Discrimination device, discrimination method, and program

Abstract

To provide a discrimination device capable of discriminating a walking situation concerning an arbitrary object person.SOLUTION: A discrimination device comprises: a data acquisition unit which acquires sensor data measured corresponding to the movement of feet; a calculation unit which calculates a relative change value indicating relative change from an advancing axis for each walking cycle using time series data of the acquired sensor data; a discrimination unit which discriminates the walking situation using time series data of the relative change value in an object period; and an output unit which outputs walking information including the discriminated walking situation.SELECTED DRAWING: Figure 33

Description

[Technical Field]

[0001] The present disclosure relates to a discrimination device, a discrimination method, and a program. [Background technology]

[0002] With growing interest in healthcare, services that provide information based on gait patterns are gaining attention. For example, technology is being developed to analyze gait patterns using sensor data measured by sensors mounted on footwear such as shoes. Time-series data from sensor data reveals characteristics associated with walking events related to physical conditions. If the subject's health condition can be estimated based on the characteristics associated with walking events, early detection and prevention of diseases will become possible.

[0003] Patent Document 1 discloses a walking condition measuring device in which a measuring unit for acquiring walking information is mounted in a shoe insole. The device in Patent Document 1 acquires data on acceleration in the vertical direction of the foot and data on the elevation and depression angles of the toes. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 2019-217182 Summary of the Invention [Problem to be solved by the invention]

[0005] To accurately estimate a subject's health condition, it is preferable to use data measured during straight walking (normal walking) on ​​flat ground. However, the method of Patent Document 1 could not distinguish between normal walking and walking on meandering roads, stairs, or slopes (exceptional walking). Therefore, the method of Patent Document 1 could potentially determine that a subject's health condition is abnormal based on data measured during exceptional walking. For subjects with no health problems, data measured during exceptional walking can be removed by setting a threshold for the data. However, for subjects with weakened muscles, such as elderly people or rehabilitation patients, the data strength is weak, making it difficult to distinguish between exceptional walking and normal walking. It is desirable to be able to determine the walking status of any subject, including elderly people and rehabilitation patients, using data corresponding to their walking.

[0006] An object of the present disclosure is to provide a discrimination device, a discrimination method, and a program that can discriminate the walking status of any subject. [Means for solving the problem]

[0007] A discrimination device according to one aspect of the present disclosure includes a data acquisition unit that acquires sensor data measured in accordance with foot movement, a calculation unit that calculates a relative change value indicating a relative change from the axis of progression for each walking cycle using time-series data of the acquired sensor data, a discrimination unit that discriminates a walking condition using time-series data of the relative change value during a target period, and an output unit that outputs walking information including the discriminated walking condition.

[0008] In a discrimination method according to one aspect of the present disclosure, a computer acquires sensor data measured in accordance with foot movement, calculates a relative change value indicating a relative change from the axis of progression for each walking cycle using time-series data of the acquired sensor data, discriminates the walking condition using the time-series data of the relative change value during a target period, and outputs walking information including the discriminated walking condition.

[0009] A program according to one aspect of the present disclosure causes a computer to perform the following processes: acquiring sensor data measured in accordance with foot movement; calculating a relative change value indicating a relative change from the axis of progression for each walking cycle using time-series data of the acquired sensor data; determining a walking condition using time-series data of the relative change value during a target period; and outputting walking information including the determined walking condition. [Effects of the Invention]

[0010] According to the present disclosure, it is possible to provide a discrimination device, a discrimination method, and a program that can discriminate the walking status of any subject. [Brief explanation of the drawings]

[0011] [Figure 1] 1 is a block diagram showing an example of the configuration of a gait measurement system according to the present disclosure. FIG. [Figure 2] 1 is a block diagram illustrating an example of a configuration of a measurement device according to the present disclosure. [Figure 3] FIG. 1 is a conceptual diagram showing an example in which a measurement device according to the present disclosure is placed inside the shoes of both feet. [Figure 4] FIG. 1 is a conceptual diagram for explaining a local coordinate system and a world coordinate system in the present disclosure. [Figure 5] FIG. 2 is a conceptual diagram for explaining a human body plane set for a human body. [Figure 6] FIG. 1 is a conceptual diagram for explaining a stride cycle based on the right foot. [Figure 7] 1 is a block diagram illustrating an example of a configuration of a determination device according to the present disclosure. [Figure 8] 10A and 10B are conceptual diagrams for explaining a relative change value calculated by a discrimination device according to the present disclosure. [Figure 9] An example of a trajectory when walking along a curve (curve walking) is shown in the form of footprints. [Figure 10] An example of the trajectory of a staggered walk is shown in the form of footprints. [Figure 11]1 is a conceptual diagram for explaining an example of estimation of a walking state by a discrimination device according to the present disclosure. [Figure 12] 10 is a flowchart illustrating an example of an operation of the discrimination device according to the present disclosure. [Figure 13] 10 is a flowchart illustrating an example of a relative change value calculation process performed by the discrimination device according to the present disclosure. [Figure 14] 1 is a block diagram illustrating an example of a configuration of a determination device according to the present disclosure. [Figure 15] 10A and 10B are conceptual diagrams illustrating examples of displaying information according to walking conditions determined by a determination device according to the present disclosure. [Figure 16] 10A and 10B are conceptual diagrams illustrating examples of displaying information according to walking conditions determined by a determination device according to the present disclosure. [Figure 17] 1 is a block diagram illustrating an example of a configuration of a determination device according to the present disclosure. [Figure 18] 10A and 10B are conceptual diagrams for explaining a relative change value calculated by a discrimination device according to the present disclosure. [Figure 19] 1 is a conceptual diagram for explaining an example of a walking state to be discriminated by a discrimination device in the present disclosure. [Figure 20] 1 is a conceptual diagram for explaining an example of a walking state to be discriminated by a discrimination device in the present disclosure. [Figure 21] 1 is a conceptual diagram for explaining an example of estimation of a walking state by a discrimination device according to the present disclosure. [Figure 22] 10 is a flowchart illustrating an example of a relative change value calculation process performed by the discrimination device according to the present disclosure. [Figure 23] 10A and 10B are conceptual diagrams illustrating examples of displaying information according to walking conditions determined by a determination device according to the present disclosure. [Figure 24] 10A and 10B are conceptual diagrams illustrating examples of displaying information according to walking conditions determined by a determination device according to the present disclosure. [Figure 25] 10A and 10B are conceptual diagrams illustrating examples of displaying information according to walking conditions determined by a determination device according to the present disclosure. [Figure 26] 1 is a block diagram illustrating an example of a configuration of a determination device according to the present disclosure. [Figure 27] 10 is a flowchart illustrating an example of an operation of the discrimination device according to the present disclosure. [Figure 28] 1 is a block diagram illustrating an example of a configuration of a determination device according to the present disclosure. [Figure 29] FIG. 10 is a conceptual diagram showing an example of a user interface for inputting tags according to the present disclosure displayed on the screen of a mobile terminal. [Figure 30] 10 is a flowchart illustrating an example of an operation of the discrimination device according to the present disclosure. [Figure 31] 10A and 10B are conceptual diagrams illustrating examples of displaying information according to walking conditions determined by a determination device according to the present disclosure. [Figure 32] 10A and 10B are conceptual diagrams illustrating examples of displaying information according to walking conditions determined by a determination device according to the present disclosure. [Figure 33] 1 is a block diagram illustrating an example of a configuration of a determination device according to the present disclosure. [Figure 34] 10 is a flowchart illustrating an example of an operation of the discrimination device according to the present disclosure. [Figure 35] FIG. 2 is a block diagram illustrating an example of a hardware configuration for executing control and processing in the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0012] Below, embodiments for implementing the present disclosure will be described using the drawings. In this disclosure, the drawings used in the description of each embodiment relate to one or more embodiments. Furthermore, elements included in each drawing may apply to one or more embodiments. The embodiments described below are limited in a way that is technically preferable for implementing the present disclosure, but this does not limit the scope of the disclosure to the following. In all drawings used to describe the following embodiments, similar parts are designated by the same reference numerals unless otherwise specified. In the following embodiments, repeated description of similar configurations and operations may be omitted. The direction of arrows in the drawings is an example and does not limit the direction of data, signals, etc.

[0013] (First embodiment) First, an example of a gait measurement system according to a first embodiment will be described with reference to the drawings. The gait measurement system according to this embodiment uses sensor data relating to foot movements according to the user's walking to determine the walking state of the user. Walking states include normal walking and exceptional walking. Normal walking refers to a linear walking state on flat ground. Exceptional walking refers to a walking state different from normal walking. For example, exceptional walking includes walking on meandering roads, stairs, or slopes. This embodiment will exemplify distinguishing between normal walking and non-linear exceptional walking on flat ground.

[0014] (composition) FIG. 1 is a block diagram showing an example of the configuration of a gait measurement system according to the present disclosure. Gait measurement system 1 includes a measurement device 10 and a discrimination device 12. For example, measurement device 10 is attached to the footwear of a subject (user) whose physical state is to be estimated. For example, the functions of discrimination device 12 are installed in a mobile device carried by the subject (user). Below, the configurations of measurement device 10 and discrimination device 12 will be described separately.

[0015] [Measuring equipment] 2 is a block diagram showing an example of the configuration of a measurement device according to the present disclosure. The measurement device 10 includes a sensor 110, a control unit 113, a communication unit 115, and a power supply 117. The sensor 110 includes an acceleration sensor 111 and an angular velocity sensor 112. The sensor 110 may include sensors other than the acceleration sensor 111 and the angular velocity sensor 112. A description of sensors other than the acceleration sensor 111 and the angular velocity sensor 112 that may be included in the sensor 110 will be omitted.

[0016] The acceleration sensor 111 is a sensor that measures acceleration in three axial directions (also called spatial acceleration). The acceleration sensor 111 measures acceleration as a physical quantity related to foot movement. The acceleration sensor 111 outputs the measured acceleration to the control unit 113. For example, a piezoelectric, piezo-resistive, or capacitance type sensor can be used as the acceleration sensor 111. There are no limitations on the sensor used as the acceleration sensor 111 as long as it can measure acceleration.

[0017] The angular velocity sensor 112 is a sensor that measures angular velocity around three axes (also called spatial angular velocity). The angular velocity sensor 112 measures angular velocity as a physical quantity related to foot movement. The angular velocity sensor 112 outputs the measured angular velocity to the control unit 113. For example, a vibration type or capacitance type sensor can be used as the angular velocity sensor 112. There are no limitations on the sensor used as the angular velocity sensor 112 as long as it can measure angular velocity.

[0018] The sensor 110 is realized by, for example, an inertial measurement unit that measures acceleration and angular velocity. An example of an inertial measurement unit is an IMU (Inertial Measurement Unit). The IMU includes an acceleration sensor 111 that measures acceleration in three axial directions and an angular velocity sensor 112 that measures angular velocity around three axes. The sensor 110 may be realized by an inertial measurement unit such as a VG (Vertical Gyro) or an AHRS (Attitude Heading Reference System). The sensor 110 may also be realized by a GPS / INS (Global Positioning System / Inertial Navigation System). The sensor 110 may be realized by a device other than an inertial measurement unit as long as it can measure physical quantities related to foot movement.

[0019] FIG. 3 is a conceptual diagram showing an example in which measurement devices according to the present disclosure are placed inside shoes of both feet. In the example of FIG. 3, the measurement device 10 is placed at a position corresponding to the back of the arch of the foot. For example, the measurement device 10 is placed in an insole inserted into the shoe 100. For example, the measurement device 10 may be placed on the bottom of the shoe 100. For example, the measurement device 10 may be embedded in the body of the shoe 100. The measurement device 10 may be detachable from the shoe 100 or may not be detachable from the shoe 100. The measurement device 10 may be placed at a position other than the back of the arch of the foot as long as it can measure sensor data related to foot movement. The measurement device 10 may also be placed in socks worn by the user or in an accessory such as an anklet worn by the user. The measurement device 10 may also be attached directly to the foot or embedded in the foot. The measurement device 10 may also be placed inside one of the shoes 100 as long as it can measure data that can be used to estimate a physical state.

[0020] In the example of FIG. 3, a local coordinate system is set with the measuring device 10 (sensor 110) as the reference, and includes an x-axis in the left-right direction, a y-axis in the front-back direction, and a z-axis in the up-down direction. FIG. 3 shows an example in which the same coordinate system is set for the left foot and the right foot. For example, if sensors 110 manufactured to the same specifications are placed in left and right shoes 100, the up-down orientations (Z-axis orientations) of the sensors 110 placed in the left and right shoes 100 are the same. In this case, the three axes of the local coordinate system set for the sensor data derived from the left foot and the three axes of the local coordinate system set for the sensor data derived from the right foot are the same for the left and right. In the present disclosure, the x-axis is positive to the left, the y-axis is positive forward, and the z-axis is positive upward. The positive and negative orientations of the x-axis, y-axis, and z-axis are set arbitrarily.

[0021] FIG. 4 is a conceptual diagram for explaining the local coordinate system and the world coordinate system in the present disclosure. The world coordinate system (X-axis, Y-axis, Z-axis) is set relative to the ground. The local coordinate system (x-axis, y-axis, z-axis) is set relative to the measurement device. In the world coordinate system (X-axis, Y-axis, Z-axis), the X-axis is set in the horizontal direction of the user, the Y-axis is set in the front-to-back direction of the user, and the Z-axis is set in the up-to-down direction when the user is standing upright and facing the direction of travel. Note that the example in FIG. 4 conceptually illustrates the relationship between the local coordinate system (x-axis, y-axis, z-axis) and the world coordinate system (X-axis, Y-axis, Z-axis), and does not accurately illustrate the relationship between the local coordinate system and the world coordinate system, which changes according to the user's walking.

[0022] FIG. 5 is a conceptual diagram illustrating the human body planes set for the human body. In this embodiment, a sagittal plane, a coronal plane, and a horizontal plane are defined. The sagittal plane is a human body plane that divides the body into left and right halves. The coronal plane is a human body plane that divides the body into front and back halves. The horizontal plane is a human body plane that divides the body horizontally. Note that, as shown in FIG. 5, when the user is standing upright with the center lines of the feet pointing in the direction of travel, the world coordinate system and the local coordinate system are assumed to coincide. FIG. 5 shows an example in which different coordinate systems are set for the left and right feet. In this embodiment, rotation in the sagittal plane around the X-axis (x-axis) as the rotation axis is defined as roll, rotation in the coronal plane around the Y-axis (y-axis) as the rotation axis is defined as pitch, and rotation in the horizontal plane around the Z-axis (z-axis) as the rotation axis is defined as yaw. In addition, the rotation angle in the sagittal plane around the X-axis (x-axis) as the axis of rotation is defined as the roll angle, the rotation angle in the coronal plane around the Y-axis (y-axis) as the axis of rotation is defined as the pitch angle, and the rotation angle in the horizontal plane around the Z-axis (z-axis) as the axis of rotation is defined as the yaw angle.

[0023] The control unit 113 causes the acceleration sensor 111 and the angular velocity sensor 112 to measure sensor data. For example, the control unit 113 causes the acceleration sensor 111 and the angular velocity sensor 112 to start measurement in response to a measurement start signal transmitted from the discrimination device 12. For example, the control unit 113 may cause the acceleration sensor 111 and the angular velocity sensor 112 to start measurement at the timing when it is detected that the user is walking. For example, the control unit 113 starts measuring the sensor data when it is detected that either the left or right foot has started to move in the direction of travel after both feet have been at the same vertical height for a predetermined period of time. The control unit 113 may also be configured to start measuring the sensor data at a predetermined timing.

[0024] The control unit 113 acquires acceleration in three axial directions from the acceleration sensor 111. The control unit 113 also acquires angular velocities around three axes from the angular velocity sensor 112. For example, the control unit 113 performs analog-to-digital conversion (AD conversion) on physical quantities (analog data) such as the acquired angular velocities and accelerations. The physical quantities (analog data) measured by the acceleration sensor 111 and the angular velocity sensor 112 may be converted to digital data in each of the acceleration sensor 111 and the angular velocity sensor 112. For example, an AD conversion circuit that AD converts the physical quantities (analog data) such as the angular velocity and acceleration may be provided. The control unit 113 outputs the converted digital data (also referred to as sensor data) to the communication unit 115. For example, the control unit 113 may temporarily store the sensor data in a storage unit (not shown).

[0025] The sensor data includes at least acceleration data converted into digital data and angular velocity data converted into digital data. The acceleration data includes acceleration vectors in three axial directions. The angular velocity data includes angular velocity vectors around three axes. The acceleration data and angular velocity data are associated with the time at which they were acquired. Furthermore, the control unit 113 may apply corrections such as corrections for mounting errors, temperature corrections, and linearity corrections to the acceleration data and angular velocity data.

[0026] For example, the control unit 113 is realized by a microcomputer or microcontroller that performs overall control and data processing of the measuring device 10. For example, the control unit 113 includes a CPU (Central Processing Unit), RAM (Random Access Memory), ROM (Read Only Memory), flash memory, etc.

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

[0028] For example, the communication unit 115 transmits the sensor data to the discrimination device 12 via wireless communication. For example, the communication unit 115 transmits the sensor data to the discrimination device 12 via a wireless communication function (not shown) conforming to a standard such as Bluetooth (registered trademark) or WiFi (registered trademark). The communication function of the communication unit 115 may be conforming to a standard other than Bluetooth (registered trademark) or WiFi (registered trademark). The communication unit 115 may transmit the sensor data to the discrimination device 12 via a wired connection such as a cable.

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

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

[0031] As shown in Figure 6, multiple events occur during walking. These multiple events are also called walking events. P1 represents the event in which the heel of the right foot touches the ground (heel strike) (HS: Heel Strike). P2 represents the event in which the toe of the left foot leaves the ground (opposite toe off) while the sole of the right foot remains on the ground (opposite toe off) (OTO: Opposite Toe Off). P3 represents the event in which the heel of the right foot rises (heel rise) while the sole of the right foot remains on the ground (HR: Heel Rise). P4 represents the event in which the heel of the left foot touches the ground (opposite heel strike) (OHS: Opposite Heel Strike). P5 represents the event in which the toe of the right foot leaves the ground (toe off) while the sole of the left foot remains on the ground (TO: Toe Off). P6 represents an event in which the left and right feet cross (foot crossing) with the sole of the left foot touching the ground (FA: Foot Adjacent). P7 represents an event in which the tibia of the right foot is nearly perpendicular to the ground (TV: Tibia Vertical) with the sole of the left foot touching the ground (TV: Tibia Vertical). P8 represents an event in which the heel of the right foot touches the ground (heel strike) (HS: Heel Strike). P8 corresponds to the end point of the walking cycle that begins with P1 and also corresponds to the starting point of the next walking cycle. Note that the walking events shown in Figure 6 are merely examples and do not limit the events that occur during walking or the names of these events.

[0032] The timing of heel strike is the timing of the minimum peak immediately after the maximum peak that appears in the time series data of forward acceleration (Y-direction acceleration). The maximum peak that marks the timing of heel strike corresponds to the maximum peak of the walking waveform for one step cycle. The section between successive heel strikes corresponds to one step cycle. The timing of toe lift is the timing of the rise of the maximum peak that appears after the stance phase period when no fluctuations appear in the time series data of forward acceleration (Y-direction acceleration). The timing midway between the timing of the minimum roll angle and the timing of the maximum roll angle corresponds to the mid-stance phase.

[0033] [Discrimination device] 7 is a block diagram showing an example of the configuration of the discrimination device 12 according to the present disclosure. The discrimination device 12 includes a data acquisition unit 121, a calculation unit 122, a storage unit 123, a discrimination unit 125, and an output unit 127.

[0034] The data acquisition unit 121 acquires time-series data of sensor data from the measurement device 10. The data acquisition unit 121 receives the time-series data of sensor data from the measurement device 10 via wireless communication. For example, the data acquisition unit 121 receives the time-series data of sensor data from the measurement device 10 via a wireless communication function (not shown) that complies with standards such as Bluetooth (registered trademark) or WiFi (registered trademark). Note that the communication function of the data acquisition unit 121 may be compliant with standards other than Bluetooth (registered trademark) or WiFi (registered trademark) as long as it can communicate with the measurement device 10. The data acquisition unit 121 may also receive the time-series data of sensor data from the measurement device 10 via a wired connection such as a cable.

[0035] The calculation unit 122 extracts the endpoints of a gait cycle from the time-series data of the sensor data. The interval between consecutive endpoints corresponds to a step gait cycle. Of two consecutive endpoints, the one that precedes the other in the time series is set as the start point of one gait cycle. Of two consecutive endpoints, the one that follows the other in the time series is set as the end point of one gait cycle. For example, the endpoints of a gait cycle are set at the timing of mid-stance or heel strike. The midpoint between the timing of the minimum roll angle and the timing of the maximum roll angle corresponds to the mid-stance phase. In this case, the interval between consecutive mid-stance phases corresponds to a step gait cycle. The timing of heel strike is the timing of the minimum peak immediately after the maximum peak that appears in the time-series data of the forward acceleration (Y-direction acceleration). The maximum peak that marks the heel strike timing corresponds to the maximum peak of the gait waveform for one step gait cycle. The interval between consecutive mid-stance phases or heel strikes corresponds to a step gait cycle. In this case, the interval between successive heel strikes corresponds to a gait cycle. The timing of mid-stance and heel strike is merely an example and does not limit the endpoints of the gait cycle. For example, the endpoints of the gait cycle may be set to the timing of gait events such as toe-off, opposite toe-off, heel lift, opposite heel-strike, toe-off, foot crossing, and tibia vertical. A description of the method for detecting the timing of gait events will be omitted.

[0036] The calculation unit 122 extracts time-series data of the sensor data between two consecutive endpoints as a gait waveform for one gait cycle. The calculation unit 122 may normalize the extracted gait waveform. For example, the calculation unit 122 normalizes (first normalization) the time of the extracted gait waveform for one step cycle to a gait cycle of 0 to 100% (percent). A section such as 1% or 10% included in the gait cycle of 0 to 100% is also called a gait phase. For example, the calculation unit 122 normalizes (second normalization) the gait waveform for the first-normalized one step cycle so that the stance phase is 60% and the swing phase is 40%. If the gait waveform is second-normalized, it is possible to reduce the discrepancy in the gait phase from which the feature amount used to estimate the walking state is extracted.

[0037] For example, the calculation unit 122 extracts a walking waveform for one step cycle using the traveling direction acceleration (Y-direction acceleration). In this case, the calculation unit 122 extracts a walking waveform for one step cycle for accelerations / angular velocities / angles other than the traveling direction acceleration (Y-direction acceleration) in accordance with the walking cycle of the traveling direction acceleration (Y-direction acceleration). The calculation unit 122 extracts a walking waveform for accelerations in three axial directions, a walking waveform for angular velocities around three axes, and a walking waveform for angles around three axes. The calculation unit 122 may generate time series data of angles around three axes by integrating time series data of angular velocities around three axes. The calculation unit 122 normalizes the extracted walking waveform for one step cycle.

[0038] The calculation unit 122 may extract a gait waveform for one step gait cycle using acceleration / angular velocity other than the forward acceleration (Y-direction acceleration). For example, the calculation unit 122 detects heel strike and toe lift from time-series data of vertical acceleration (Z-direction acceleration). The timing of heel strike is the timing of a steep minimum peak that appears in the time-series data of vertical acceleration (Z-direction acceleration). At the timing of the steep minimum peak, the value of vertical acceleration (Z-direction acceleration) becomes almost zero. The minimum peak that marks the timing of heel strike corresponds to the minimum peak of the gait waveform for one step gait cycle. The section between consecutive heel strikes is a gait cycle. The timing of toe lift is the timing of an inflection point in the time-series data of vertical acceleration (Z-direction acceleration) that gradually increases after passing through a section of small fluctuation following the maximum peak immediately after heel strike. The calculation unit 122 may also extract a gait waveform for one step walking cycle using both the forward acceleration (Y-direction acceleration) and the vertical acceleration (Z-direction acceleration).The calculation unit 122 may also extract a gait waveform for one step walking cycle using acceleration, angular velocity, angle, etc. other than the forward acceleration (Y-direction acceleration) and the vertical acceleration (Z-direction acceleration).

[0039] The calculation unit 122 uses the time-series data (gait waveform) of the sensor data to calculate a relative change value indicating a relative change from the axis of progression in the horizontal plane for each step cycle. The calculation unit 122 uses the extracted gait waveform to calculate a relative change value from the start point to the end point in the horizontal plane (XY plane). The relative change value in the horizontal plane (XY plane) indicates a relative change from the axis of progression at the start point.

[0040] 8 is a conceptual diagram for explaining the relative change value calculated by the discrimination device in the present disclosure. s From the end point P e The relative change value for one walking cycle (one stride) to the relative displacement d x and the relative angle θ z Relative angle θ z is the starting point P s The relative displacement d corresponds to the angle formed in the horizontal plane (XY plane) between the axis of travel (-Y) and the line passing through the start and end points. x is the starting point P s The axis of progression (-Y) and the end point P e The calculation unit 122 calculates the relative angle θ between the axis of travel at the starting point and the line passing through the starting point and the end point on the horizontal plane. z Furthermore, the calculation unit 122 calculates the relative displacement d x The calculation unit 122 calculates the calculated relative angle θ z and relative displacement d x is stored in the storage unit 123.

[0041] The storage unit 123 stores the sensor data acquired by the data acquisition unit 121. The storage unit 123 stores the relative angle θ calculated by the calculation unit 122. z and relative displacement d x As will be described later, the storage unit 123 also stores the walking conditions determined by the determination unit 125.

[0042] The discrimination unit 125 acquires the relative change value for the target period from the storage unit 123. The target period is a time period spanning multiple walking cycles (strides). The discrimination unit 125 discriminates the walking status for the target period using time-series data of the relative change value. For example, the discrimination unit 125 discriminates the walking status for the target period using three-dimensional rotation correction performed using the relative change value. For example, the discrimination unit 125 discriminates the walking status for the target period using a machine learning model (discrimination model) generated by machine learning. The walking status includes walking in a straight line (normal walking), walking along a curve (curved walking), walking with a stagger (wandering walking), etc. The walking status is not limited to the examples given here as long as it relates to walking on a horizontal plane. The discrimination unit 125 records the walking status for the target period in association with sensor data measured during walking cycles included in the target period.

[0043] 9 and 10 are conceptual diagrams for explaining an example of a walking condition to be discriminated by the discrimination device of the present disclosure. FIGS. 9 and 10 are views looking down from an upper viewpoint. FIG. 9 shows an example of a trajectory of walking along a curve (curve walking) using footprints. FIG. 10 shows an example of a trajectory of walking while stumbling (staggering). Note that FIGS. 9 and 10 are merely examples and do not limit the walking conditions to be discriminated by the discrimination device 12. For example, walking conditions such as shuffling, lameness, and walking with a cane may be included in the walking conditions to be discriminated by the discrimination device 12.

[0044] 11 is a conceptual diagram for explaining an example of estimation of a walking state by a discrimination device according to the present disclosure. The discrimination model 150 is a machine learning model generated by machine learning. For example, the discrimination model 150 is a model generated by a relative angle θ z and relative displacement d x The discriminant model 150 is a model trained by using a data set in which the walking situation is used as a target variable and the relative angle θ z and relative displacement d xThe discrimination unit 125 outputs the walking status in response to input of the time-series data. The discrimination model 150 may be stored in an external storage device constructed in the cloud, a server, or the like. In this case, the discrimination unit 125 uses the discrimination model 150 via an interface (not shown) connected to the storage device.

[0045] For example, the discriminant model 150 is a learning model trained using a convolutional neural network (CNN) technique. For example, the discriminant model 150 is a model trained using a principal component analysis (PCA) technique. For example, the discriminant model 150 is a learning model trained using a variational autoencoder (VAE). For example, the discriminant model 150 is a learning model trained using a conditional generative adversarial network (GAN) technique. For example, the discriminant model 150 may be generated by learning using a linear regression algorithm. For example, the discriminant model 150 may be generated by learning using a support vector machine (SVM) algorithm. For example, the discriminant model 150 may be generated by learning using a Gaussian process regression (GPR) algorithm. For example, the discriminant model 150 may be generated by learning using a random forest (RF) algorithm. The above techniques are merely examples and do not limit the techniques for training the discriminant model 150.

[0046] The output unit 127 outputs the sensor data stored in the storage unit 123. The sensor data is linked to the walking status at the time of measurement. Information including the sensor data linked to the walking status is also called walking information. For example, the output unit 127 outputs the walking information to a mobile terminal carried by the subject. For example, the output unit 127 outputs the walking information to a terminal device or a server that uses the sensor data via the mobile terminal carried by the subject. For example, the output unit 127 may be configured to output the sensor data to an external system or the like that uses the sensor data.

[0047] For example, the discrimination device 12 is constructed in a cloud or a server connected to a mobile terminal carried by the subject via a communication network. The mobile terminal is a portable communication device. For example, the mobile terminal is a portable communication device having a communication function, such as a smartphone, a smart watch, or a mobile phone. For example, the discrimination device 12 is connected to the mobile terminal via wireless communication. For example, the discrimination device 12 is connected to the mobile terminal via a wireless communication device (not shown) conforming to standards such as Bluetooth (registered trademark) or WiFi (registered trademark). Note that the wireless communication device may conform to standards other than Bluetooth (registered trademark) or WiFi (registered trademark). The corrected gait data may be used by an application installed on the mobile terminal. For example, the mobile terminal executes processing using sensor data using an application installed on the mobile terminal.

[0048] The discrimination device 12 may be configured to calculate a gait index. For example, the discrimination device 12 calculates the gait index using a normalized walking waveform. The gait index is used to estimate a physical condition, physical ability, and the like. There are no particular limitations on the gait index calculated by the discrimination device 12. For example, the discrimination device 12 calculates gait indices related to distance, height, angle, speed, time, CPEI (Center of Pressure Exclusion Index), frailty level, and the like.

[0049] For example, the discrimination device 12 calculates indices related to distance and height as gait indices. For example, the discrimination device 12 calculates stride length, turning distance, foot lift height, FTC (Foot Clearance), and MTC (Minimum Toe Clearance). The stride length indicates the distance between the front foot and the rear foot while walking. The turning distance indicates the maximum distance that the foot is separated outward in the direction of travel during the swing phase. The foot lift height indicates the maximum distance between the measurement device 10 (sensor 110) and the ground during the swing phase. The FTC indicates the maximum distance between the heel and the ground during the swing phase. The MTC indicates the minimum distance between the toe and the ground during the swing phase.

[0050] For example, the discrimination device 12 calculates angle-related indices as gait indices. For example, the discrimination device 12 calculates the contact angle, the takeoff angle, the toe direction, the heel-strike roll angle, the toe-off roll angle, the swing leg peak angular velocity, and the hallux angle. The contact angle indicates the maximum angle between the sole of the foot and the ground at heel-strike. The takeoff angle indicates the angle between the sole of the foot and the ground during the swing phase. The toe direction indicates the average value of the toe direction relative to the forward direction during the swing phase. The heel-strike roll angle is the angle between the ankle and the ground at heel-strike, as viewed from a rear perspective. The toe-off roll angle is the angle between the ankle and the ground at push-off, as viewed from a rear perspective. The swing leg peak angular velocity is the angular velocity in the ankle dorsiflexion direction from immediately after push-off until the toe comes closest to the ground. The hallux angle indicates the angle at which the big toe is tilted toward the index toe. Specifically, the hallux angle is the angle between the center line of the first metatarsal and the center line of the first proximal phalanx.

[0051] For example, the discrimination device 12 calculates speed-related indices as gait indices. For example, the discrimination device 12 calculates walking speed, cadence, and maximum swing speed. Walking speed indicates the speed at which the foot is walked. Cadence indicates the number of steps per minute. Maximum swing speed indicates the speed at which the foot is swung out during the swing phase.

[0052] For example, the discrimination device 12 calculates time-related indices as gait indices. For example, the discrimination device 12 calculates stance time, load-bearing time, sole contact time, push-off time, swing time, and DST (Double Support Time). Stance time indicates the time during which the foot is in contact with the ground during walking. Stance time is the sum of load-bearing time, sole contact time, and push-off time. Load-bearing time is the time during the stance phase from when the heel touches the ground to when the toe touches the ground. Sole contact time is the time during the stance phase when the entire sole of the foot is in contact with the ground and is horizontal to the ground. Push-off time is the time during the stance phase from when the sole is in contact with the ground to when the toe pushes off the ground. Swing time indicates the time during which the foot is off the ground during walking. DST is divided into DST1 and DST2. DST1 indicates the time during which the foot equipped with the measuring device 10 (sensor 110) is in front of the other foot during a period when both feet are in contact with the ground at the same time. DST2 indicates the time during which the foot equipped with the measuring device 10 (sensor 110) is behind the other foot during a period when both feet are in contact with the ground at the same time.

[0053] For example, the discriminator 12 calculates a Center of Pressure Exclusion Index (CPEI) as a gait index, which indicates an estimated rate of expansion of the center of foot pressure on the ground during the stance phase.

[0054] For example, the discrimination device 12 calculates a frailty level as a gait index. The frailty level is an estimated value of the frailty state according to the walking state. For example, the discrimination device 12 estimates an index indicating a determination result regarding frailty as the frailty level. If there is no possibility of frailty, the discrimination device 12 estimates an index indicating that the subject is not frail. If there is a possibility of frailty, the discrimination device 12 estimates an index indicating that the subject is likely to be frail. Furthermore, if there is a high possibility of frailty, the discrimination device 12 estimates an index indicating that there is a high possibility of frailty.

[0055] The discrimination device 12 may extract, from the walking waveform, feature amounts used to calculate or estimate gait indices. For example, the discrimination device 12 extracts feature amounts for each walking phase cluster according to preset conditions. A walking phase cluster is a cluster that integrates temporally consecutive walking phases. A walking phase cluster includes at least one walking phase. A walking phase cluster may also include a single walking phase. The discrimination device 12 may extract physical ability feature amounts used to estimate physical ability. For example, the physical ability feature amounts are used to estimate at least one of physical abilities such as grip strength (total muscle strength of the whole body), dynamic balance, lower limb muscle strength, mobility ability, and static balance.

[0056] (operation) Next, the operation of gait measurement system 1 will be described with reference to the drawings. Below, the operation of discriminator 12 included in gait measurement system 1 will be described.

[0057] Fig. 12 is a flowchart for explaining an example of the operation of the discrimination device in the present disclosure. In the explanation of the processing according to the flowchart in Fig. 12, the components of the discrimination device 12 will be described as the subject of the operations. The subject of the operations according to the flowchart in Fig. 12 may be the discrimination device 12.

[0058] In FIG. 12, first, the data acquisition unit 121 acquires time-series data of sensor data measured in accordance with the movement of the feet (step S11).

[0059] Next, the calculation unit 122 executes a relative change value calculation process (step S12). The relative change value calculation process will be described in detail later (FIG. 13).

[0060] If the walking condition is to be determined (Yes in step S13), the determination unit 125 determines the walking condition using the time-series data of the relative change value in the target period (step S14). On the other hand, if the walking condition is not to be determined (No in step S13), the process returns to step S12.

[0061] After step S14, the storage unit 123 records the walking status during the target period in association with the sensor data (step S15).

[0062] If the sensor data is to be output (Yes in step S16), the output unit 127 outputs the sensor data associated with the walking situation (step S17). On the other hand, if the sensor data is not to be output (No in step S16), the process returns to step S12.

[0063] [Relative change value calculation process] Next, the relative change value calculation process (step S12 in FIG. 12) performed by the discriminator 12 will be described in detail with reference to the drawings.

[0064] 13 is a flowchart for explaining an example of a relative change value calculation process performed by the discriminator according to the present disclosure. In the explanation of the process according to the flowchart of FIG. 13, the components of the discriminator 12 will be described as the subject of the operations. The subject of the operations according to the flowchart of FIG. 13 may be the discriminator 12.

[0065] In FIG. 13, first, the calculation unit 122 extracts the end points of the walking cycle from the time-series data of the sensor data (step S121).

[0066] Next, the calculation unit 122 extracts the time-series data of the sensor data between two consecutive endpoints as a walking waveform for one walking cycle (step S122).

[0067] Next, the calculation unit 122 uses the extracted walking waveform to calculate the relative angle θ z is calculated (step S123).

[0068] Next, the calculation unit 122 calculates the relative displacement d in the horizontal direction from the start point to the end point. x (Step S124) The order of the process of step S123 and the process of step S124 may be reversed.

[0069] Next, the storage unit 123 stores the calculated relative angle θ z and relative displacement d x The relative angle θ stored in the storage unit 123 is stored (step S125). z and relative displacement d x is used to determine the walking status.

[0070] (Application example) Next, an application example of this embodiment will be described with reference to the drawings. In this application example, information according to the walking situation is generated using sensor data processed by the discrimination device 12. The generated information is output to a mobile terminal carried by the user.

[0071] 14 is a block diagram showing an example of the configuration of a discrimination device according to the present disclosure. Discrimination device 12-1 includes a data acquisition unit 121, a calculation unit 122, a storage unit 123, a discrimination unit 125, an information generation unit 126, and an output unit 127. Discrimination device 12-1 is similar to discrimination device 12 except for including information generation unit 126. Description of components other than information generation unit 126 will be omitted.

[0072] The information generation unit 126 acquires sensor data associated with the walking situation. The information generation unit 126 may be configured to acquire gait indices generated using the sensor data. The information generation unit 126 generates information according to the walking situation using the sensor data associated with the walking situation. For example, the information processing unit generates information according to the user's walking situation using a pre-constructed, trained machine learning model. For example, the information processing unit may be configured to generate information according to the user's walking situation using a large-scale language model (LLM). For example, the information generation unit 126 generates information according to the walking situation. For example, the information generation unit 126 generates action recommendation information that recommends an action according to the walking situation. The information generated by the information generation unit 126 is output from the output unit 127. As will be described later, the information output from the output unit 127 may be displayed on a screen of a mobile device carried by the user or output as audio from the mobile device.

[0073] 15 and 16 are conceptual diagrams showing examples of displaying information according to the walking condition determined by the determination device of the present disclosure. Fig. 15 shows an example in which information according to the walking condition of a user is displayed on the screen of a mobile terminal 170 carried by a user walking while wearing shoes 100 in which a measuring device 10 is placed. Fig. 16 shows an example in which information according to the walking condition of a user is displayed on the screen of a terminal device 180 used by a physical therapist who is caring for the physical condition of the user.

[0074] In the example of FIG. 15, information such as "Your walking tends to be 'unsteady'" is displayed on the screen of the mobile terminal 170 in accordance with the walking condition determined for the user. Also, in the example of FIG. 15, action recommendation information such as "Make sure to walk straight" is displayed on the screen of the mobile terminal 170 in accordance with the walking condition determined for the user. The action recommendation information is optimized according to the walking condition of the user. Furthermore, the action recommendation information includes information that prompts the user to make a decision. After checking the information displayed on the screen of the mobile terminal 170, the user can make an effort to improve their walking condition by acting in accordance with the action recommendation information.

[0075] In the example of FIG. 16, information such as "Person A's gait has a tendency to be a 'wandering gait'" is displayed on the screen of the terminal device 180 in accordance with the walking condition determined for the user. Also, in the example of FIG. 16, action recommendation information including an instruction policy such as "Please instruct me on how to walk" is displayed on the screen of the terminal device 180 in accordance with the walking condition determined for the user. The action recommendation information is optimized according to the instruction policy of the physical therapist. Also, the action recommendation information includes information that prompts the physical therapist to make a decision. The physical therapist, having checked the information displayed on the screen of the terminal device 180, can decide on an instruction policy for the user's walking by acting in accordance with the action recommendation information.

[0076] As described above, the gait measurement system of this embodiment includes a measurement device and a discrimination device. The measurement device is attached to the user's footwear. The measurement device has sensors that measure acceleration and angular velocity. The measurement device generates sensor data using the acceleration and angular velocity measured by the sensors. The measurement device transmits the generated sensor data to the discrimination device.

[0077] The discrimination device includes a data acquisition unit, a calculation unit, a memory unit, a discrimination unit, and an output unit. The data acquisition unit acquires sensor data measured according to foot movement. The calculation unit calculates a relative change value indicating a relative change from the axis of progression for each walking cycle using time-series data of the acquired sensor data. The calculation unit extracts endpoints to be set as the start and end points of a walking cycle from the time-series data of the sensor data. The calculation unit sets the chronologically earlier endpoint of two consecutive endpoints as the start point of one walking cycle. The calculation unit sets the chronologically later endpoint of two consecutive endpoints as the end point of one walking cycle. The calculation unit calculates a relative change value indicating a relative change from the axis of progression at the start point. Specifically, the calculation unit calculates the relative change value as a relative angle corresponding to the angle formed in a horizontal plane between a straight line passing through the start point and the axis of progression at the start point, and a relative displacement corresponding to the distance in a horizontal plane between the axis of progression at the start point and the end point. The memory unit stores the sensor data acquired by the data acquisition unit. The storage unit stores the relative angle and relative displacement calculated by the calculation unit. The storage unit also stores the walking condition determined by the determination unit. The determination unit determines the walking condition using time-series data of the relative change value during a target period. The output unit outputs walking information including the determined walking condition.

[0078] In this embodiment, the walking status is determined using time series data of relative change values, including relative angles and relative displacements in the horizontal plane, calculated for each walking cycle. Using the time series data of relative change values ​​in the horizontal plane makes it possible to detect lateral changes corresponding to the walking status that cannot be detected by sensor data. Therefore, using the time series data of relative change values ​​in the horizontal plane makes it possible to determine the walking status of subjects with weakened muscles, such as elderly people and rehabilitation patients. In other words, this embodiment makes it possible to determine the walking status of any subject.

[0079] In one aspect of the present embodiment, the determination unit determines the walking state using a machine learning model that outputs the walking state in response to input of time-series data of the relative change value. According to this aspect, the walking state can be determined by using the machine learning model.

[0080] The discrimination device according to one aspect of the present embodiment further includes an information generation unit. The information generation unit uses sensor data associated with walking conditions to generate action recommendation information that is optimized according to the user's walking conditions and that encourages the user to make a decision. The output unit displays the walking information including the action recommendation information on the screen of the mobile device used by the user. According to this aspect, the action recommendation information optimized according to the walking conditions is presented to the user, thereby encouraging the user to make a decision.

[0081] (Second embodiment) Next, a discrimination device according to a second embodiment will be described with reference to the drawings. The discrimination device according to this embodiment differs from the discrimination device according to the first embodiment in that it calculates a relative change value from the start point to the end point on the sagittal plane. The discrimination device according to this embodiment is combined with the measurement device according to the first embodiment to form a gait measurement system. In the following, a description of the same components as those in the first embodiment will be omitted. The method according to this embodiment may be combined with the method according to the first embodiment.

[0082] (composition) 17 is a block diagram showing an example of the configuration of a discrimination device according to the present disclosure. The discrimination device 22 includes a data acquisition unit 221, a calculation unit 222, a storage unit 223, a discrimination unit 225, and an output unit 227.

[0083] The data acquisition unit 221 has the same configuration as the data acquisition unit 121 of the first embodiment. The data acquisition unit 221 acquires time-series data of sensor data from the measurement device.

[0084] The calculation unit 222 has the same configuration as the calculation unit 122 in the first embodiment. The calculation unit 222 extracts endpoints of a walking cycle from the time-series data of the sensor data. The section between consecutive endpoints corresponds to a walking cycle. Of the two consecutive endpoints, the earlier endpoint is set as the start point of one walking cycle. Of the two consecutive endpoints, the later endpoint is set as the end point of one walking cycle. The calculation unit 222 extracts the time-series data of the sensor data between the two consecutive endpoints as a walking waveform for one walking cycle. The calculation unit 222 may normalize the extracted walking waveform.

[0085] The calculation unit 222 uses the time-series data (gait waveform) of the sensor data to calculate a relative change value indicating a relative change from the axis of progression in the horizontal plane for each step cycle. Specifically, the calculation unit 222 uses the extracted gait waveform to calculate a relative change value from the start point to the end point in the sagittal plane (YZ plane). The relative change value in the sagittal plane (YZ plane) indicates a relative change from the axis of progression at the start point.

[0086] 18 is a conceptual diagram for explaining the relative change value calculated by the discriminator according to the present disclosure. s From the end point P e The relative change value for one walking cycle (one stride) to the relative displacement d z and the relative angle θ x Relative displacement d z is the starting point P s The relative displacement d corresponds to the angle formed in the sagittal plane (YZ plane) between the axis of travel (-Y) and the line passing through the start and end points. z is the starting point P s The axis of progression (-Y) and the end point P e The calculation unit 222 calculates the relative angle θ between the axis of travel at the starting point and the line passing through the starting point and the end point on the sagittal plane. x The calculation unit 222 also calculates the relative angle θ in the vertical direction from the start point to the end point. x The calculation unit 222 calculates the calculated relative displacement d z and the relative angle θ xis stored in the storage unit 223.

[0087] The storage unit 223 has the same configuration as the storage unit 123 of the first embodiment. The storage unit 223 stores the sensor data acquired by the data acquisition unit 221. The storage unit 223 stores the relative displacement d calculated by the calculation unit 222. z and the relative angle θ x As will be described later, the storage unit 223 also stores the walking conditions determined by the determination unit 225.

[0088] The discrimination unit 225 acquires the relative change value for the target period from the storage unit 223. The target period is a time period spanning multiple walking cycles (strides). The discrimination unit 225 discriminates the walking status for the target period using time-series data of the relative change value. For example, the discrimination unit 225 discriminates the walking status for the target period using three-dimensional rotation correction performed using the relative change value. For example, the discrimination unit 225 discriminates the walking status for the target period using a machine learning model (discrimination model) generated by machine learning. The walking status includes walking on flat ground (normal walking), walking going up and down stairs (stair walking), walking going up and down slopes (slope walking), walking on an uneven road surface (uneven walking), etc. The walking status is not limited to the examples given here as long as it relates to walking on a road surface that changes vertically. The discrimination unit 225 records the walking status for the target period in association with sensor data measured during walking cycles included in the target period.

[0089] 19 and 20 are conceptual diagrams for explaining an example of a walking situation to be discriminated by the discrimination device in the present disclosure. FIGS. 19 and 20 are views seen from a side perspective. FIG. 19 shows an example of walking up stairs (stair walking). FIG. 20 shows an example of walking down stairs (stair walking). Note that FIGS. 19 and 20 are merely examples and do not limit the walking situations to be discriminated by the discrimination device 22. For example, walking situations such as walking on uneven surfaces may be included in the discrimination situations to be discriminated by the discrimination device 22.

[0090] 21 is a conceptual diagram for explaining an example of estimation of a walking state by a discrimination device in the present disclosure. The discrimination model 250 is a machine learning model generated by machine learning. For example, the discrimination model 250 is a model generated by a relative angle θ x and relative displacement d z The discriminant model 250 is a model trained by using a data set in which the walking situation is used as a target variable and the relative angle θ x and relative displacement d z The discrimination unit 225 outputs the walking status in response to input of the time-series data. The discrimination model 250 may be stored in an external storage device constructed in the cloud, a server, or the like. In this case, the discrimination unit 225 uses the discrimination model 250 via an interface (not shown) connected to the storage device.

[0091] For example, the discriminant model 250 is a learning model trained using a convolutional neural network (CNN) technique. For example, the discriminant model 250 is a model trained using a principal component analysis (PCA) technique. For example, the discriminant model 250 is a learning model trained using a variational autoencoder (VAE). For example, the discriminant model 250 is a learning model trained using a conditional generative adversarial network (GAN) technique. For example, the discriminant model 250 may be generated by learning using a linear regression algorithm. For example, the discriminant model 250 may be generated by learning using a support vector machine (SVM) algorithm. For example, the discriminant model 250 may be generated by learning using a Gaussian process regression (GPR) algorithm. For example, the discriminant model 250 may be generated by learning using a random forest (RF) algorithm. The above techniques are merely examples and do not limit the techniques for training the discriminant model 250.

[0092] The output unit 227 outputs the sensor data stored in the storage unit 223. The sensor data is linked to the walking status at the time of measurement. Information including the sensor data linked to the walking status is also called walking information. For example, the output unit 227 outputs the walking information to a mobile terminal carried by the subject. For example, the output unit 227 outputs the walking information to a terminal device or a server that uses the sensor data via the mobile terminal carried by the subject. For example, the output unit 227 may be configured to output the sensor data to an external system or the like that uses the sensor data.

[0093] (operation) Next, the operation of the discriminator 22 will be described with reference to the drawings. The main operation of the discriminator 22 is similar to the operation of the discriminator 12 of the first embodiment (FIG. 12). The operation of the discriminator 22 differs from that of the discriminator 12 in the relative change value calculation process in step S12 of FIG. 12. In the following, a description of the main operation of the discriminator 22 will be omitted, and only the relative change value calculation process will be described.

[0094] [Relative change value calculation process] Fig. 22 is a flowchart for explaining an example of a relative change value calculation process performed by the discriminator according to the present disclosure. In explaining the process according to the flowchart of Fig. 22, the components of the discriminator 22 will be described as the subject of operations. The discriminator 22 may be the subject of operations in the process according to the flowchart of Fig. 22.

[0095] In FIG. 22, first, the calculation unit 222 extracts the end points of the walking cycle from the time-series data of the sensor data (step S221).

[0096] Next, the calculation unit 222 extracts the time-series data of the sensor data between two consecutive endpoints as a walking waveform for one walking cycle (step S222).

[0097] Next, the calculation unit 222 uses the extracted walking waveform to calculate the relative angle θ x is calculated (step S223).

[0098] Next, the calculation unit 222 calculates the relative displacement d in the horizontal direction from the start point to the end point. z (Step S224) The order of the process of step S223 and the process of step S224 may be reversed.

[0099] Next, the storage unit 223 stores the calculated relative angle θ x and relative displacement d z The relative angle θ stored in the storage unit 223 is stored (step S225). x and relative displacement d z is used to determine the walking status.

[0100] (Application example) Next, application examples of this embodiment will be described with reference to the drawings. FIGS. 23 to 25 are conceptual diagrams showing display examples of information according to the walking status determined by the discrimination device of the present disclosure. FIGS. 23 to 25 show examples in which information according to the user's walking status is output as audio from a mobile terminal 270 carried by a user walking while wearing shoes 200 on which a measuring device 20 is placed. In the examples using FIGS. 23 to 25, it is assumed that information according to the user's walking status is generated by an information generation unit (not shown) that generates information according to the walking status using sensor data processed by the discrimination device 22. For example, the information generation unit generates information according to the user's walking status using a trained machine learning model that has been constructed in advance.

[0101] FIG. 23 shows an example in which the walking situation of the user determined by the determination device 22 and advice according to the walking situation are output as voice from the mobile terminal used by the user. In the example of FIG. 23, information such as "Climbing stairs" is output as voice from the mobile terminal 270 according to the walking situation determined for the user. Also, in the example of FIG. 23, action recommendation information such as "Lift your knees a little higher" is output as voice from the mobile terminal 270 according to the walking situation determined for the user. The action recommendation information is optimized according to the walking situation of the user. Also, the action recommendation information includes information that prompts the user to make a decision. A user who hears the information output as voice from the mobile terminal 270 can be careful not to trip on the stairs by acting in accordance with the action recommendation information.

[0102] FIG. 24 shows an example in which the walking status of the user determined by the determination device 22 and advice according to the walking status are output as voice from the mobile terminal 270 used by the user. In the example of FIG. 24, information such as "Going down the stairs" is output as voice from the mobile terminal 270 in accordance with the walking status determined for the user. Also, in the example of FIG. 24, action recommendation information such as "Go down a little more slowly" is output as voice from the mobile terminal 270 in accordance with the walking status determined for the user. The action recommendation information is optimized according to the walking status of the user. Also, the action recommendation information includes information that prompts the user to make a decision. A user who hears the information output as voice from the mobile terminal 270 can take action in accordance with the action recommendation information, thereby being careful not to fall down the stairs.

[0103] FIG. 25 shows an example in which the walking situation of the user determined by the determination device 22 and advice corresponding to the walking situation are output as audio from the mobile terminal used by the user. In the example of FIG. 25, information such as "You are walking on a road with large irregularities" is output as audio from the mobile terminal 270 in accordance with the walking situation determined for the user. Also, in the example of FIG. 25, action recommendation information such as "Be careful not to trip" is output as audio from the mobile terminal 270 in accordance with the walking situation determined for the user. The action recommendation information is optimized according to the walking situation of the user. Furthermore, the action recommendation information includes information that prompts the user to make a decision. A user who hears the information output as audio from the mobile terminal 270 can take action in accordance with the action recommendation information to avoid tripping over uneven surfaces.

[0104] As described above, the discrimination device of this embodiment includes a data acquisition unit, a calculation unit, a storage unit, a discrimination unit, and an output unit. The data acquisition unit acquires sensor data measured in response to foot movement. The calculation unit calculates a relative change value indicating a relative change from the progression axis for each walking cycle using time-series data of the acquired sensor data. The calculation unit extracts endpoints to be set as the start and end points of a walking cycle from the time-series data of the sensor data. The calculation unit sets the chronologically earlier endpoint of two consecutive endpoints as the start point of one walking cycle. The calculation unit sets the chronologically later endpoint of two consecutive endpoints as the end point of one walking cycle. The calculation unit calculates a relative change value indicating a relative change from the progression axis at the starting point. Specifically, the calculation unit calculates, as the relative change value, a relative angle corresponding to the angle formed in the sagittal plane between a straight line passing through the starting point and the end point and the progression axis at the starting point, and a relative displacement corresponding to the distance in the sagittal plane between the progression axis at the starting point and the end point. The storage unit stores the sensor data acquired by the data acquisition unit. The storage unit stores the relative angle and relative displacement calculated by the calculation unit. The storage unit also stores the walking status determined by the determination unit. The determination unit determines the walking status using time-series data of the relative change value during a target period. The output unit outputs walking information including the determined walking status.

[0105] In this embodiment, the walking status is determined using time series data of relative change values, including the relative angle and relative displacement in the sagittal plane, calculated for each gait cycle. Using the time series data of relative change values ​​in the sagittal plane makes it possible to detect changes in the height direction corresponding to the walking status, which cannot be detected by sensor data. Therefore, using the time series data of relative change values ​​in the sagittal plane makes it possible to determine the walking status even for subjects with weakened muscles, such as elderly people or rehabilitation patients. In other words, this embodiment makes it possible to determine the walking status of any subject.

[0106] (Third embodiment) Next, a discrimination device according to a third embodiment will be described with reference to the drawings. The discrimination device according to this embodiment differs from the first and second embodiments in that it removes sensor data from a time period in which walking conditions were exceptional rather than normal. The discrimination device according to this embodiment is combined with the measurement device according to the first embodiment to form a gait measurement system. The method of this embodiment may be combined with the method of the first and second embodiments. In the following, a description of the same configuration as in the first and second embodiments will be omitted.

[0107] (composition) 26 is a block diagram showing an example of the configuration of a discrimination device according to the present disclosure. The discrimination device 32 includes a data acquisition unit 321, a calculation unit 322, a storage unit 323, a discrimination unit 325, an exceptional data removal unit 326, and an output unit 327.

[0108] The data acquisition unit 321 has the same configuration as the data acquisition unit 321 in the first embodiment. The data acquisition unit 321 acquires time-series data of sensor data from the measurement device.

[0109] The calculation unit 322 has the same configuration as the calculation unit 322 in the first embodiment. The calculation unit 322 extracts endpoints of a walking cycle from the time-series data of the sensor data. The section between consecutive endpoints corresponds to a walking cycle. Of the two consecutive endpoints, the earlier endpoint is set as the start point of one walking cycle. Of the two consecutive endpoints, the later endpoint is set as the end point of one walking cycle. The calculation unit 322 extracts the time-series data of the sensor data between the two consecutive endpoints as a walking waveform for one walking cycle. The calculation unit 322 may normalize the extracted walking waveform.

[0110] The calculation unit 322 uses time-series data (gait waveform) of the sensor data to calculate a relative change value indicating a relative change from the axis of progression in the horizontal plane for each walking cycle. The calculation unit 322 uses the extracted gait waveform to calculate a relative change value from the start point to the end point. For example, the calculation unit 322 uses the extracted gait waveform to calculate a relative change value from the start point to the end point in the horizontal plane (XY plane). The relative change value in the horizontal plane (XY plane) indicates a relative change from the axis of progression at the start point. For example, the calculation unit 322 uses the extracted gait waveform to calculate a relative change value from the start point to the end point in the sagittal plane (YZ plane). The relative change value in the sagittal plane (YZ plane) indicates a relative change from the axis of progression at the start point.

[0111] The storage unit 323 has the same configuration as the storage unit 323 in the first embodiment. The storage unit 323 stores the relative change value calculated by the calculation unit 322. For example, the storage unit 323 stores the relative displacement d x and the relative angle θ z For example, the storage unit 323 stores the relative displacement d z and the relative angle θ x As will be described later, the storage unit 323 also stores the walking conditions determined by the determination unit 325. The storage unit 323 also stores the sensor data acquired by the data acquisition unit 321.

[0112] The discrimination unit 325 acquires the relative change value for the target period from the storage unit 323. The target period is a time period spanning multiple walking cycles (strides). The discrimination unit 325 discriminates the walking status for the target period using time-series data of the relative change value. For example, the discrimination unit 325 discriminates the walking status for the target period using three-dimensional rotation correction performed using the relative change value. For example, the discrimination unit 325 discriminates the walking status for the target period using a machine learning model (discrimination model) generated by machine learning.

[0113] If the relative change value does not exceed the discrimination reference value, the discrimination unit 325 determines that the walking situation was normal walking. On the other hand, if the relative change value exceeds the discrimination reference value, the discrimination unit 325 determines that the walking situation was exceptional walking. The discrimination reference value is the relative displacement d x and the relative angle θ z , relative displacement in the sagittal plane d z and the relative angle θ x is set for each of the above.

[0114] The exceptional data removal unit 326 removes sensor data measured during a target period determined to be exceptional walking that is different from normal walking. That is, the exceptional data removal unit 326 removes sensor data for a time period determined to be exceptional walking. On the other hand, the exceptional data removal unit 326 records sensor data for a time period determined to be normal walking in the storage unit 323 in association with the walking status during the target period.

[0115] The output unit 327 outputs the sensor data stored in the memory unit 323. The sensor data is sensor data for a time period determined to be normal walking. The walking status at the time of measurement is linked to the sensor data. Information including the sensor data linked to the walking status is also called walking information. For example, the output unit 327 outputs the walking information to a mobile terminal carried by the subject. For example, the output unit 327 outputs the walking information to a terminal device or a server that uses the sensor data via the mobile terminal carried by the subject. For example, the output unit 327 may be configured to output the sensor data to an external system or the like that uses the sensor data.

[0116] (operation) Next, the operation of the discriminator 32 will be described with reference to the drawings. The main operation of the discriminator 32 is similar to the operation of the discriminator 12 of the first embodiment (FIG. 12). The operation of the discriminator 32 differs from the operation of the discriminator 12 in the processing between steps S13 and S16 in FIG. 12. In the following, a description of the main operation of the discriminator 32 will be omitted, and the relative change value calculation processing will be described.

[0117] Fig. 27 is a flowchart for explaining an example of the operation of the discrimination device according to the present disclosure. The processing in Fig. 27 is inserted between step S13 and step S16 in the flowchart in Fig. 12. In explaining the processing according to the flowchart in Fig. 27, the components of the discrimination device 32 will be described as the subject of operations. The subject of operations in the processing according to the flowchart in Fig. 27 may be the discrimination device 32.

[0118] In FIG. 27, after step S13 in FIG. 12, the determination unit 325 determines the walking condition using the time-series data of the relative change value in the target period (step S361).

[0119] Here, if exceptional walking is determined to occur during the target period (Yes in step S362), the exceptional data removal unit 326 removes the sensor data for the time period determined to be exceptional walking (step S363).

[0120] If exceptional walking is not determined in the target period (No in step S362), or after step S363, the storage unit 323 stores the sensor data for the time period determined to be normal walking (step S364). After step S364, the process proceeds to step S16 in FIG. 12.

[0121] As described above, the discrimination device of this embodiment includes a data acquisition unit, a calculation unit, a memory unit, a discrimination unit, an exceptional data removal unit, and an output unit. The data acquisition unit acquires sensor data measured in response to foot movement. The calculation unit calculates a relative change value indicating a relative change from the axis of progression for each walking cycle using time-series data of the acquired sensor data. The calculation unit extracts endpoints to be set as the start and end points of a walking cycle from the time-series data of the sensor data. The calculation unit sets the chronologically earlier endpoint of two consecutive endpoints as the start point of one walking cycle. The calculation unit sets the chronologically later endpoint of two consecutive endpoints as the end point of one walking cycle. The calculation unit calculates a relative change value indicating a relative change from the axis of progression at the start point. The memory unit stores the sensor data acquired by the data acquisition unit. The memory unit stores the relative angle and relative displacement calculated by the calculation unit. The memory unit also stores the walking status discriminated by the discrimination unit. The discrimination unit discriminates the walking status using time-series data of the relative change value during the target period. If the relative change value does not exceed the discrimination reference value, the discrimination unit discriminates that the walking status was normal walking. On the other hand, if the relative change value exceeds the discrimination reference value, the discrimination unit discriminates that the walking status was exceptional walking. The exceptional data removal unit removes sensor data measured during the target period that was discriminated as exceptional walking, which is different from normal walking. The exceptional data removal unit removes sensor data for a time period that was discriminated as exceptional walking. On the other hand, the exceptional data removal unit links sensor data for a time period that was discriminated as normal walking to the walking status. The output unit outputs walking information including the discriminated walking status.

[0122] In this embodiment, the sensor data for the time period determined to be exceptional walking is removed, and the sensor data for the time period determined to be normal walking is linked to the walking situation. According to this embodiment, the physical condition, etc. can be accurately estimated using only the sensor data measured during normal walking situations.

[0123] (Fourth embodiment) Next, a discrimination device according to a fourth embodiment will be described with reference to the drawings. The discrimination device according to this embodiment differs from the first to third embodiments in that a tag indicating a gait type input by a user is set. The discrimination device according to this embodiment is combined with the measurement device according to the first embodiment to form a gait measurement system. The method of this embodiment may be combined with the methods of the first to third embodiments. In the following, a description of the same configuration as in the first to third embodiments will be omitted.

[0124] (composition) 28 is a block diagram showing an example of the configuration of a discrimination device according to the present disclosure. The discrimination device 42 includes a data acquisition unit 421, a calculation unit 422, a storage unit 423, a tag acquisition unit 424, a discrimination unit 425, and an output unit 427.

[0125] The data acquisition unit 421 has the same configuration as the data acquisition unit 421 in the first embodiment. The data acquisition unit 421 acquires time-series data of sensor data from the measurement device.

[0126] The calculation unit 422 has the same configuration as the calculation unit 422 in the first embodiment. The calculation unit 422 extracts endpoints of a walking cycle from the time-series data of the sensor data. The section between consecutive endpoints corresponds to a walking cycle. Of the two consecutive endpoints, the earlier endpoint is set as the start point of one walking cycle. Of the two consecutive endpoints, the later endpoint is set as the end point of one walking cycle. The calculation unit 422 extracts the time-series data of the sensor data between the two consecutive endpoints as a walking waveform for one walking cycle. The calculation unit 422 may normalize the extracted walking waveform.

[0127] The calculation unit 422 uses time-series data (gait waveform) of the sensor data to calculate a relative change value indicating a relative change from the axis of progression in the horizontal plane for each walking cycle. The calculation unit 422 uses the extracted gait waveform to calculate a relative change value from the start point to the end point. For example, the calculation unit 422 uses the extracted gait waveform to calculate a relative change value from the start point to the end point in the horizontal plane (XY plane). The relative change value in the horizontal plane (XY plane) indicates a relative change from the axis of progression at the start point. For example, the calculation unit 422 uses the extracted gait waveform to calculate a relative change value from the start point to the end point in the sagittal plane (YZ plane). The relative change value in the sagittal plane (YZ plane) indicates a relative change from the axis of progression at the start point.

[0128] The storage unit 423 has the same configuration as the storage unit 423 in the first embodiment. The storage unit 423 stores the relative change value calculated by the calculation unit 422. For example, the storage unit 423 stores the relative displacement d x and the relative angle θ z For example, the storage unit 423 stores the relative displacement d z and the relative angle θ x As will be described later, the storage unit 423 also stores the walking conditions determined by the determination unit 425. The storage unit 423 also stores the sensor data acquired by the data acquisition unit 421.

[0129] The tag acquisition unit 424 acquires a setting signal of a tag indicating a gait type selected by the user. The gait types are classifications of characteristic gaits. For example, the gait types include stair walking, mountain climbing walking, meandering path walking, walking with an umbrella, and walking on a snowy path. The tag acquisition unit 424 sets the acquired tag in the discrimination unit 425. The tag acquisition unit 424 also acquires a tag release signal. The tag acquisition unit 424 releases the tag set in the discrimination unit 425 in response to the acquired release signal. For example, the tag is set via a user interface displayed on the screen of a mobile terminal used by the user.

[0130] FIG. 29 is a conceptual diagram showing an example of a user interface for inputting tags according to the present disclosure, displayed on the screen of a mobile device. A user is walking wearing shoes 400 equipped with a measuring device 40. A selection area 475 for accepting tag selection is displayed on the screen of the mobile device 470. A plurality of walking situation candidates are displayed in the selection area 475. In the example of FIG. 29, walking types such as stair walking, mountain climbing walking, meandering path walking, walking with an umbrella, and walking on a snowy road are displayed. For example, in the example of FIG. 29, mountain climbing walking is selected as the walking situation. When the user taps the start button 476, a setting signal for the selected tag is sent to the discrimination device 42, and a tag indicating the walking situation of mountain climbing walking is set. Furthermore, when the user taps the end button 477, a tag release signal is sent to the discrimination device 42, and the tag indicating the walking situation of mountain climbing walking is released.

[0131] The discrimination unit 425 acquires the relative change value for the target period from the storage unit 423. The target period is a time period spanning multiple walking cycles (strides). The discrimination unit 425 discriminates the walking status for the target period using time-series data of the relative change value. For example, the discrimination unit 425 discriminates the walking status for the target period using three-dimensional rotation correction performed using the relative change value. For example, the discrimination unit 425 discriminates the walking status for the target period using a machine learning model (discrimination model) generated by machine learning. The discrimination unit 425 records the walking status for the target period in association with sensor data measured in walking cycles included in the target period.

[0132] Furthermore, the discrimination unit 425 receives tag setting / cancellation. The discrimination unit 425 associates the walking status indicated by the tag with the sensor data measured during the period in which the tag is set. For example, the discrimination unit 425 preferentially associates the walking status indicated by the tag with the sensor data measured during the period in which the tag is set. For example, the discrimination unit 425 may be configured to remove the sensor data measured during the period in which the tag is set. In this case, the sensor data measured during the period in which the tag is set is not output from the output unit 427. When the tag is released, the discrimination unit 425 discriminates the walking status during the target period using the time-series data of the relative change value.

[0133] The output unit 427 outputs the sensor data stored in the storage unit 423. The sensor data is linked to the walking status at the time of measurement. Information including the sensor data linked to the walking status is also called walking information. For example, the output unit 427 outputs the walking information to a mobile terminal carried by the subject. For example, the output unit 427 outputs the walking information to a terminal device or a server that uses the sensor data via the mobile terminal carried by the subject. For example, the output unit 427 may be configured to output the sensor data to an external system that uses the sensor data.

[0134] (operation) Next, the operation of the discriminator 42 will be described with reference to the drawings. The main operation of the discriminator 42 is similar to the operation of the discriminator 12 of the first embodiment (FIG. 12). The operation of the discriminator 42 differs from the operation of the discriminator 12 in the processing between steps S13 and S16 in FIG. 12. In the following, a description of the main operation of the discriminator 42 will be omitted, and the relative change value calculation processing will be described.

[0135] Fig. 30 is a flowchart for explaining an example of the operation of the discrimination device according to the present disclosure. The processing in Fig. 30 is inserted between step S13 and step S16 in the flowchart in Fig. 12. In explaining the processing according to the flowchart in Fig. 30, the components of the discrimination device 42 will be described as the subject of operations. The subject of operations in the processing according to the flowchart in Fig. 30 may be the discrimination device 42.

[0136] In FIG. 30, after step S13 in FIG. 12, the determination unit 425 determines the walking state using the time-series data of the relative change value in the target period (step S461).

[0137] Here, if a tag is set (Yes in step S462) and the sensor data for the time period in which the tag is set is to be removed (Yes in step S463), the determination unit 425 removes the sensor data for the time period in which the tag is set (step S464).If a tag is set (Yes in step S462) and the sensor data for the time period in which the tag is set is not to be removed (No in step S463), the process proceeds to step S465.

[0138] If the answers to steps S462 and S463 are No, or if the tag is not set (No in step S462), the storage unit 423 records the walking status during the target period in association with the sensor data (step S465).

[0139] (Application example) Next, application examples of this embodiment will be described with reference to the drawings. FIGS. 31 and 32 are conceptual diagrams showing display examples of information according to the walking status determined by the discrimination device of the present disclosure. FIGS. 31 and 32 show an example in which information according to the walking status is output as audio on the screen of a mobile terminal 470 carried by a user walking while wearing shoes 400 in which a measuring device 40 is placed, in accordance with a tag set by the user. In the example using FIGS. 31 and 32, it is assumed that the tag "mountain climbing walking" is selected. In the example using FIGS. 31 and 32, it is assumed that information according to the user's walking status is generated by an information generation unit (not shown) that generates information using sensor data processed by the discrimination device 42. For example, the information generation unit generates information according to the user's walking status using a pre-constructed, trained machine learning model.

[0140] FIG. 31 shows an example in which information according to a walking situation corresponding to a tag set by a user is output as audio from a mobile terminal used by the user. In the example of FIG. 31, information such as "You are walking uphill" is output as audio from the mobile terminal 470 in accordance with the walking situation determined for the user. Also, in the example of FIG. 31, action recommendation information such as "Lift your knees a little higher" is output as audio from the mobile terminal 470 in accordance with the walking situation determined for the user. The action recommendation information is optimized according to the walking situation of the user. Furthermore, the action recommendation information includes information that prompts the user to make a decision. A user who hears the information output as audio from the mobile terminal 470 can walk uphill while being conscious of lifting their knees higher by acting in accordance with the action recommendation information.

[0141] FIG. 32 shows an example in which information according to a walking situation corresponding to a tag set by a user is output as audio from a mobile terminal used by the user. In the example of FIG. 32, information such as "You are walking down a slope" is output as audio from the mobile terminal 470 in accordance with the walking situation determined for the user. Also, in the example of FIG. 32, action recommendation information such as "Please walk a little more slowly" is output as audio from the mobile terminal 470 in accordance with the walking situation determined for the user. The action recommendation information is optimized according to the walking situation of the user. Furthermore, the action recommendation information includes information that prompts the user to make a decision. A user who hears the information output as audio from the mobile terminal 470 can walk down a slope while being conscious of walking slowly by acting in accordance with the action recommendation information.

[0142] As described above, the discrimination device of this embodiment includes a data acquisition unit, a tag acquisition unit, a calculation unit, a memory unit, a discrimination unit, and an output unit. The data acquisition unit acquires sensor data measured in response to foot movement. The tag acquisition unit acquires a tag setting signal and a tag release signal indicating a gait type selected by the user. The calculation unit calculates a relative change value indicating a relative change from the axis of progression for each gait cycle using the time-series data of the acquired sensor data. The calculation unit extracts endpoints to be set as the start and end points of a gait cycle from the time-series data of the sensor data. The calculation unit sets the chronologically earlier endpoint of two consecutive endpoints as the start point of one gait cycle. The calculation unit sets the chronologically later endpoint of two consecutive endpoints as the end point of one gait cycle. The calculation unit calculates a relative change value indicating a relative change from the axis of progression at the start point. The memory unit stores the sensor data acquired by the data acquisition unit. The memory unit stores the relative angle and relative displacement calculated by the calculation unit. The memory unit also stores the walking status discriminated by the discrimination unit. The determination unit determines the walking status using time-series data of the relative change value during a target period. The determination unit associates the walking status indicated by the tag with the sensor data measured during the period in which the tag is set. The output unit outputs walking information including the determined walking status.

[0143] In this embodiment, the walking status indicated by a tag representing a walking type selected by the user is linked to the sensor data. According to this aspect, the walking status can be determined not only based on the walking status determined by the sensor data but also based on the tag selected by the user. Therefore, according to this embodiment, the walking status can be determined more accurately in a situation where exceptional walking continues to occur.

[0144] (Fifth embodiment) Next, a discrimination device according to a fifth embodiment will be described with reference to the drawings. The discrimination device according to this embodiment has a simplified configuration of the discrimination devices according to the first to fourth embodiments. For example, the functions of the components included in the discrimination device according to this embodiment are realized by the functions of the components included in the discrimination devices according to the first to fourth embodiments.

[0145] (composition) 33 is a block diagram showing an example of the configuration of a discrimination device according to the present disclosure. The discrimination device 52 includes a data acquisition unit 521, a calculation unit 522, a discrimination unit 525, and an output unit 527.

[0146] The data acquisition unit 521 acquires sensor data measured in accordance with foot movement. The calculation unit 522 calculates a relative change value indicating a relative change from the axis of progression for each walking cycle using time-series data of the acquired sensor data. The discrimination unit 525 discriminates the walking status using time-series data of the relative change value during a target period. The output unit 527 outputs walking information including the discriminated walking status.

[0147] (operation) Fig. 34 is a flowchart for explaining an example of the operation (discrimination method) of the discrimination device according to the present disclosure. In the explanation of the processing according to the flowchart of Fig. 34, the components of the discrimination device 52 will be described as the subject of the operations. The subject of the operations according to the flowchart of Fig. 34 may be the discrimination device 52.

[0148] In FIG. 34, first, the data acquisition unit 521 acquires sensor data measured in accordance with the movement of the feet (step S51).

[0149] Next, the calculation unit 522 calculates a relative change value indicating a relative change from the axis of progression for each walking cycle using the time-series data of the acquired sensor data (step S52).

[0150] Next, the determination unit 525 determines the walking condition using the time-series data of the relative change value in the target period (step S53).

[0151] Next, the output unit 527 outputs walking information including the determined walking state (step S54).

[0152] In this embodiment, the walking status is determined using time-series data of relative change values ​​calculated for each walking cycle. Using the time-series data of relative change values ​​makes it possible to detect changes according to the walking status that cannot be detected using sensor data. Therefore, using the time-series data of relative change values ​​makes it possible to determine the walking status even for subjects with weakened muscles, such as elderly people and rehabilitation patients. In other words, according to this embodiment, the walking status of any subject can be determined.

[0153] (Hardware) Next, a hardware configuration for executing the control and processing in the present disclosure will be described with reference to the drawings. Fig. 35 is a block diagram showing an example of a hardware configuration for executing the control and processing in the present disclosure. Here, an information processing device 90 (computer) is given as an example of such a hardware configuration. The information processing device 90 is an example of a configuration for executing the control and processing in the present disclosure and does not limit the scope of the present disclosure.

[0154] As shown in Fig. 35, an information processing device 90 includes a processor 91, a memory 92, an auxiliary storage device 93, an input / output interface 95, and a communication interface 96. In Fig. 35, interface is abbreviated as I / F (Interface). The processor 91, memory 92, auxiliary storage device 93, input / output interface 95, and communication interface 96 are connected to each other via a bus 98 so as to be able to communicate data with each other. The processor 91, memory 92, auxiliary storage device 93, and input / output interface 95 are also connected to a network such as the Internet or an intranet via the communication interface 96.

[0155] The processor 91 loads a program (instructions) stored in an auxiliary storage device 93 or the like into the memory 92. For example, the program is a software program for executing the control and processing in the present disclosure. The processor 91 executes the program loaded into the memory 92. The processor 91 executes the program to execute the control and processing in the present disclosure.

[0156] The memory 92 is a storage device having an area in which a program is loaded. The processor 91 loads a program stored in an auxiliary storage device 93 or the like into the memory 92. The memory 92 is realized by a volatile memory such as a DRAM (Dynamic Random Access Memory). Alternatively, a non-volatile memory such as an MRAM (Magnetoresistive Random Access Memory) may be used as the memory 92.

[0157] The auxiliary storage device 93 stores various data such as programs. For example, the auxiliary storage device 93 is realized by a local disk such as a hard disk or flash memory. Note that it is also possible to configure the system so that various data is stored in the memory 92, and omit the auxiliary storage device 93.

[0158] The input / output interface 95 is an interface for connecting the information processing device 90 to peripheral devices based on standards and specifications. The communication interface 96 is an interface for connecting to external systems and devices via a network such as the Internet or an intranet based on standards and specifications. The input / output interface 95 and the communication interface 96 may be a common interface for connecting to external devices.

[0159] Input devices such as a keyboard, mouse, and touch panel may be connected to the information processing device 90 as needed. These input devices are used to input information and settings. When a touch panel is used as the input device, a screen having the function of the touch panel serves as the interface. The processor 91 and the input devices are connected via an input / output interface 95.

[0160] The information processing device 90 may be equipped with a display device for displaying information. When a display device is equipped, the information processing device 90 is equipped with a display control device (not shown) for controlling the display of the display device. The information processing device 90 and the display device are connected via an input / output interface 95.

[0161] The information processing device 90 may be equipped with a drive device. The drive device acts as an intermediary between the processor 91 and a recording medium (program recording medium) to read data and programs stored on the recording medium and to write processing results of the information processing device 90 to the recording medium. The information processing device 90 and the drive device are connected via an input / output interface 95.

[0162] The above is an example of a hardware configuration for enabling the control and processing in the present disclosure. The hardware configuration in Figure 35 is an example of a hardware configuration for executing the control and processing in the present disclosure, and does not limit the scope of the present disclosure. A program that causes a computer to execute the control and processing in the present disclosure is also included in the scope of the present disclosure.

[0163] A program recording medium on which a program for executing the processing in this embodiment is recorded is also included in the scope of the present invention. For example, the program recording medium is a computer-readable non-transitory recording medium. The recording medium can be realized as an optical recording medium such as a CD (Compact Disc) or a DVD (Digital Versatile Disc). The recording medium may also be realized as a semiconductor recording medium such as a USB (Universal Serial Bus) memory or an SD (Secure Digital) card. The recording medium may also be realized as a magnetic recording medium such as a flexible disk or other recording medium.

[0164] The components in the present disclosure may be combined in any manner. The components in the present disclosure may be realized by software. The components in the present disclosure may be realized by circuits.

[0165] Although the present disclosure has been described above with reference to the embodiments, the present disclosure is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate.

[0166] A part or all of the above-described embodiments can be described as, but not limited to, the following supplementary notes. (Appendix 1) a data acquisition unit that acquires sensor data measured in accordance with foot movement; a calculation unit that calculates a relative change value indicating a relative change from a progression axis for each walking cycle using time series data of the acquired sensor data; a determination unit that determines a walking state using time series data of the relative change value during a target period; an output unit that outputs walking information including the determined walking condition. (Appendix 2) The calculation unit extracting end points set at the start and end points of a walking cycle from the time-series data of the sensor data; setting the end point that precedes the two consecutive end points in time series as the start point of one walking cycle; setting the chronologically succeeding end point of the two consecutive end points as the end point of one walking cycle; 2. The discrimination device according to claim 1, wherein the relative change value indicates a relative change from the axis of travel at the starting point. (Appendix 3) The calculation unit calculating, as the relative change value, a relative angle corresponding to the angle formed in a horizontal plane between a straight line passing through the start point and the end point and the traveling axis at the start point, and a relative displacement corresponding to the distance in the horizontal plane between the traveling axis at the start point and the end point; The determination unit 3. The discrimination device according to claim 2, wherein the walking condition is discriminated using the calculated relative change value. (Appendix 4) The calculation unit a relative angle corresponding to the angle formed on the sagittal plane between a straight line passing through the start point and the end point and the progression axis at the start point, and a relative displacement corresponding to the distance on the sagittal plane between the progression axis at the start point and the end point, as the relative change value; The determination unit 3. The discrimination device according to claim 2, wherein the walking condition is discriminated using the calculated relative change value. (Appendix 5) an exceptional data removal unit that removes the sensor data measured during the target period that is determined to be exceptional walking that is different from normal walking; The determination unit If the relative change value does not exceed the discrimination reference value, the walking condition is determined to be normal walking; If the relative change value exceeds a discrimination reference value, the walking situation is determined to be exceptional walking; The exceptional data removal unit Remove the sensor data for the time period determined to be exceptional walking; 5. The discrimination device according to claim 1, wherein the sensor data for the time period in which the walking status was determined to be normal walking is linked to the walking status. (Appendix 6) a tag acquisition unit that acquires a setting signal and a release signal of a tag that indicates a walking type selected by a user; The determination unit 5. The discrimination device according to claim 1, wherein the sensor data measured during the period in which the tag is set is linked to the walking status indicated by the tag. (Appendix 7) The determination unit 5. The discrimination device according to claim 1, wherein the walking condition is discriminated using a machine learning model that outputs the walking condition in response to input of time-series data of the relative change value. (Appendix 8) an information generation unit that generates action recommendation information that is optimized according to the walking status of the user and that encourages decision-making for the user, using the sensor data linked to the walking status; The output unit 5. The discrimination device according to claim 1, wherein the walking information including the action recommendation information is displayed on a screen of a mobile terminal used by the user. (Appendix 9) The computer Acquire sensor data measured according to foot movements, Using the acquired time series data of the sensor data, a relative change value indicating a relative change from the axis of progression is calculated for each walking cycle; determining a walking state using time series data of the relative change value during a target period; A determination method that outputs walking information including the determined walking condition. (Appendix 10) A process of acquiring sensor data measured according to foot movement; a process of calculating a relative change value indicating a relative change from the axis of progression for each walking cycle using the time series data of the acquired sensor data; A process of determining a walking state using time series data of the relative change value during a target period; and outputting walking information including the determined walking condition. Furthermore, some or all of the configurations described in Supplementary Notes 2 to 8, which are dependent on Supplementary Note 1, may also be dependent on Supplementary Notes 9 and 10 in the same dependent relationship as Supplementary Notes 2 to 8. Furthermore, not limited to Supplementary Notes 1, 9, and 10, but within the scope of each of the above-mentioned embodiments, some or all of the configurations described as Supplements may also be dependent on various hardware, software, various recording means for recording software, or systems. [Explanation of symbols]

[0167] 1 Gait measurement system 10. Measuring equipment 12, 22, 32, 42, 52 Discrimination device 110 Sensors 111 Acceleration Sensor 112 Angular rate sensor 113 Control Unit 115 Communications Department 117 Power supply 121, 221, 321, 421, 521 Data acquisition section 122, 222, 322, 422, 522 calculation section 123, 223, 323, 423 storage section 125, 225, 325, 425, 525 Discrimination section 126 Information generation section 127, 227, 327, 427, 527 output section 326 Exception Data Removal Unit 424 Tag Acquisition Unit

Claims

1. a data acquisition unit that acquires sensor data measured in accordance with foot movement; a calculation unit that calculates a relative change value indicating a relative change from a progression axis for each walking cycle using time series data of the acquired sensor data; a determination unit that determines a walking state using time series data of the relative change value during a target period; an output unit that outputs walking information including the determined walking condition.

2. The calculation unit extracting end points set at the start and end points of a walking cycle from the time-series data of the sensor data; setting the end point that precedes the two consecutive end points in time series as the start point of one walking cycle; setting the chronologically succeeding end point of the two consecutive end points as the end point of one walking cycle; 2. The discrimination device according to claim 1, wherein the relative change value indicates a relative change from the axis of travel at the starting point.

3. The calculation unit calculating, as the relative change value, a relative angle corresponding to the angle formed in a horizontal plane between a straight line passing through the start point and the end point and the traveling axis at the start point, and a relative displacement corresponding to the distance in the horizontal plane between the traveling axis at the start point and the end point; The determination unit The determination device according to claim 2 , wherein the walking condition is determined using the calculated relative change value.

4. The calculation unit a relative angle corresponding to the angle formed on the sagittal plane between a straight line passing through the start point and the end point and the progression axis at the start point, and a relative displacement corresponding to the distance on the sagittal plane between the progression axis at the start point and the end point, as the relative change value; The determination unit The determination device according to claim 2 , wherein the walking condition is determined using the calculated relative change value.

5. an exceptional data removal unit that removes the sensor data measured during the target period that is determined to be exceptional walking that is different from normal walking; The determination unit If the relative change value does not exceed the discrimination reference value, the walking condition is determined to be normal walking; If the relative change value exceeds a discrimination reference value, the walking situation is determined to be exceptional walking; The exceptional data removal unit Remove the sensor data for the time period determined to be exceptional walking; The determination device according to claim 1 , wherein the sensor data for the time period in which the person was determined to be walking normally is linked to the walking situation.

6. a tag acquisition unit that acquires a setting signal and a release signal of a tag that indicates a walking type selected by a user; The determination unit The discrimination device according to claim 1 , wherein the walking status indicated by the tag is linked to the sensor data measured during a period in which the tag is set.

7. The determination unit The determination device according to claim 1 , wherein the walking condition is determined using a machine learning model that outputs the walking condition in response to input of time-series data of the relative change value.

8. an information generation unit that generates action recommendation information that is optimized according to the walking status of the user and that encourages decision-making for the user, using the sensor data linked to the walking status; The output unit The determination device according to claim 1 , wherein the walking information including the action recommendation information is displayed on a screen of a mobile terminal used by the user.

9. The computer Acquire sensor data measured according to foot movements, Using the acquired time series data of the sensor data, a relative change value indicating a relative change from the axis of progression is calculated for each walking cycle; determining a walking state using time series data of the relative change value during a target period; A determination method that outputs walking information including the determined walking condition.

10. A process of acquiring sensor data measured according to foot movement; a process of calculating a relative change value indicating a relative change from the axis of progression for each walking cycle using the time series data of the acquired sensor data; A process of determining a walking state using time series data of the relative change value during a target period; and outputting walking information including the determined walking condition.

Images