a road surface map that allows the road surface condition of a walkway to be understood. However, the road surface condition of walkways that are blocked by trees in towns and parks, or walkways under road bridges, cannot be seen from the air. Therefore, it is not possible to generate a road surface map that allows the road surface condition of a walkway to be fully understood using only remote sensing data and aerial photographs. According to the method of this embodiment, the road surface condition of roads that cannot be seen from the air can be determined using sensor data measured according to pedestrians' walking. Therefore, according to this embodiment, it is possible to generate a road surface map that allows the road surface condition to be understood even for roads in locations where the road surface condition cannot be seen from the air. For example, using the method of this embodiment, it is possible to generate a road surface map that reflects the road surface conditions of parks and mountain paths with many obstacles such as trees, and underground passages that cannot be seen from the air.

[0096] In one aspect of the present embodiment, the road surface discrimination unit inputs the gait data to a road surface discrimination model. The road surface discrimination model is a machine learning model generated by machine learning using a dataset in which the gait data is an explanatory variable and a road surface category corresponding to the gait data is an objective variable as training data. The road surface discrimination unit discriminates the road surface category output from the road surface discrimination model in response to the input of the gait data as the road surface condition at the position indicated by the position data. According to this aspect, the road surface discrimination model can be used to discriminate the road surface category of the walkway on which the user is walking. Furthermore, according to this aspect, the road surface discrimination model can be used to provide a road surface map updated in accordance with the road surface condition of the walkway.

[0097] In one aspect of this embodiment, the road surface discrimination model is a machine learning model generated by machine learning using, as training data, a dataset in which gait data is an explanatory variable and a road surface category is an objective variable. The road surface discrimination model is a machine learning model trained by machine learning using, as training data, a dataset in which gait data measured for each road surface category is an explanatory variable and reference gait data measured on a reference road surface is an objective variable. For example, the road surface discrimination model outputs gait data for walking on a reference road surface in reference weather in response to inputs of gait data, road surface category, and weather data. According to this aspect, the road surface discrimination model and the road surface discrimination model generated by machine learning can be used to generate gait data corrected in accordance with the road surface conditions of the walkway.

[0098] In one aspect of the present embodiment, the output unit displays information corresponding to the road surface condition of the walkway on the screen of the mobile terminal used by the user, allowing the user to check the information corresponding to the road surface condition of the walkway on the spot.

[0099] In one aspect of the present embodiment, the output unit superimposes a recommended route that recommends passing through a missing area where the road surface condition has not been determined on a road surface map and displays the recommended route on the screen of a mobile device carried by the user. According to this aspect, information on the missing area included in the road surface map can be efficiently collected.

[0100] In one aspect of the present embodiment, the output unit displays information optimized for the road surface conditions of the walkway along which the user is walking, and prompts the user to make a decision, on the screen of the mobile device carried by the user. According to this aspect, the information optimized for the road surface conditions of the walkway can prompt the user to make a decision.

[0101] Second Embodiment Next, a map generation system according to a second embodiment will be described with reference to the drawings. The map generation system of this embodiment determines a road surface category using difference data between gait data that changes depending on road surface conditions and reference gait data. In this respect, the map generation system of this embodiment differs from the map generation system according to the first embodiment.

[0102] (Configuration) FIG. 27 is a block diagram showing an example of the configuration of a map generation system according to the present disclosure. The map generation system 2 includes a measurement device 20, a map update device 22, and a map generation device 24. The measurement device 20 has the same configuration as the measurement device 10 of the first embodiment. For example, the measurement device 20 is attached to the footwear of a user whose gait is to be measured. The measurement device 20 is capable of communicating with a mobile device carried by the user. The mobile device carried by the user is connected to a server or a cloud via a network such as the Internet. The map generation device 24 has the same configuration as the map generation device 14 of the first embodiment. For example, the map generation device 24 is attached to a server or a cloud.

[0103] The map update device 22 has a configuration having the same functions as the map update device 12 of the first embodiment. Unlike the map update device 12 of the first embodiment, the map update device 22 determines a road surface category using difference data between gait data that changes depending on road surface conditions and reference gait data. For example, the map update device 22 is installed on a server or a cloud. For example, the functions of the map update device 22 may be implemented in a mobile terminal carried by a user. When a pre-generated road surface map is used, the map generation system 2 may be composed of a measurement device 20 and a map update device 22. In the following, a description of the measurement device 20 and the map generation device 24, which are the same as those of the first embodiment, will be omitted. Furthermore, a description of functions common to the map update device 12 of the first embodiment will be simplified.

[0104] 28 is a block diagram showing an example of the configuration of the map updating device 22. The map updating device 22 has an acquisition unit 221, a determination unit 222, a gait data generation unit 223, a difference calculation unit 224, a road surface determination unit 225, an update unit 226, and an output unit 227. For example, the map updating device 22 is constructed on a server or in the cloud. For example, the functions of the map updating device 22 may be implemented in a mobile terminal carried by the user.

[0105] The map update device 22 also stores a road surface category table 232, reference gait data 234, and a road surface map 236. The road surface category table 232 is similar to the road surface category table 132 in the first embodiment. The road surface map 236 is similar to the road surface map 136 in the first embodiment. The reference gait data 234 is gait data that serves as a reference for gait data that changes depending on the road surface conditions of the walkway. For example, the reference gait data is generated using sensor data measured while walking on a reference road surface that serves as a reference for the road surface conditions of the walkway. For example, the reference road surface is a walkway with an easy-to-walk-on vinyl surface, such as an indoor corridor. For example, the reference gait data is measured for each user. In this case, the gait data measured for each user is compared to reference gait data generated using sensor data measured for each user. For example, the reference gait data may be the average value of reference gait data measured for multiple subjects. In this case, the gait data measured for each user is compared to the average value of reference gait data generated using sensor data measured for multiple subjects.

[0106] For example, the road surface category table 232, reference gait data 234, and road surface map 236 are stored in the storage unit 230. The road surface category table 232, reference gait data 234, and road surface map 236 may also be stored in a storage device (not shown) accessible from the map update device 22. In this case, the map update device 22 accesses the road surface category table 232, reference gait data 234, and road surface map 236 via an interface (not shown) connected via a network. For example, such an interface is realized by an API (Application Programming Interface).

[0107] The map updating device 22 also has a road surface discrimination model 252. The road surface discrimination model 252 may be stored in the storage unit 230. The road surface discrimination model 252 may also be stored in a storage device (not shown) accessible from the map updating device 22. In this case, the map updating device 22 uses the road surface discrimination model 252 via an interface (not shown), such as an API, connected via a network.

[0108] The acquisition unit 221 has the same configuration as the acquisition unit 121 of the first embodiment. The acquisition unit 221 acquires sensor data from a measurement device 20 mounted on the user's footwear. The acquisition unit 221 receives the sensor data from the measurement device 20 via wireless communication. The sensor data includes location information of the mobile device that is the sender of the sensor data. For example, the location information is measured by a global positioning system (GPS) function mounted on the mobile device and added to the sensor data.

[0109] FIG. 29 is a conceptual diagram illustrating an example of sensor data collection in the present disclosure. The example in FIG. 29 is an example in which sensor data is collected from multiple users. A measuring device 20 is disposed in shoes 200 worn by each of multiple users. The measuring device 20 is disposed in a position that contacts the sole of the user's arch. Sensor data measured by the measuring device 20 according to the walking of each user is transmitted to a portable terminal 270 carried by each user. The portable terminal 270 receives the sensor data transmitted from the measuring device 20. The portable terminal 270 adds position data to the received sensor data. The position data includes longitude information and latitude information corresponding to the position where the sensor data was measured. The portable terminal 270 transmits the sensor data with the added position data to the map update device 22.

[0110] The determination unit 222 has the same configuration as the determination unit 122 of the first embodiment. The determination unit 222 acquires position data from the acquisition unit 221. The determination unit 222 references the road surface category table 232 and determines whether the road surface category corresponding to the acquired position data is registered in the road surface category table 232. If the road surface category corresponding to the acquired position data is not registered in the road surface category table 232, the determination unit 222 outputs a data generation instruction to the gait data generation unit 223 to determine the road surface category of the position data. Furthermore, the determination unit 222 outputs position data corresponding to the position for which the road surface category is being determined to the update unit 226. If the road surface category corresponding to the acquired position data is registered in the road surface category table 232, the determination unit 222 does not execute processing.

[0111] The gait data generation unit 223 has a configuration similar to that of the gait data generation unit 123 of the first embodiment. The gait data generation unit 223 acquires a data generation instruction from the determination unit 222. In response to the acquisition of the data generation instruction, the gait data generation unit 223 acquires sensor data from the acquisition unit 221. The gait data generation unit 223 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 included in the sensor data. The time series data for one walking cycle is also referred to as gait waveform data. The gait data generation unit 223 extracts gait waveform data based on the timing of walking events detected from the time series data of the sensor data. For example, the gait data generation unit 223 extracts gait waveform data that starts at the timing of a heel strike and ends at the timing of the next heel strike.

[0112] The gait data generation unit 223 normalizes (first normalization) the time of the extracted gait waveform data for one step cycle to a gait cycle of 0 to 100% (percent). Furthermore, with respect to the first-normalized gait waveform data for one step cycle, the gait data generation unit 223 normalizes (second normalization) the gait waveform data so that the stance phase is 60% and the swing phase is 40%. For example, the gait data generation unit 223 calculates a gait index using the normalized gait waveform data. For example, the gait data generation unit 223 extracts feature amounts used for calculating and estimating the gait index from the gait waveform data. The gait data generation unit 223 outputs gait data including the normalized gait waveform data, gait indexes, and feature amounts to the difference calculation unit 224. The gait data generation unit 223 outputs gait data including at least one of the normalized gait waveform data, gait indexes, and feature amounts to the difference calculation unit 224.

[0113] The difference calculation unit 224 acquires gait data from the gait data generation unit 223. The difference calculation unit 224 calculates the difference between the acquired gait data and reference gait data 234. The difference calculation unit 224 outputs difference data corresponding to the difference between the calculated gait data and the reference gait data 234 to the road surface determination unit 225.

[0114] The road surface discrimination unit 225 acquires the difference data from the difference calculation unit 224. The road surface discrimination unit 225 uses the acquired difference data to determine the road surface condition of the walkway along which the user is walking. The road surface discrimination unit 225 uses the road surface discrimination model 252 to determine a road surface category indicating the road surface condition of the walkway along which the user is walking. For example, the road surface discrimination unit 225 may be configured to determine the road surface condition of the walkway along which the user is walking based on the similarity or correlation coefficient of the difference data. The road surface discrimination unit 225 outputs the determined road surface category to the update unit 226.

[0115] The road surface discrimination model 252 is a machine learning model. For example, the road surface discrimination model 252 is a model trained using a dataset in which difference data is used as an explanatory variable and road surface categories are used as objective variables (labels) as training data. For example, the road surface discrimination model 252 is a learning model trained using a convolutional neural network (CNN) technique. For example, the road surface discrimination model 252 is a model trained using a principal component analysis (PCA) technique. For example, the road surface discrimination model 252 is a learning model trained using a variational autoencoder (VAE). For example, the road surface discrimination model 252 is a learning model trained using a conditional generative adversarial network (GAN) technique. The above techniques are merely examples and do not limit the techniques for training the road surface discrimination model 252.

[0116] In response to input of differential data, the road surface discrimination model 252 outputs a road surface category corresponding to the differential data. The road surface discrimination model 252 may be stored in an external storage device constructed in the cloud, a server, or the like. In this case, the road surface discrimination unit 225 uses the road surface discrimination model 252 via an interface (not shown) connected to the storage device.

[0117] 30 and 31 are graphs showing an example in which characteristics corresponding to the surface category of a walkway are expressed in gait waveform difference data. In FIGS. 30 and 31, the reference road surface is a vinyl-coated floor surface. FIGS. 30 and 31 show graphs of gait waveform difference data, which are the average of two 10-meter walking tests conducted by nine subjects. FIG. 30 shows a waveform (dashed line) of gait waveform difference data measured while walking on a walkway with a reference road surface and a waveform (solid line) of gait waveform difference data measured while walking on a grass walkway, superimposed on each other. FIG. 31 shows a waveform (dashed line) of gait waveform difference data measured while walking on a walkway with a reference road surface and a waveform (solid line) of gait waveform difference data measured while walking on a sand walkway, superimposed on each other. FIGS. 30 and 31 show a reference line (dotted line) where the value of the difference data becomes 0. As shown in the dashed-dotted circles in Figures 30 and 31 , the differential data of walking phases where there is a large deviation from the reference line and the differential data value is 0, or the differential data of walking phases where a characteristic waveform appears, exhibits characteristics corresponding to the walkway. This differential data is used to determine the road surface category. The road surface condition of the walkway can be estimated by using a machine learning model that has learned differential data that exhibits characteristics corresponding to the walkway.

[0118] Fig. 32 is a conceptual diagram for explaining an example of learning a road surface discrimination model according to the present disclosure. In the example of Fig. 32, a dataset in which difference data is used as an explanatory variable and road surface category is used as a target variable (label) is used as training data to train a road surface discrimination model 252. Explanation of a learning device (not shown) that trains the road surface discrimination model 252 will be omitted. The road surface condition of the walkway corresponding to difference data 1 is road surface category a. The road surface condition of the walkway corresponding to difference data 2 is road surface category b. The road surface condition of the walkway corresponding to difference data K is road surface category k.

[0119] 33 is a conceptual diagram showing an example of estimation of a road surface category using the road surface identification model according to the present disclosure. In response to input of difference data, the road surface discrimination model 252 outputs a road surface category according to the difference data.

[0120] The output unit 227 has the same configuration as the output unit 127 of the first embodiment. The output unit 227 outputs the road surface map 236 updated by the update unit 226. For example, the output unit 227 outputs the road surface map 236 to a mobile terminal carried by a user. For example, the output unit 227 outputs the road surface map 236 to a terminal device or a server that uses the road surface map 236. For example, the output unit 227 may be configured to output the road surface map 236 to an external system or the like that uses the road surface map 236.

[0121] For example, the map update device 22 is built in a cloud or a server connected to a mobile device carried by a user via a communication network. For example, the map update device 22 is connected to the mobile device via wireless communication. For example, the map update device 22 is connected to the mobile device via a wireless communication device (not shown) that complies with standards such as Bluetooth (registered trademark) or Wi-Fi (registered trademark). Note that the wireless communication device may also be compliant with standards other than Bluetooth (registered trademark) or Wi-Fi (registered trademark). The road surface map 236 may be used by an application installed on the mobile device. For example, the mobile device executes processing using the road surface map 236 using an application installed on the mobile device.

[0122] (Operation) Next, the operation of the map generation system 2 will be described with reference to the drawings. The operation of the map update device 22 included in the map generation system 2 will be described below. Fig. 34 is a flowchart for explaining an example of the operation of the map generation device according to the present disclosure. In describing the processing according to the flowchart of Fig. 34, the components of the map update device 22 will be described as the subject of the operations. The subject of the processing according to the flowchart of Fig. 34 may be the map update device 22.

[0123] 34 , first, the acquisition unit 221 acquires sensor data and position data transmitted from the mobile terminal 270 carried by the user (step S21). The sensor data includes acceleration in three axial directions and angular velocity around three axes. The position data corresponds to the position where the sensor data was measured.

[0124] Next, the determination unit 222 determines whether a road surface category corresponding to the acquired position data is registered (step S22). If the road surface category of the acquired position data is not registered (No in step S22), the determination unit 222 outputs a data generation instruction to the gait data generation unit 223. The data generation instruction is a signal instructing the generation of gait data using sensor data measured at the timing when the position data was measured. In response to the data generation instruction, the gait data generation unit 223 generates gait data using sensor data measured at the timing when the position data was measured (step S23). For example, the gait data includes walking waveform data, gait indices, feature amounts, etc. On the other hand, if the road surface category of the acquired position data is registered (Yes in step S22), the processing according to the flowchart of FIG. 34 ends.

[0125] Following step S23, the difference calculation unit 224 calculates the difference between the gait data generated using sensor data measured at a position where no road surface category was registered and the reference gait data 234 (step S24).

[0126] Next, the road surface discrimination unit 225 uses the road surface discrimination model 252 to discriminate a road surface category according to the difference data (step S25). The road surface discrimination unit 225 uses the calculated difference data to discriminate the road surface category of the walkway on which the user was walking at the time when the sensor data used to generate the difference data was measured. The road surface discrimination unit 225 discriminates the road surface category output from the road surface discrimination model 252 in response to the input of the difference data as the road surface category corresponding to the position data.

[0127] Next, the update unit 226 associates the determined road surface category with the position data and registers it in the road surface category table 232 (step S26).

[0128] Next, the update unit 226 associates the determined road surface category with the position data and updates the road surface map 236 (step S27). The order of steps S26 and S27 may be reversed. For example, the output unit 227 may be configured to output the updated road surface map 236. For example, the output unit 227 outputs the road surface map 236 to a mobile terminal 270 carried by a user. For example, the output unit 227 outputs the road surface map 236 to a terminal device or a server that uses the road surface map 236. For example, the output unit 227 outputs the road surface map 236 to an external system or the like that uses the road surface map 236.

[0129] (Application Examples) Next, application examples according to this embodiment will be described with reference to the drawings. Below, application examples relating to updating of a road surface map and application examples using the updated road surface map will be shown.

[0130] Fig. 35 is a conceptual diagram showing an example of displaying information including a road surface map updated by a map updating device according to the present disclosure. Fig. 35 shows an example in which information including a road surface map is displayed on the screen of a mobile terminal 270 carried by a user walking while wearing shoes 200 in which a measuring device 20 is placed. In the example using Fig. 35 , information including a road surface map is generated by an information processing device (not shown) that generates information related to the road surface map updated by the map updating device 22. For example, the information processing device is configured in the map generation system 2. For example, the information processing device may be configured in an external system.

[0131] Fig. 35 is a display example of information including a road surface map updated by a map updating device according to the present disclosure. In the example of Fig. 35, information including a road surface map updated by the map updating device 22 and incentives for multiple users is displayed on the screen of a mobile terminal 270 carried by each of multiple users. In the example of Fig. 35, a road surface map around the user is displayed on the screen of the mobile terminal 270. In the example of Fig. 35, road surface categories at positions around the user are displayed with different hatching for each road surface category. In addition, in the example of Fig. 35, a missing area A where the road surface category has not been determined is displayed. Mis included in the road surface map. In the example of FIG. 35, the missing area A M The arrows pointing to the missing area A are superimposed on the road surface map. M Furthermore, in the example of FIG. M Information including an incentive such as "Points will be awarded in the order of sending information" is displayed on the screen of the mobile terminal 270. The information including the incentive is optimized according to the road surface condition of the path on which the user is walking. The information including the incentive also encourages the user to make a decision. When the user checks the information displayed on the screen of the mobile terminal 270 and is motivated by the incentive to walk, the user can fill the missing area A. M By using the sensor data measured in this way, the missing area A M In the example of FIG. 35, information including an incentive is presented to multiple users. M If sensor data can be collected at the position of the missing area A M The accuracy of determining the road surface category at the position is improved.

[0132] Defective area A M The data complementation may be linked to a specific event. For example, it may be linked to a game that uses position data in the world coordinate system, M If the data of the missing area A is complemented, M For example, it is possible to efficiently collect data on the missing area A. M If we recruit part-time workers to supplement the data in the missing area A M This may allow for efficient collection of data.

[0133] FIG. 36 is a conceptual diagram illustrating an application example using a road surface map according to the present disclosure. FIG. 36 illustrates an example in which information including a recommended walking route as training according to a road surface category is displayed on the screen of a mobile device 270. In the example of FIG. 36, a recommended route according to road surface conditions is displayed on the screen of the mobile device 270. Furthermore, the screen of the mobile device 270 displays recommendation information such as, "The following route, including a road surface with a load, is recommended." The recommended route displayed on the road surface map is optimized to provide appropriate exercise for the user based on the road surface conditions of the path the user will be walking on. For example, the recommended route is provided based on the user's attributes and health condition. For example, the recommended route is provided using a machine learning model that outputs a recommended route based on input of the user's attributes, health condition, and road surface map. For example, the recommended route may be generated using a model that combines a large-scale language model and an image analysis model. The provided recommendation information prompts the user to make a decision. After checking the information displayed on the screen of the mobile device 270, the user can practice appropriate training by walking the recommended route. In this way, by using the road surface map according to the present disclosure, it is possible to recommend to the user training with an appropriate load according to the road surface conditions.

[0134] Next, a modification of the present embodiment will be described with reference to the drawings. In this modification, the road surface category of a location included in a location identified by position data measured using a GPS or the like is determined according to the measurement accuracy of the position data.

[0135] FIG. 37 is a conceptual diagram showing an example of road surface categories for each pixel included in a square range (measurement accuracy range) whose center of gravity is the position identified by the position data. The measurement accuracy range R1 includes four pixels. A pixel is a unit area included in the subdivided measurement accuracy range R1. FIG. 37 shows an example in which the measurement accuracy range is divided into four pixels by mutually perpendicular line segments passing through the center of gravity C1. The measurement accuracy range R1 includes pixel P1, pixel P2, pixel P3, and pixel P4. The number of divisions of the measurement accuracy range R1 is not limited to four. Furthermore, the shape of the measurement accuracy range R1 does not have to be square. The pixels that make up the measurement accuracy range R1 may be of different sizes and shapes.

[0136] In the example of Figure 37, the road surface categories in the measurement accuracy range R1 include category 1, category 2, and category 3. Each category indicates a different road surface condition. Each pixel is assigned a score for each road surface category. The sum of the scores for each road surface category for each pixel is 1. The score corresponds to the probability that each pixel belongs to a particular road surface category. For pixel P1, the score for category 1 is a 11 , category 2 score is b 11 , Category 3 score is C 11 For pixel P2, the score of category 1 is a 12 , category 2 score is b 12 , Category 3 score is C 12 For pixel P3, the score of category 1 is a 13 , category 2 score is b 13 , Category 3 score is C 13 For pixel P4, the score of category 1 is a 14 , category 2 score is b 14 , Category 3 score is C 14 is.

[0137] The road surface category of each pixel included in the measurement accuracy range R1 is determined for each pixel. For example, the road surface category of each pixel is determined using a machine learning model. The machine learning model outputs a score for each category for each pixel in response to input gait data. For example, the machine learning model is a trained model. For example, the machine learning model may be a model that randomly outputs a score for each category for each pixel. The score for each category for each pixel is set to a value estimated using the machine learning model.

[0138] FIG. 38 is a conceptual diagram showing an example of changes in road surface category for each pixel included in the measurement accuracy range with the position specified by the position data as the center of gravity. As the user walks, the position data indicating the user's position changes from center of gravity C1 to center of gravity C2. Measurement accuracy range R2 includes pixels P1, P2, P3, and P4. In the example of FIG. 38, for pixel P1, the score for category 1 is a 21 , category 2 score is b 21 , Category 3 score is C 21 For pixel P2, the score of category 1 is a 22 , category 2 score is b 22 , Category 3 score is C 22 For pixel P3, the score of category 1 is a 23 , category 2 score is b 23 , Category 3 score is C 23 For pixel P4, the score of category 1 is a 24 , category 2 score is b 24 , Category 3 score is C 24The score for each category included in each pixel may or may not change depending on the change from the measurement accuracy range R1 to the measurement accuracy range R2. For overlapping pixels in the measurement accuracy range R1 and the measurement accuracy range R2, an average value of the category for each overlapping pixel is calculated. For example, the average value of the category for each overlapping pixel is the arithmetic mean value. The average value of the category for each overlapping pixel may also be the geometric mean value or the harmonic mean value.

[0139] For example, the road surface category of a position included in the measurement accuracy range specified by the position data is determined to be the category with the largest score for each category included in each pixel. For example, the road surface category of a position included in the measurement accuracy range may be determined for each pixel. For example, the road surface category of a position included in the measurement accuracy range may be expressed in a display state indicating that multiple categories are included, depending on the score for each category included in each pixel. For example, the road surface category of a position included in the measurement accuracy range may be expressed using a hue, saturation, or brightness that is expressed in gradation depending on the score for each category included in each pixel.

[0140] The measurement accuracy range may include multiple road surface categories. According to this modification, by subdividing the road surface categories included in the measurement accuracy range, it is possible to grasp the road surface condition at the user's position more precisely. Furthermore, according to this modification, when different road surface categories are determined to exist for multiple users located within the same measurement accuracy range, one of the road surface categories can be associated with that measurement accuracy range. For example, the road surface map may be set to be updated for measurement accuracy ranges determined to exist as different road surface categories for multiple users.

[0141] As described above, the map generation system of this embodiment includes a measurement device, a map generation device, and a map update device. The measurement device is attached to a user's footwear. The measurement device has a sensor that measures acceleration and angular velocity. The measurement device generates sensor data using the acceleration and angular velocity measured by the sensor. The measurement device transmits the generated sensor data to the map generation device. The map generation device generates a road surface map on which road surface conditions are mapped. The map update device includes an acquisition unit, a determination unit, a gait data generation unit, a difference calculation unit, a road surface discrimination unit, an update unit, and an output unit. The acquisition unit acquires sensor data measured by a measurement device attached to the user's footwear and position data corresponding to the position at which the sensor data was acquired. The determination unit references a road surface category table to determine whether or not a road surface category is associated with the acquired position data. The road surface category table is a table in which road surface categories are associated with position data corresponding to positions included in the road surface map. If the road surface category associated with the acquired position data is not registered in the road surface category table, the determination unit outputs an instruction to generate gait data to the gait data generation unit. The gait data generation unit generates gait data using sensor data in response to instructions from the determination unit. The difference calculation unit calculates difference data between the generated gait data and reference gait data. The road surface determination unit determines the road surface condition of the walkway using the calculated difference data. The update unit associates the determined road surface condition with the position data and updates a road surface map in which an indication of the road surface condition for each position is set. The output unit outputs the updated road surface map.

[0142] The map updating device of this embodiment determines the road surface condition of a walkway using differential data generated in response to a user's walking. The map updating device of this embodiment associates the determined road surface condition of the walkway with position data, and updates a road surface map in which a display showing the road surface condition for each position is set. The differential data includes gait characteristics that change depending on the road surface condition. The differential data includes characteristics that are independent of the person. Therefore, the road surface map updated by the map updating device of this embodiment is more versatile. In other words, this embodiment can provide a road surface map that more accurately reflects the road surface condition of an actual walkway.

[0143] Third Embodiment Next, a map generation device according to a third embodiment will be described with reference to the drawings. The map generation device of this embodiment has a simplified configuration of the map update device included in the map generation systems according to the first and second embodiments.

[0144] 39 is a block diagram showing an example of the configuration of the map update device 32 in the present disclosure. The map update device 32 includes an acquisition unit 321, a gait data generation unit 323, a road surface determination unit 325, and an update unit 326.

[0145] The acquisition unit 321 acquires sensor data measured by a measuring device mounted on the user's footwear and position data corresponding to the position at which the sensor data was acquired. The gait data generation unit 323 generates gait data using the sensor data. The road surface determination unit 325 determines the road surface condition of the walkway using the gait data. The update unit 326 associates the determined road surface condition with the position data and updates a road surface map in which a display showing the road surface condition for each position is set.

[0146] (Operation) Next, the operation of the map updating device 32 will be described with reference to the drawings. Fig. 40 is a flowchart for explaining an example of the operation of the map updating device 32. In explaining the processing according to the flowchart of Fig. 40, the components of the map updating device 32 will be described as the main actors in the operations. The main actor in the processing according to the flowchart of Fig. 40 may be the map updating device 32.

[0147] In FIG. 40, first, the acquisition unit 321 acquires sensor data measured by a measurement device mounted on the user's footwear and position data corresponding to the position where the sensor data was acquired (step S31).

[0148] Next, the gait data generator 323 generates gait data using the sensor data (step S32).

[0149] Next, the road surface determination unit 325 determines the road surface condition of the walkway using the gait data (step S33).

[0150] Next, the update unit 326 associates the determined road surface condition with the position data and updates the road surface map in which a display showing the road surface condition for each position is set (step S34).

[0151] The map updating device of this embodiment determines the road surface condition of a walkway using gait data generated in response to the user's walking. The map updating device of this embodiment associates the determined road surface condition of the walkway with position data and updates a road surface map in which a display showing the road surface condition for each position is set. Therefore, the road surface condition determined in response to actual walking is reflected in the road surface map. In other words, this embodiment can provide a road surface map that makes it possible to grasp the road surface condition of the actual walkway.

[0152] (Hardware) Next, a hardware configuration for executing the control and processing in the present disclosure will be described with reference to the drawings. Here, an information processing device 90 (computer) in Fig. 41 is given as an example of such a hardware configuration. The information processing device 90 in Fig. 41 is an example configuration for executing the control and processing in the present disclosure and does not limit the scope of the present disclosure.

[0153] As shown in Fig. 41 , an information processing device 90 includes a processor 91, a memory 92, an auxiliary storage device 93, an input / output interface 95, and a communication interface 96. In Fig. 41 , interface is abbreviated as I / F (Interface). The processor 91, memory 92, auxiliary storage device 93, input / output interface 95, and communication interface 96 are connected to each other via a bus 98 so as to be able to communicate data with each other. The processor 91, memory 92, auxiliary storage device 93, and input / output interface 95 are also connected to a network such as the Internet or an intranet via the communication interface 96.

[0154] The processor 91 loads a program (instructions) stored in an auxiliary storage device 93 or the like into the memory 92. For example, the program is a software program for executing the control and processing in the present disclosure. The processor 91 executes the program loaded into the memory 92. The processor 91 executes the program to execute the control and processing in the present disclosure.

[0155] The memory 92 is a storage device having an area in which a program is loaded. The processor 91 loads a program stored in an auxiliary storage device 93 or the like into the memory 92. The memory 92 is realized by a volatile memory such as a dynamic random access memory (DRAM). Alternatively, a non-volatile memory such as a magnetoresistive random access memory (MRAM) may be used as the memory 92.

[0156] The auxiliary storage device 93 stores various data such as programs. For example, 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 configure the system so that various data is stored in the memory 92, thereby omitting the auxiliary storage device 93.

[0157] 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.

[0158] Input devices such as a keyboard, mouse, and touch panel may be connected to the information processing device 90 as needed. 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 the touch panel serves as the interface. The processor 91 and the input devices are connected via an input / output interface 95.

[0159] The information processing device 90 may be equipped with a display device for displaying information. When the 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.

[0160] 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 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.

[0161] The above is an example of a hardware configuration for enabling the control and processing of the present disclosure. The hardware configuration of Figure 41 is an example of a hardware configuration for executing the control and processing of the present disclosure, and does not limit the scope of the present disclosure. A program that causes a computer to execute the control and processing of the present disclosure is also included in the scope of the present disclosure.

[0162] A program recording medium on which a program for executing the processing of this embodiment is recorded is also included within the scope of the present invention. For example, the program recording medium is a computer-readable, non-transitory recording medium. The recording medium can be, for example, an optical recording medium such as a CD (Compact Disc) or a DVD (Digital Versatile Disc). The recording medium may also be a semiconductor recording medium such as a USB (Universal Serial Bus) memory or an SD (Secure Digital) card. The recording medium may also be a magnetic recording medium such as a flexible disk, or other recording medium.

[0163] The components in the present disclosure may be combined in any manner. The components in the present disclosure may be realized by software. The components in the present disclosure may be realized by circuits.

[0164] Although the present disclosure has been described above with reference to the embodiments, the present disclosure is not limited to the above-described 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.

[0165] Some or all of the above embodiments may be described as, but are not limited to, the following supplementary notes. In the supplementary notes below, dependent claims in each category may also be made dependent on other categories. The statements included in the supplementary notes below have significance as grounds for amendment. (Supplementary Note 1) A map update device comprising: an acquisition unit that acquires sensor data measured by a measurement device mounted on a user's footwear and position data corresponding to the position at which the sensor data was acquired; a gait data generation unit that generates gait data using the sensor data; a road surface determination unit that determines the road surface condition of a walkway using the gait data; and an update unit that associates the determined road surface condition with the position data and updates a road surface map on which a display showing the road surface condition for each position is set. (Supplementary Note 2) The road surface discrimination unit inputs the gait data into a road surface discrimination model, which is a machine learning model generated by machine learning using as training data a dataset in which the gait data is an explanatory variable and a road surface category corresponding to the gait data is an objective variable, and discriminates the road surface category output from the road surface discrimination model in response to the input of the gait data as the road surface condition at the position of the position data. (Supplementary Note 3) A map update device according to Supplementary Note 2, comprising: a determination unit that determines whether or not a road surface category is associated with the acquired position data by referring to a road surface category table in which road surface categories are associated with the position data corresponding to positions included in the road surface map; the determination unit outputs an instruction to a gait data generation unit to generate the gait data if the road surface category associated with the acquired position data is not registered in the road surface category table; the gait data generation unit generates the gait data using the sensor data in accordance with the instruction from the determination unit; the road surface determination unit determines the road surface condition of the walkway using the gait data; and the update unit updates the road surface category table and the road surface map by associating the determined road surface condition with the position data.(Supplementary Note 4) The map updating device according to Supplementary Note 1, comprising a difference calculation unit that calculates difference data between the generated gait data and reference gait data, wherein the road surface discrimination unit discriminates the road surface condition of a walkway using the calculated difference data. (Supplementary Note 5) The map updating device according to Supplementary Note 1, comprising an output unit that displays information according to the road surface condition of the walkway along which the user is walking on a screen of a portable terminal used by the user. (Supplementary Note 6) The map updating device according to Supplementary Note 5, wherein the output unit superimposes on the road surface map a recommended route that recommends passing through a missing area where the road surface condition has not been determined, and displays the recommended route on the screen of the portable terminal carried by the user. (Supplementary Note 7) The map updating device according to Supplementary Note 5, wherein the output unit displays information that is optimized according to the road surface condition of the walkway along which the user is walking and that prompts the user to make a decision on the screen of the portable terminal carried by the user. (Supplementary Note 8) A map generation system comprising: the map update device according to any one of Supplementary Notes 1 to 7; and a measurement device having a sensor that measures acceleration and angular velocity, generating the sensor data using the acceleration and angular velocity measured by the sensor, and transmitting the generated sensor data to the map update device. (Supplementary Note 9) A map updating method comprising: a computer acquiring sensor data measured by a measurement device mounted on a user's footwear and position data corresponding to a position at which the sensor data was acquired, generating gait data using the acquired sensor data, determining the road surface condition of a walkway using the generated gait data, and associating the determined road surface condition with the position data to update a road surface map on which a display showing the road surface condition for each position is set. (Supplementary Note 10) A map updating method according to Supplementary Note 9, in which a computer inputs the gait data into a road surface discrimination model, which is a machine learning model generated by machine learning using a dataset in which the gait data is an explanatory variable and a road surface category corresponding to the gait data is an objective variable, and discriminates the road surface category output from the road surface discrimination model in response to the input of the gait data as the road surface condition at the position of the position data.(Supplementary Note 11) The map updating method according to Supplementary Note 10, wherein a computer refers to a road surface category table in which road surface categories are associated with the position data corresponding to positions included in the road surface map, and determines whether or not there is a road surface category associated with the acquired position data, and if the road surface category associated with the acquired position data is not registered in the road surface category table, generates the gait data using the sensor data, determines the road surface condition of the walkway using the gait data, and associates the determined road surface condition with the position data, thereby updating the road surface category table and the road surface map. (Supplementary Note 12) The map updating method according to Supplementary Note 9, wherein a computer calculates difference data between the generated gait data and reference gait data, and determines the road surface condition of the walkway using the calculated difference data. (Supplementary Note 13) The map updating method according to Supplementary Note 9, wherein a computer displays information corresponding to the road surface condition of the walkway along which the user is walking on a screen of a portable terminal used by the user. (Supplementary Note 14) The map updating method according to Supplementary Note 13, wherein a computer superimposes on the road surface map a recommended route that recommends passing through a missing area where the road surface condition has not been determined, and displays the recommended route on a screen of the portable terminal carried by the user. (Supplementary Note 15) A computer-readable non-transitory recording medium having recorded thereon a program that causes a computer to execute the following processes: acquiring sensor data measured by a measuring device mounted on the user's footwear and position data corresponding to the position where the sensor data was acquired; generating gait data using the acquired sensor data; determining the road surface condition of the walkway using the generated gait data; and updating a road surface map on which a display showing the road surface condition for each position is set by associating the determined road surface condition with the position data.(Supplementary Note 16) A computer-readable non-transitory recording medium according to Supplementary Note 15, having recorded thereon a program that causes a computer to execute the following steps: inputting the gait data into a road surface discrimination model, which is a machine learning model generated by machine learning using as training data a dataset in which the gait data is an explanatory variable and a road surface category corresponding to the gait data is an objective variable; and discriminating the road surface category output from the road surface discrimination model in response to the input of the gait data as the road surface condition at the position of the position data. (Supplementary Note 17) The computer-readable, non-transitory recording medium according to Supplementary Note 16, having recorded thereon a program that causes a computer to execute the following processes: a process of determining whether or not a road surface category exists associated with the acquired position data, by referencing a road surface category table in which the road surface category is associated with the position data corresponding to a position included in the road surface map; a process of generating the gait data using the sensor data and determining the road surface condition of the walkway using the gait data, if the road surface category associated with the acquired position data is not registered in the road surface category table; and a process of associating the determined road surface condition with the position data, and updating the road surface category table and the road surface map. (Supplementary Note 18) The computer-readable, non-transitory recording medium according to Supplementary Note 15, having recorded thereon a program that causes a computer to execute the processes of calculating difference data between the generated gait data and reference gait data, and determining the road surface condition of the walkway using the calculated difference data. (Supplementary Note 19) A computer-readable non-transitory recording medium according to Supplementary Note 15, having recorded thereon a program that causes a computer to execute a process of displaying information according to the road surface condition of the walkway along which the user is walking on a screen of a mobile terminal used by the user. (Supplementary Note 20) A computer-readable non-transitory recording medium according to Supplementary Note 19, having recorded thereon a program that causes a computer to execute a process of superimposing on the road surface map a recommended route that recommends passing through a missing area where the road surface condition has not been determined, and displaying the recommended route on a screen of the mobile terminal carried by the user.

[0166] Furthermore, some or all of the configurations described in Supplementary Notes 2 to 8 that are dependent on Supplementary Note 1 above may also be dependent on Supplementary Notes 9 and 15 in the same dependent relationship as Supplementary Notes 2 to 8. Furthermore, not limited to Supplementary Notes 1, 9, and 15, some or all of the configurations described as Supplements may be made dependent on various hardware, software, various recording means for recording software, or systems, within the scope of each of the above-mentioned embodiments.

[0167] 1, 2 Map generation system 10, 20 Measuring device 12, 22, 32 Map update device 14, 24 Map generation device 110 Sensor 111 Acceleration sensor 112 Angular velocity sensor 113 Control unit 115 Communication unit 117 Power supply 121, 221, 321 Acquisition unit 122, 222 Determination unit 123, 223, 323 Gait data generation unit 125, 225, 325 Road surface discrimination unit 126, 226, 326 Update unit 127, 227 Output unit 130, 230 Storage unit 132, 232 Road surface category table 136, 236 Road surface map 141 Image acquisition unit 142 Road surface identification unit 146 Map generation unit 147 Output unit 152 Road surface discrimination model 154 Road surface identification model 224 Difference calculation unit 234 Reference gait data

Claims

1. An acquisition unit that acquires sensor data measured by a measurement device mounted on a user's footwear and position data corresponding to the position where the sensor data was acquired; a gait data generation unit that generates gait data using the sensor data; a road surface discrimination unit that discriminates the road surface state of a walking path using the gait data; and an update unit that updates a road surface map in which a display indicating the road surface state for each position is set by associating the discriminated road surface state with the position data. A map update device comprising:

2. The road surface discrimination unit inputs the gait data into a road surface discrimination model, which is a machine learning model generated by machine learning using, as explanatory variables, the gait data and, as target variables, road surface categories corresponding to the gait data as teacher data, and discriminates, as the road surface state at the position of the position data, the road surface category output from the road surface discrimination model in response to the input of the gait data. The map update device according to claim 1.

3. A determination unit that determines the presence or absence of the road surface category associated with the acquired position data by referring to a road surface category table in which the road surface category is associated with the position data corresponding to the positions included in the road surface map. When the road surface category associated with the acquired position data is not registered in the road surface category table, the determination unit outputs an instruction to generate the gait data to the gait data generation unit. The gait data generation unit generates the gait data using the sensor data in response to an instruction from the determination unit. The road surface discrimination unit discriminates the road surface state of the walking path using the gait data. The update unit updates the road surface category table and the road surface map by associating the discriminated road surface state with the position data. The map update device according to claim 2.

4. A difference calculation unit that calculates difference data between the generated gait data and reference gait data. The road surface discrimination unit discriminates the road surface state of the walking path using the calculated difference data. The map update device according to claim 1.

5. The map update device according to claim 1, further comprising an output unit that displays information corresponding to the road surface state of the walking path on which the user walks on a screen of a mobile terminal used by the user.

6. The map updating device according to claim 5, wherein the output unit superimposes a recommended route that recommends passing through a defective area where the road surface condition has not been determined on the road surface map and displays it on the screen of the mobile terminal carried by the user.

7. The map updating device according to claim 5, wherein the output unit optimizes according to the road surface condition of the walking path on which the user walks and displays information for prompting a decision-making on the screen of the mobile terminal carried by the user.

8. A map generation system comprising the map updating device according to any one of claims 1 to 7, and a measurement device having a sensor that measures acceleration and angular velocity, generating sensor data using the acceleration and angular velocity measured by the sensor, and transmitting the generated sensor data to the map updating device.

9. A map updating method in which a computer acquires sensor data measured by a measurement device mounted on a user's footwear and position data corresponding to the position where the sensor data is acquired, generates gait data using the acquired sensor data, determines the road surface condition of the walking path using the generated gait data, associates the determined road surface condition with the position data, and updates a road surface map in which a display indicating the road surface condition for each position is set.

10. The map updating method according to claim 9, wherein the computer inputs the gait data to a road surface discrimination model, which is a machine learning model generated by machine learning using a data set having the gait data as an explanatory variable and a road surface category corresponding to the gait data as an objective variable as teacher data, and discriminates the road surface category output from the road surface discrimination model in response to the input of the gait data as the road surface condition at the position of the position data.

11. The computer refers to a road surface category table in which the road surface category is associated with the position data corresponding to the positions included in the road surface map, determines the presence or absence of the road surface category associated with the acquired position data, and if the road surface category associated with the acquired position data is not registered in the road surface category table, generates the gait data using the sensor data, discriminates the road surface state of the walking path using the gait data, and updates the road surface category table and the road surface map by associating the discriminated road surface state with the position data. The map update method according to claim 10.

12. The computer calculates difference data between the generated gait data and reference gait data, and discriminates the road surface state of the walking path using the calculated difference data. The map update method according to claim 9.

13. The computer causes information corresponding to the road surface state of the walking path on which the user walks to be displayed on the screen of the mobile terminal used by the user. The map update method according to claim 9.

14. The computer superimposes a recommended route recommending passing through a missing area where the road surface state has not been discriminated on the road surface map, and causes the recommended route to be displayed on the screen of the mobile terminal carried by the user. The map update method according to claim 13.

15. A computer-readable non-transitory recording medium recording a program for causing a computer to execute a process of acquiring sensor data measured by a measuring device mounted on the user's footwear and position data corresponding to the position where the sensor data is acquired, a process of generating gait data using the acquired sensor data, a process of discriminating the road surface state of the walking path using the generated gait data, and a process of updating a road surface map in which a display indicating the road surface state for each position is set by associating the discriminated road surface state with the position data.

16. A process of inputting the gait data into a road surface discrimination model, which is a machine learning model generated by machine learning using, as teacher data, a data set having the gait data as an explanatory variable and a road surface category corresponding to the gait data as an objective variable; and a process of discriminating, as a road surface state at the position of the position data, the road surface category output from the road surface discrimination model in response to the input of the gait data, are recorded in a computer-readable non-transitory recording medium according to claim 15, which causes a computer to execute the program.

17. A process of determining the presence or absence of the road surface category associated with the acquired position data by referring to a road surface category table in which the road surface category is associated with the position data included in the road surface map; when the road surface category associated with the acquired position data is not registered in the road surface category table, generating the gait data using the sensor data, a process of discriminating the road surface state of the walking path using the gait data, and a process of updating the road surface category table and the road surface map by associating the discriminated road surface state with the position data, are recorded in a computer-readable non-transitory recording medium according to claim 16, which causes a computer to execute the program.

18. A program for causing a computer to execute a process of calculating difference data between the generated gait data and reference gait data and discriminating the road surface state of the walking path using the calculated difference data is recorded in the computer-readable non-transitory recording medium according to claim 15.

19. A program for causing a computer to execute a process of displaying information corresponding to the road surface state of the walking path on which the user walks on a screen of a mobile terminal used by the user is recorded in the computer-readable non-transitory recording medium according to claim 15.

20. A program for causing a computer to execute a process of superimposing a recommended route recommending passing through a missing area where the road surface state has not been discriminated on the road surface map and displaying it on a screen of the mobile terminal carried by the user is recorded in the computer-readable non-transitory recording medium according to claim 19.

Images