Feature amount data generation device, gait measurement device, physical state estimation system, feature amount data generation method, and program

Abstract

According to the present invention, to generate feature quantity data that makes it possible to achieve highly-accurate physical condition estimation, a feature quantity data generation device comprises an acquisition unit that acquires time series data for sensor data related to the movement of a leg, a normalization unit that extracts walking waveform data for one walking cycle from the time series data for the sensor data and normalizes the extracted walking waveform data, an extraction unit that extracts feature quantities related to the physical condition of an estimation target from the normalized walking waveform data from walking phase clusters that are made up of one or more temporally consecutive walking phases, a selection unit that uses a preset threshold value to select feature quantities to be used for physical condition estimation from the feature quantities extracted for each of the walking phase clusters, a generation unit that generates feature quantity data that includes the selected feature quantities, and an output unit that outputs the generated feature quantity data.

Description

Technical Field

[0001] The present disclosure relates to a feature data generation device that generates feature data from data related to walking, etc.

Background Art

[0002] With the increasing interest in healthcare, attention has been focused on services that provide information according to features (also called gait) included in a walking pattern. For example, technologies for analyzing gait based on sensor data measured by sensors mounted on footwear such as shoes have been developed. The features of gait events (also called walking events) related to the physical state appear in the time-series data of the sensor data. That is, if the feature amounts of the walking events can be accurately extracted, the physical state can be estimated with high accuracy.

[0003] Patent Document 1 discloses an apparatus for detecting foot abnormalities based on the walking characteristics of a walker. The apparatus of Patent Document 1 extracts characteristic walking feature amounts in the walking of a walker wearing the footwear using data acquired from sensors installed in the footwear. The apparatus of Patent Document 1 detects abnormalities of a walker walking while wearing the footwear based on the extracted walking feature amounts. For example, the apparatus of Patent Document 1 extracts a feature site related to hallux valgus from the walking waveform data for one walking cycle. The apparatus of Patent Document 1 estimates the progression state of hallux valgus using the walking feature amounts of the extracted feature site.

[0004] Patent Document 2 discloses a system for calculating an index for analyzing split-step walking. The system of Patent Document 2 acquires information on the angular velocity of the ankle during walking detected by a sensor attached to a person's ankle. The system of Patent Document 2 detects a swing phase, which is the time when the foot is floating above the ground, based on the temporal change in the angular velocity about a first axis extending in the left-right direction of the person among the acquired angular velocity information. The system of Patent Document 2 specifies a predetermined time from the start of the swing phase as the time of interest. The system of Patent Document 2 calculates an index used for determining whether a person is performing split-step walking based on the temporal change within the time of interest in the angular velocity about a second axis extending in the vertical direction among the acquired angular velocity information.

[0005] Patent Document 3 discloses a system for estimating the trip attributes of a terminal holder. The system of Patent Document 3 estimates a plurality of trip attributes that define the characteristics of the movement of a user holding a mobile terminal using the GPS (Global Positioning System) data and acceleration sensor data of the mobile terminal. The system of Patent Document 3 corrects the estimation result of a second trip attribute different from the first trip attribute using the estimation result of the first trip attribute included in the estimation results of the plurality of trip attributes and the estimation result of the inter-trip attribute correlation information. For example, the system of Patent Document 3 clusters the final positions of the main trips in a day in which the difference between the end time of the preceding main trip and the start time of the subsequent main trip is the largest. The system of Patent Document 3 extracts the cluster with the largest number of elements and estimates the coordinates of the centroid of that cluster as the location of the workplace.

Prior Art Documents

Patent Documents

[0006]

Patent Document 1

Patent Document 2

Patent Document 3

Summary of the Invention

Problems to be Solved by the Invention

[0007] In the method of Patent Document 1, the mid-stance phase is detected using the walking waveform data of the plantar angle for two gait cycles, and based on the detected mid-stance phase, the walking waveform data for one gait cycle is generated. That is, in the method of Patent Document 1, in order to generate the walking waveform data for one gait cycle, the walking waveform data of the plantar angle for two gait cycles was required. Also, in the method of Patent Document 1, the gait cycle of the walking waveform data is normalized based on the time series data of the plantar angle. In the method of Patent Document 1, in order to normalize the gait cycle of the walking waveform data, the time series data of the angular velocity detected by the sensor is integrated to generate the time series data of the plantar angle. That is, in the method of Patent Document 1, several stages of preprocessing were required to generate the walking waveform data used for extracting the feature amount used for estimating the body state.

[0008] In the method of Patent Document 2, based on the time change of the angular velocity around the first axis, toe-off and heel strike can be detected. Patent Document 2 performs normalization considering the walking speed of the patient by using, as a feature amount, the value obtained by dividing the difference (width) between the minimum value and the maximum value of the angular velocity around the second axis by the maximum value of the angular velocity around the first axis. Patent Document 2 does not disclose normalizing the time series data of the angular velocity in the time direction. Therefore, in the method of Patent Document 2, it is not possible to accurately detect walking events other than toe-off and heel strike from the time change of the angular velocity.

[0009] In the method of Patent Document 3, the position of the workplace of the terminal holder etc. can be estimated according to the number of components of the cluster generated according to the position. Patent Document 3 does not disclose generating the walking waveform data for one gait cycle or normalizing the gait cycle of the walking waveform data. Therefore, in the method of Patent Document 3, it is not possible to detect the walking events for extracting the feature amount used for estimating the body state.

[0010] An object of the present disclosure is to provide a feature amount data generation device and the like that can generate feature amount data enabling highly accurate estimation of a physical state.

Means for Solving the Problems

[0011] A feature amount data generation device according to an aspect of the present disclosure includes an acquisition unit that acquires time-series data of sensor data related to the movement of a foot, a normalization unit that extracts walking waveform data for one walking cycle from the time-series data of the sensor data and normalizes the extracted walking waveform data, an extraction unit that extracts, from the normalized walking waveform data, a feature amount related to a physical state to be estimated from a walking phase cluster composed of at least one temporally continuous walking phase, a selection unit that selects, from the feature amounts for each of the extracted walking phase clusters, a feature amount used for estimating the physical state based on a preset threshold, a generation unit that generates feature amount data including the selected feature amount, and an output unit that outputs the generated feature amount data.

[0012] In a feature amount data generation method according to an aspect of the present disclosure, time-series data of sensor data related to the movement of a foot is acquired, walking waveform data for one walking cycle is extracted from the time-series data of the sensor data, the extracted walking waveform data is normalized, a feature amount related to a physical state to be estimated is extracted from the normalized walking waveform data from a walking phase cluster composed of at least one temporally continuous walking phase, a feature amount used for estimating the physical state is selected from the feature amounts for each of the extracted walking phase clusters based on a preset threshold, feature amount data including the selected feature amount is generated, and the generated feature amount data is output.

[0013] The program according to one aspect of the present disclosure causes a computer to execute a process of acquiring time-series data of sensor data related to foot movement, a process of extracting gait waveform data for one gait cycle from the time-series data of the sensor data, a process of normalizing the extracted gait waveform data, a process of extracting a feature amount related to the body state to be estimated from the normalized gait waveform data from a gait phase cluster composed of at least one gait phase that is temporally continuous, a process of selecting a feature amount used for estimating the body state based on a preset threshold value from the feature amounts for each of the extracted gait phase clusters, a process of generating feature amount data including the selected feature amount, and a process of outputting the generated feature amount data.

Advantages of the Invention

[0014] According to the present disclosure, it becomes possible to provide a feature amount data generation device or the like that can generate feature amount data enabling highly accurate estimation of the body state.

Brief Description of the Drawings

[0015]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Figure 18

Figure 19

Figure 20

Figure 21

Figure 22

Figure 23

Figure 24

Figure 25

Figure 26

Figure 27

Embodiments for Carrying Out the Invention

[0016] Hereinafter, embodiments for implementing the present invention will be described with reference to the drawings. However, although the embodiments described below have technically preferable limitations for implementing the present invention, they do not limit the scope of the invention below. In all the drawings used in the description of the following embodiments, the same reference numerals are given to the same parts unless otherwise specified. Also, in the following embodiments, repeated descriptions of the same configurations and operations may be omitted.

[0017] (First Embodiment) First, a gait measurement device according to the first embodiment will be described with reference to the drawings. The gait measurement device of this embodiment measures sensor data related to the movement of the feet measured according to the user's walking. The gait measurement device of this embodiment uses the measured sensor data to generate feature amount data used for estimating the physical state of the user.

[0018] (Configuration) FIG. 1 is a block diagram showing an example of the configuration of a gait measurement device 10 according to this embodiment. The gait measurement device 10 includes a sensor 11 and a feature amount data generation unit 12. In this embodiment, the gait measurement device 10 in which the sensor 11 and the feature amount data generation unit 12 are integrated will be described. For example, the gait measurement device 10 is installed on the footwear or the like of a subject (user) whose physical state is to be estimated. Hereinafter, the sensor 11 and the feature amount data generation unit 12 will be described individually.

[0019] 〔Sensor〕 The sensor 11 has an acceleration sensor 111 and an angular velocity sensor 112. FIG. 1 shows an example in which the acceleration sensor 111 and the angular velocity sensor 112 are included in the sensor 11. The sensor 11 may include sensors other than the acceleration sensor 111 and the angular velocity sensor 112. The description of sensors other than the acceleration sensor 111 and the angular velocity sensor 112 that may be included in the sensor 11 will be omitted.

[0020] The acceleration sensor 111 is a sensor that measures the acceleration in three axial directions (also called spatial acceleration). The acceleration sensor 111 measures the acceleration (also called spatial acceleration) as a physical quantity related to the movement of the foot. The acceleration sensor 111 outputs the measured acceleration to the gait measurement device 10. For example, as the acceleration sensor 111, a piezoelectric type, piezoresistive type, capacitive type, or other type of sensor can be used. The sensor used as the acceleration sensor 111 is not limited to the measurement method as long as it can measure the acceleration.

[0021] The angular velocity sensor 112 is a sensor that measures the angular velocity around three axes (also called spatial angular velocity). The angular velocity sensor 112 measures the angular velocity (also called spatial angular velocity) as a physical quantity related to the movement of the foot. The angular velocity sensor 112 outputs the measured angular velocity to the gait measurement device 10. For example, as the angular velocity sensor 112, a vibration type, capacitive type, or other type of sensor can be used. The sensor used as the angular velocity sensor 112 is not limited to the measurement method as long as it can measure the angular velocity.

[0022] The sensor 11 is realized by, for example, an inertial measurement device that measures acceleration and angular velocity. As an example of the inertial measurement device, an IMU (Inertial Measurement Unit) can be mentioned. The IMU includes an acceleration sensor 111 that measures the acceleration in three axial directions and an angular velocity sensor 112 that measures the angular velocity around three axes. The sensor 11 may be realized by an inertial measurement device such as a VG (Vertical Gyro) or an AHRS (Attitude Heading). Also, the sensor 11 may be realized by a GPS / INS (Global Positioning System / Inertial Navigation System). The sensor 11 may be realized by a device other than the inertial measurement device as long as it can measure the physical quantity related to the movement of the foot.

[0023] FIG. 2 is a conceptual diagram showing an example in which the gait measurement device 10 is disposed inside the shoe 100 for the right foot. In the example of FIG. 2, the gait measurement device 10 is installed at a position corresponding to the back side of the arch of the foot. For example, the gait measurement device 10 is disposed on an insole inserted into the shoe 100. For example, the gait measurement device 10 may be disposed on the bottom surface of the shoe 100. For example, the gait measurement device 10 may be embedded in the main body of the shoe 100. The gait measurement device 10 may be detachable from the shoe 100 or may not be detachable from the shoe 100. The gait measurement device 10 may be installed at a position other than the back side of the arch of the foot as long as it can measure sensor data related to the movement of the foot. Further, the gait measurement device 10 may be installed on socks worn by the user or ornaments such as anklets worn by the user. Further, the gait measurement device 10 may be directly attached to the foot or embedded in the foot. In FIG. 2, an example in which the gait measurement device 10 is installed in the shoe 100 for the right foot is shown. The gait measurement device 10 may be installed in the shoes 100 for both feet.

[0024] In the example of FIG. 2, a local coordinate system including the x-axis in the left-right direction, the y-axis in the front-back direction, and the z-axis in the up-down direction is set with respect to the gait measurement device 10 (sensor 11). The x-axis is positive to the left, the y-axis is positive to the rear, and the z-axis is positive upward. The direction of the axes set for the sensor 11 may be the same for the left and right feet or may be different for the left and right feet. For example, when sensors 11 produced with the same specifications are disposed inside the left and right shoes 100, the up-down directions (directions in the Z-axis direction) of the sensors 11 disposed in the left and right shoes 100 are the same direction. In that case, the three axes of the local coordinate system set for the sensor data derived from the left foot and the three axes of the local coordinate system set for the sensor data derived from the right foot are the same for the left and right.

[0025] FIG. 3 is a conceptual diagram for explaining the local coordinate system (x-axis, y-axis, z-axis) set for the gait measurement device 10 (sensor 11) installed on the back side of the arch of the foot and the world coordinate system (X-axis, Y-axis, Z-axis) set with respect to the ground. In the world coordinate system (X-axis, Y-axis, Z-axis), with the user standing upright facing the traveling direction, the lateral direction of the user is the X-axis direction (left is positive), the direction of the user's back is the Y-axis direction (backward is positive), and the direction of gravity is the Z-axis direction (vertically upward is positive). Note that the example in FIG. 3 conceptually shows the relationship between the local coordinate system (x-axis, y-axis, z-axis) and the world coordinate system (X-axis, Y-axis, Z-axis), and does not accurately show the relationship between the local coordinate system and the world coordinate system that varies according to the user's walking.

[0026] FIG. 4 is a conceptual diagram for explaining the plane set for the human body (also called the human body plane). In the present embodiment, a sagittal plane that divides the body into left and right, a coronal plane that divides the body into front and back, and a horizontal plane that divides the body horizontally are defined. Note that as shown in FIG. 4, in the state of standing upright with the center line of the foot facing the traveling direction, the world coordinate system and the local coordinate system coincide. In the present embodiment, the rotation in the sagittal plane with the x-axis as the rotation axis is defined as roll, the rotation in the coronal plane with the y-axis as the rotation axis is defined as pitch, and the rotation in the horizontal plane with the z-axis as the rotation axis is defined as yaw. Also, the rotation angle in the sagittal plane with the x-axis as the rotation axis is defined as the roll angle, the rotation angle in the coronal plane with the y-axis as the rotation axis is defined as the pitch angle, and the rotation angle in the horizontal plane with the z-axis as the rotation axis is defined as the yaw angle. In the present embodiment, when looking at the body from behind, the counterclockwise rotation in the coronal plane is defined as positive, and the clockwise rotation in the coronal plane is defined as negative.

[0027] 〔Feature amount data generation unit〕 The feature quantity data generation unit 12 includes an acquisition unit 121, a normalization unit 122, an extraction unit 123, a selection unit 125, a generation unit 126, and an output unit 127. For example, the feature quantity data generation unit 12 is realized by a microcomputer or a microcontroller that performs overall control and data processing of the gait measurement device 10. For example, the feature quantity data generation unit 12 has a CPU (Central Processing Unit), a RAM (Random Access Memory), a ROM (Read Only Memory), a flash memory, etc. The feature quantity data generation unit 12 controls the acceleration sensor 111 and the angular velocity sensor 112 to measure the angular velocity and acceleration. For example, the feature quantity data generation unit 12 may be mounted on the side of a mobile terminal (not shown) carried by the subject (user).

[0028] The acquisition unit 121 acquires the acceleration in the three-axis directions from the acceleration sensor 111. Also, the acquisition unit 121 acquires the angular velocity around the three axes from the angular velocity sensor 112. For example, the acquisition unit 121 performs AD conversion (Analog-to-Digital Conversion) on physical quantities (analog data) such as the acquired angular velocity and acceleration. Note that the physical quantities (analog data) measured by the acceleration sensor 111 and the angular velocity sensor 112 may be converted into digital data in each of the acceleration sensor 111 and the angular velocity sensor 112. The acquisition unit 121 outputs the converted digital data (also referred to as sensor data) to the normalization unit 122. The acquisition unit 121 may be configured to store the sensor data in a storage unit (not shown). The sensor data at least includes the acceleration data converted into digital data and the angular velocity data converted into digital data. The acceleration data includes the acceleration vector in the three-axis directions. The angular velocity data includes the angular velocity vector around the three axes. The acquisition time of those data is associated with the acceleration data and the angular velocity data. Also, the acquisition unit 121 may apply corrections such as mounting error, temperature correction, and linearity correction to the acceleration data and the angular velocity data.

[0029] The normalization unit 122 acquires sensor data from the acquisition unit 121. The normalization unit 122 extracts time-series data for one walking cycle (also referred to as walking waveform data) from the time-series data of the acceleration in three axial directions and the angular velocity around the three axes included in the sensor data. The normalization unit 122 normalizes (also referred to as the first normalization) the time of the extracted walking waveform data for one walking cycle to a walking cycle of 0 to 100% (percent). Timings such as 1% and 10% included in the walking cycle of 0 to 100% are also referred to as walking phases. Further, the normalization unit 122 normalizes (also referred to as the second normalization) the walking waveform data for one walking cycle that has been first-normalized so that the stance phase is 60% and the swing phase is 40%. The stance phase is a period during which at least a part of the sole of the foot is in contact with the ground. The swing phase is a period during which the sole of the foot is off the ground. By second-normalizing the walking waveform data, it is possible to suppress the deviation of the walking phase from which the feature amount is extracted from being disturbed by external disturbances.

[0030] Figure 5 is a conceptual diagram for explaining one walking cycle with the right foot as a reference. One walking cycle with the left foot as a reference is the same as that of the right foot. The horizontal axis in Figure 5 represents one walking cycle of the right foot starting from the point in time when the heel of the right foot touches the ground and ending at the point in time when the heel of the right foot touches the ground next. The horizontal axis in Figure 5 is first-normalized with one walking cycle being 100%. Further, the horizontal axis in Figure 5 is second-normalized so that the stance phase is 60% and the swing phase is 40%. One walking cycle of a single foot is roughly divided into a stance phase in which at least a part of the sole of the foot is in contact with the ground and a swing phase in which the sole of the foot is off the ground. The stance phase is further subdivided into a loading response period T1, a mid-stance period T2, a terminal stance period T3, and a pre-swing period T4. The swing phase is further subdivided into an initial swing period T5, a mid-swing period T6, and a terminal swing period T7. Note that Figure 5 is an example and does not limit the periods constituting one walking cycle or the names of those periods.

[0031] As shown in Fig. 5, in walking, a plurality of events (also called walking events) occur. E1 represents the event where the heel of the right foot touches the ground (heel contact) (HC: Heel Contact). E2 represents the event where the tip of the left foot leaves the ground while the sole of the right foot is in contact with the ground (opposite toe off) (OTO: Opposite Toe Off). E3 represents the event where the heel of the right foot is lifted while the sole of the right foot is in contact with the ground (heel rise) (HR: Heel Rise). E4 is the event where the heel of the left foot touches the ground (opposite heel strike) (OHS: Opposite Heel Strike). E5 represents the event where the tip of the right foot leaves the ground while the sole of the left foot is in contact with the ground (toe off) (TO: Toe Off). E6 represents the event where the left and right feet cross while the sole of the left foot is in contact with the ground (foot adjacent) (FA: Foot Adjacent). E7 represents the event where the tibia of the right foot becomes substantially perpendicular to the ground while the sole of the left foot is in contact with the ground (tibia vertical) (TV: Tibia Vertical). E8 represents the event where the heel of the right foot touches the ground (heel contact) (HC: Heel Contact). E8 corresponds to the end point of the walking cycle starting from E1 and also corresponds to the starting point of the next walking cycle. Note that Fig. 5 is an example and does not limit the events occurring in walking or the names of those events.

[0032] FIG. 6 is a diagram for explaining an example of detecting heel contact HC and toe-off TO from time-series data (solid line) of the acceleration in the traveling direction (Y-direction acceleration). The timing of heel contact HC is the timing of the minimum peak immediately after the maximum peak appearing in the time-series data of the acceleration in the traveling direction (Y-direction acceleration). The maximum peak serving as a mark for the timing of heel contact HC corresponds to the maximum peak of the walking waveform data for one walking cycle. The interval between consecutive heel contacts HC is one walking cycle. The timing of toe-off TO is the rising timing of the maximum peak that appears after the period of the stance phase in which no variation appears in the time-series data of the acceleration in the traveling direction (Y-direction acceleration). FIG. 6 also shows time-series data (dashed line) of the roll angle (angular velocity around the X axis). The timing at the midpoint between the timing when the roll angle is minimum and the timing when the roll angle is maximum corresponds to the midstance phase. For example, parameters such as walking speed, step length, cadence, internal rotation / external rotation, plantar flexion / dorsiflexion (also referred to as gait parameters) can be obtained based on the midstance phase.

[0033] FIG. 7 is a diagram for explaining an example of the walking waveform data normalized by the normalization unit 122. The normalization unit 122 detects heel contact HC and toe-off TO from the time-series data of the acceleration in the traveling direction (Y-direction acceleration). The normalization unit 122 extracts the interval between consecutive heel contacts HC as the walking waveform data for one walking cycle. The normalization unit 122 converts the horizontal axis (time axis) of the walking waveform data for one walking cycle to a walking cycle of 0 to 100% by the first normalization. In FIG. 7, the walking waveform data after the first normalization is shown by a dashed line. In the walking waveform data (dashed line) after the first normalization, the timing of toe-off TO is deviated from 60%.

[0034] In the example of FIG. 7, the normalization unit 122 normalizes the section from the heel contact HC with a walking phase of 0% to the toe-off TO following the heel contact HC to 0 to 60%. Further, the normalization unit 122 normalizes the section from the toe-off TO to the heel contact HC with a walking phase of 100% following the toe-off TO to 60 to 100%. As a result, the walking waveform data for one walking cycle is normalized into a section with a walking cycle of 0 to 60% (stance phase) and a section with a walking cycle of 60 to 100% (swing phase). In FIG. 7, the walking waveform data after the second normalization is shown by a solid line. In the walking waveform data (solid line) after the second normalization, the timing of the toe-off TO coincides with 60%.

[0035] FIGS. 6 to 7 show an example of extracting / normalizing the walking waveform data for one walking cycle based on the acceleration in the traveling direction (Y-direction acceleration). Regarding accelerations / angular velocities other than the acceleration in the traveling direction (Y-direction acceleration), the normalization unit 122 extracts / normalizes the walking waveform data for one walking cycle in accordance with the walking cycle of the acceleration in the traveling direction (Y-direction acceleration). Further, the normalization unit 122 may generate time-series data of angles around three axes by integrating the time-series data of angular velocities around the three axes. In that case, the normalization unit 122 also extracts / normalizes the walking waveform data for one walking cycle in accordance with the walking cycle of the acceleration in the traveling direction (Y-direction acceleration) regarding the angles around the three axes.

[0036] The normalization unit 122 may extract / normalize the gait waveform data for one gait cycle based on the acceleration / angular velocity other than the acceleration in the traveling direction (Y-direction acceleration). FIG. 8 is a diagram for explaining an example of detecting the heel contact HC and the toe-off TO from the time-series data of the vertical acceleration (Z-direction acceleration). The timing of the heel contact HC is the timing of the steep minimum peak appearing in the time-series data of the vertical acceleration (Z-direction acceleration). At the timing of the steep minimum peak, the value of the vertical acceleration (Z-direction acceleration) becomes almost zero. The minimum peak serving as a mark of the timing of the heel contact HC corresponds to the minimum peak of the gait waveform data for one gait cycle. The section between consecutive heel contacts HC is one gait cycle. The timing of the toe-off TO is the timing of the inflection point during the gentle increase after the time-series data of the vertical acceleration (Z-direction acceleration) passes through a section with little variation after the maximum peak immediately after the heel contact HC.

[0037] FIG. 9 is a diagram for explaining an example of the gait waveform data normalized by the normalization unit 122. The normalization unit 122 detects the heel contact HC and the toe-off TO from the time-series data of the vertical acceleration (Z-direction acceleration). The normalization unit 122 extracts the section between consecutive heel contacts HC as the gait waveform data for one gait cycle. The normalization unit 122 converts the horizontal axis (time axis) of the gait waveform data for one gait cycle to the gait cycle of 0 to 100% by the first normalization. In the figure 9 the gait waveform data after the first normalization is shown by a broken line. In the gait waveform data (broken line) after the first normalization, the timing of the toe-off TO is deviated from 60%.

[0038] In the example of FIG. 9, the normalization unit 122 normalizes the section from the heel contact HC with the gait phase of 0% to the toe-off TO following the heel contact HC to 0 to 60%. Also, the normalization unit 122 normalizes the section from the toe-off TO to the heel contact HC with the subsequent gait phase of 100% to 60 to 100%. As a result, the gait waveform data for one gait cycle is normalized into a section with a gait cycle of 0 to 60% (stance phase) and a section with a gait cycle of 60 to 100% (swing phase). In the figure 9The walking waveform data after the second normalization is shown by a solid line. In the walking waveform data after the second normalization (solid line), the timing of toe-off (TO) coincides with 60%.

[0039] Figs. 8 to 9 show an example of extracting / normalizing the walking waveform data for one walking cycle based on the vertical acceleration (Z-direction acceleration). For accelerations / angular velocities other than the vertical acceleration (Z-direction acceleration), the normalization unit 122 extracts / normalizes the walking waveform data for one walking cycle in accordance with the walking cycle of the vertical acceleration (Z-direction acceleration). Further, the normalization unit 122 may generate time-series data of angles around three axes by integrating the time-series data of angular velocities around the three axes. In that case, the normalization unit 122 also extracts / normalizes the walking waveform data for one walking cycle for the angles around the three axes in accordance with the walking cycle of the vertical acceleration (Z-direction acceleration). Further, the normalization unit 122 may extract / normalize the walking waveform data for one walking cycle based on both the forward acceleration (Y-direction acceleration) and the vertical acceleration (Z-direction acceleration). Further, the normalization unit 122 may extract / normalize the walking waveform data for one walking cycle based on accelerations, angular velocities, angles, etc. other than the forward acceleration (Y-direction acceleration) and the vertical acceleration (Z-direction acceleration).

[0040] The extraction unit 123 acquires gait waveform data for one gait cycle normalized by the normalization unit 122. The extraction unit 123 extracts feature quantities corresponding to the physical state to be estimated from the gait waveform data for one gait cycle. The extraction unit 123 extracts feature quantities for each gait phase cluster obtained by integrating temporally continuous gait phases based on preset conditions. For example, the extraction unit 123 extracts feature quantities used for estimating the first metatarsophalangeal angle (FMTPA) of the subject. For example, the extraction unit 123 extracts feature quantities used for estimating the center of pressure excursion index (CPEI). Note that the physical state to be estimated is not limited to the first metatarsophalangeal angle (FMTPA) or the center of pressure excursion index (CPEI) as long as it can be estimated based on sensor data related to the movement of the foot.

[0041] FIG. 10 is a conceptual diagram for explaining the extraction of feature quantities for estimating the physical state from the gait waveform data for one gait cycle. For example, the extraction unit 123 extracts temporally continuous gait phases i to i + m as the gait phase cluster C (i and m are natural numbers). The gait phase cluster C includes m +1 gait phases (constituent elements). That is, the number of gait phases (constituent elements) constituting the gait phase cluster C (also referred to as the number of constituent elements) is m +1 is. FIG. 10 shows an example in which the gait phase is an integer value, but the gait phase may be subdivided down to the decimal point. When the gait phase is subdivided down to the decimal point, the number of constituent elements of the gait phase cluster C becomes a number corresponding to the number of data points in the interval of the gait phase cluster. The extraction unit 123 extracts feature quantities from each of the gait phases i to i + m. When the gait phase cluster C is composed of a single gait phase j, the extraction unit 123 extracts feature quantities from the single gait phase j (j is a natural number).

[0042] The selection unit 125 selects, from among the feature quantities for estimating the physical state extracted by the extraction unit 123, the feature quantities with small fluctuations in the feature quantities. The smaller the number of components of the walking phase cluster, the greater the error due to the shift of the walking phase back and forth, and the greater the fluctuations. Therefore, for example, the selection unit 125 selects a feature quantity with small fluctuations according to the number of components of the walking phase cluster. For example, the selection unit 125 selects a feature quantity based on a preset threshold (also referred to as a selection threshold) with respect to the number of components of the walking phase cluster. For example, when the selection threshold is 5, the selection unit 125 selects a walking phase cluster with 5 or more components. In other words, when the selection threshold is 5, the selection unit 125 excludes a walking phase cluster with 4 or fewer components. If the number of components of the walking phase cluster is 5 or more, since it is averaged by the feature quantities of the walking phases that make up the same walking phase cluster, the influence of the walking phase with large fluctuations in the feature quantity can be mitigated. Note that the selection threshold set with respect to the number of components of the walking phase cluster is not limited to 5 and can be set arbitrarily.

[0043] Here, taking hallux valgus as an example, the selection of the feature quantity by the selection unit 125 will be described. The degree of hallux valgus can be evaluated by the first metatarsophalangeal angle FMTPA. The first metatarsophalangeal angle FMTPA is the angle of the metatarsophalangeal joint of the first toe (big toe). In the present embodiment, when the first metatarsophalangeal angle FMTPA exceeds 25 degrees, it is classified as hallux valgus. When the first metatarsophalangeal angle FMTPA is 15 degrees or more and 25 degrees or less, it is classified as having a tendency of hallux valgus. When the first metatarsophalangeal angle FMTPA is less than 15 degrees, it is classified as normal.

[0044] FIG. 11 is a correspondence table summarizing the feature quantities used for estimating the first metatarsophalangeal angle FMTPA. The correspondence table in FIG. 11 associates the walking waveform data from which the feature quantity is extracted, the number of the walking phase cluster, the walking phase (%) in which the walking phase cluster is extracted, the number of components, and the corresponding walking motion.

[0045] The walking waveform data Ax is the walking waveform data for one walking cycle regarding the time-series data of the lateral acceleration (X-direction acceleration). The walking waveform data Ax includes two walking phase clusters. The walking phase cluster C1 is the section of the walking phase from 22% to 24%. The number of components of the walking phase cluster C1 is 3. The walking motion corresponding to the section of the walking phase from 22% to 24% is the sole contact at the beginning of the mid-stance phase. The walking phase cluster C2 is the section of the walking phase from 27% to 29%. The number of components of the walking phase cluster C 2 is 3. The walking motion corresponding to the walking phase from 27% to 29% is the sole contact at the end of the mid-stance phase.

[0046] The walking waveform data Az is the walking waveform data for one walking cycle regarding the time-series data of the vertical acceleration (Z-direction acceleration). The walking waveform data Az includes one walking phase cluster. The walking phase cluster C3 is the section of the walking phase from 3% to 4%. The number of components of the walking phase cluster C3 is 2. The walking motion corresponding to the section of the walking phase from 3% to 4% is immediately after the heel contact.

[0047] The walking waveform data Gx is the walking waveform data for one walking cycle regarding the time-series data of the angular velocity around the X-axis (roll angular velocity). The walking waveform data Gx includes one walking phase cluster. The walking phase cluster C4 is the section of the walking phase from 35% to 46%. The number of components of the walking phase cluster C4 is 12. The walking motion corresponding to the section of the walking phase from 35% to 46% is the heel lift at the end of the stance phase.

[0048] The walking waveform data Gy is the walking waveform data for one walking cycle regarding the time-series data of the angular velocity around the Y-axis (pitch angular velocity). The walking waveform data Gy includes four walking phase clusters. The walking phase cluster C5 is the section of the walking phase from 22% to 23%. The number of components of the walking phase cluster C5 is 2. The walking motion corresponding to the section of the walking phase from 22% to 23% is the sole contact at the beginning of the mid-stance phase. The walking phase cluster C6 is the section of the walking phase from 27% to 28%. The number of components of the walking phase cluster C6 is 2. The walking motion corresponding to the section of the walking phase from 27% to 28% is the sole contact at the end of the mid-stance phase. The walking phase cluster C7 is the section of the walking phase from 46% to 56%. The number of components of the walking phase cluster C7 is 11. The walking motion corresponding to the section of the walking phase from 46% to 56% is from the end of the terminal stance phase to the pre-swing phase. The walking phase cluster C8 is the section of the walking phase from 68% to 72%. The number of components of the walking phase cluster C8 is 5. The walking motion corresponding to the section of the walking phase from 68% to 72% is the end of the initial swing phase.

[0049] The walking waveform data Ex is the walking waveform data for one walking cycle regarding the time-series data of the attitude angle (roll angle) around the X-axis. The attitude angle (roll angle) around the X-axis is obtained by integrating the angular velocity around the X-axis (roll angular velocity). The walking waveform data Ex includes one walking phase cluster. The walking phase cluster C9 is the section of the walking phase from 41% to 77%. The number of components of the walking phase cluster C9 is 12. The walking motion corresponding to the section of the walking phase from 41% to 77% is from the terminal stance phase to the end of the mid-swing phase.

[0050] The walking waveform data Ey is the walking waveform data for one walking cycle regarding the time-series data of the attitude angle (pitch angle) around the Y-axis. The attitude angle (pitch angle) around the Y-axis is obtained by integrating the angular velocity (pitch angular velocity) around the Y-axis. The walking waveform data Ey includes two walking phase clusters. The walking phase cluster C10 is the section of the walking phase from 23% to 25%. The number of components of the walking phase cluster C10 is 2. The walking motion corresponding to the section of the walking phase from 23% to 25% is the sole contact at the beginning of the mid-stance phase. The walking phase cluster C11 is the section of the walking phase from 54% to 63%. The number of components of the walking phase cluster C11 is 10. The walking motion corresponding to the section of the walking phase from 54% to 63% is around the toe-off.

[0051] Figure 12 is an example of the walking waveform data from which the feature amount used for estimating the first metatarsophalangeal angle FMTPA is extracted. Figure 12 is the walking waveform data Gy for one walking cycle regarding the time-series data of the angular velocity (pitch angular velocity) around the Y-axis. Figure 12 relates to the verification performed on 50 subjects. The verification in Figure 12 was performed under the condition that the subject wearing the shoes with the measuring device walked at a comfortable speed without specifying the walking speed or the like. The measurement was performed in a sequence where 50 subjects walked back and forth 4 times over a distance of 8 meters under the same conditions. The 50 subjects were classified into group A with the first metatarsophalangeal angle FMTPA exceeding 25 degrees, group B with the first metatarsophalangeal angle FMTPA between 15 degrees and 25 degrees, and group C with the first metatarsophalangeal angle FMTPA less than 15 degrees. In Figure 12, the waveform of group A is shown by a solid line, the waveform of group B is shown by a dashed line, and the waveform of group C is shown by a dotted-dashed line. In the sequence of walking back and forth 4 times over a distance of 8 meters, sensor data for about 50 steps was acquired. The sensor data acquired from each subject was averaged according to the number of steps.

[0052] The graph of FIG. 13 is a graph of the correlation coefficient between the value (the first metatarsophalangeal angle of the foot, FMTPA) related to the physical state to be estimated and the feature quantity. The walking phases (%) in which the maximum / minimum of the correlation coefficient between the first metatarsophalangeal angle of the foot, FMTPA, and the feature quantity are prominent constitute the walking phase clusters. In the case of the example of FIG. 13, for the walking phase clusters C5 to C8, the maximum / minimum of the correlation coefficient is prominent.

[0053] The graph of FIG. 14 is the number (also called the count number) determined to be significant in the correlation between the value (the first metatarsophalangeal angle of the foot, FMTPA) related to the physical state to be estimated and the feature quantity by the leave-one-subject-out correlation analysis. In the leave-one-subject-out correlation analysis, in order to remove the individual difference factors and verify whether the output value by the estimation model follows the essential distribution of the data, the correlation analysis is performed by excluding one subject at a time in order. In this verification example, the correlation analysis using the feature quantity data of 49 subjects obtained by excluding the feature quantity data of one subject from the feature quantity data of 50 subjects was repeated 50 times. In this verification, the threshold value of the count number was set to 47, and the feature quantities with a count number of 47 or more were extracted. The feature quantities with a count number less than 47 were regarded as not essentially reflecting the influence of the hallux valgus. Since the feature quantities with a count number less than 47 cause a low correlation, they are not extracted as the feature quantities of the walking phase cluster. The threshold value of the count number may be set according to the purpose.

[0054] Next, the variation of the first metatarsophalangeal angle (FMTPA) according to the number of components of the walking phase cluster will be described by comparing the walking phase cluster C5 and the walking phase cluster C7. FIG. 15 is a graph showing the relationship between the value of the first metatarsophalangeal angle (FMTPA) and the feature amount for the walking phase cluster C5. FIG. 16 is a graph showing the relationship between the value of the first metatarsophalangeal angle (FMTPA) and the feature amount for the walking phase cluster C7. The feature amounts in FIGS. 15 and 16 are the integrated average values of the signal intensities for each walking phase cluster. FIGS. 15 and 16 show regression lines (broken lines) obtained by fitting the relationship between the value of the first metatarsophalangeal angle (FMTPA) and the feature amount to a linear function. Compared with the walking phase cluster C7 (FIG. 16) with a large number of components, in the walking phase cluster C5 (FIG. 15) with a small number of components, the feature amount only varies slightly, while the change in the first metatarsophalangeal angle (FMTPA) varies greatly. In other words, compared with the walking phase cluster C5 (FIG. 15) with a small number of components, in the walking phase cluster C7 (FIG. 16) with a large number of components, the first metatarsophalangeal angle (FMTPA) does not change significantly even when the feature amount varies slightly. That is, the smaller the number of components of the walking phase cluster, the more sensitive the estimated value of the physical state to be estimated is to the change in the feature amount. Therefore, the selection unit 125 selects the feature amount of the walking phase cluster with a large number of components, for which the estimated value is less likely to change with respect to the change in the feature amount. In other words, the selection unit 125 excludes the feature amount of the walking phase cluster with a small number of components, for which the estimated value is likely to change with respect to the change in the feature amount. For example, the selection unit 125 selects the walking phase cluster according to the relationship between a preset selection threshold and the magnitude of the number of components. The selection unit 125 selects the walking phase cluster whose number of components is equal to or greater than the selection threshold. That is, the selection unit 125 excludes the walking phase cluster whose number of components is smaller than the selection threshold.

[0055] The selection unit 125 may determine the gait phase cluster to be excluded according to the value of the feature quantity. For example, for each gait phase cluster, a threshold value of the feature quantity (also referred to as a variation threshold value) is set in advance. The variation threshold value is set to a value at which the estimated value of the physical state to be estimated does not indicate an abnormal value. When the value of the feature quantity regarding the gait phase cluster exceeds the variation threshold value, the feature quantity regarding the gait phase cluster may be over-evaluated, and the estimated value of the physical state to be estimated may indicate an abnormal value. When estimating the physical state to be estimated by the multiple regression prediction method using the feature quantities extracted from a plurality of gait phase clusters, each feature quantity is weighted by multiplying by a coefficient for each of the plurality of feature quantities. The value of the feature quantity extracted from the gait phase cluster with a smaller number of components is smaller than the value of the feature quantity extracted from the gait phase cluster with a larger number of components. Therefore, a larger coefficient is multiplied by the value of the feature quantity extracted from the gait phase cluster with a smaller number of components compared to the value of the feature quantity extracted from the gait phase cluster with a larger number of components. Therefore, the variation of the feature quantity extracted from the gait phase cluster with a smaller number of components may have a great influence on the estimated value of the physical state. If the feature quantity extracted from the gait phase cluster with a smaller number of components is excluded, the influence on the estimated value due to the variation of the feature quantity is reduced.

[0056] The selection unit 125 may determine the gait phase cluster to be excluded according to the number of digits of the value of the feature quantity. For example, the selection unit 125 excludes the feature quantity whose number of digits of the value of the feature quantity varies by two or more digits compared to the feature quantities of other gait phase clusters. For example, the selection unit 125 excludes the feature quantity whose number of digits of the value of the feature quantity has varied by two or more digits.

[0057] When the value of the feature amount exceeds the variation threshold, the selection unit 125 may scan the feature amounts in the walking phases before and after the walking phase in which the feature amount was extracted. For example, the selection unit 125 scans the feature amounts in the walking phases within five points before and after the walking phase in which the feature amount exceeding the variation threshold was extracted. When the number of components of the walking phase cluster is small, the walking phases in which features related to the physical state appear may shift forward and backward. In such a case, the features of the physical state may be included before and after the walking phase in which the features related to the physical state are assumed to appear. Therefore, by scanning about five points before and after the walking phase in which the feature amount exceeding the variation threshold was extracted, there is a possibility of extracting the features related to the physical state. For example, when a feature amount below the variation threshold is extracted before and after the walking phase in which the feature amount exceeding the variation threshold was extracted, the selection unit 125 selects the feature amount of that walking phase.

[0058] For example, when the subject (user) walks obliquely, the variation of the vertical acceleration (Z-direction acceleration) also increases during the stance phase. Normally, during the stance period, since the foot is in contact with the ground, the acceleration in the traveling direction (Y-direction acceleration) and the lateral acceleration (X-direction acceleration) are almost zero. However, when the subject (user) walks obliquely, the acceleration in the oblique direction is detected by the sensor 11, and the acceleration in the traveling direction (Y-direction acceleration) and the lateral acceleration (X-direction acceleration) are detected. Using the feature amounts extracted from such sensor data may cause an incorrect determination of the physical state. Also, even if a steep measured value is measured due to factors such as noise, it may lead to an incorrect determination of the physical state. By removing the feature amounts that exceed the variation threshold, it is possible to suppress the incorrect determination of the physical state due to factors such as oblique walking and noise.

[0059] The generation unit 126 applies a feature quantity composition formula to the feature quantities (first feature quantities) extracted from each of the walking phases constituting the walking phase cluster to generate a feature quantity (second feature quantity) of the walking phase cluster. The feature quantity composition formula is a calculation formula set in advance for generating the feature quantity of the walking phase cluster. For example, the feature quantity composition formula is a calculation formula related to arithmetic operations. For example, the second feature quantity calculated using the feature quantity composition formula is the integrated average value, arithmetic average value, slope, variation, etc. of the first feature quantities in each walking phase included in the walking phase cluster. For example, the generation unit 126 applies, as the feature quantity composition formula, a calculation formula for calculating the slope and variation of the first feature quantities extracted from each of the walking phases constituting the walking phase cluster. For example, when the walking phase cluster is composed of a single walking phase, since the slope and variation cannot be calculated, a feature quantity composition formula for calculating the integrated average value, arithmetic average value, etc. may be used. The generation unit 126 outputs feature quantity data including the feature quantities for each generated walking phase cluster.

[0060] The output unit 127 outputs the feature quantity data generated by the generation unit 126. The output unit 127 outputs the feature quantity data of the generated walking phase cluster to an external system or the like that uses the feature quantity data.

[0061] Regarding the use of the feature amount data of the walking phase cluster output from the walking posture measurement device 10, no particular limitation is imposed. For example, the walking posture measurement device 10 is connected to an external system or the like constructed in a cloud or a server via a portable terminal (not shown) carried by a subject (user). The portable terminal (not shown) is a portable communication device. For example, the portable terminal is a portable communication device having a communication function such as a smartphone, a smartwatch, or a mobile phone. For example, the output unit 127 is connected to the portable terminal via a wire such as a cable. For example, the output unit 127 is connected to the portable terminal via wireless communication. For example, the walking posture measurement device 10 is connected to the portable terminal via a wireless communication function (not shown) conforming to a standard such as Bluetooth (registered trademark) or WiFi (registered trademark). Note that the communication function of the walking posture measurement device 10 may conform to a standard other than Bluetooth (registered trademark) or WiFi (registered trademark). The feature amount data of the walking phase cluster may be used by an application installed in the portable terminal. In that case, the portable terminal processes the feature amount data of the walking phase cluster by application software or the like installed in the portable terminal.

[0062] (Operation) Next, the operation of the walking posture measurement device 10 will be described with reference to the drawings. Here, the operation of the feature amount data generation unit 12 included in the walking posture measurement device 10 will be described. FIG. 17 is a flowchart for explaining the operation of the feature amount data generation unit 12. In the description along the flowchart of FIG. 17, the feature amount data generation unit 12 will be described as the operating entity.

[0063] In FIG. 17, first, the feature amount data generation unit 12 acquires time-series data of sensor data regarding the movement of the foot (step S11).

[0064] Next, the feature amount data generation unit 12 extracts gait waveform data for one gait cycle from the time-series data of the sensor data (step S12). The feature amount data generation unit 12 detects heel strike and toe off from the time-series data of the sensor data. The feature amount data generation unit 12 extracts the time-series data of the section between consecutive heel strikes as gait waveform data for one gait cycle.

[0065] Next, the feature amount data generation unit 12 normalizes the extracted gait waveform data for one gait cycle (step S13). The feature amount data generation unit 12 normalizes the gait waveform data for one gait cycle to a gait cycle of 0 to 100% (first normalization). Further, the feature amount data generation unit 12 normalizes the ratio of the stance phase to the swing phase of the gait waveform data for one gait cycle that has been first-normalized to 60:40 (second normalization).

[0066] Next, the feature amount data generation unit 12 extracts features from the gait phase corresponding to the physical state to be estimated with respect to the normalized gait waveform (step S14). For example, the feature amount data generation unit 12 extracts features corresponding to the physical state such as the first metatarsophalangeal angle FMTPA and the center of foot pressure trajectory index CPEI.

[0067] Next, the feature amount data generation unit 12 selects features based on a preset threshold regarding the number of components of the gait phase cluster (step S15). For example, the feature amount data generation unit 12 selects a gait phase cluster whose number of components is equal to or greater than the selection threshold. For example, the feature amount data generation unit 12 excludes a gait phase cluster whose number of components is less than the selection threshold. For example, the feature amount data generation unit 12 removes features that exceed the variation threshold.

[0068] Next, the feature amount data generation unit 12 generates features for each gait phase cluster using the selected features (step S16).

[0069] Next, the feature amount data generation unit 12 integrates the features for each gait phase cluster to generate feature amount data for one gait cycle (step S17).

[0070] Next, the feature quantity data generation unit 12 outputs the generated feature quantity data (step S18).

[0071] As described above, the gait measurement device of the present embodiment includes a sensor and a feature quantity data generation unit. The sensor has an acceleration sensor and an angular velocity sensor. The sensor measures the spatial acceleration using the acceleration sensor. The sensor measures the spatial angular velocity using the angular velocity sensor. The sensor generates sensor data related to the movement of the foot using the measured spatial acceleration and spatial angular velocity. The sensor transmits the generated sensor data to the feature quantity data generation device.

[0072] The feature quantity data generation device includes an acquisition unit, a normalization unit, an extraction unit, a selection unit, a generation unit, and an output unit. The acquisition unit acquires the time-series data of the sensor data related to the movement of the foot. The normalization unit extracts the gait waveform data for one gait cycle from the time-series data of the sensor data and normalizes the extracted gait waveform data. The extraction unit extracts features related to the body state to be estimated from the normalized gait waveform data from a gait phase cluster composed of at least one gait phase that is temporally continuous. The selection unit selects features used for estimating the body state from the features for each of the extracted gait phase clusters based on a preset threshold. The generation unit generates feature quantity data including the selected features. The output unit outputs the generated feature quantity data.

[0073] The gait measurement device of the present embodiment normalizes the gait waveform for one gait cycle and selects features used for estimating the body state based on a preset threshold. Therefore, according to the present embodiment, it is possible to generate feature quantity data that enables highly accurate estimation of the body state.

[0074] In one aspect of the present embodiment, when the value of the feature amount of the extracted walking phase cluster exceeds the variation threshold value set in advance for each feature amount of the walking phase cluster, the selection unit removes the feature amount that exceeds the variation threshold value. According to this aspect, when an abnormal value of the feature amount is detected, the abnormality that may be included in the feature amount data used for estimating the physical state can be eliminated by deleting the feature amount indicating the abnormal value.

[0075] In one aspect of the present embodiment, when the value of the feature amount of the extracted walking phase cluster exceeds the variation threshold value, the selection unit scans the feature amounts of the walking phases before and after the walking phase that constitutes the walking phase cluster, and selects the feature amounts that are below the variation threshold value. According to this aspect, when an abnormal value of the feature amount is detected, normal feature amounts can be extracted from the walking phases before and after the walking phase in which the feature amount indicating the abnormal value is detected.

[0076] In one aspect of the present embodiment, the selection unit selects the feature amounts of the walking phase clusters in which the number of components of the walking phases that constitute the walking phase cluster exceeds the selection threshold value. According to this aspect, by selecting a walking phase cluster with a large number of components that is highly resistant to noise and the like, it is possible to generate feature amount data that enables highly accurate estimation of the physical state. In other words, according to this aspect, by removing a walking phase cluster with a small number of components that is less resistant to noise and the like, it is possible to generate feature amount data that enables highly accurate estimation of the physical state.

[0077] In one aspect of the present embodiment, the normalization unit detects the timings of heel strike and toe-off from the time-series data of the sensor data. The normalization unit extracts the section between consecutive heel strikes as gait waveform data for one gait cycle. The normalization unit performs a first normalization in which the gait cycle of the gait waveform data has the previous heel strike as 0 percent and the subsequent heel strike as 100 percent. The normalization unit performs a second normalization in which the section between the previous heel strike and toe-off is 60 percent and the section between toe-off and the subsequent heel strike is 40 percent. According to this aspect, it is possible to suppress the deviation in the timings of gait events such as heel strike and toe-off detected from the gait waveform data for one gait cycle. Therefore, according to this aspect, it is possible to generate feature data that enables more accurate estimation of the physical state.

[0078] (Second Embodiment) Next, a physical state estimation system according to the second embodiment will be described with reference to the drawings. The physical state estimation system according to this embodiment estimates the physical state of a user based on sensor data regarding the movement of the feet measured in response to the user's walking.

[0079] (Configuration) FIG. 18 is a block diagram showing an example of the configuration of a physical state estimation system 2 according to this embodiment. The physical state estimation system 2 includes a gait measurement device 20 and an estimation device 23. In this embodiment, an example in which the gait measurement device 20 and the estimation device 23 are configured as separate hardware will be described. For example, the gait measurement device 20 is installed in the footwear or the like of a subject (user) whose physical state is to be estimated. For example, the function of the estimation device 23 is installed in a mobile terminal carried by the subject (user). The gait measurement device 20 has the same configuration as the gait measurement device 10 of the first embodiment. In the following, the description of the gait measurement device 20 will be omitted, and mainly the estimation device 23 will be described.

[0080] 〔Estimation Device〕 FIG. 19 is a block diagram showing an example of the configuration of the estimation device 23. The estimation device 23 includes a data reception unit 231, a storage unit 232, an estimation unit 233, and an estimation result output unit 235.

[0081] The data reception unit 231 receives the feature amount data from the gait measurement device 20. The data reception unit 231 outputs the received feature amount data to the estimation unit 233. The data reception unit 231 may receive the feature amount data from the gait measurement device 20 via a wired connection such as a cable, or may receive the feature amount data from the gait measurement device 20 via wireless communication. For example, the data reception unit 231 is configured to receive the feature amount data from the gait measurement device 20 via a wireless communication function (not shown) conforming to a standard such as Bluetooth (registered trademark) or WiFi (registered trademark). Note that the communication function of the data reception unit 231 may conform to a standard other than Bluetooth (registered trademark) or WiFi (registered trademark).

[0082] The storage unit 232 stores an estimation model for estimating the physical state of the estimation target using the feature amount data extracted from the walking waveform data. The storage unit 232 stores an estimation model learned for a plurality of subjects. For example, the storage unit 232 stores an estimation model for estimating the physical state learned for a plurality of subjects. The estimation model may be stored in the storage unit 232 at the time of factory shipment of the product or at the time of calibration before the user uses the physical state estimation system. Note that when using an estimation model stored in a storage device such as an external server, it may be configured to use the estimation model via an interface (not shown) connected to the storage device. In that case, it is not necessary to store the estimation model for estimating the physical state in the storage unit 232.

[0083] The estimation unit 233 acquires feature amount data from the data reception unit 231. The estimation unit 233 uses the acquired feature amount data to estimate the physical state of the object to be estimated. The estimation unit 233 inputs the feature amount data into the estimation model stored in the storage unit 232. The estimation unit 233 outputs an estimation result according to the output (estimated value) from the estimation model. When using an estimation model stored in an external storage device constructed in a cloud, server, etc., it may be configured to use the estimation model via an interface (not shown) connected to the storage device.

[0084] FIG. 20 is a conceptual diagram showing an example in which an estimated value is output by inputting feature amount data corresponding to sensor data measured along with a user's walking into an estimation model 230 constructed in advance for estimating the physical state of the object to be estimated. For example, in the case of the estimation model 230 for estimating the first metatarsophalangeal angle FMTPA, the first metatarsophalangeal angle FMTPA is output from the estimation model 230 according to the input of the feature amount data. For example, in the case of the estimation model 230 for estimating the center of foot pressure trajectory index CPEI, the center of foot pressure trajectory index CPEI is output from the estimation model 230 according to the input of the feature amount data. The estimation result regarding the physical characteristics is not limited as long as it is output according to the input of the feature amount data of the walking phase cluster by the estimation model 230.

[0085] For example, the estimation unit 233 estimates the physical state of the object to be estimated using the multiple regression prediction method. For example, the estimation unit 233 estimates the first metatarsophalangeal angle FMTPA using the following Equation 1. FMTPA = β1×C1 + β2×C2 + ··· + β11×C11 + β0 ··· (1) In the above Equation 1, C1, C2, ···, C11 are the feature amounts for each walking phase cluster used for the estimation of the first metatarsophalangeal angle FMTPA shown in the correspondence table of FIG. 11. β1, β2, ···, β11 are the coefficients multiplied by C1, C2, ···, C11. β0 is a constant term. For example, coefficients such as β1, β2, ···, β11 and the constant term β0 are stored in the storage unit 232.

[0086] In the above formula to 1 In this case, the value of the feature quantity of the walking phase cluster with a small number of components is sufficiently small compared to other walking phase clusters. Therefore, the coefficient multiplied by the feature quantity of the walking phase cluster with a small number of components is set to a larger value compared to the coefficient multiplied by other walking phase clusters. For example, in the above formula 1, β1 is set to about -100 and β2 is set to about 3000, while other coefficients are set to 20 or less.

[0087] The sudden change in the feature quantity of the walking phase cluster with a small number of components becomes a factor that greatly varies the estimated value of the physical state. In the present embodiment, in the selection of the feature quantity by the gait measurement device 20, the feature quantity that can be a factor of variation in the estimated value is removed. Therefore, the method of the present embodiment is less affected by the variation in the feature quantity of the walking phase cluster with a small number of components. If the feature quantity of the walking phase cluster with a small number of components is removed, the estimation accuracy of the physical state to be estimated may decrease. However, if the number of walking phase clusters that are the extraction sources of the plurality of feature quantities constituting the feature quantity data is large, the decrease in the estimation accuracy due to the removal of the feature quantity of the walking phase cluster with a small number of components can be ignored.

[0088] The estimation result output unit 235 outputs the estimation result of the physical state by the estimation unit 233. For example, the estimation result output unit 235 displays the estimation result of the physical state on the screen of the mobile terminal of the subject (user). For example, the estimation result output unit 235 outputs the estimation result to an external system or the like that uses the estimation result.

[0089] Regarding the use of the feature amount data of the walking phase cluster output from the estimation device 23, no particular limitation is imposed. For example, the estimation device 23 is connected to an external system or the like constructed in a cloud or a server via a portable terminal (not shown) carried by a subject (user). The portable terminal (not shown) is a portable communication device. For example, the portable terminal is a portable communication device having a communication function such as a smartphone, a smartwatch, or a mobile phone. For example, the estimation device 23 is connected to the portable terminal via a wired connection such as a cable. For example, the estimation device 23 is connected to the portable terminal via wireless communication. For example, the estimation device 23 is connected to the portable terminal via a wireless communication function (not shown) conforming to a standard such as Bluetooth (registered trademark) or WiFi (registered trademark). Note that the communication function of the estimation device 23 may conform to a standard other than Bluetooth (registered trademark) or WiFi (registered trademark). The estimation result of the physical state may be used by an application installed in the portable terminal. In that case, the portable terminal executes processing using the estimation result by application software or the like installed in the portable terminal.

[0090] (Operation) Next, the operation of the physical state estimation system 2 will be described with reference to the drawings. Here, the operation of the estimation device 23 included in the physical state estimation system 2 will be described. FIG. 21 is a flowchart for explaining the operation of the estimation device 23. In the description along the flowchart of FIG. 21, the estimation device 23 will be described as the operation subject.

[0091] In FIG. 21, first, the estimation device 23 acquires feature amount data generated using sensor data related to the movement of the feet (step S21).

[0092] Next, the estimation device 23 inputs the acquired feature amount data into an estimation model 230 that estimates the physical state of the estimation target (step S22).

[0093] Next, the estimation device 23 estimates the physical state of the object to be estimated according to the output (estimated value) from the estimation model 230 (step S23).

[0094] Next, the estimation device 23 outputs information regarding the estimated physical state (step S24).

[0095] 〔Application Example〕 Next, an application example according to the present embodiment will be described with reference to the drawings. In the following application example, an example is shown in which the estimation device 23 installed in the portable terminal carried by the user estimates the physical state using the feature amount data measured by the gait measurement device 20 disposed on the shoe.

[0096] FIG. 22 is a conceptual diagram showing an example in which the estimation result by the estimation device 23 is displayed on the screen of the portable terminal 260 carried by the user walking while wearing the shoe 200 on which the gait measurement device 20 is disposed. FIG. 22 is an example in which information regarding the estimation result using the feature amount data corresponding to the sensor data measured during the user's walking is displayed on the screen of the portable terminal 260.

[0097] FIG. 22 is an example in which the degree of hallux valgus progression according to the magnitude of the first metatarsophalangeal angle (FMTPA) is displayed on the screen of the portable terminal 260. In the example of FIG. 22, based on the feature amount data including the feature amounts extracted from the sensor data measured during the user's walking, information such as "Your FMTPA is 22 degrees. There is a tendency of hallux valgus." is displayed on the display unit of the portable terminal 260. The user who has confirmed the information displayed on the display unit of the portable terminal 260 can recognize the degree of hallux valgus progression of himself / herself. For example, when the degree of hallux valgus progression is high, a message recommending a medical examination at a hospital or the contact information of an appropriate hospital may be displayed on the display unit of the portable terminal 260.

[0098] Figure 22This is an example and does not limit the method of using the estimation result by the estimation device 23 of the present embodiment. For example, information regarding gait such as the degree of internal / external rotation of the left and right feet, the step length of the left and right feet, the trajectory of the rotation, symmetry, foot angle, etc. may be displayed on the screen of the mobile terminal 260.

[0099] As described above, the physical state estimation system of the present embodiment includes a gait measurement device and an estimation device. The gait measurement device acquires time-series data of sensor data related to the movement of the feet. The gait measurement device extracts gait waveform data for one walking cycle from the time-series data of the sensor data and normalizes the extracted gait waveform data. The gait measurement device extracts a feature quantity related to the physical state to be estimated from the normalized gait waveform data from a gait phase cluster composed of at least one gait phase that is temporally continuous. The gait measurement device selects a feature quantity used for estimating the physical state based on a preset threshold value from the feature quantities for each of the extracted gait phase clusters. The gait measurement device generates feature quantity data including the selected feature quantity. The gait measurement device outputs the generated feature quantity data to the estimation device.

[0100] The estimation device estimates the physical state to be estimated regarding the user wearing the footwear on which the gait measurement device is installed using the feature quantity data output from the gait measurement device. For example, the estimation device inputs the feature quantity data output from the gait measurement device into an estimation model and estimates the physical state of the user according to the output from the estimation model. For example, the estimation model is a model that has learned teacher data having, as explanatory variables, feature quantities extracted from a gait phase cluster in which features related to the physical state to be estimated appear, and having, as the objective variable, a value corresponding to the physical state to be estimated.

[0101] The physical state estimation system of the present embodiment estimates the physical state of the user using feature quantity data that enables highly accurate estimation of the physical state measured by the gait measurement device. Therefore, according to this aspect, highly accurate estimation of the physical state becomes possible.

[0102] (Third Embodiment) Next, a learning system according to the third embodiment will be described with reference to the drawings. The learning system of this embodiment generates an estimation model for estimating a physical state according to an input of feature quantities by learning using the feature quantity data extracted from the sensor data measured by the gait measurement device.

[0103] (Configuration) FIG. 23 is a block diagram showing an example of the configuration of the learning system 3 according to this embodiment. The learning system 3 includes a gait measurement device 30 and a learning device 35. The gait measurement device 30 and the learning device 35 may be connected by wire or wirelessly. The gait measurement device 30 and the learning device 35 may be configured as a single device. Also, excluding the gait measurement device 30 from the configuration of the learning system 3, the learning system 3 may be configured by only the learning device 35. Although only one gait measurement device 30 is shown in FIG. 23, two gait measurement devices 30 may be arranged, one on each of the left and right feet. Further, the learning device 35 may be configured to execute learning using the feature quantity data that has been generated in advance by the gait measurement device 30 and stored in a database without being connected to the gait measurement device 30.

[0104] The gait measurement device 30 is installed on at least one of the left and right feet. The gait measurement device 30 has the same configuration as the gait measurement device 10 of the first embodiment. The gait measurement device 30 includes an acceleration sensor and an angular velocity sensor. The gait measurement device 30 converts the measured physical quantity into digital data (also referred to as sensor data). The gait measurement device 30 generates gait waveform data for one normalized gait cycle from the time-series data of the sensor data. The gait measurement device 30 generates feature quantity data used for estimating the physical state of the estimation target. The gait measurement device 30 transmits the generated feature quantity data to the learning device 35. Note that the gait measurement device 30 may be configured to transmit the feature quantity data to a database (not shown) accessed by the learning device 35. The feature quantity data accumulated in the database is used for the learning of the learning device 35.

[0105] The learning device 35 receives feature data from the gait measurement device 30. When using the feature data stored in a database (not shown), the learning device 35 receives the feature data from the database. The learning device 35 executes learning using the received feature data. For example, the learning device 35 learns, as teacher data, the feature data extracted from the walking waveform data of a plurality of subjects and the value related to the physical state to be estimated according to the feature data. The learning algorithm executed by the learning device 35 is not particularly limited. The learning device 35 generates an estimation model learned for a plurality of subjects. The learning device 35 stores the generated estimation model. The estimation model learned by the learning device 35 may be stored in a storage device external to the learning device 35.

[0106] 〔Learning Device〕 Next, the details of the learning device 35 will be described with reference to the drawings. FIG. 24 is a block diagram showing an example of the detailed configuration of the learning device 35. The learning device 35 includes a reception unit 351, a learning unit 353, and a storage unit 355.

[0107] The reception unit 351 receives feature data from the gait measurement device 30. The reception unit 351 outputs the received feature data to the learning unit 353. The reception unit 351 may receive the feature data from the gait measurement device 30 via a wired connection such as a cable, or may receive the feature data from the gait measurement device 30 via wireless communication. For example, the reception unit 351 is configured to receive the feature data from the gait measurement device 30 via a wireless communication function (not shown) conforming to a standard such as Bluetooth (registered trademark) or WiFi (registered trademark). Note that the communication function of the reception unit 351 may conform to a standard other than Bluetooth (registered trademark) or WiFi (registered trademark).

[0108] The learning unit 353 acquires feature quantity data from the reception unit 351. The learning unit 353 executes learning using the acquired feature quantity data. For example, the learning unit 353 uses, as explanatory variables, the feature quantities extracted from a user whose certain physical state has been measured, and learns using, as teacher data, a data set in which the physical state of that user is the objective variable. For example, the learning unit 353 generates an estimation model for estimating a physical state based on feature quantity data learned for a plurality of users. For example, the learning unit 353 stores the estimation model learned for a plurality of users in the storage unit 355.

[0109] For example, the learning unit 353 executes learning using the algorithm of linear regression. For example, the learning unit 353 executes learning using the algorithm of support vector machine (SVM). For example, the learning unit 353 executes learning using the algorithm of Gaussian process regression (GPR). For example, the learning unit 353 executes learning using the algorithm of random forest (RF). For example, the learning unit 353 may execute unsupervised learning for classifying the user who is the source of the feature quantity data according to the feature quantity data. There is no particular limitation on the learning algorithm executed by the learning unit 353.

[0110] The learning unit 353 may execute learning using, as explanatory variables, the walking waveform data for one walking cycle. For example, the learning unit 353 executes supervised learning using, as explanatory variables, the walking waveform data of the acceleration in three axial directions, the angular velocity around three axes, and the angle (posture angle) around three axes, and using, as the objective variable, the correct value of the physical state to be estimated. For example, when the walking phase is set in 1% increments in the walking cycle from 0 to 100%, the learning unit 353 learns using 909 explanatory variables.

[0111] FIG. 25 is a conceptual diagram showing an example in which the learning unit 353 is caused to learn using, as teacher data, a data set of feature amount data D1 to Dn that are explanatory variables and data of a physical state P that is an objective variable (n is a natural number). For example, the learning unit 353 learns data regarding a plurality of subjects and generates an estimation model that outputs an output (estimated value) regarding the physical state to be estimated in response to an input of a feature amount extracted from sensor data.

[0112] The storage unit 355 stores an estimation model learned regarding a plurality of subjects. For example, the storage unit 355 stores an estimation model that estimates the physical state to be estimated, learned regarding a plurality of subjects. For example, the estimation model stored in the storage unit 355 is used for estimating the physical state by the estimation device 23 of the second embodiment.

[0113] As described above, the learning system of the present embodiment includes a gait measurement device and a learning device. The gait measurement device acquires time-series data of sensor data regarding the movement of the feet. The gait measurement device extracts gait waveform data for one gait cycle from the time-series data of the sensor data and normalizes the extracted gait waveform data. The gait measurement device extracts, from the normalized gait waveform data, a feature amount regarding the physical state to be estimated from a gait phase cluster constituted by at least one gait phase that is temporally continuous. The gait measurement device selects, from the feature amounts for each of the extracted gait phase clusters, a feature amount used for estimating the physical state based on a preset threshold value. The gait measurement device generates feature amount data including the selected feature amount. The gait measurement device outputs the generated feature amount data to the learning device.

[0114] The learning device has a receiving unit, a learning unit, and a storage unit. The receiving unit acquires the feature amount data generated by the gait measurement device. The learning unit executes learning using the feature amount data. The learning unit generates an estimation model that outputs a physical state in response to the input of the feature amount (second feature amount) of the gait phase cluster extracted from the time-series data of the sensor data measured as the user walks. For example, the learning unit generates an estimation model that outputs the degree of hallux valgus (first metatarsophalangeal angle, FMTPA) in response to the input of the feature amount (second feature amount) of the gait phase cluster extracted from the time-series data of the sensor data measured as the user walks. The estimation model generated by the learning unit is stored in the storage unit.

[0115] The learning system of this embodiment generates an estimation model using the feature amount data measured by the gait measurement device, which enables highly accurate estimation of the physical state. Therefore, according to this aspect, an estimation model that enables highly accurate estimation of the physical state can be generated.

[0116] (Fourth Embodiment) Next, the feature amount data generation device according to the fourth embodiment will be described with reference to the drawings. The feature amount data generation device of this embodiment has a simplified configuration of the feature amount data generation unit included in the gait measurement devices of the first to third embodiments.

[0117] FIG. 26 is a block diagram showing an example of the configuration of the feature amount data generation device 42 according to this embodiment. The feature amount data generation device 42 includes an acquisition unit 421, a normalization unit 422, an extraction unit 423, a selection unit 425, a generation unit 426, and an output unit 427.

[0118] The acquisition unit 421 acquires time-series data of sensor data related to the movement of the feet. The normalization unit 422 extracts gait waveform data for one gait cycle from the time-series data of the sensor data and normalizes the extracted gait waveform data. The extraction unit 423 extracts, from the normalized gait waveform data, feature quantities related to the physical state to be estimated, from a gait phase cluster composed of at least one temporally continuous gait phase. The selection unit 425 selects, from the feature quantities for each of the extracted gait phase clusters, feature quantities to be used for estimating the physical state, based on a preset threshold value. The generation unit 426 generates feature quantity data including the selected feature quantities. The output unit 427 outputs the generated feature quantity data.

[0119] As described above, in the present embodiment, the gait waveform for one gait cycle is normalized, and feature quantities to be used for estimating the physical state are selected based on a preset threshold value. Therefore, according to the present embodiment, it is possible to generate feature quantity data that enables highly accurate estimation of the physical state.

[0120] (Hardware) Here, regarding the hardware configuration for executing the control and processing according to each embodiment of the present disclosure, the information processing apparatus 90 in FIG. 27 will be described as an example. Note that the information processing apparatus 90 in FIG. 27 is a configuration example for executing the control and processing of each embodiment, and does not limit the scope of the present disclosure.

[0121] As shown in FIG. 27, the information processing apparatus 90 includes a processor 91, a main storage device 92, an auxiliary storage device 93, an input / output interface 95, and a communication interface 96. In FIG. 27, the interface is abbreviated as I / F (Interface). The processor 91, the main storage device 92, the auxiliary storage device 93, the input / output interface 95, and the communication interface 96 are connected to each other via a bus 98 so as to be capable of data communication. Further, the processor 91, the main storage device 92, the auxiliary storage device 93, and the input / output interface 95 are connected to a network such as the Internet or an intranet via the communication interface 96.

[0122] The processor 91 expands the program stored in the auxiliary storage device 93 or the like into the main storage device 92. The processor 91 executes the program expanded in the main storage device 92. In the present embodiment, a configuration using the software program installed in the information processing apparatus 90 may be employed. The processor 91 executes the control and processing according to each embodiment.

[0123] The main storage device 92 has an area where the program is expanded. In the main storage device 92, the program stored in the auxiliary storage device 93 or the like is expanded by the processor 91. The main storage device 92 is realized by a volatile memory such as a DRAM (Dynamic Random Access Memory), for example. Further, a non-volatile memory such as an MRAM (Magnetoresistive Random Access Memory) may be configured / added as the main storage device 92.

[0124] The auxiliary storage device 93 stores various data such as programs. The auxiliary storage device 93 is realized by a local disk such as a hard disk or a flash memory. Note that it is also possible to configure to store various data in the main storage device 92 and omit the auxiliary storage device 93.

[0125] The input / output interface 95 is an interface for connecting the information processing apparatus 90 and peripheral devices based on standards and specifications. The communication interface 96 is an interface for connecting to an external system or device through 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 made common as an interface for connecting to external devices.

[0126] The information processing apparatus 90 may be connected with input devices such as a keyboard, a mouse, and a touch panel as necessary. These input devices are used for inputting information and settings. When using a touch panel as an input device, the display screen of the display device may also serve as the interface of the input device. Data communication between the processor 91 and the input device may be mediated by the input / output interface 95.

[0127] In addition, the information processing apparatus 90 may be equipped with a display device for displaying information. When equipped with a display device, it is preferable that the information processing apparatus 90 is provided with a display control device (not shown) for controlling the display of the display device. The display device may be connected to the information processing apparatus 90 via the input / output interface 95.

[0128] Furthermore, the information processing apparatus 90 may be equipped with a drive device. The drive device mediates the reading of data and programs from the recording medium and the writing of the processing results of the information processing apparatus 90 to the recording medium between the processor 91 and the recording medium (program recording medium). The drive device may be connected to the information processing apparatus 90 via the input / output interface 95.

[0129] The above is an example of a hardware configuration for enabling the control and processing according to each embodiment of the present invention. Note that the hardware configuration in FIG. 27 is an example of a hardware configuration for executing the control and processing according to each embodiment, and does not limit the scope of the present invention. Also, a program for causing a computer to execute the control and processing according to each embodiment is included in the scope of the present invention. Furthermore, a program recording medium on which the program according to each embodiment is recorded is included in the scope of the present invention. The recording medium can be realized by, for example, an optical recording medium such as a CD (Compact Disc) or a DVD (Digital Versatile Disc). The recording medium may be realized by a semiconductor recording medium such as a USB (Universal Serial Bus) memory or an SD (Secure Digital) card. Also, the recording medium may be realized by a magnetic recording medium such as a flexible disk or other recording media. When the program executed by the processor is recorded on the recording medium, the recording medium corresponds to a program recording medium.

[0130] The components of each embodiment may be arbitrarily combined. Also, the components of each embodiment may be realized by software or by a circuit.

[0131] Although the present invention has been described with reference to the embodiments above, the present invention is not limited to the above embodiments. Various changes that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention.

Explanation of Reference Numerals

[0132] 2 Body state estimation system 3 Learning system 10, 20, 30 Gait measurement device 11 Sensor 12 Feature data generation unit 23 Estimation device 35 Learning device 42 Feature data generation device 111 Acceleration sensor 112 Angular velocity sensor 121, 421 Acquisition Unit 122, 422 Normalization Unit 123, 423 Extraction Unit 125, 425 Selection Unit 126, 426 Generation Unit 127, 427 Output Unit 230 Estimation Model 231 Data Reception Unit 232 Storage Unit 233 Estimation Unit 235 Estimation Result Output Unit 351 Reception Unit 353 Learning Unit 355 Storage Unit

Claims

1. An acquisition means for acquiring time-series data of sensor data related to foot movement; A normalization means for extracting gait waveform data for one gait cycle from the time-series data of the sensor data and normalizing the extracted gait waveform data; An extraction means for extracting a feature quantity related to a physical state to be estimated from the normalized gait waveform data from a gait phase cluster composed of at least one gait phase that is temporally continuous; A selection means for selecting a feature quantity used for estimating a physical state based on a preset threshold value from the feature quantities for each of the extracted gait phase clusters; A generation means for generating feature quantity data including the selected feature quantity; An output means for outputting the generated feature quantity data, and comprising: The selection means is: A feature quantity data generation device that selects a feature quantity that is equal to or greater than a preset selection threshold value regarding the number of components of the gait phase cluster and is equal to or less than a variation threshold value set to a value indicating no abnormal value in the estimated value of the physical state to be estimated.

2. The selection means is: The feature quantity data generation device according to claim 1, wherein when the value of the feature quantity of the extracted gait phase cluster exceeds the variation threshold value, the feature quantity that exceeds the variation threshold value is removed, thereby selecting a feature quantity that is equal to or less than the variation threshold value.

3. The selection means is: The feature quantity data generation device according to claim 1, wherein when the value of the feature quantity of the extracted gait phase cluster exceeds the variation threshold value, the feature quantities of the gait phases before and after the gait phase constituting the gait phase cluster whose feature quantity value exceeds the variation threshold value are scanned, and a feature quantity that is less than the variation threshold value is selected.

4. The selection means is: The feature quantity data generation device according to any one of claims 1 to 3, which selects a feature quantity of a gait phase cluster in which the number of components of the gait phase constituting the gait phase cluster exceeds a selection threshold value.

5. The normalization means is: Detecting the timing of heel strike and toe-off from the time-series data of the sensor data; Extracting an interval between consecutive heel strikes as the gait waveform data for one gait cycle; Performing a first normalization in which the gait cycle of the gait waveform data is set to 0 percent for the preceding heel strike and 100 percent for the subsequent heel strike. Execute a second normalization in which the section between the preceding heel strike and the subsequent toe-off is set to 60 percent and the section between the toe-off and the subsequent heel strike is set to 40 percent. The feature amount data generation device according to any one of claims 1 to 4.

6. A feature amount data generation device according to any one of claims 1 to 5, A sensor that is installed in a user's footwear, which is an object of estimation of the physical state, measures spatial acceleration and spatial angular velocity, generates sensor data related to the movement of the foot using the measured spatial acceleration and spatial angular velocity, and transmits the generated sensor data to the feature amount data generation device. A gait measurement device comprising:

7. The gait measurement device according to claim 6, An estimation device that estimates an object physical state related to a user wearing the footwear in which the gait measurement device is installed using the feature amount data output from the gait measurement device. A physical state estimation system comprising:

8. The estimation device Inputs the feature amount data output from the gait measurement device into an estimation model that has learned teacher data with feature amounts extracted from a gait phase cluster in which features related to the physical state to be estimated appear as explanatory variables and values corresponding to the physical state to be estimated as target variables, and estimates the physical state of the user according to the output from the estimation model. The physical state estimation system according to claim 7.

9. A computer Obtains time series data of sensor data related to the movement of the foot, Extracts gait waveform data for one gait cycle from the time series data of the sensor data, Normalizes the extracted gait waveform data, Extracts feature amounts related to the physical state to be estimated from the normalized gait waveform data from a gait phase cluster composed of at least one temporally continuous gait phase, Selects feature amounts to be used for estimating the physical state based on a preset threshold value from the feature amounts for each of the extracted gait phase clusters, Generates feature amount data including the selected feature amounts, Outputs the generated feature amount data, In the selection, A feature amount data generation method for selecting a feature amount that is equal to or greater than a preset selection threshold value regarding the number of components of the gait phase cluster and is equal to or less than a variation threshold value set to a value that does not indicate an abnormal value for the estimated value of the physical state to be estimated.

10. To a computer, A process of obtaining time series data of sensor data related to the movement of the foot, A process of extracting walking waveform data for one walking cycle from the time-series data of the sensor data, A process of normalizing the extracted walking waveform data, A process of extracting, from the normalized walking waveform data, a feature quantity related to the physical state to be estimated from a walking phase cluster composed of at least one walking phase that is temporally continuous, A process of selecting, from the feature quantities for each of the extracted walking phase clusters, a feature quantity used for estimating the physical state based on a preset threshold value, A process of generating feature quantity data including the selected feature quantity, A process of outputting the generated feature quantity data, In the process of the selection, A process of selecting a feature quantity that is equal to or greater than a preset selection threshold value with respect to the number of components of the walking phase cluster and is equal to or less than a variation threshold value set to a value that does not indicate an abnormal value for the estimated value of the physical state to be estimated. A program for executing.

Images