Walking posture state estimation system, walking posture state estimation method, walking posture state estimation apparatus, and control program

Abstract

To provide a walking posture state estimation system capable of more accurately estimating a walking posture state, a walking posture state estimation method, a walking posture state estimation apparatus, and a control program.SOLUTION: A walking posture estimation system comprises: a first wearable device which is wearable on a user and acquires first data acquirable when the user walks; a second wearable device which is wearable on the user and acquires second data different from the first data acquirable when the user walks; an information processing device which receives the first data and the second data and can output an estimated walking posture state of the user wearing the first wearable device and the second wearable device. The information processing device includes a storage part which stores a learned model capable of outputting the walking posture state estimated based on the first data and the second data.SELECTED DRAWING: Figure 6

Description

Technical Field

[0001] The present disclosure relates to a walking posture state estimation system, a walking posture state estimation method, a walking posture state estimation device, and a control program.

Background Art

[0002] Conventionally, systems have been developed that analyze a user's walking style, postural habits, etc. and propose improvement methods. In such systems, in order to propose appropriate improvement methods, it is necessary to estimate the user's walking style, postural habits, etc. more accurately.

[0003] Patent Document 1 discloses a motion posture derivation device that is worn on a user's body and derives a walking or running posture.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] There is a demand for providing a system capable of more accurately estimating a walking posture state.

[0006] The purpose of the walking posture state estimation system, the walking posture state estimation method, the walking posture state estimation device, and the control program is to enable more accurate estimation of the walking posture state.

Means for Solving the Problems

[0007] The walking posture estimation system according to the embodiment includes a first wearable device that can be worn by a user and acquires first data obtained when the user walks, a second wearable device that can be worn by the user and acquires second data different from the first data obtained when the user walks, and an information processing device that receives the first data and the second data and can output an estimated walking posture state of the user wearing the first wearable device and the second wearable device. The information processing device has a storage unit that stores a learned model capable of outputting a walking posture state estimated based on the first data and the second data.

[0008] In the walking posture estimation system according to the embodiment, it is preferable that the first wearable device has a receiving unit that receives the second data from the second wearable device and a transmitting unit that transmits the first data and the second data for a predetermined number of steps of the user to the information processing device.

[0009] In the walking posture estimation system according to the embodiment, the walking posture state preferably includes any one or more of a state of step width, a state of center of gravity position, a state of swinging leg, a state of supporting leg, and a state of hip joint.

[0010] In the walking posture estimation system according to the embodiment, the learned model preferably includes a first learned model capable of outputting a first walking posture state estimated based on the first data and a second learned model capable of outputting a second walking posture state estimated based on the second data.

[0011] In the walking posture estimation system according to the embodiment, the learned model is preferably a single learned model capable of outputting a walking posture state estimated based on the first data and the second data.

[0012] In the walking posture estimation system according to the embodiment, the learned model preferably includes a first learned model capable of outputting a first walking posture state estimated based on first image data based on first data, and a second learned model capable of outputting a second walking posture state estimated based on second image data based on second data.

[0013] In the walking posture estimation system according to the embodiment, the learned model is preferably a single learned model capable of outputting a walking posture state estimated based on image data based on first data and second data.

[0014] In the walking posture estimation system according to the embodiment, it is preferable that the information processing apparatus inputs data based on first data to a first layer of a first learned model included in the learned model, and inputs data based on second data to a second layer different from the first layer of the second learned model included in the learned model, thereby obtaining a walking posture state.

[0015] In the walking posture estimation system according to the embodiment, the walking posture state preferably includes information output from a first layer of the learned model when data based on first data is input to the learned model, and information output from a second layer different from the first layer of the learned model when data based on second data is input to the learned model.

[0016] The walking posture estimation method according to the embodiment acquires first data obtained when a user walks by a first wearable device wearable by the user, acquires second data different from the first data obtained when the user walks by a second wearable device wearable by the user, and uses a learned model capable of outputting a walking posture state estimated based on the first data and the second data to estimate the walking posture state of the user wearing the first wearable device and the second wearable device based on the acquired first data and second data, and outputs the walking posture state.

[0017] The walking posture estimation device according to the embodiment includes an acquisition unit that acquires first data and second data from a first sensor that measures first data obtained when the user walks and a second sensor that measures second data different from the first data obtained when the user walks, and an estimation unit that uses a learned model capable of outputting a walking posture state estimated based on the first data and the second data to acquire the walking posture state estimated based on the acquired first data and second data.

[0018] The walking posture estimation method according to the embodiment acquires first data and second data from a first sensor that acquires first data obtained when the user walks and a second sensor that acquires second data different from the first data obtained when the user walks, and uses a learned model capable of outputting a walking posture state estimated based on the first data and the second data to acquire the walking posture state estimated based on the acquired first data and second data.

[0019] The control program according to the embodiment is a control program for a walking posture estimation device, and causes the walking posture estimation device to acquire first data and second data from a first sensor that acquires first data obtained when the user walks and a second sensor that acquires second data different from the first data obtained when the user walks, and use a learned model capable of outputting a walking posture state estimated based on the first data and the second data to acquire the walking posture state estimated based on the acquired first data and second data.

[0020] The walking posture estimation device according to the embodiment includes an acquisition unit that acquires second data from a first sensor that measures first data obtained when the user walks and a second sensor that measures second data different from the first data obtained when the user walks, a storage unit that stores a learned model capable of outputting a walking posture state estimated based on the first data and the second data, and an estimation unit that uses the learned model to acquire the walking posture state estimated based on the acquired first data and second data.

[0021] The walking posture estimation method according to the embodiment is a walking posture state estimation method by a walking posture state estimation device having a first sensor that acquires first data obtained when a first user walks, wherein the second data is acquired from a second sensor that acquires second data different from the first data obtained when the user walks, a learned model capable of outputting a walking posture state estimated based on the first data and the second data is stored, and the learned model is used to acquire a walking posture state estimated based on the acquired first data and second data.

[0022] The control program according to the embodiment is a control program for a walking posture state estimation device having a first sensor that acquires first data obtained when a first user walks, wherein the second data is acquired from a second sensor that acquires second data different from the first data obtained when the user walks, a learned model capable of outputting a walking posture state estimated based on the first data and the second data is stored, and the learned model is used to cause the walking posture state estimation device to acquire a walking posture state estimated based on the acquired first data and second data.

Advantages of the Invention

[0023] The walking posture state estimation system, the walking posture state estimation method, the walking posture state estimation device, and the control program can estimate the walking posture state with higher accuracy.

Brief Description of the Drawings

[0024]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Mode for Carrying Out the Invention

[0025] Hereinafter, a walking posture state estimation system, a walking posture state estimation method, a walking posture state estimation device, and a control program according to one aspect of the embodiment will be described with reference to the drawings. However, note that the technical scope of the present invention is not limited to those embodiments, and extends to the invention described in the claims and its equivalents.

[0026] FIG. 1 is a diagram showing a schematic configuration of a walking posture state estimation system 1 according to the embodiment.

[0027] As shown in FIG. 1, the walking posture state estimation system 1 includes a first wearable device 100, one or more second wearable devices 200, an information processing device 300, a server device 400, and the like. The first wearable device 100 and each second wearable device 200 are worn and used by the user. The information processing device 300 is used by an administrator or the like who manages the health of the user. The server device 400 is, for example, a server arranged on a cloud network.

[0028] The first wearable device 100 and each second wearable device 200 are communicably connected to each other via a wireless network such as Bluetooth (registered trademark) or wireless LAN (Local Area Network). Also, the first wearable device 100, the information processing device 300, and the server device 400 are communicably connected to each other via the network N. The network N is a wired network such as the Internet or an intranet. The network N may also be a wireless network such as wireless LAN (Local Area Network). Further, each second wearable device 200, the information processing device 300, and the server device 400 may be communicably connected to each other via the network N.

[0029] FIG. 2 is a diagram showing a schematic configuration of the first wearable device 100.

[0030] The first wearable device 100 is an example of a walking state estimation device. The first wearable device 100 is a terminal device that can be worn by a user, such as a multifunctional mobile phone (so-called smartphone) or a tablet PC. The first wearable device 100 includes a first input device 101, a first display device 102, a first communication device 103, a first interface device 104, a first sensor 105, a first storage device 110, a first processing device 120, and the like. The first input device 101, the first display device 102, the first communication device 103, the first interface device 104, the first sensor 105, the first storage device 110, and the first processing device 120 are connected to each other via a CPU (Central Processing Unit) bus or the like.

[0031] The first input device 101 includes an input device such as a touch panel type and an interface circuit that acquires a signal from the input device, and outputs an operation signal corresponding to a user's input operation.

[0032] The first display device 102 is an example of an output unit. The first display device 102 includes a display such as a liquid crystal or an organic EL (Electro-Luminescence), and an interface circuit that outputs image data to the display, and displays the image data on the display.

[0033] The first communication device 103 is an example of an output unit. The first communication device 103 includes an antenna that transmits and receives radio signals, and a wireless communication interface circuit that conforms to a communication protocol such as a wireless LAN. The first communication device 103 communicates and connects to the network N in accordance with a communication standard such as a wireless LAN. The first communication device 103 sends the data received from the information processing device 300 or the server device 400 or the like to the first processing device 120 via the network N. Also, the first communication device 103 transmits the data received from the first processing device 120 to the information processing device 300 or the server device 400 or the like via the network N.

[0034] The first interface device 104 includes an antenna that transmits and receives radio signals, and a wireless communication interface circuit that conforms to a communication protocol such as Bluetooth (registered trademark). The first interface device 104 communicates and connects to each second wearable device 200 in accordance with a communication standard such as Bluetooth (registered trademark). The first interface device 104 sends the data received from each second wearable device 200 to the first processing device 120. Also, the first interface device 104 transmits the data received from the first processing device 120 to each second wearable device 200.

[0035] The first sensor 105 includes an acceleration sensor that measures the acceleration in the three-axis directions applied to the first wearable device 100, a gyro sensor that measures the angular velocity in the three-axis directions applied to the first wearable device 100, and the like. The acceleration sensor and the gyro sensor output a measurement signal indicating the measured acceleration and angular velocity to the first processing device 120.

[0036] Note that the first sensor 105 may include a geomagnetic sensor that detects the geomagnetism related to the first wearable device 100, that is, the movement of the user wearing the first wearable device 100. Further, the first sensor 105 may include a barometric pressure sensor that detects the barometric pressure around the first wearable device 100, that is, the movement of the user wearing the first wearable device 100 in the vertical direction. Further, the first sensor 105 may include a GPS (Global Positioning System) sensor that detects the position of the first wearable device 100, that is, the movement of the user wearing the first wearable device 100. In that case, the first sensor 105 outputs a measurement signal indicating the detected geomagnetism, barometric pressure, or position to the first processing device 120.

[0037] The first storage device 110 is an example of a storage unit. The first storage device 110 has a memory device such as a RAM (Random Access Memory) or a ROM (Read Only Memory), a fixed disk device such as a hard disk, or a portable storage device such as a flexible disk or an optical disk. Further, various computer programs, databases, tables, etc. used for various processes of the first wearable device 100 are stored in the first storage device 110. The computer program may be installed in the first storage device 110 using a known setup program or the like from a computer-readable portable recording medium. The portable recording medium is, for example, a CD-ROM (compact disc read only memory), a DVD-ROM (digital versatile disc read only memory), or the like. The computer program may be stored in a recording medium of a predetermined server and installed via the network N.

[0038] The first processing device 120 operates based on a program stored in advance in the first storage device 110. The first processing device 120 is, for example, a CPU. As the first processing device 120, a DSP (digital signal processor), LSI (large scale integration), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array), or the like may be used. The first processing device 120 is connected to the first input device 101, the first display device 102, the first communication device 103, the first interface device 104, the first sensor 105, the first storage device 110, etc., and controls each device. The first processing device 120 acquires data measured by the first sensor 105 when the user walks. Also, the first processing device 120 acquires data measured by the second wearable device 200 when the user holding the second wearable device 200 walks, from the second wearable device 200 via the first interface device 104. The first processing device 120 transmits the acquired data to the information processing device 300 via the first communication device 103.

[0039] The first processing device 120 reads a computer program stored in the first storage device 110 and operates according to the read computer program. Thereby, the first processing device 120 functions as the first acquisition unit 121 and the first transmission unit 122. The first acquisition unit 121 is an example of a reception unit, and the first transmission unit 122 is an example of a transmission unit.

[0040] FIG. 3 is a diagram showing a schematic configuration of the second wearable device 200.

[0041] The second wearable device 200 is a terminal device wearable by a user. For example, the second wearable device 200 is a wristwatch-type wearable computer worn on the user's wrist. Also, the second wearable device 200 is an earphone-type wearable computer worn on the user's ear. Also, the second wearable device 200 is an insole-type wearable computer worn inside the user's shoe. The second wearable device 200 includes a second input device 201, a second display device 202, a second communication device 203, a second interface device 204, a second sensor 205, a second storage device 210, a second processing device 220, and the like. The second input device 201, the second display device 202, the second communication device 203, the second interface device 204, the second sensor 205, the second storage device 210, and the second processing device 220 are interconnected via a CPU bus or the like.

[0042] The second input device 201 includes an input device such as a button and an interface circuit that acquires a signal from the input device, and outputs an operation signal according to the user's input operation. The second input device 201 may be omitted.

[0043] The second display device 202 includes a display including liquid crystal, organic EL, etc. and an interface circuit that outputs image data to the display, and displays the image data on the display. The second display device 202 may have an LED (Light Emitting Diode) or the like, and may notify the user by lighting or extinguishing. The second display device 202 may be omitted.

[0044] The second communication device 203 includes an antenna that transmits and receives wireless signals and a wireless communication interface circuit according to a communication protocol such as wireless LAN. The second communication device 203 communicates and connects with the network N according to a communication standard such as wireless LAN. The second communication device 203 sends the data received from the information processing device 300, the server device 400, or the like via the network N to the second processing device 220. Also, the second communication device 203 transmits the data received from the second processing device 220 to the information processing device 300, the server device 400, or the like via the network N.

[0045] The second interface device 204 includes an antenna for transmitting and receiving wireless signals and a wireless communication interface circuit according to a communication protocol such as Bluetooth (registered trademark). The second interface device 204 communicatively connects with the first wearable device 100 according to a communication standard such as Bluetooth (registered trademark). The second interface device 204 sends the data received from the first wearable device 100 to the second processing device 220. Further, the second interface device 204 transmits the data received from the second processing device 220 to the first wearable device 100.

[0046] The second sensor 205 includes an acceleration sensor that measures the triaxial acceleration applied to the second wearable device 200, a gyro sensor that measures the triaxial angular velocity applied to the second wearable device 200, and the like. The acceleration sensor and the gyro sensor output measurement signals indicating the measured acceleration and angular velocity to the second processing device 220. The second sensor 205 may include an insole type pressure sensor. In that case, the second sensor 205 includes a resistance change type or capacitance change type pressure sensor arranged in one dimension or two dimensions, generates sole data indicating the magnitude of the pressure measured by each pressure sensor, and outputs the sole data to the second processing device 220. The sole data is, for example, a sole image in which the magnitude of the pressure measured by each pressure sensor is the gradation value of each pixel. The sole data may be, for example, a sole vector having the pressure measured by each pressure sensor as an element.

[0047] The second storage device 210 includes a memory device such as a RAM or a ROM, a fixed disk device such as a hard disk, or a portable storage device such as a flexible disk or an optical disk. Further, the second storage device 210 stores computer programs, databases, tables, etc. used for various processes of the second wearable device 200. The computer program may be installed in the second storage device 210 using a known setup program or the like from a computer-readable portable recording medium. The portable recording medium is, for example, a CD-ROM, a DVD-ROM, or the like. The computer program may be stored in a recording medium of a predetermined server and installed via the network N.

[0048] The second processing device 220 operates based on a program stored in the second storage device 210 in advance. The second processing device 220 is, for example, a CPU. As the second processing device 220, a DSP, an LSI, an ASIC, an FPGA, or the like may be used. The second processing device 220 is connected to the second input device 201, the second display device 202, the second communication device 203, the second interface device 204, the second sensor 205, the second storage device 210, etc., and controls each device. The second processing device 220 acquires data measured by the second sensor 205 when the user walks and transmits it to the first wearable device 100 via the second interface device 204.

[0049] The second processing device 220 reads the computer program stored in the second storage device 210 and operates according to the read computer program. Thereby, the second processing device 220 functions as a second acquisition unit 221 and a second transmission unit 222.

[0050] FIG. 4 is a diagram showing a schematic configuration of the information processing apparatus 300.

[0051] The information processing device 300 is an example of a walking posture state estimation device. The information processing device 300 includes a third communication device 301, a third storage device 310, a third processing device 320, and the like. The third communication device 301, the third storage device 310, and the third processing device 320 are mutually connected via a CPU bus or the like.

[0052] The third communication device 301 is an example of an output unit. The third communication device 301 has a wired communication interface circuit according to a communication protocol such as TCP / IP. The third communication device 301 communicates and connects with the network N according to a communication standard such as Ethernet (registered trademark). The third communication device 301 sends the data received from the first wearable device 100, the second wearable device 200, the server device 400, or the like via the network N to the third processing device 320. The third communication device 301 transmits the data received from the third processing device 320 to the first wearable device 100, the second wearable device 200, the server device 400, or the like via the network N. Note that the third communication device 301 may have an antenna for transmitting and receiving radio signals and a wireless communication interface circuit according to a communication protocol such as a wireless LAN, and communicate and connect with the network N according to a communication standard such as a wireless LAN.

[0053] The third storage device 310 includes a memory device such as a RAM and a ROM, a fixed disk device such as a hard disk, or a portable storage device such as a flexible disk and an optical disk. In addition, various computer programs, databases, tables, and the like used for various processes of the information processing device 300 are stored in the third storage device 310. The computer program may be installed in the third storage device 310 using a known setup program or the like from a computer-readable portable recording medium such as a CD-ROM and a DVD-ROM. The computer program may be stored in a recording medium of a predetermined server and installed via the network N.

[0054] In the third memory device 310, a learned model 311, a data table 312, etc. are stored as data. The learned model 311 is a model for estimating the walking posture state of a user wearing the first wearable device 100 and the second wearable device 200. In the data table 312, each piece of information measured by the first sensor 105 of the first wearable device 100 or the second sensor 205 of the second wearable device 200 is stored. Details of the data table 312 will be described later.

[0055] The third processing device 320 operates based on a program stored in the third memory device 310 in advance. The third processing device 320 is, for example, a CPU. As the third processing device 320, a DSP, an LSI, an ASIC, an FPGA, etc. may be used. The third processing device 320 is connected to the third communication device 301, the third memory device 310, etc., and controls each device.

[0056] The third processing device 320 reads a computer program stored in the third memory device 310 and operates according to the read computer program. Thereby, the third processing device 320 functions as a third acquisition unit 321, an estimation unit 322, and an output control unit 323.

[0057] FIG. 5 is a schematic diagram showing an example of the data structure of the data table 312.

[0058] In the data table 312, the angular velocity, acceleration, geomagnetism, atmospheric pressure (not shown), position (not shown), or sole data acquired from the first wearable device 100 or the second wearable device 200 are stored in association with the identification information (device ID) of each device and the acquisition time at which each data was acquired.

[0059] FIG. 6 is a sequence showing an example of the operation of the estimation process in the walking posture state estimation system 1.

[0060] Next, an example of the operation of the estimation process will be described while referring to the flowchart shown in FIG. 6. The flowchart of the operation described below is mainly executed in cooperation with each element of each device by each processing device of each device based on a program stored in each storage device of each device of the walking posture state estimation system 1 in advance.

[0061] First, the second acquisition unit 221 of each second wearable device 200 acquires a measurement signal from the second sensor 205. The second acquisition unit 221 acquires, as second data obtained when the user walks, the triaxial acceleration and angular velocity applied to the second wearable device 200 indicated by the measurement signal or the sole data indicating the magnitude of the pressure applied to each position of the user's sole (step S101). The second acquisition unit 221 periodically acquires the second data.

[0062] Next, the second transmission unit 222 transmits the second data acquired by the second acquisition unit 221 to the first wearable device 100 via the second interface device 204 together with the device ID of the second wearable device 200 and the acquisition time when the second data was acquired (step S102). The second transmission unit 222 transmits the second data to the first wearable device 100 every time the second acquisition unit 221 acquires the second data. The second transmission unit 222 may transmit a plurality of second data acquired by the second acquisition unit 221 to the first wearable device 100 collectively at an arbitrary timing.

[0063] Next, the first acquisition unit 121 of the first wearable device 100 acquires the second data, the device ID, and the acquisition time from the second wearable device 200 via the first interface device 104 (step S103).

[0064] Next, the first acquisition unit 121 acquires a measurement signal from the first sensor 105. The first acquisition unit 121 acquires, as first data obtained when the user walks, the acceleration, angular velocity, geomagnetism, air pressure, or position in the three-axis directions applied to the first wearable device 100 indicated by the measurement signal (step S104). The first data is different from the second data. The first acquisition unit 121 periodically acquires the first data.

[0065] Next, the first transmission unit 122 transmits the first data and the second data acquired by the first acquisition unit 121 to the information processing device 300 via the first communication device 103, together with the device ID and acquisition time corresponding to each data (step S105). The first transmission unit 122 analyzes a plurality of continuously measured first data and second data, and detects the maximum and minimum values in the first data and second data arranged in time series. The first transmission unit 122 detects the vibration periods of the first wearable device 100 and the second wearable device 200 based on the detected maximum and minimum values. The first transmission unit 122 specifies the swing interval of the legs of the user wearing the first wearable device 100 and the second wearable device 200 based on the detected vibration periods. Then, the first transmission unit 122 transmits the first data and the second data for a predetermined number of steps (for example, 10 steps) of the user to the information processing device 300.

[0066] Thereby, as will be described later, when the input data to be input to the learned model 311 is data for a predetermined number of steps, the information processing device 300 does not need to extract data for a predetermined number of steps from the acquired first data and second data. The walking posture state estimation system 1 can reduce the processing load in the information processing device 300, and can reduce the processing load as a whole.

[0067] Note that the first transmission unit 122 may transmit the first data or the second data to the information processing device 300 each time the first acquisition unit 121 acquires the first data or the second data. Further, the first transmission unit 122 may collectively transmit the plurality of first data and second data acquired by the first acquisition unit 121 to the information processing device 300 at an arbitrary timing.

[0068] Next, the third acquisition unit 321 of the information processing apparatus 300 acquires the first data, the second data, the device ID, and the acquisition time from the first wearable device 100 via the third communication device 301 (step S106). The third acquisition unit 321 stores the acquired first data and second data in the data table 312 in association with the corresponding device ID and acquisition time.

[0069] Next, the estimation unit 322 estimates the walking posture state of the user wearing the first wearable device 100 and the second wearable device 200 based on the first data and the second data acquired by the third acquisition unit 321 (step S107). The estimation unit 322 estimates the walking posture state of the user using the learned model 311.

[0070] The learned model 311 includes one or more learned models. The learned model 311 is generated in advance by the information processing apparatus 300 or the server apparatus 400 or the like. The learned model 311 is pre-trained by supervised learning such as deep learning or support vector machine. The learned model 311 may be pre-trained by random forest or the like. The learned model 311 is trained to output the walking posture state of the user wearing the wearable device that generated the input data when the input data is input.

[0071] The input data is the first data acquired by the first wearable device 100 and / or the second data acquired by the second wearable device 200. The input data may also be data generated based on the first data and / or the second data. For example, the input data is a set of the first data and / or the second data for a predetermined number of consecutive steps or a predetermined period (e.g., 5 seconds) (a vector in which each data is arranged one-dimensionally or two-dimensionally with each data as an element). The input data may be a statistical value such as an average value, a median value, a maximum value, or a minimum value of the first data and / or the second data for a predetermined number of consecutive steps or a predetermined period. Also, the input data may be a quaternion calculated from the angular velocity, acceleration, or geomagnetism included in the first data and / or the second data.

[0072] Further, the input data may be a predetermined component (such as a first principal component and / or a second principal component, etc.) calculated by principal component analysis on the three-axis angular velocity or acceleration or sole data included in the first data and / or the second data. In that case, when the contribution rate of the first principal component is greater than a predetermined ratio (e.g., 80%), the first principal component is used as the input data, and when the contribution rate of the first principal component is less than or equal to the predetermined ratio, the second principal component may be used as the input data. Also, the principal component analysis may be performed after noise is removed using a known noise processing technique. In these cases, as the learned model 311, a model pre-trained by a random forest or the like is used. In these cases, as the learned model 311, a model pre-trained by a neural network or the like may also be used. Thereby, the walking posture state estimation system 1 can further improve the accuracy of the learned model 311.

[0073] Further, the input data may be an image of a spectrum obtained by performing a short-time Fourier transform or a wavelet transform on each angular velocity and / or acceleration in three axial directions included in the first data and / or the second data. An image of a spectrum obtained by performing a short-time Fourier transform or a wavelet transform on each angular velocity and / or acceleration in three axial directions included in the first data is an example of the first image data and the image data. An image of a spectrum obtained by performing a short-time Fourier transform or a wavelet transform on each angular velocity and / or acceleration in three axial directions included in the second data is an example of the second image data and the image data. In these cases, as the learned model 311, a model pre-trained by a random forest or the like is used. In these cases, as the learned model 311, a model pre-trained by a neural network or the like may be used. Thereby, the walking posture state estimation system 1 can further improve the accuracy of the learned model 311.

[0074] Further, the input data may be a feature vector including the gradation value (pressure) of each pixel of the sole image or each element of the sole vector, and the angular velocity, acceleration, geomagnetism, atmospheric pressure, and / or position.

[0075] The walking posture state output from the learned model 311 includes five elements. The first element indicates the state of the step length, particularly whether the user's step length is sufficient or insufficient. The second element indicates the state of the center-of-gravity position, particularly whether the user's center of gravity is normal, forward-tilted, or backward-tilted. The third element indicates the state of the swing leg, particularly whether the user is not kicking, dragging, or kicking the leg being put forward. The fourth element indicates the state of the supporting leg, particularly whether the user's axis leg is tensed or not. The fifth element indicates the state of the hip joint, particularly whether the user's hip joint is open or not. The first element is an element related to the premise of the walking posture. The second and third elements are elements related to the axis in the front-rear direction. The fourth and fifth elements are elements related to the axis of rotation (in the left-right direction). The walking posture state does not have to include all the elements from the first element to the fifth element, and may include at least one element.

[0076] The walking posture state output from the learned model 311 is not limited to information directly indicating each element from the first element to the fifth element, and may be a predetermined feature amount regarding each element from the first element to the fifth element.

[0077] The learned model 311 includes, for example, learned models corresponding to each of the first wearable device 100 and each second wearable device 200. That is, the learned model 311 includes a first learned model capable of outputting a first walking posture state estimated based on first data acquired from the first wearable device 100, and a second learned model capable of outputting a second walking posture state estimated based on second data acquired from each second wearable device 200.

[0078] Alternatively, the learned model 311 includes a first learned model capable of outputting a first walking posture state estimated based on first image data based on first data acquired from the first wearable device 100, and a second learned model capable of outputting a second walking posture state estimated based on second image data based on second data acquired from each second wearable device 200.

[0079] Thereby, the walking posture state estimation system 1 can estimate the walking posture state for each body part on which the wearable device is worn, and comprehensively estimate the walking posture state of the user based on the walking posture states estimated for each part.

[0080] In these cases, the estimation unit 322 may obtain the walking posture state by inputting the input data based on the first data to the first layer of the first trained model, and obtain the walking posture state by inputting the input data based on the second data to the second layer of the second trained model. This first layer is a specific layer among the input layer or the intermediate layer. This second layer is a layer different from the first layer and is a specific layer among the input layer or the intermediate layer. Thereby, the walking posture state estimation system 1 can flexibly change the number of processing layers (number of processing steps) in each trained model, and can suppress an increase in processing time and processing load.

[0081] Alternatively, the estimation unit 322 may obtain, as the walking posture state, the information output from the first layer of the first trained model when the input data based on the first data is input to the first trained model, and obtain, as the walking posture state, the information output from the second layer of the second trained model when the input data based on the second data is input to the second trained model. This first layer is a specific layer among the intermediate layer or the output layer. This second layer is a layer different from the first layer and is a specific layer among the intermediate layer or the output layer. Thereby, the walking posture state estimation system 1 can flexibly change the number of processing layers (number of processing steps) in each trained model, and can suppress an increase in processing time and processing load.

[0082] Note that the trained model 311 may be generated to correspond to a plurality of devices among the first wearable device 100 and the second wearable device 200. In particular, the trained model 311 may be generated to correspond to all of the first wearable device 100 and the second wearable device 200. That is, the trained model 311 includes a single trained model capable of outputting the walking posture state estimated based on the first data acquired from the first wearable device 100 and the second data acquired from each second wearable device 200.

[0083] Alternatively, the learned model 311 includes a single learned model capable of outputting a walking posture state estimated based on the first data and each second data acquired from the first wearable device 100 and each second wearable device 200, and the image data based thereon.

[0084] In these cases, the learned model 311 is learned to output a walking posture state when a vector including the first data and the second data acquired from a plurality of wearable devices at mutually corresponding times (substantially matching times) is input.

[0085] Thereby, the walking posture state estimation system 1 can comprehensively estimate the walking posture state based on the data acquired from a plurality of wearable devices.

[0086] Further, the learned model 311 includes learned models corresponding to each element from the first element to the fifth element. That is, the learned model 311 includes a plurality of learned models capable of outputting information regarding each element from the first element to the fifth element. The learned model 311 may include a single learned model capable of collectively outputting information regarding each element from the first element to the fifth element.

[0087] Further, the learned model 311 may include an upstream learned model and a downstream learned model arranged in series. In that case, the upstream learned model is learned to output a predetermined feature amount when input data is input, and the downstream learned model is learned to output a walking posture state when the feature amount output from the intermediate layer or the output layer of the upstream learned model is input. The predetermined feature amount is a feature amount regarding the input data or a feature amount regarding the walking posture state.

[0088] Also, the learned model 311 may include any combination of the above-described learned models. For example, the learned model 311 includes a first upstream learned model, a second upstream learned model, a third upstream learned model, and a downstream learned model. The first upstream learned model is learned to output a predetermined feature amount when the first principal component of the sole data is input. The second upstream learned model is learned to output a predetermined feature amount when the second principal component of the sole data is input. The third upstream learned model is learned to output a predetermined feature amount when the first principal component of the angular velocity or acceleration is input. Alternatively, the third upstream learned model is learned to output a predetermined feature amount when an image of a spectrum obtained by performing a short-time Fourier transform or a wavelet transform on the angular velocity and / or acceleration is input. The downstream learned model is learned to output a walking posture state when a feature vector including data output from the output layer or the intermediate layer of the first upstream learned model, the second upstream learned model, and the third upstream learned model is input. Thereby, the walking posture state estimation system 1 can further improve the accuracy of the learned model 311.

[0089] Alternatively, the learned model 311 includes a first upstream learned model, a second upstream learned model, and a downstream learned model. The first upstream learned model is learned to output a predetermined feature amount when sole data is input. The second upstream learned model is learned to output a predetermined feature amount when the angular velocity or acceleration is input. The downstream learned model is learned to output a walking posture state when a feature vector including data output from the output layer or the intermediate layer of the first upstream learned model and the second upstream learned model is input. Thereby, the walking posture state estimation system 1 can further improve the accuracy of the learned model 311.

[0090] Thus, the learned model 311 is provided to be able to output the estimated walking posture state of the user wearing the first wearable device 100 and the second wearable device 200.

[0091] The learning data of the learned model 311 includes a combination of pre-generated input data and the walking posture state of the user wearing the wearable device that generated the input data. Each piece of learning data is created by an expert who has viewed a moving image of the user wearing the wearable device that generated the first data or the second data when the first data or the second data was generated by each wearable device.

[0092] Each piece of learning data is composed of, for example, a set of the first data or the second data for a predetermined number of consecutive steps or a predetermined period, and a combination with the walking posture state. In that case, each piece of learning data may be generated such that a part of the first data or the second data included in each piece of learning data overlaps. That is, the first learning data may include data for a predetermined number of steps or a predetermined period from the first time, and the second learning data may include data for a predetermined number of steps or a predetermined period from the second time immediately after the first time (for example, 1 second later). Thereby, the walking posture state estimation system 1 can efficiently generate the learned model 311 from a small amount of sample data, and can reduce the time and labor required for generating the learned model 311.

[0093] When the learned model 311 is pre-learned by a random forest or the like, each piece of learning data is composed of, for example, a vector in which the first data or the second data for a predetermined number of consecutive steps or a predetermined period is arranged one-dimensionally, and a combination with the walking posture state. Each piece of learning data may include only the angular velocity in the three-axis directions, for example, among the first data or the second data. The walking posture state estimation system 1 can improve the accuracy of the learned model 311 by generating the learned model 311 based on both the angular velocity and the acceleration. On the other hand, the walking posture state estimation system 1 can reduce the time and labor required for generating the learned model 311 by generating the learned model 311 based only on the angular velocity. Also in these cases, each piece of learning data may be generated such that a part of the first data or the second data included in each piece of learning data overlaps.

[0094] The estimation unit 322 converts the first data and the second data acquired in step S106 into a format corresponding to the learned model 311, and inputs them into the learned model 311. Based on the information output from the learned model 311, the estimation unit 322 estimates the walking posture state of the user wearing the first wearable device 100 and the second wearable device 200. The estimation unit 322 estimates the walking posture state of the user for each element included in the walking posture state.

[0095] When the information output from the learned model 311 is a feature amount, the information processing device 300 stores in advance in the third storage device 310 a table or formula indicating the relationship between the feature amount and the walking posture state. The estimation unit 322 refers to the table or formula stored in the third storage device 310, and specifies the walking posture state of the user corresponding to the feature amount output from the learned model 311.

[0096] Also, when the learned model 311 includes a plurality of learned models corresponding to each wearable device, the estimation unit 322 estimates that the walking posture state output from the most learned models among the walking posture states output from each learned model is the walking posture state of the user.

[0097] In this way, the estimation unit 322 estimates the walking posture state of the user based on the acquired first data and second data by using the learned model 311. That is, the estimation unit 322 uses the learned model 311 to obtain the walking posture state estimated based on the acquired first data and second data.

[0098] Next, the output control unit 323 outputs by transmitting the estimated walking posture state of the user wearing the first wearable device 100 and the second wearable device 200 to the first wearable device 100 via the third communication device 301 (step S108).

[0099] Next, the first acquisition unit 121 of the first wearable device 100 acquires the estimated walking posture state of the user by receiving it from the information processing device 300 via the first communication device 103 (step S109).

[0100] Next, the first acquisition unit 121 outputs and notifies the user by displaying the acquired walking posture state on the first display device 102 (step S110), and ends a series of steps. As a result, the user can recognize their own walking posture state.

[0101] In step S108, the output control unit 323 of the information processing device 300 may transmit the estimated walking posture state of the user wearing the first wearable device 100 and the second wearable device 200 to an administrator device owned by an administrator who manages the user's health. In that case, the administrator device notifies the administrator by displaying the received walking posture state. The administrator can recognize the walking posture state of the user and propose improvements to the walking posture state to the user.

[0102] Also, the timings at which the processes of step S101 and step S104 are executed may be arbitrary and may be simultaneous. For example, when the first acquisition unit 121 of the first wearable device 100 receives an instruction to start measurement from the user using the first input device 101, it transmits a measurement request signal for requesting start of measurement to the second wearable device 200 via the first interface device 104 and acquires first data. On the other hand, when the second acquisition unit 221 of the second wearable device 200 receives a measurement request signal from the first wearable device 100 via the second interface device 204, it acquires second data and transmits it to the first wearable device 100 via the second interface device 204. The first acquisition unit 121 repeats the above processes until it receives an instruction to end measurement from the user using the first input device 101, and then executes the process of step S105.

[0103] The inventor evaluated the learned model 311 for all of the first to fifth elements, and confirmed that the accuracy rate of the information output from the learned model 311 was 93% or more, indicating that the accuracy was sufficiently high. That is, it was confirmed that the walking posture state estimation system 1 can more accurately estimate the user's walking posture state by using the learned model 311. In addition, the walking posture state estimation system 1 can calculate the walking posture state for various combinations of various types of parameters with high accuracy and efficiency by using the learned model 311. Further, the walking posture state estimation system 1 can identify the walking posture state without storing the corresponding walking posture state for various combinations of various types of parameters by using the learned model 311, so that the storage capacity of the storage device can be reduced. Moreover, the walking posture state estimation system 1 can identify the walking posture state without performing complex determinations according to various combinations of various types of parameters by using the learned model 311, thus reducing the processing time and processing load of the estimation process.

[0104] Hereinafter, the technical significance of the walking posture state including the first to fifth elements will be described.

[0105] The main power source of the walking motion is the lifting of the thigh, and the main power source of the running motion is the kick of the toes. Therefore, the walking motion and the running motion, that is, the motion of running slowly to the extreme, are fundamentally different motions, and clearly changing the movement between the walking motion and the running motion is related to the user's health. In order to kick with the toes, the foot turns inward to place the ball of the thumb on the floor, and the arch disappears. As a result, the bones of the foot become loose as a whole, and the impact on the foot is easily transmitted to the knee or waist. Since the running motion involves a burden on the foot, it is not desirable to perform a running motion that places a burden on the foot while walking.

[0106] The walking posture state estimation system 1 can identify whether a user is performing an appropriate walking motion without running by estimating each element from the first element to the fifth element as the walking posture state of the user. In particular, each of the elements from the first element to the fifth element is related to each other, and in the order from the first element to the fifth element, as the user's posture is improved, the user can easily improve the walking posture.

[0107] First, it should not be the case that the stride length is too short and the walking speed is too slow. The stride length needs to be guaranteed to be a certain length or more. By including, as a first element indicating whether the user's stride length is sufficient or insufficient, in the walking posture state, the walking posture state estimation system 1 can ensure that the user's stride length is a certain length or more.

[0108] Next, when the user's posture is not straight, the user has to run. When the user stands straight with the heel as the center of gravity, the user can lift the leg using the thigh, but when in a forward-leaning posture, the upper body covers and it becomes difficult to lift the leg using the thigh, and the user has to kick with the toes. By including, as a second element indicating whether the user's center of gravity is normal, forward-leaning, or backward-leaning, as an element related to the axis in the front-rear direction, in the walking posture state, the walking posture state estimation system 1 can confirm whether the user's posture is kept straight.

[0109] Next, even if the user's center of gravity is straight, if the thigh lift is not performed correctly, the user has to run. Even if the user's center of gravity is straight and the foot rises without kicking with the toes, kicking with the toes will cause violent up and down movement. Also, even though the user's center of gravity is straight, since the user does not have the habit of lifting the foot with the thigh, the user may drag the foot. By including, as an element related to the axis in the front-rear direction, a third element indicating whether the user is not kicking, dragging, or kicking the foot being put out, the walking posture state estimation system 1 can confirm whether the user's thigh lift is being performed correctly.

[0110] Next, even if the axis in the front-rear direction is correct, if the axis of rotation (in the left-right direction) is incorrect, the appropriate walking motion cannot be performed. If the knee is inside relative to the toes, the knee gets in the way and the opposite foot cannot come out correctly. That is, when the axis foot is tense or the hip joint is not open, the foot that wants to be put out cannot rise correctly. On the other hand, when the user rotates the hip joint, space is secured for the opposite foot to come out, the foot rises easily, and the thigh lift is performed correctly. By including, as an element related to the axis of rotation (in the left-right direction), a fourth element indicating whether the user's axis foot is tense or not and a fifth element indicating whether the user's hip joint is open or not, the walking posture state estimation system 1 can confirm whether the axis of rotation is correct.

[0111] As described in detail above, the walking posture state estimation system 1 estimates the user's walking posture state using the learned model 311 based on the first data acquired by the first wearable device 100 and the second data acquired by the second wearable device 200. Thereby, the walking posture state estimation system 1 can estimate the user's walking posture state with higher accuracy.

[0112] FIG. 7 is a sequence showing an example of the operation of the estimation process in the walking posture state estimation system 1 according to another embodiment.

[0113] Next, an example of the operation of the estimation process according to this embodiment will be described with reference to the flowchart shown in FIG. 7. Note that the flowchart of the operation described below is mainly executed by each processing device of each device in cooperation with each element of each device based on a program stored in each storage device of each device included in the walking posture state estimation system 1 in advance. In this embodiment, the learned model 311 is stored in the server device 400. Since the processes of steps S201 to S206 and S213 to S215 in FIG. 7 are the same as the processes of steps S101 to S106 and S108 to S110 in FIG. 6, the description thereof will be omitted, and only steps S207 to S212 will be described below.

[0114] In step S207, the estimation unit 322 of the information processing device 300 transmits a request signal for requesting transmission of the user's walking posture information to the server device 400 via the third communication device 301 (step S207). The request signal includes the first data and the second data acquired in step S106 and converted into a format corresponding to the learned model 311.

[0115] Next, the server device 400 receives the request signal from the information processing device 300 (step S208). Next, the server device 400 inputs the first data and the second data included in the received request signal into the learned model 311, and acquires output information output from the learned model 311 (step S209). Next, the server device 400 transmits the acquired output information to the information processing device 300 (step S210).

[0116] Next, the estimation unit 322 of the information processing device 300 acquires the output information by receiving it from the server device 400 via the third communication device 301 (step S211). Next, the estimation unit 322 estimates the walking posture state of the user wearing the first wearable device 100 and the second wearable device 200 based on the acquired output information (step S212). The estimation unit 322 estimates the walking posture state of the user in the same manner as the process of step S107 in FIG. 6.

[0117] As described in detail above, the walking posture state estimation system 1 can estimate the walking posture state of the user with higher accuracy even when the learned model 311 is stored in a server device 400 other than the information processing device 300.

[0118] The walking posture state estimation system 1 can estimate the walking posture state of the user using the latest learned model updated by the server device 400 by using the learned model 311 stored in the server device 400. Also, the walking posture state estimation system 1 can reduce the storage capacity of the information processing device 300 by using the learned model 311 stored in the server device 400. On the other hand, the information processing device 300 can estimate the walking posture state of the user even when the communication connection with the server device 400 is disconnected by using the learned model 311 stored in its own device. Also, the information processing device 300 can reduce the communication volume between the information processing device 300 and the server device 400 by using the learned model 311 stored in its own device.

[0119] FIG. 8 is a sequence showing an example of the operation of the estimation process in the walking posture state estimation system 1 according to still another embodiment.

[0120] Next, an example of the operation of the estimation process according to this embodiment will be described with reference to the flowchart shown in FIG. 8. Note that the operation flow described below is mainly executed by each processing device of each device in cooperation with each element of each device based on a program stored in each storage device of each device included in the walking posture state estimation system 1 in advance. In this embodiment, the learned model 311 and the data table 312 are stored in the first storage device 110 of the first wearable device 100. Further, the first processing device 120 functions as the first acquisition unit 121 and the first transmission unit 122, and also functions as an estimation unit and an output control unit having the same functions as the estimation unit 322 and the output control unit 323. Since the processes of steps S301 to S303 and S306 in FIG. 8 are the same as the processes of steps S101 to S103 and S110 in FIG. 6, the description thereof will be omitted, and hereinafter, only steps S304 to S305 will be described.

[0121] In step S304, the first acquisition unit 121 of the first wearable device 100 acquires first data obtained when the user walks, in the same manner as the process of step S104 (step S304). The first acquisition unit 121 stores the acquired first data and second data in the data table 312 in association with the corresponding device ID and acquisition time.

[0122] Next, the estimation unit of the first wearable device 100 estimates the walking posture state of the user wearing the first wearable device 100 and the second wearable device 200 based on the first data and the second data, in the same manner as the process of step S107 (step S305).

[0123] As described in detail above, the walking posture state estimation system 1 can estimate the walking posture state of the user with higher accuracy even when the first wearable device 100 estimates the walking posture state of the user.

[0124] Although the preferred embodiments have been described above, the embodiments are not limited thereto. For example, when the first wearable device 100 estimates the user's walking posture state, the first wearable device 100 may also estimate the user's walking posture state based on the output information of the learned model 311 stored in the server device 400.

[0125] In addition, the second wearable device 200 may directly transmit the second data to the information processing device 300 instead of transmitting the second data to the information processing device 300 via the first wearable device 100. Thereby, the walking posture state estimation system 1 can reduce the processing load on the first wearable device 100. On the other hand, by aggregating the second data from the second wearable device 200 by the first wearable device 100, the walking posture state estimation system 1 can reduce the processing load on the information processing device 300.

[0126] Also, in the walking posture state estimation system 1, a plurality of first wearable devices 100 and / or a plurality of information processing devices 300 may cooperate to share each step of the above-described respective processes.

Description of Reference Numerals

[0127] 1 Walking Posture State Estimation System, 100 First Wearable Device, 105 First Sensor, 110 First Storage Device, 121 First Acquisition Unit, 122 First Transmission Unit, 200 Second Wearable Device, 205 Second Sensor, 300 Information Processing Device, 310 Third Storage Device, 311 Learned Model, 321 Third Acquisition Unit, 322 Estimation Unit

Claims

1. A first wearable device that can be worn by a user and acquires first data obtained when the user walks; A second wearable device that can be worn by a user and acquires second data different from the first data obtained when the user walks; An information processing device that receives the first data and the second data and can output an estimated walking posture state of the user wearing the first wearable device and the second wearable device. The information processing device has a storage unit that stores a learned model capable of outputting the walking posture state estimated based on the first data and the second data. A walking posture state estimation system characterized by the above.

2. The first wearable device includes: A receiving unit that receives the second data from the second wearable device; A transmitting unit that transmits the first data and the second data for a predetermined number of steps of the user to the information processing device. The walking posture state estimation system according to claim 1.

3. The walking posture state includes any one or more of a state of step width, a state of center of gravity position, a state of the swinging leg, a state of the supporting leg, and a state of the hip joint. The walking posture state estimation system according to claim 1 or 2.

4. The learned model includes a first learned model capable of outputting a first walking posture state estimated based on the first data, and a second learned model capable of outputting a second walking posture state estimated based on the second data. The walking posture state estimation system according to claim 1 or 2.

5. The learned model is a single learned model capable of outputting the walking posture state estimated based on the first data and the second data. The walking posture state estimation system according to claim 1 or 2.

6. The learned model includes a first learned model capable of outputting a first walking posture state estimated based on first image data based on the first data, and a second learned model capable of outputting a second walking posture state estimated based on second image data based on the second data. The walking posture state estimation system according to claim 1 or 2.

7. The learned model is a single learned model capable of outputting the walking posture state estimated based on image data based on the first data and the second data. The walking posture state estimation system according to claim 1 or 2.

8. The information processing device inputs data based on the first data into a first layer of a first learned model included in the learned model, and inputs data based on the second data into a second layer different from the first layer of a second learned model included in the learned model, thereby obtaining the walking posture state. The walking posture state estimation system according to claim 1 or 2.

9. The walking posture state includes information output from a first layer of the learned model when data based on the first data is input into the learned model, and information output from a second layer different from the first layer of the learned model when data based on the second data is input into the learned model. The walking posture state estimation system according to claim 1 or 2.

10. A first wearable device wearable by a user acquires first data obtained when the user walks. A second wearable device wearable by a user acquires second data different from the first data obtained when the user walks. Using a learned model capable of outputting the walking posture state of the user wearing the first wearable device and the second wearable device estimated based on the first data and the second data, the walking posture state is estimated based on the acquired first data and second data. Output the walking posture state. A walking posture state estimation method characterized by the above.

11. An acquisition unit that acquires the first data and the second data from a first sensor that measures the first data obtained when the user walks and a second sensor that measures the second data different from the first data obtained when the user walks. An estimation unit that uses a learned model capable of outputting a walking posture state estimated based on the first data and the second data, and acquires a walking posture state estimated based on the acquired first data and second data. A walking posture state estimation device characterized by having the above.

12. The first data and the second data are acquired from a first sensor that acquires the first data obtained when the user walks and a second sensor that acquires the second data different from the first data obtained when the user walks. Using a learned model capable of outputting a walking posture state estimated based on the first data and the second data, obtain a walking posture state estimated based on the acquired first data and the second data. A walking posture state estimation method characterized by the above.

13. A control program for a walking posture state estimation device, acquire the first data and the second data from a first sensor that acquires the first data obtained when the user walks and a second sensor that acquires the second data different from the first data obtained when the user walks, Using a learned model capable of outputting a walking posture state estimated based on the first data and the second data, obtain a walking posture state estimated based on the acquired first data and the second data. A control program characterized by causing the walking posture state estimation device to execute the above.

14. A first sensor that measures the first data obtained when the user walks, an acquisition unit that acquires the second data from a second sensor that measures the second data different from the first data obtained when the user walks, a storage unit that stores a learned model capable of outputting a walking posture state estimated based on the first data and the second data, an estimation unit that uses the learned model to obtain a walking posture state estimated based on the acquired first data and the second data, A walking posture state estimation device characterized by having the above.

15. A walking posture state estimation method by a walking posture state estimation device having a first sensor that acquires the first data obtained when a first user walks, acquire the second data from a second sensor that acquires the second data different from the first data obtained when the user walks, store a learned model capable of outputting a walking posture state estimated based on the first data and the second data, Using the learned model, obtain a walking posture state estimated based on the acquired first data and the second data. A walking posture state estimation method characterized by the above.

16. A control program for a walking posture state estimation device having a first sensor that acquires the first data obtained when a first user walks, acquire the second data from a second sensor that acquires the second data different from the first data obtained when the user walks, Stores a learned model capable of outputting a walking posture state estimated based on the first data and the second data. Uses the learned model to obtain a walking posture state estimated based on the acquired first data and second data. A control program that causes the walking posture state estimation device to execute the above.

Images