Pelvic tilt estimation device, estimation system, pelvic tilt estimation method, and program

Abstract

To provide a pelvis inclination estimation device, etc. capable of estimating a pelvis inclination, which is an index of a motion of the lumbar, in a daily life accurately and easily.SOLUTION: A pelvis inclination estimation device includes: a communication unit for acquiring feature amount data including a feature amount used for estimating a pelvis inclination, which is an index on a motion of the lumbar, extracted from a walking waveform of a space acceleration and a space angular velocity included in sensor data on a motion of the foot of a subject; a storage unit for storing an estimation model for outputting an estimation value on the pelvis inclination in response to input of the feature amount included in the feature amount data; an estimation unit for inputting the feature amount included in the acquired feature amount data to the estimation model, and estimating the pelvis inclination of the subject according to the estimation value on the pelvis inclination output from the estimation model; and an output unit for outputting information according to the pelvis inclination of the subject.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] This disclosure relates to a pelvic tilt estimation device, etc., which estimates pelvic tilt, an indicator related to hip movement. [Background technology]

[0002] With the growing interest in healthcare, services that provide information based on gait patterns are attracting attention. For example, technologies are being developed that analyze gait patterns using sensor data measured by sensors implemented in footwear such as shoes. The time-series data of the sensor data reveals features associated with walking events that relate to the body's physical condition. By analyzing walking data that includes features associated with walking events, it is possible to estimate the subject's physical condition.

[0003] The anterior-posterior, lateral, and vertical tilt of the pelvis (lumbar region) during walking (also called pelvic tilt) is an indicator of lumbar sway and movement. Pelvic tilt is used as an indicator for visualizing gait and evaluating gait stability. If pelvic tilt can be estimated with high accuracy by analyzing gait data, services that meet healthcare needs can be provided.

[0004] Patent Document 1 discloses a gait evaluation device for evaluating a user's walking ability. The device in Patent Document 1 calculates multiple gait indices related to the walking state using multiple gait data acquired from a subject. In the method of Patent Document 1, the subject's walking score is calculated using gait data acquired by an acceleration sensor attached to the subject's waist. In the method of Patent Document 1, the Harmonic Ratio, one of the gait indices, is calculated from the vertical, lateral, and anterior-posterior acceleration waveforms measured by the acceleration sensor attached to the subject's waist.

[0005] Patent Document 2 discloses a computing device that calculates the step length of both the left and right feet using sensor data based on foot movements measured by sensors installed on the feet of pedestrians. The device in Patent Document 2 calculates the step length of both the left and right feet according to the acceleration in the direction of travel and the timing of walking events that appear in the walking waveform of the trajectory in the direction of travel.

[0006] Patent Document 3 discloses a physical condition detection device that identifies a user's physical condition using captured images, including the user's walking motion, captured by a camera. The device in Patent Document 3 extracts the area in which the user is captured in the captured image and analyzes the user's walking motion in real space based on depth data within the extracted area. Patent Document 3 lists items including lateral tilt of the pelvis as walking characteristics that indicate the properties of walking motion. [Prior art documents] [Patent Documents]

[0007] [Patent Document 1] Japanese Patent Publication No. 2020-151470 [Patent Document 2] International Publication No. 2022 / 038664 [Patent Document 3] International Publication No. 2016 / 031313 [Overview of the project] [Problems that the invention aims to solve]

[0008] The method described in Patent Document 1 uses acceleration measured by an acceleration sensor attached to the waist to measure one of the indicators related to waist movement. In daily life, a sensor attached to the waist may restrict free movement. Also, if the position of the attached sensor shifts, the measurement accuracy decreases. Therefore, the method described in Patent Document 1 could not measure indicators related to waist movement with high accuracy and ease in daily life.

[0009] In the method of Patent Document 2, the step lengths of both the left and right feet are calculated using sensor data based on the movement of the feet. Patent Document 2 does not disclose estimating pelvic tilt using sensor data based on the movement of the feet.

[0010] In the method of Patent Document 3, a walking motion corresponding to walking characteristics including lateral tilt of the pelvis is analyzed using a captured image. Patent Document 3 did not disclose estimating pelvic tilt in conjunction with the movement of the feet. Also, in the method of Patent Document 3, in order to analyze the walking motion including walking characteristics, it was necessary to photograph the user with a camera.

[0011] An object of the present disclosure is to provide a pelvic tilt estimation device and the like that can accurately and easily estimate pelvic tilt, which is an index of lumbar movement, in daily life.

Means for Solving the Problems

[0012] A pelvic tilt estimation device according to an aspect of the present disclosure includes a communication unit that acquires feature amount data including feature amounts used for estimating pelvic tilt, which is an index of lumbar movement, extracted from the walking waveforms of spatial acceleration and spatial angular velocity included in sensor data regarding the movement of a subject's feet, a storage unit that stores an estimation model that outputs an estimated value regarding pelvic tilt in response to an input of the feature amounts included in the feature amount data, an estimation unit that inputs the feature amounts included in the acquired feature amount data into the estimation model and estimates the pelvic tilt of the subject according to the estimated value regarding pelvic tilt output from the estimation model, and an output unit that outputs information according to the pelvic tilt of the subject.

[0013] In a pelvic tilt estimation method according to an aspect of the present disclosure, feature amount data including feature amounts used for estimating pelvic tilt, which is an index of lumbar movement, extracted from sensor data regarding the movement of a subject's feet is acquired, an estimation model that outputs an estimated value regarding pelvic tilt is stored in response to an input of the feature amount data, the acquired feature amount data is input into the estimation model, the pelvic tilt of the subject is estimated according to the estimated value regarding pelvic tilt output from the estimation model, and information according to the pelvic tilt of the subject is output.

[0014] A program in one aspect of this disclosure causes a computer to perform the following processes: acquiring feature data, which includes features used to estimate pelvic tilt, an index of hip movement, extracted from sensor data relating to the movement of a subject's feet; storing an estimation model that outputs an estimated value for pelvic tilt in response to the input of feature data; inputting the acquired feature data into the estimation model to estimate the subject's pelvic tilt according to the estimated value for pelvic tilt output from the estimation model; and outputting information corresponding to the subject's pelvic tilt. [Effects of the Invention]

[0015] According to this disclosure, it will be possible to provide a pelvic tilt estimation device, etc., that can estimate pelvic tilt, which is an indicator of hip movement in daily life, with high accuracy and ease. [Brief explanation of the drawing]

[0016] [Figure 1] This is a block diagram showing an example of the configuration of the estimation system according to the first embodiment. [Figure 2] This is a block diagram showing an example of the configuration of a measuring device included in the estimation system according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the arrangement of a measuring device according to the first embodiment. [Figure 4] This is a conceptual diagram illustrating an example of the relationship between the local coordinate system and the world coordinate system set in the measuring device according to the first embodiment. [Figure 5] This is a conceptual diagram used to explain the human body. [Figure 6] This is a conceptual diagram to explain the gait cycle. [Figure 7] This graph illustrates an example of time-series data of sensor data measured by the measuring device according to the first embodiment. [Figure 8] This figure illustrates an example of normalization of gait waveform data using a measuring device according to the first embodiment. [Figure 9]This is a conceptual diagram illustrating the feature clusters from which the feature data generation unit of the measuring device according to the first embodiment extracts features. [Figure 10] This is a block diagram showing an example of the configuration of a pelvic tilt estimation device included in the estimation system according to the first embodiment. [Figure 11] This graph illustrates an example of the difference in pelvic tilt around the left-right axis. [Figure 12] This graph illustrates another example of the difference in pelvic tilt around the left-right axis. [Figure 13] This graph illustrates an example of the difference in pelvic tilt around the axis of progression. [Figure 14] This graph illustrates an example of the difference in pelvic tilt around the vertical axis. [Figure 15] This is a conceptual diagram illustrating the learning process of the estimation model used by the pelvic tilt estimation device in the estimation system according to the first embodiment. [Figure 16] This table summarizes an example of input data used for estimating pelvic tilt around the axis of motion by the pelvic tilt estimation device included in the estimation system according to the first embodiment. [Figure 17] This table summarizes an example of input data used for estimating pelvic tilt around the left-right axis by the pelvic tilt estimation device included in the estimation system according to the first embodiment. [Figure 18] This is a flowchart illustrating an example of the operation of a measuring device included in the estimation system according to the first embodiment. [Figure 19] This is a flowchart illustrating an example of the operation of the pelvic tilt estimation device included in the estimation system according to the first embodiment. [Figure 20] This is a conceptual diagram illustrating an example of the application of the estimation system according to the first embodiment. [Figure 21] This is a conceptual diagram illustrating an example of the application of the estimation system according to the first embodiment. [Figure 22]This is a block diagram showing an example of the configuration of a pelvic tilt estimation device according to the second embodiment. [Figure 23] Block diagram showing an example of a hardware configuration for executing the processing of each embodiment. [Modes for carrying out the invention]

[0017] The embodiments for carrying out the present invention will be described below with reference to the drawings. However, the embodiments described below have technically preferred limitations for carrying out the present invention, but the scope of the invention is not limited thereto. In all the figures used in the description of the embodiments below, the same parts are denoted by the same reference numerals unless there is a particular reason not to. Also, in the embodiments below, repeated explanations of similar configurations and operations may be omitted.

[0018] (First Embodiment) First, the estimation system according to the first embodiment will be described with reference to the drawings. The estimation system of this embodiment uses a measuring device mounted on footwear to measure sensor data related to the movement of the user's feet in accordance with their walking. The estimation system of this embodiment uses the measured sensor data to estimate pelvic tilt, which is an indicator related to the movement of the hips. Pelvic tilt corresponds to the angle of inclination of the pelvis during walking.

[0019] The left and right feet are connected to the pelvis through the lower leg and thigh. The hip and knee joints are located between the left and right feet and the pelvis, but the periodicity of the pelvis and lumbar region during walking is similar. Therefore, there are phases in which the movement of the left and right feet and the movement of the lumbar region are interconnected. In this embodiment, pelvic tilt, which is an indicator of lumbar movement, is estimated using sensor data related to the movement of the feet. Details of pelvic tilt will be described later.

[0020] (composition) Figure 1 is a block diagram showing an example of the configuration of the estimation system 1 according to this embodiment. The estimation system 1 comprises a measuring device 10 and a pelvic tilt estimation device 13. In this embodiment, an example in which the measuring device 10 and the pelvic tilt estimation device 13 are configured on separate hardware will be described. For example, the measuring device 10 is installed on the footwear of the subject (user) whose pelvic tilt is to be estimated. For example, the functions of the pelvic tilt estimation device 13 are installed on a portable terminal carried by the subject (user). In the following, the configurations of the measuring device 10 and the pelvic tilt estimation device 13 will be described individually.

[0021] [Measuring device] Figure 2 is a block diagram showing an example of the configuration of the measuring device 10. The measuring device 10 includes a sensor 11 and a feature data generation unit 12. In this embodiment, an example is given in which the sensor 11 and the feature data generation unit 12 are integrated. The sensor 11 and the feature data generation unit 12 may be provided as separate devices.

[0022] As shown in Figure 2, sensor 11 includes an acceleration sensor 111 and an angular velocity sensor 112. Figure 2 shows an example in which the acceleration sensor 111 and the angular velocity sensor 112 are included in sensor 11. Sensor 11 may also include sensors other than the acceleration sensor 111 and the angular velocity sensor 112. The description of sensors other than the acceleration sensor 111 and the angular velocity sensor 112 that may be included in sensor 11 is omitted.

[0023] The acceleration sensor 111 is a sensor that measures acceleration in three axes (also called spatial acceleration). The acceleration sensor 111 measures acceleration (also called spatial acceleration) as a physical quantity related to the movement of the foot. The acceleration sensor 111 outputs the measured acceleration to the feature data generation unit 12. For example, the acceleration sensor 111 can be a piezoelectric, piezoresistive, or capacitive type sensor. The sensor used as the acceleration sensor 111 is not limited to any measurement method as long as it can measure acceleration.

[0024] The angular velocity sensor 112 is a sensor that measures angular velocity (also called spatial angular velocity) around three axes. The angular velocity sensor 112 measures angular velocity (also called spatial angular velocity) as a physical quantity related to the movement of the foot. The angular velocity sensor 112 outputs the measured angular velocity to the feature data generation unit 12. For example, the angular velocity sensor 112 can use sensors of the vibration type, capacitive type, etc. The sensor used as the angular velocity sensor 112 is not limited to any measurement method as long as it can measure angular velocity.

[0025] Sensor 11 can be implemented, for example, by an inertial measurement device that measures acceleration and angular velocity. An example of an inertial measurement device is an IMU (Inertial Measurement Unit). An IMU includes an acceleration sensor 111 that measures acceleration in three axes and an angular velocity sensor 112 that measures angular velocity around three axes. Sensor 11 may also be implemented by an inertial measurement device such as a VG (Vertical Gyro) or AHRS (Attitude Heading). Alternatively, sensor 11 may be implemented by a GPS / INS (Global Positioning System / Inertial Navigation System). Sensor 11 may also be implemented by a device other than an inertial measurement device, as long as it can measure physical quantities related to foot movement.

[0026] Figure 3 is a conceptual diagram showing an example of how the measuring device 10 is positioned inside both shoes 100. In the example in Figure 3, the measuring device 10 is installed in a position corresponding to the underside of the arch of the foot. The measuring device 10 may be installed in a position other than the underside of the arch of the foot, as long as it can measure sensor data related to foot movement. For example, the measuring device 10 may be placed in the insole inserted into the shoe 100. The measuring device 10 may be placed on the bottom surface of the shoe 100. The measuring device 10 may be embedded in the body of the shoe 100. The measuring device 10 may or may not be detachable from the shoe 100. The measuring device 10 may also be installed in the socks worn by the user or in anklets or other decorative items worn by the user. Furthermore, the measuring device 10 may be directly attached to the foot or embedded in the foot. Figure 3 shows an example in which the measuring device 10 is installed in both shoes 100. The measuring device 10 may also be installed in one shoe 100.

[0027] In the example shown in Figure 3, a local coordinate system is set with the measuring device 10 (sensor 11) as the reference point, including the x-axis in the left-right direction, the y-axis in the direction of travel, and the z-axis in the vertical direction. The x-axis is positive to the left, the y-axis is positive backward, and the z-axis is positive upward. The orientation of the axes set on the sensor 11 may be the same for the left and right feet, or it may be different for the left and right feet. For example, if sensors 11 manufactured to the same specifications are placed inside the left and right shoes 100, the up-down orientation (Z-axis direction) of the sensors 11 placed in the left and right shoes 100 will be the same. In that case, the three axes of the local coordinate system set for the sensor data originating from the left foot and the three axes of the local coordinate system set for the sensor data originating from the right foot will be the same for the left and right. If sensors 11 manufactured to different specifications for the left and right are placed inside the shoes 100, the up-down orientation (Z-axis direction) of the sensors 11 placed in the left and right shoes 100 may be different.

[0028] Figure 4 is a conceptual diagram illustrating the local coordinate system (x-axis, y-axis, z-axis) set for the measuring device 10 (sensor 11) installed on the underside of the arch of the foot, and the world coordinate system (X-axis, Y-axis, Z-axis) set relative to the ground. In the world coordinate system (X-axis, Y-axis, Z-axis), with the user standing upright and facing the direction of travel, the user's lateral direction is set to the X-axis (leftward is positive), the direction of the user's back is set to the Y-axis (backward is positive), and the direction of gravity is set to the Z-axis (vertically upward is positive). Note that the example in Figure 4 conceptually shows the relationship between the local coordinate system (x-axis, y-axis, z-axis) and the world coordinate system (X-axis, Y-axis, Z-axis), and does not accurately show the relationship between the local coordinate system and the world coordinate system that changes according to the user's walking.

[0029] Figure 5 is a conceptual diagram illustrating the planes (also called body planes) set for the human body. In this embodiment, the sagittal plane divides the body into left and right halves, the coronal plane divides the body into front and back halves, and the horizontal plane divides the body horizontally. Note that, as shown in Figure 5, when the body is standing upright with the centerlines of the feet facing the direction of travel, the world coordinate system and the local coordinate system coincide. In this embodiment, rotation in the sagittal plane with the x-axis as the axis of rotation is defined as roll, rotation in the coronal plane with the y-axis as the axis of rotation is defined as pitch, and rotation in the horizontal plane with the z-axis as the axis of rotation is defined as yaw. Furthermore, the angle of rotation in the sagittal plane with the x-axis as the axis of rotation is defined as the roll angle, the angle of rotation in the coronal plane with the y-axis as the axis of rotation is defined as the pitch angle, and the angle of rotation in the horizontal plane with the z-axis as the axis of rotation is defined as the yaw angle. Hereafter, the x-axis, y-axis, and z-axis will be referred to as the three axes.

[0030] As shown in Figure 2, the feature data generation unit 12 (also called a feature data generation device) includes an acquisition unit 121, a normalization unit 122, an extraction unit 123, a generation unit 125, and a transmission unit 127. For example, the feature data generation unit 12 is implemented by a microcomputer or microcontroller that performs overall control and data processing of the measurement device 10. For example, the feature data generation unit 12 includes a CPU (Central Processing Unit), RAM (Random Access Memory), ROM (Read Only Memory), flash memory, etc. The feature data generation unit 12 controls the acceleration sensor 111 and the angular velocity sensor 112 to measure angular velocity and acceleration. For example, the feature data generation unit 12 may be implemented on the side of a mobile terminal (not shown) carried by the subject (user). In that case, the sensor 11 can be provided with a communication function, and the sensor data transmitted from the sensor 11 can be received by the mobile terminal on which the feature data generation unit 12 is implemented.

[0031] The acquisition unit 121 acquires acceleration in the three axes from the acceleration sensor 111. The acquisition unit 121 also acquires angular velocity around the three axes from the angular velocity sensor 112. For example, the acquisition unit 121 performs analog-to-digital conversion (AD conversion) on the acquired physical quantities (analog data) such as angular velocity and acceleration. Note that the physical quantities (analog data) measured by the acceleration sensor 111 and the angular velocity sensor 112 may be converted to digital data by the acceleration sensor 111 and the angular velocity sensor 112, respectively. The acquisition unit 121 outputs the converted digital data (also called sensor data) to the normalization unit 122. The acquisition unit 121 may be configured to store the sensor data in a storage unit (not shown). The sensor data includes at least the acceleration data converted to digital data and the angular velocity data converted to digital data. The acceleration data includes acceleration vectors in the three axes. The angular velocity data includes angular velocity vectors around the three axes. The acquisition time of the acceleration data and angular velocity data is associated with the data. The acquisition unit 121 may also apply corrections to the acceleration data and angular velocity data, such as correction for mounting errors, temperature correction, and linearity correction.

[0032] The normalization unit 122 acquires sensor data from the acquisition unit 121. The normalization unit 122 extracts time-series data equivalent to one walking cycle (also called walking waveform data) from the time-series data of acceleration in the three axes and angular velocity around the three axes included in the sensor data. The normalization unit 122 normalizes the time of the extracted walking waveform data equivalent to one walking cycle to a walking cycle of 0 to 100% (percent) (also called first normalization). Timings such as 1% and 10% included in the 0 to 100% walking cycle are also called walking phases. Furthermore, the normalization unit 122 normalizes the walking waveform data equivalent to one walking cycle that has been first normalized so that the stance phase accounts for 60% and the swing phase accounts for 40% (also called second normalization). The stance phase is the period during which at least a portion of the sole of the foot is in contact with the ground. The swing phase is the period during which the sole of the foot is off the ground. If gait waveform data is second normalized, the effects of potential gait phase shifts that may occur in each gait cycle can be reduced.

[0033] Figure 6 is a conceptual diagram illustrating the gait cycle of a single foot, with the right foot as the reference point. The gait cycle of a single foot, with the left foot as the reference point, is similar to that of the right foot. The horizontal axis of Figure 6 represents one gait cycle of the right foot, starting from the moment the right heel touches the ground and ending from the moment the right heel touches the ground again. The horizontal axis of Figure 6 is first normalized with the gait cycle set to 100%. Furthermore, the horizontal axis of Figure 6 is second normalized so that the stance phase accounts for 60% and the swing phase accounts for 40%. One gait cycle of a single foot is broadly divided into the stance phase, in which at least a portion of the sole of the foot is in contact with the ground, and the swing phase, in which the sole of the foot is off the ground. The stance phase is further subdivided into the loading response phase T1, mid-stance phase T2, terminal stance phase T3, and early swing phase T4. The swing phase is further subdivided into early swing phase T5, mid-swing phase T6, and terminal swing phase T7. Note that Figure 6 is just one example and does not limit the periods that constitute a one-step cycle or the names of those periods.

[0034] As shown in Figure 6, multiple events (also called walking events) occur during walking. E1 represents the event of the right heel making contact with the ground (heel contact) (HC: Heel Contact). E2 represents the event of the left toes leaving the ground while the sole of the right foot is in contact with the ground (opposite toe off) (OTO: Opposite Toe Off). E3 represents the event of the right heel lifting up while the sole of the right foot is in contact with the ground (heel rise) (HR: Heel Rise). E4 is the event of the left heel making contact with the ground (opposite heel strike) (OHS: Opposite Heel Strike). E5 represents the event of the right toes leaving the ground while the sole of the left foot is in contact with the ground (toe off) (TO: Toe Off). E6 represents the event of the left and right feet crossing over while the sole of the left foot is in contact with the ground (foot adjacent) (FA: Foot Adjacent). E7 represents the event where the tibia of the right foot is nearly perpendicular to the ground (Tibia Vertical) when the sole of the left foot is in contact with the ground (TV: Tibia Vertical). E8 represents the event where the heel of the right foot makes contact with the ground (Heel Contact) (HC: Heel Contact). E8 corresponds to the end of the gait cycle that begins with E1, and also to the beginning of the next gait cycle. Note that Figure 6 is just an example and does not limit the events that occur during walking or the names of those events.

[0035] Figure 7 illustrates an example of detecting heel strike (HC) and toe-off (TO) from time-series data (solid line) of forward acceleration (Y-direction acceleration). The timing of heel strike (HC) is the timing of the minimum peak immediately following the maximum peak in the time-series data of forward acceleration (Y-direction acceleration). The maximum peak that serves as a marker for the timing of heel strike (HC) corresponds to the maximum peak of the gait waveform data for one step cycle. The interval between consecutive heel strike (HC) is one step cycle. The timing of toe-off (TO) is the timing of the rise of the maximum peak that appears after the stance phase period in the time-series data of forward acceleration (Y-direction acceleration) where no fluctuations are observed. Figure 8 also shows time-series data (dashed line) of roll angle (angular velocity around the X-axis). The midpoint between the timing of the minimum roll angle and the timing of the maximum roll angle corresponds to the timing of the transition from mid-stance T2 to late-stance T3. mThis corresponds to the timing of the transition from mid-stance T2 to terminal-stance T3. m This roughly coincides with the timing of heel lift HR. The parameters used to estimate the physical state (also called gait parameters) are the timing of the transition from mid-stance T2 to terminal stance T3. m It can be calculated based on this.

[0036] Figure 8 illustrates an example of normalization of gait waveform data. The normalization unit 122 detects heel strike (HC) and toe-off (TO) from time-series data of acceleration in the direction of travel (Y-direction acceleration). The normalization unit 122 extracts the interval between consecutive heel strikes (HC) as gait waveform data for one gait cycle. Through first normalization, the normalization unit 122 converts the horizontal axis (time axis) of the gait waveform data for one gait cycle to a gait cycle of 0-100%. Figure 9 shows the gait waveform data after first normalization as a dashed line. In the gait waveform data after first normalization (dashed line), the timing of toe-off (TO) is shifted from 60%.

[0037] In the example shown in Figure 8, the normalization unit 122 normalizes the section from heel strike (HC) at 0% of the walking phase to toe-off (TO) following that heel strike to 60%. The normalization unit 122 also normalizes the section from toe-off (TO) to heel strike (HC) at 100% of the walking phase following that toe-off to 60% to 100%. As a result, the walking waveform data for one walking cycle is normalized into a section where the walking cycle is 0-60% (stance phase) and a section where the walking cycle is 60-100% (swing phase). Figure 9 shows the walking waveform data after the second normalization as a solid line. In the walking waveform data after the second normalization (solid line), the timing of toe-off (TO) coincides with 60%. For example, when verifying the duration of the stance phase and the swing phase, or their ratios, the second normalization may be omitted.

[0038] Figures 7 and 8 show an example of extracting and normalizing walking waveform data for one step cycle based on the acceleration in the direction of travel (Y-direction acceleration). For accelerations / angular velocities other than the acceleration in the direction of travel (Y-direction acceleration), the normalization unit 122 extracts and normalizes walking waveform data for one step cycle in accordance with the walking cycle of the acceleration in the direction of travel (Y-direction acceleration). Alternatively, the normalization unit 122 may generate time-series data of angles around the three axes by integrating the time-series data of angular velocity around the three axes. In that case, the normalization unit 122 also extracts and normalizes walking waveform data for angles around the three axes for one step cycle in accordance with the walking cycle of the acceleration in the direction of travel (Y-direction acceleration).

[0039] The normalization unit 122 may extract and normalize walking waveform data for one step cycle based on acceleration / angular velocity other than the acceleration in the direction of travel (Y direction acceleration) (diagram omitted). For example, the normalization unit 122 may detect heel strike (HC) and toe-off (TO) from time-series data of vertical acceleration (Z direction acceleration). The timing of heel strike (HC) 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) is approximately 0. The minimum peak that serves as a marker for the timing of heel strike (HC) corresponds to the smallest peak in the walking waveform data for one step cycle. The interval between consecutive heel strike (HC) is one step cycle. The timing of toe-off (TO) is the inflection point in the time-series data of vertical acceleration (Z-direction acceleration) where it gradually increases after passing through a period of small fluctuation following a maximum peak immediately after heel strike (HC). The normalization unit 122 may also extract and normalize walking waveform data for one step cycle based on both forward acceleration (Y-direction acceleration) and vertical acceleration (Z-direction acceleration). Alternatively, the normalization unit 122 may extract and normalize walking waveform data for one step cycle based on accelerations other than forward acceleration (Y-direction acceleration) and vertical acceleration (Z-direction acceleration), such as angular velocity or angle.

[0040] The extraction unit 123 acquires walking waveform data for one step cycle that has been normalized by the normalization unit 122. The extraction unit 123 extracts features used for estimating pelvic tilt from the walking waveform data for one step cycle. Based on pre-set conditions, the extraction unit 123 extracts features (also called cluster features) for each walking phase cluster from walking phase clusters that integrate temporally consecutive walking phases. A walking phase cluster contains at least one walking phase. A walking phase cluster may also contain a single walking phase. The walking waveform data and walking phases from which features used for estimating pelvic tilt are extracted will be described later.

[0041] Figure 9 is a conceptual diagram illustrating the extraction of features for estimating pelvic tilt from gait waveform data for one step cycle. For example, the extraction unit 123 extracts temporally continuous gait phases i to i+m as gait phase cluster C (where i and m are natural numbers). In this embodiment, an example is given in which gait phase cluster C used for estimating pelvic tilt is selected by correlation analysis using statistical parametric mapping. For example, gait phase cluster C may be selected by Pearson correlation analysis.

[0042] In the example in Figure 9, the walking phase cluster C contains m walking phases (components). That is, the number of walking phases (components) constituting the walking phase cluster C (also called the number of components) is m. Figure 9 shows an example where the walking phases are integer values, but walking phases may be subdivided to decimal places. When walking phases are subdivided to decimal places, the number of components of the walking phase cluster C will be a number corresponding to the number of data points in the interval of the walking phase cluster. The extraction unit 123 extracts features from each of the walking phases i to i+m. When the walking phase cluster C is composed of a single walking phase j, the extraction unit 123 extracts features from that single walking phase j (where j is a natural number).

[0043] The generation unit 125 generates the features of the walking phase cluster (cluster features) by applying a feature constructor formula to the features extracted from each of the walking phases that make up the walking phase cluster. Cluster features are also called first features. The feature constructor formula is a pre-set calculation formula for generating the features of the walking phase cluster. For example, the feature constructor formula is a calculation formula related to arithmetic operations. For example, the cluster features calculated using the feature constructor formula are the integral mean, arithmetic mean, slope, and variability of the features in each walking phase included in the walking phase cluster. For example, the generation unit 125 applies a calculation formula that calculates the slope and variability of the features extracted from each of the walking phases that make up the walking phase cluster as the feature constructor formula. For example, if the walking phase cluster consists of a single walking phase, the slope and variability cannot be calculated, so a feature constructor formula that calculates the integral mean or arithmetic mean should be used. For example, if the walking phase cluster consists of a single walking phase, the features extracted from that walking phase may be set as the cluster features.

[0044] Furthermore, the generation unit 125 calculates parameters related to gait (also called gait parameters). The generation unit 125 calculates the gait parameters using feature quantities derived from the gait waveform data. The gait parameters include features used to estimate the body state. The estimation system 1 may be configured to calculate the gait parameters on the side of the pelvic tilt estimation device 13. Examples of gait parameters calculated by the generation unit 125 are listed below. The following gait parameters are examples and do not cover all parameters including gait features. In this embodiment, among the gait parameters listed below, those with a high correlation in the estimation of pelvic tilt are selected. Details of the calculation method for the gait parameters are omitted.

[0045] Examples of gait parameters include stride length, gait pitch, gait speed, ground contact angle, lift-off angle, outward rotation distance (circumference), and toe direction (internal / external rotation). Stride length is the distance between the toes of both feet when either the left or right foot has taken a step and the toes have touched the ground. Gait pitch is the number of steps taken in a given time and is used to calculate gait speed. Gait speed is the speed of movement in one gait cycle. Gait speed may also be an average value over multiple gait cycles. Ground contact angle is the angle of the sole of the foot relative to the ground (postural angle) when the heel is in contact with the ground. Ground contact angle is the angle of the sole of the foot relative to the ground (postural angle) when the toenails are in contact with the ground. Outward rotation distance is the distance between the straight line representing the movement path of one foot and the foot at the point when the foot is furthest from the movement path of that foot in one gait cycle. Toe direction is the angle formed by the straight line representing the movement path of one foot in one gait cycle and the center line of the foot when it is on the ground.

[0046] Examples of gait parameters include roll angle, foot lift height, maximum angular velocity in the plantarflexion direction, maximum angular velocity in the dorsiflexion direction, maximum velocity, maximum foot acceleration during the swing phase, and cadence. For example, the roll angle at heel strike and toe-off is used as a gait parameter. Foot lift height corresponds to the vertical height of the foot. For example, the maximum angular velocity in the plantarflexion direction and the maximum angular velocity in the dorsiflexion direction during the swing phase are used as gait parameters. For example, the maximum velocity during the swing phase is used as a gait parameter. Maximum foot acceleration during the swing phase is the maximum value of the vertical acceleration of the leg during the swing phase and is related to the rise of the hips in accordance with the coordination of foot and hip movements. Cadence corresponds to the number of steps in 60 seconds.

[0047] Examples of gait parameters include stance time, swing time, DST (Double Support Time), load-bearing time, sole contact time, and push-off time. Stance time is the duration of the stance phase. Swing time is the duration of the swing phase. DST is the duration of double support during walking. DST includes DST1, which is the double support period after heel strike, and DST2, which is the double support period immediately before push-off. Load-bearing time is the time when load is applied to the sole of the foot. Load-bearing time is the time from heel strike to sole contact. Sole contact time is the time when the main surface of the sole of the foot is in contact with the ground. Sole contact time is the time from sole contact to heel-off. Push-off time is the time from when load is applied to the main surface of the sole of the foot until the foot is pushed off. Push-off time is the time from sole contact to toe-off.

[0048] The transmitting unit 127 outputs feature data including cluster features generated by the generating unit 125. If gait parameters are used to estimate pelvic tilt, the transmitting unit 127 outputs feature data including cluster features and gait parameters. The transmitting unit 127 transmits the feature data to the pelvic tilt estimation device 13. For example, the transmitting unit 127 transmits the feature data to the pelvic tilt estimation device 13 via wireless communication. For example, the transmitting unit 127 is configured to transmit the feature data to the pelvic tilt estimation device 13 via a wireless communication function (not shown) conforming to standards such as Bluetooth® or WiFi®. The communication function of the transmitting unit 127 may conform to standards other than Bluetooth® or WiFi®.

[0049] [Pelvic tilt estimation device] Figure 10 is a block diagram showing an example of the configuration of the pelvic tilt estimation device 13. The pelvic tilt estimation device 13 includes a communication unit 131, a calculation unit 133, a storage unit 135, an estimation unit 137, and an output unit 139.

[0050] The communication unit 131 acquires feature data from the measuring device 10. The communication unit 131 outputs the received data to the calculation unit 133. The communication unit 131 may receive feature data from the measuring device 10 via a wired connection such as a cable, or it may receive feature data from the measuring device 10 via wireless communication. For example, the communication unit 131 is configured to receive feature data from the measuring device 10 via a wireless communication function (not shown) conforming to standards such as Bluetooth® or WiFi®. The communication function of the communication unit 131 may conform to standards other than Bluetooth® or WiFi®.

[0051] The calculation unit 133 acquires feature data. The calculation unit 133 uses the acquired feature data, including cluster features and gait parameters, to calculate the input data used for estimating pelvic tilt. The calculation unit 133 calculates the mean value for the first features for both feet used in estimating pelvic tilt. The calculation unit 133 calculates the absolute value of the difference for the first features for both feet used in estimating pelvic tilt. The calculation unit 133 also calculates the mean value for the gait parameters for both feet used in estimating pelvic tilt. The calculation unit 133 calculates the absolute value of the difference for the gait parameters for both feet used in estimating pelvic tilt. Hereafter, the absolute value of the difference will also be referred to as the difference. The mean value and difference for the first features / gait parameters for both feet calculated by the calculation unit 133 will also be referred to as the second features. The second features are used in estimating pelvic tilt. Instead of using the mean or difference of the first feature and gait parameters included in the feature data generated by the measurement device 10, the first feature and gait parameters themselves may be used to estimate pelvic tilt. In that case, the calculation unit 133 can be omitted.

[0052] The memory unit 135 stores estimation models for estimating pelvic tilt. The estimation model outputs estimation results regarding pelvic tilt in response to input data calculated by the calculation unit 133. The memory unit 135 stores estimation models learned for multiple subjects. If subject attributes are used in the estimation, the memory unit 135 stores the subject attributes. For example, subject attributes include the subject's gender, age, weight, height, etc. The pelvic tilt estimation device 13 estimates pelvic tilt along three axes: the direction of movement, the left-right axis, and the vertical axis. The subject attributes differ depending on the tilt axis of the pelvic tilt being estimated.

[0053] The estimation model is stored in the storage unit 135 at times such as when the product is shipped from the factory or during calibration before the user uses the estimation system. For example, the estimation system 1 may be configured to use an estimation model stored in a storage device such as an external server. In that case, the estimation system 1 should be configured so that the estimation model is used via an interface (not shown) connected to the storage device.

[0054] The estimation unit 137 obtains input data from the calculation unit 133 to be used for estimating pelvic tilt. If the feature data generated by the measurement device 10 is used as is, the estimation unit 137 obtains the feature data as input data. If the subject's attributes are used for estimation, the estimation unit 137 obtains the subject's attributes from the storage unit 135.

[0055] The estimation unit 137 estimates the pelvic tilt using the acquired input data. In this embodiment, an example is given in which the variation range of the pelvic tilt, which is the difference between the maximum and minimum values ​​of the pelvic tilt during one step cycle, is estimated. The estimation unit 137 inputs the input data to the estimation model stored in the storage unit 135. The estimation unit 137 outputs the estimated result of the pelvic tilt output from the estimation model. When using an estimation model stored in an external storage device built on a cloud or server, the estimation unit 137 is configured to use the estimation model via an interface (not shown) connected to that storage device.

[0056] Pelvic tilt is an index indicating the tilt of the pelvis. The estimation unit 137 estimates the pelvic tilt with respect to three axes around the left - right axis (roll), the forward - backward axis (pitch), and the vertical axis (yaw). The pelvic tilt with respect to the left - right axis corresponds to the pelvic tilt in the sagittal plane. The pelvic tilt with respect to the forward - backward axis corresponds to the pelvic tilt in the coronal plane. The pelvic tilt with respect to the vertical axis corresponds to the pelvic tilt in the horizontal plane. The pelvic tilt around the left - right axis (roll) corresponds to the inclination of the body in the front - back direction (in the sagittal plane) centered on the pelvic position. The pelvic tilt around the forward - backward axis (pitch) corresponds to the inclination of the body in the up - down direction (in the coronal plane) centered on the pelvic position. The pelvic tilt around the vertical axis (yaw) corresponds to the rotation of the body (in the horizontal plane) centered on the pelvic position. By using the pelvic tilt, it is possible to grasp the movement of the subject, which cannot be grasped only by the movement of the feet.

[0057] Regarding the pelvic tilt around the left - right axis (roll), either the forward flexion or the backward flexion in the sagittal plane is positive and the other is negative. FIG. 11 is a graph showing an example of time - series data of the pelvic tilt around the left - right axis (roll). In the graph of FIG. 11, the time - series data of the pelvic tilt around the left - right axis (roll) is associated with the walking cycle. In one walking cycle, the difference d r between the maximum value and the minimum value of the pelvic tilt around the axis (roll) corresponds to the fluctuation range of the pelvic tilt around the left - right axis (roll).

[0058] FIG. 12 is a graph showing another example of time - series data of the pelvic tilt around the left - right axis (roll). In the graph of FIG. 12, the time - series data of the pelvic tilt around the left - right axis (roll) is associated with the walking cycle. In the time - series data of the pelvic tilt around the left - right axis (roll), the fluctuation range (difference d r1 ) of the preceding amplitude and the fluctuation range (difference d r2 ) of the subsequent amplitude appear. In the example of FIG. 12, in one walking cycle, the fluctuation range (difference d r1 ) of the preceding amplitude and the fluctuation range (difference d r2 ) of the subsequent amplitude are estimated separately. For example, the fluctuation range (difference d r1 ) of the preceding amplitude and the fluctuation range (difference d r2These are estimated using different estimation models corresponding to each.

[0059] Regarding pelvic tilt around the axis of motion (pitch), either leftward or rightward tilt within the coronal plane is positive, and the other is negative. Figure 13 is a graph showing an example of time-series data for pelvic tilt around the axis of motion (pitch). In the graph of Figure 13, the time-series data for pelvic tilt around the axis of motion (pitch) is associated with the gait cycle. In one gait cycle, the difference d is between the maximum and minimum values ​​of pelvic tilt around the axis of motion (pitch). p However, this corresponds to the range of variation in pelvic tilt around the axis of motion (pitch).

[0060] Regarding pelvic tilt around the vertical axis, either clockwise or counterclockwise rotation around the lumbar region in the horizontal plane is positive, and the other is negative. Figure 14 is a graph showing an example of time-series data for pelvic tilt around the vertical axis. In the graph of Figure 14, the time-series data for pelvic tilt around the vertical axis is associated with the gait cycle. In one gait cycle, the difference d between the maximum and minimum values ​​of pelvic tilt around the vertical axis is shown. y However, this corresponds to the range of variation in pelvic tilt around the vertical axis.

[0061] The output unit 139 outputs the pelvic tilt estimation result from the estimation unit 137. For example, the output unit 139 displays the pelvic tilt estimation result on the screen of the subject's (user's) mobile device. For example, the output unit 139 outputs the estimation result to an external system that uses the estimation result. There are no particular limitations on the use of the pelvic tilt information output from the pelvic tilt estimation device 13.

[0062] For example, the pelvic tilt estimation device 13 is connected to an external system built on a cloud or server via a mobile terminal (not shown) carried by the subject (user). The mobile terminal (not shown) is a portable communication device. For example, the mobile terminal is a portable communication device with communication functions such as a smartphone, smartwatch, or mobile phone. For example, the pelvic tilt estimation device 13 is connected to the mobile terminal via a wired connection such as a cable. For example, the pelvic tilt estimation device 13 is connected to the mobile terminal via wireless communication. For example, the pelvic tilt estimation device 13 is connected to the mobile terminal via wireless communication function (not shown) conforming to standards such as Bluetooth® or WiFi®. Note that the communication function of the pelvic tilt estimation device 13 may conform to standards other than Bluetooth® or WiFi®. The pelvic tilt estimation result may be used by an application installed on the mobile terminal. In that case, the mobile terminal performs processing using the estimation result by application software installed on the mobile terminal.

[0063] [Learning Example] Next, we will explain an example of training the estimation model used to estimate pelvic tilt by the pelvic tilt estimation device 13, along with the verification results regarding the correlation between the difference in pelvic tilt and feature data. Below, we will give an example of verification conducted on 45 subjects. In the following verification example, the correlation between measured and estimated values ​​of pelvic tilt during walking was verified. In this verification example, subjects wearing smart apparel and shoes equipped with the measurement device 10 walked two round trips along a 5m straight path. The waist area of ​​the smart apparel is equipped with an IMU that measures spatial acceleration and spatial angular velocity. The measured values ​​were derived using the measured spatial acceleration and spatial angular velocity of the subject's waist. The predicted values ​​are estimated values ​​that were estimated using sensor data measured by the measurement device 10 mounted on the subject's shoes, simultaneously with the measurement of the measured values. The correlation between the measured and estimated values ​​is evaluated by the correlation coefficient.

[0064] Figure 15 is a conceptual diagram illustrating an example of training an estimation model used to estimate pelvic tilt. The estimation model is trained using explanatory and response variables for multiple subjects. Explanatory variables include subject attributes, cluster features generated according to the subject's gait, and gait parameters. The response variable is the measured pelvic tilt value, simultaneously measured at the time of sensor data collection for generating the cluster features and gait parameters. The measured pelvic tilt value includes the difference d around the left-right axis. r , difference d around the axis of progression p , difference d around the vertical axis y This includes, for example, the measured value of pelvic tilt is derived using measurements taken by an IMU attached to the subject's lumbar region. For example, the estimation model is a multiple regression model constructed using features selected using the Leave-one-subject-out LASSO method.

[0065] For example, the estimation model may be constructed by training using a linear regression algorithm. For example, the estimation model may be constructed by training using a support vector machine (SVM) algorithm. For example, the estimation model may be constructed by training using a Gaussian process regression (GPR) algorithm. For example, the estimation model may be constructed by training using a random forest (RF) algorithm. The estimation model may also be constructed by unsupervised learning that classifies the subjects who generated the feature data according to the feature data. There are no particular limitations on the algorithm used to train the estimation model.

[0066] The estimation model may be constructed by learning using gait waveform data (sensor data) for one step cycle as explanatory variables. For example, the estimation model can be constructed by supervised learning using gait waveform data of acceleration in three axes, angular velocity around three axes, and angles (postural angles) around three axes as explanatory variables, and the measured value of pelvic tilt, which is the target of estimation, as the dependent variable.

[0067] <Roll (left-right axis)> To estimate the difference in pelvic tilt around the left-right axis, the mean or difference of the first feature / gait parameter for both feet is used. Furthermore, weight is used as a user attribute to estimate the difference in pelvic tilt around the left-right axis. In this embodiment, an example is given in which the first feature is not used.

[0068] To estimate the difference in pelvic tilt around the left-right axis, the first feature / gait parameter for both feet is used. For example, the average values ​​of stride length, roll angle at toe-off, and maximum speed during the swing phase for both feet are used as the second feature. For example, the difference between both feet regarding maximum rotation, roll angle at heel strike, minimum swing phase value, and swing phase peak is used as the second feature. In this verification, the correlation coefficient between the measured values ​​and the estimated values ​​for estimating the difference in pelvic tilt around the left-right axis was 0.4580.

[0069] Regarding the estimation of the difference in pelvic tilt around the left-right axis, as shown in Figure 12, the difference in the preceding amplitude d in one step period r1 and the subsequent amplitude difference d r2 Here is an example where the two are estimated separately. In this case, the difference d of the preceding amplitude r1 Regarding this, the correlation coefficient between the measured value and the estimated value was 0.4945. The subsequent amplitude difference d r2 Regarding this, the correlation coefficient between the measured value and the estimated value was 0.6842. Thus, for estimating the difference in pelvic tilt around the left-right axis, the difference in preceding amplitude d r1 And the difference d that appears in the second half r2 The correlation coefficient was higher when the two factors were estimated separately.

[0070] <Around the axis of progression (pitch)> To estimate the difference in pelvic tilt around the axis of movement, the mean or difference of the first feature / gait parameter for both feet is used. Additionally, user attributes such as age and weight are used to estimate the difference in pelvic tilt around the axis of movement.

[0071] Figure 16 is a table summarizing an example of a second feature for both feet used to estimate the difference in pelvic tilt around the axis of motion. For the estimation of the difference in pelvic tilt around the axis of motion, the acceleration A in the direction of motion is used. y , angle E about the axis of motion y , and angle E about the vertical axis z The average value of both feet for this is used as the second feature. Directional acceleration A y Regarding this, the second feature F of the 70% walking phase interval y1 However, this is used for estimation. The angle (pitch angle) E is the angle around the axis of motion. y Regarding this, the second feature F for the 69-74% walking phase is y2 However, it is used for estimation. The angle around the vertical axis (yaw angle) E z Regarding this, the second feature F for the 17-20% walking phase y3 However, this is used for estimation. Furthermore, regarding the estimation of the difference in pelvic tilt around the axis of motion, the angle (pitch angle) E around the axis of motion is used. y The difference between the two feet regarding this is used as the second feature. The angle (pitch angle) E around the axis of motion. y Regarding this, the second feature F for the 17-19% walking phase y4 And the first feature F for the 27-28% walking phase. y5 However, it is used for estimation.

[0072] Multiple gait parameters are used to estimate the difference in pelvic tilt around the axis of movement. For example, the average values ​​of both feet for maximum plantarflexion angle, maximum circumduction, adduction / abduction angle, heel-strike roll angle, load-bearing time, and plantar contact time, as well as DST2, are used as secondary features. For example, the differences between both feet for walking speed, maximum dorsiflexion angle, adduction / abduction angle, cadence, swing phase time, plantar contact time, DST1, and minimum swing phase time are used as secondary features. In this study, the correlation coefficient between measured and estimated values ​​for estimating the difference in pelvic tilt around the axis of movement was 0.7468.

[0073] <Around the vertical axis (yaw)> To estimate the difference in pelvic tilt around the vertical axis, the mean or difference of gait parameters for both feet is used. Additionally, user weight is used as a user attribute to estimate the difference in pelvic tilt around the vertical axis.

[0074] Figure 17 is a table summarizing an example of the mean or difference of the first feature for both feet used to estimate the difference in pelvic tilt around the vertical axis. For the estimation of the difference in pelvic tilt around the vertical axis, the lateral acceleration A x and angular velocity G around the left and right axes x The average value for both feet regarding lateral acceleration A is used as the second feature. x Regarding this, the first feature F for the 67-78% walking phase z1 However, this is used for estimation. Angular velocity G about the left-right axis. x Regarding this, the first feature F for the 27-28% walking phase z2 However, it is used for estimation.

[0075] Multiple gait parameters are used to estimate the difference in pelvic tilt around the vertical axis. For example, the average values ​​of stride length and push-off time for both feet are used as secondary features. For example, the differences between both feet in maximum plantarflexion angle, adduction / abduction angle, stance time, swing peak, and maximum swing speed are also used as secondary features. In this study, the correlation coefficient between measured and estimated values ​​for the estimation of the difference in pelvic tilt around the vertical axis was 0.5630.

[0076] (operation) Next, the operation of the estimation system 1 will be explained with reference to the diagrams. Here, the measurement device 10 and the pelvic tilt estimation device 13 included in the estimation system 1 will be explained individually. Regarding the measurement device 10, the operation of the feature data generation unit 12 included in the measurement device 10 will be explained.

[0077] [Measuring device] Figure 18 is a flowchart illustrating the operation of the feature data generation unit 12 included in the measurement device 10. In the explanation following the flowchart in Figure 18, the feature data generation unit 12 will be described as the main operator.

[0078] In Figure 18, first, the feature data generation unit 12 acquires time-series data of sensor data relating to the movement of both feet (step S101).

[0079] Next, the feature data generation unit 12 extracts walking waveform data for one step cycle from the time-series data of the sensor data (step S102). The feature data generation unit 12 detects heel strike and toe-off from the time-series data of the sensor data. The feature data generation unit 12 extracts the time-series data of the interval between consecutive heel strikes as walking waveform data for one step cycle.

[0080] Next, the feature data generation unit 12 normalizes the extracted walking waveform data for one walking cycle (step S103). The feature data generation unit 12 normalizes the walking waveform data for one walking cycle to a walking cycle of 0 to 100% (first normalization). Furthermore, the feature data generation unit 12 normalizes the ratio of the stance phase to the swing phase of the walking waveform data for one walking cycle that has been first normalized to 60:40 (second normalization).

[0081] Next, the feature data generation unit 12 extracts features from the gait phase used to estimate pelvic tilt with respect to the normalized gait waveform (step S104). The feature data generation unit 12 extracts features used to estimate pelvic tilt.

[0082] Next, the feature data generation unit 12 generates cluster features (first features) for each gait phase cluster using the extracted features (step S105). If gait parameters are used to estimate pelvic tilt, the feature data generation unit 12 generates gait parameters.

[0083] Next, the feature data generation unit 12 integrates the cluster features for each walking phase cluster to generate feature data for one step cycle (step S106).

[0084] Next, the feature data generation unit 12 outputs the generated feature data to the pelvic tilt estimation device 13 (step S107).

[0085] [Pelvic tilt estimation device] Figure 19 is a flowchart illustrating the operation of the pelvic tilt estimation device 13. In the explanation following the flowchart in Figure 19, the pelvic tilt estimation device 13 will be described as the primary operator.

[0086] In Figure 19, first, the pelvic tilt estimation device 13 acquires feature data used to estimate pelvic tilt from the measurement device 10 (step S131).

[0087] Next, the pelvic tilt estimation device 13 calculates the absolute value of the difference between the mean value and the first feature included in the acquired feature data as the second feature (step S132).

[0088] Next, the pelvic tilt estimation device 13 inputs the input data, including the calculated second feature, into an estimation model for estimating pelvic tilt (step S133).

[0089] Next, the pelvic tilt estimation device 13 estimates the user's pelvic tilt according to the output (estimated value) from the estimation model (step S134). For example, the pelvic tilt estimation device 13 estimates the difference in the user's pelvic tilt as the user's pelvic tilt.

[0090] Next, the pelvic tilt estimation device 13 outputs information corresponding to the estimated pelvic tilt (step S135). For example, the pelvic tilt is output to a terminal device (not shown) carried by the user. For example, the information corresponding to the pelvic tilt is output to a system that performs processing using that information.

[0091] (Examples of application) Next, an example of application according to this embodiment will be described with reference to the drawings. In the following example, an example is shown in which the function of a pelvic tilt estimation device 13 installed on a mobile terminal carried by the user estimates information about pelvic tilt using feature data measured by a measuring device 10 placed in the shoe.

[0092] Figures 21 and 22 are conceptual diagrams showing an example of displaying the estimation results from the pelvic tilt estimation device 13 on the screen of a mobile terminal 160 carried by a user walking while wearing shoes 100 equipped with a measuring device 10. In the example shown in Figures 21 and 22, information corresponding to the estimation results of pelvic tilt using feature data corresponding to sensor data measured during the user's walking is displayed on the screen of the mobile terminal 160.

[0093] In the example shown in Figure 21, the estimated pelvic tilt results for three axes—the axis of movement, the left-right axis, and the vertical axis—are displayed on the display of the mobile device 160. Furthermore, in the example shown in Figure 21, recommendation information corresponding to the estimated pelvic tilt, such as "You should strengthen your core," is displayed on the display of the mobile device 160. Also, in the example shown in Figure 21, recommendation information corresponding to the estimated pelvic tilt, such as "Training A is recommended. Please watch the video below," is displayed on the display of the mobile device 160. After reviewing the information displayed on the mobile device 160, the user can then refer to the video for Training A and perform the exercises to strengthen their core.

[0094] In the example shown in Figure 22, the estimated pelvic tilt results for three axes—the axis of movement, the left-right axis, and the vertical axis—are displayed on the mobile device 160. Also in the example shown in Figure 22, recommendation information such as "We recommend you see a doctor" is displayed on the mobile device 160, depending on the estimated pelvic tilt. For example, a link to a hospital's website or phone number could be displayed on the mobile device 160's screen. After reviewing the information displayed on the mobile device 160, the user can then go to a hospital as recommended and receive appropriate medical attention for knee-related conditions.

[0095] As described above, the estimation system of this embodiment comprises a measuring device and a pelvic tilt estimation device. The measuring device is installed on the footwear of the subject, which is the target of estimation for pelvic tilt, an indicator related to hip movement. The measuring device has a sensor and a feature data generation unit. The sensor measures spatial acceleration and spatial angular velocity. The sensor generates sensor data related to foot movement using the measured spatial acceleration and spatial angular velocity. The sensor outputs the generated sensor data. The feature data generation unit acquires time-series data of the sensor data, including gait characteristics. The feature data generation unit extracts walking waveform data for one step cycle from the time-series data of the sensor data. The feature data generation unit normalizes the extracted walking waveform data. From the normalized walking waveform data, the feature data generation unit extracts features used for estimating pelvic tilt from a walking phase cluster consisting of at least one temporally continuous walking phase. The feature data generation unit generates feature data including the extracted features. The feature data generation unit outputs the generated feature data to the pelvic tilt estimation device.

[0096] The pelvic tilt estimation device 23 includes a communication unit 231, a storage unit 235, an estimation unit 237, and an output unit 239.

[0097] The communication unit acquires feature data, which includes features used to estimate pelvic tilt, an indicator of hip movement, extracted from the gait waveform of spatial acceleration and spatial angular velocity contained in sensor data related to the subject's foot movements. The storage unit stores an estimation model that outputs an estimated value for pelvic tilt in response to the input of features contained in the feature data. The estimation unit inputs the features contained in the acquired feature data into the estimation model and estimates the subject's pelvic tilt according to the estimated value for pelvic tilt output from the estimation model. The output unit outputs information corresponding to the subject's pelvic tilt.

[0098] In this embodiment, pelvic tilt, an indicator of the subject's hip movement, is estimated using feature quantities extracted from sensor data related to the subject's leg movements. Therefore, according to this embodiment, pelvic tilt, an indicator of hip movement, can be estimated with high accuracy and ease in daily life.

[0099] In one embodiment of this system, the communication unit acquires feature data including gait parameters extracted from walking waveforms of spatial acceleration and spatial angular velocity contained in sensor data. The storage unit stores an estimation model that outputs estimated values ​​regarding pelvic tilt in response to input of gait parameters included in the feature data. The estimation unit inputs the gait parameters included in the acquired feature data into the estimation model and estimates the subject's pelvic tilt according to the estimated values ​​regarding pelvic tilt output from the estimation model. According to this embodiment, lumbar sway can be estimated with high accuracy by using feature data including gait parameters.

[0100] In one embodiment of this system, the communication unit acquires feature data including a first feature for each walking phase cluster extracted from the walking waveform of spatial acceleration and spatial angular velocity included in the sensor data. The storage unit stores an estimation model that outputs an estimated value regarding pelvic tilt in response to the input of the first feature included in the feature data. The estimation unit inputs the first feature included in the acquired feature data into the estimation model and estimates the subject's pelvic tilt according to the estimated value regarding pelvic tilt output from the estimation model. According to this embodiment, lumbar sway can be estimated with higher accuracy by using feature data that includes a first feature for each walking phase cluster.

[0101] A lumbar sway estimation device according to one embodiment of this model includes a calculation unit. The calculation unit calculates the mean and difference of the first feature quantities and gait parameters used for estimating pelvic tilt from among the first feature quantities and gait parameters for both feet of the subject as second feature quantities. The storage unit stores an estimation model that outputs an estimated value for pelvic tilt in response to the input of the second feature quantities. The estimation unit inputs the calculated second feature quantities into the estimation model and estimates the subject's pelvic tilt according to the estimated value for pelvic tilt output from the estimation model. According to this embodiment, lumbar sway can be estimated with higher accuracy by using the mean / difference of the feature quantities for both feet.

[0102] In one embodiment of this system, the memory unit stores an estimation model that outputs an estimated value regarding pelvic tilt in response to the input of the subject's attributes and a second feature. The estimation unit inputs the subject's attributes and the second feature into the estimation model and estimates the subject's pelvic tilt according to the estimated value regarding pelvic tilt output from the estimation model. According to this embodiment, lumbar sway can be estimated with higher accuracy by using the subject's attributes.

[0103] In one embodiment of this system, the memory unit stores an estimation model that outputs an estimated value regarding pelvic tilt in response to the input of features contained in the feature data. The estimation model outputs the range of variation of at least one pelvic tilt with respect to three axes: the forward axis, the left-right axis, and the vertical axis, as an estimated value regarding pelvic tilt. The estimation unit inputs the features contained in the acquired feature data into the estimation model and estimates the subject's pelvic tilt according to the range of variation of at least one pelvic tilt with respect to three axes: the forward axis, the left-right axis, and the vertical axis, output from the estimation model. According to this embodiment, lumbar sway can be estimated with higher accuracy according to the range of variation of lumbar sway with respect to three axes: the forward axis, the left-right axis, and the vertical axis.

[0104] In one embodiment of this design, the pelvic tilt estimation device is implemented in a terminal device having a screen visible to the subject. The pelvic tilt estimation device displays information about the estimated pelvic tilt, based on the subject's leg movements, on the screen of the terminal device. According to this design, information about the estimated pelvic tilt for a subject can be accurately presented to that subject.

[0105] Pelvic tilt, centered on the lumbar region, serves as an indicator of physical condition and health. For example, the degree of recovery after surgery for a herniated disc can be determined based on the angle of pelvic tilt. For instance, the sagittal / coronal plane angle can be used to evaluate the degree of curvature of the lumbar spine. The angle within the sagittal plane corresponds to the tilt angle around the left-right axis. The angle within the coronal plane corresponds to the tilt angle around the axis of movement. A sagittal / coronal plane angle of 5 degrees or less during walking is considered normal. An angle of 5 to 15 degrees during walking is a level that requires attention. An angle of 15 degrees or more during walking indicates a level where assistance from someone is needed. For example, the sagittal / coronal plane angle can be used to evaluate posture during walking. By setting a posture score according to the sagittal / coronal plane angle, posture can be evaluated according to the score. For example, pelvic tilt around the left-right axis, which corresponds to the angle within the coronal plane, is a check item for pelvic osteoarthritis and lateral tilt (upward / downward). Pelvic tilt around the left-right axis is related to left-right balance during walking. Therefore, pelvic tilt around the left-right axis is an indicator of walking stability.

[0106] For example, if you cannot walk with a flexible gait due to knee osteoarthritis, the pattern of body sinking immediately after the foot lands becomes awkward, affecting the vertical pelvic tilt. Therefore, vertical pelvic tilt can be an indicator of the state and progression of knee osteoarthritis. For example, in the case of hemiplegia, the body sinks abruptly when landing on the leg on the weaker side of the body, affecting the vertical pelvic tilt. Therefore, vertical pelvic tilt can be an indicator of the state and progression of hemiplegia. For example, symptoms such as lumbar spinal stenosis, neurogenic intermittent claudication, and degenerative lumbar spondylolisthesis are also related to pelvic tilt.

[0107] (Second embodiment) Next, a pelvic tilt estimation device according to the second embodiment will be described with reference to the drawings. The pelvic tilt estimation device of this embodiment has a simplified configuration compared to the pelvic tilt estimation device of the first embodiment.

[0108] Figure 22 is a block diagram showing an example of the configuration of the pelvic tilt estimation device 23 according to this embodiment. The pelvic tilt estimation device 23 comprises a communication unit 231, a storage unit 235, an estimation unit 237, and an output unit 239.

[0109] The communication unit 231 acquires feature data, which includes features used to estimate pelvic tilt, an index of hip movement, extracted from the walking waveform of spatial acceleration and spatial angular velocity contained in sensor data related to the movement of the subject's feet. The storage unit 235 stores an estimation model that outputs an estimated value regarding pelvic tilt in response to the input of features contained in the feature data. The estimation unit 237 inputs the features contained in the acquired feature data into the estimation model and estimates the subject's pelvic tilt according to the estimated value regarding pelvic tilt output from the estimation model. The output unit 239 outputs information corresponding to the subject's pelvic tilt.

[0110] In this embodiment, pelvic tilt, an indicator of the subject's hip movement, is estimated using feature quantities extracted from sensor data related to the subject's leg movements. Therefore, according to this embodiment, pelvic tilt, an indicator of hip movement, can be estimated with high accuracy and ease in daily life.

[0111] (Hardware) Here, the hardware configuration for executing the processing according to each embodiment of this disclosure will be explained using the information processing device 90 (computer) shown in Figure 23 as an example. Note that the information processing device 90 in Figure 23 is an example configuration for executing the processing according to each embodiment and does not limit the scope of this disclosure.

[0112] As shown in Figure 23, the information processing device 90 comprises a processor 91, main memory 92, auxiliary storage 93, input / output interface 95, and communication interface 96. In Figure 23, interface is abbreviated as I / F (Interface). The processor 91, main memory 92, auxiliary storage 93, input / output interface 95, and communication interface 96 are connected to each other via a bus 98, enabling data communication. Furthermore, the processor 91, main memory 92, auxiliary storage 93, and input / output interface 95 are connected to a network such as the Internet or an intranet via the communication interface 96.

[0113] The processor 91 loads programs (instructions) stored in the auxiliary storage device 93, etc., into the main memory 92. For example, the program is a software program for executing the processing of each embodiment. The processor 91 executes the program loaded into the main memory 92. By executing the program, the processor 91 executes the processing of each embodiment.

[0114] The main memory 92 has an area where the program is loaded. The processor 91 loads the program stored in the auxiliary memory 93, etc., into the main memory 92. The main memory 92 is implemented by volatile memory such as DRAM (Dynamic Random Access Memory). Alternatively, non-volatile memory such as MRAM (Magneto Resistive Random Access Memory) may be configured / added as the main memory 92.

[0115] The auxiliary storage device 93 stores various data, such as programs. The auxiliary storage device 93 is implemented by a local disk such as a hard disk or flash memory. It is also possible to omit the auxiliary storage device 93 by configuring the system to store various data in the main memory 92.

[0116] 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 shared as interfaces for connecting to external devices.

[0117] The information processing device 90 may be connected to input devices such as a keyboard, mouse, or touch panel, as needed. These input devices are used to input information and settings. When a touch panel is used as an input device, the screen with touch panel functionality serves as the interface. The processor 91 and the input devices are connected via an input / output interface 95.

[0118] The information processing device 90 may be equipped with a display device for displaying information. If a display device is provided, 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.

[0119] The information processing device 90 may be equipped with a drive device. The drive device mediates between the processor 91 and the recording medium (program recording medium) by reading data and programs stored on the recording medium and writing the processing results of the information processing device 90 to the recording medium. The information processing device 90 and the drive device are connected via an input / output interface 95.

[0120] The above is an example of a hardware configuration for enabling the processing according to each embodiment of the present invention. The hardware configuration in Figure 23 is an example of a hardware configuration for executing the processing according to each embodiment and does not limit the scope of the present invention. A program that causes a computer to execute the processing according to each embodiment is also included in the scope of the present invention.

[0121] A program recording medium that stores the program according to each embodiment is also included in the scope of the present invention. The recording medium can be implemented as an optical recording medium such as a CD (Compact Disc) or DVD (Digital Versatile Disc). The recording medium may also be implemented as a semiconductor recording medium such as a USB (Universal Serial Bus) memory or an SD (Secure Digital) card. Furthermore, the recording medium may be implemented as a magnetic recording medium such as a flexible disk, or other recording media. When a program executed by a processor is recorded on a recording medium, that recording medium corresponds to a program recording medium.

[0122] The components of each embodiment may be combined in any way. The components of each embodiment may be implemented by software. The components of each embodiment may be implemented by circuitry.

[0123] Although the present invention has been described above with reference to embodiments, the present invention is not limited to the above embodiments. Various modifications to the configuration and details of the present invention can be made that will be understood by those skilled in the art within the scope of the present invention. [Explanation of Symbols]

[0124] 1 Estimation System 10 Measuring devices 13. Pelvic tilt estimation device 111 Accelerometer 112 Angular velocity sensor 121 Acquisition Department 122 Normalization section 123 Extraction part 125 Generation part 127 Transmitter 131, 231 Communications Department 133 Calculation Department 135, 235 Storage section 137, 237 Estimation part 139, 239 Output section

Claims

1. A measuring device installed on the footwear of a subject, which is the target of estimation of pelvic tilt, an indicator related to hip movement, A pelvic tilt estimation device comprising: communication means for acquiring feature data, which includes feature quantities used to estimate pelvic tilt, an index of hip movement, extracted from walking waveforms of spatial acceleration and spatial angular velocity contained in sensor data relating to the movement of the subject's feet; storage means for storing an estimation model that outputs an estimated value relating to pelvic tilt in response to input of feature quantities contained in the feature data; estimation means for inputting the acquired feature quantities contained in the feature data into the estimation model and estimating the subject's pelvic tilt according to the estimated value relating to pelvic tilt output from the estimation model; and output means for outputting information corresponding to the subject's pelvic tilt. The aforementioned measuring device is A sensor that measures the spatial acceleration and spatial angular velocity, generates sensor data relating to foot movement using the measured spatial acceleration and spatial angular velocity, and outputs the generated sensor data, An estimation system comprising: a feature data generation means that acquires time-series data of sensor data including gait characteristics; extracts walking waveform data for one walking cycle from the time-series data of sensor data; normalizes the extracted walking waveform data; extracts feature quantities used for estimating pelvic tilt from the normalized walking waveform data from a walking phase cluster consisting of at least one temporally consecutive walking phase; generates feature data including the extracted feature quantities; and outputs the generated feature data to the pelvic tilt estimation device.

2. The pelvic tilt estimation device is It is implemented in a terminal device having a screen visible to the aforementioned subject, The estimation system according to claim 1, wherein information regarding the pelvic tilt estimated in accordance with the foot movements of the subject is displayed on the screen of the terminal device.

3. The aforementioned communication means is The feature data, which includes gait parameters extracted from the walking waveforms of the spatial acceleration and spatial angular velocity contained in the sensor data, is acquired. The aforementioned storage means is The estimation model stores an estimated value relating to pelvic tilt in response to the input of the gait parameters included in the feature data, The estimation means is, The estimation system according to claim 1, which inputs the gait parameters included in the acquired feature data into the estimation model and estimates the pelvic tilt of the subject according to the estimated value of the pelvic tilt output from the estimation model.

4. The aforementioned communication means is The feature data is obtained, which includes a first feature for each walking phase cluster extracted from the walking waveform of the spatial acceleration and spatial angular velocity included in the sensor data. The aforementioned storage means is The estimation model stores an estimated value relating to pelvic tilt in response to the input of the first feature included in the feature data, The estimation means is, The estimation system according to claim 3, wherein the first feature included in the acquired feature data is input to the estimation model, and the pelvic tilt of the subject is estimated according to the estimated value of the pelvic tilt output from the estimation model.

5. The system includes a calculation means for calculating the mean and difference of the first feature quantities and gait parameters used for estimating pelvic tilt, among the first feature quantities and gait parameters for both feet of the subject, as second feature quantities. The aforementioned storage means is The estimation model, which outputs an estimated value regarding the pelvic tilt in response to the input of the second feature, is stored. The estimation means is, The estimation system according to claim 4, wherein the calculated second feature quantity is input to the estimation model, and the pelvic tilt of the subject is estimated according to the estimated value of the pelvic tilt output from the estimation model.

6. The aforementioned storage means is The estimation model, which outputs an estimated value regarding the pelvic tilt in response to the input of the subject's attributes and the second feature quantity, is stored. The estimation means is, The estimation system according to claim 5, wherein the attributes of the subject and the second feature quantity are input to the estimation model, and the pelvic tilt of the subject is estimated according to the estimated value of the pelvic tilt output from the estimation model.

7. The aforementioned storage means is The estimation model stores, which, in response to the input of features included in the feature data, outputs the range of variation of at least one of the three axes—the forward axis, the left-right axis, and the vertical axis—of the pelvic tilt during a single step cycle as an estimated value for the pelvic tilt. The estimation means is, The estimation system according to claim 1, wherein the features contained in the acquired feature data are input to the estimation model, and the pelvic tilt of the subject is estimated according to the range of variation of at least one of the three axes, the forward axis, the left-right axis, and the vertical axis, output from the estimation model.

Images