JP7355704B2 - Information processing device, information processing method, and program - Google Patents

Description

The present invention relates to an information processing device, an information processing method, and a program.

2. Description of the Related Art Walking assist devices that assist users in walking are known (for example, see Patent Document 1). On the other hand, a technique is known in which topics are extracted from text using PLSA (Probabilistic Latent Semantic Analysis) and a Bayesian network is generated using the extracted topics as explanatory variables (for example, see Patent Document 2).

Japanese Patent Application Publication No. 2016-214504 JP2016-51220A

However, with conventional technology, it is difficult to appropriately decide what kind of guidelines should be used when a user wears a walking aid device and exercises walking on his or her own without the guidance of a doctor or physical therapist. There were cases where this was not possible.

The present invention has been made in consideration of such circumstances, and one of the objects is to provide an information processing device, an information processing method, and a program that can appropriately determine guidelines for walking training for a user. Let's do one.

An information processing device, an information processing method, and a program according to the present invention employ the following configuration.
(1) A first aspect of the present invention provides measurement of the user's movement during the n-th walking training from a walking assist device that measures the movement of the user while assisting the user's walking. A selection result of at least one parameter selected by the user from among a plurality of parameters that will serve as a guideline for the n-th walking training from a terminal device that the user can use by acquiring first data representing the results; an acquisition unit that acquires second data representing the m+kth walking training of the user; and when at least the first data and the second data of the user who has performed the m-th walking training are input, The first data and the second data acquired by the acquisition unit at the time of the user's n-th walking training are applied to a model that has been trained to output recommended parameters that should be used as guidelines. a determining unit that determines the recommended parameters to be used as guidelines for the n+kth walking training of the user, based on the output results of the model into which the first data and the second data have been input; This is an information processing device equipped with.

(2) In a second aspect of the present invention, in the information processing apparatus according to aspect (1) above, the acquisition unit further comprises, from the terminal device, the user's response to the n+kth walking training questionnaire. The determination unit obtains the first data and the second data of the user at the n-th walking training, and the third data of the user at the n+k-th walking training. data is input into the model, and based on the output result of the model into which the first data, the second data, and the third data are input, a guideline for the n+kth walking training of the user is set. The recommended parameters to be used are determined.

(3) A third aspect of the present invention is the information processing apparatus according to aspect (1) or (2) above, wherein the model is one of a deep neural network, a topic model, and a Bayesian network. One model or a combination of multiple models.

(4) A fourth aspect of the present invention is the information processing apparatus according to any one of (1) to (3) above, in which the first data of the user of the m-kth time and the second data of the user the recommended parameters for the user's m-th walking training, which are output by the model when data is input into the model; and the parameters selected by the user from among the plurality of parameters during the m-th walking training. The present invention further includes a learning section that learns the model so that the following equations match.

(5) In a fifth aspect of the present invention, the computer detects the movement of the user during the n-th walking training from a walking assist device that measures the movement of the user while assisting the user's walking. At least one parameter selected by the user from a plurality of parameters that will serve as a guideline for the n-th walking training from a terminal device that the user can use after acquiring first data representing the measurement result of the movement. When at least the first data and the second data of the user who has performed the m-th walking training are inputted, the second data representing the selection result of the m+k-th walking training of the user is inputted. The acquired first data and second data from the user's nth walking training are input to a model that has been trained to output recommended parameters that should be used as guidelines. The information processing method determines the recommended parameters to be used as guidelines for the user's (n+k)th walking training based on the output results of the model into which the first data and the second data are input.

(6) In a sixth aspect of the present invention, a walking assist device that measures the movement of the user when he/she walks while assisting the user's walking is sent to the computer. acquiring first data representing a movement measurement result; and at least one parameter selected by the user from among a plurality of parameters serving as a guideline for the n-th walking training from a terminal device available to the user. obtaining second data representing a parameter selection result; when at least the first data and the second data of the user who has performed the m-th walking training are input, the m+k-th walking of the user; inputting the acquired first data and second data of the user's n-th walking training to a model that has been learned to output recommended parameters that should be used as guidelines during training; A program for determining the recommended parameters to be used as guidelines for the n+kth walking training of the user based on the output results of the model into which the first data and the second data are input. It is.

According to the above aspect, it is possible to appropriately determine guidelines for user's walking training.

1 is a diagram illustrating an example of the configuration of a walking assistance system according to an embodiment. 1 is a diagram illustrating an example of the configuration of a walking assist device according to an embodiment. FIG. 1 is a diagram illustrating an example of the configuration of a terminal device according to an embodiment. It is a figure showing an example of the content of a walking training application. It is a figure showing other examples of contents of a walking training application. It is a figure showing other examples of contents of a walking training application. FIG. 1 is a diagram illustrating an example of the configuration of a server according to an embodiment. 2 is a flowchart illustrating an example of the flow of a series of processes performed by the server according to the embodiment. FIG. 3 is a diagram illustrating an example of a parameter estimation model. This figure represents an example of a database that includes walking training measurement data, parameter selection data, and questionnaire response data. FIG. 3 is a diagram for explaining a topic model. FIG. 1 is a diagram illustrating an example of a Bayesian network.

DESCRIPTION OF THE PREFERRED EMBODIMENTS Embodiments of an information processing apparatus, an information processing method, and a program according to the present invention will be described below with reference to the drawings.

[System configuration]
FIG. 1 is a diagram illustrating an example of the configuration of a walking assistance system 1 according to an embodiment. The walking assistance system 1 according to the embodiment includes, for example, a walking assistance device 100, a terminal device 200, and a server 300. The walking assist device 100 and the terminal device 200 are connected, for example, by wireless communication such as Wi-Fi or Bluetooth (registered trademark, hereinafter omitted). The terminal device 200 and the server 300 are connected via a network NW such as a LAN (Local Area Network) or a WAN (Wide Area Network), for example. The server 300 is an example of an "information processing device."

[Configuration of walking aid device]
FIG. 2 is a diagram illustrating an example of the configuration of the walking assist device 100 according to the embodiment. The walking assist device 100 according to the embodiment includes, for example, a main frame 102, subframes 103L and 103R, drive sources 104L and 104R, a control device 105, hip joint angle sensors 106L and 106R, and a battery 107.

Main frame 102 is attached to the user's torso. The main frame 102 is composed of a combination of a rigid material such as hard resin or metal and a flexible material such as fiber. A belt 111 is attached to the main frame 102, and the belt 111 is worn around the user's waist. A lumbar supporter 112 made of a flexible material is attached to the front surface of the main frame 102 (a position facing the back surface of the lumbar region).

Each of the subframes 103L and 103R is connected to the main frame 102 so as to be able to be displaced around the user's hip joint. The subframe 103L is attached to the user's left leg, and the subframe 103R is attached to the user's right leg. The subframe 103L includes a leg supporter 113L and an arm portion 114L. The subframe 103R includes a leg supporter 113R and an arm portion 114R. Each of the leg supports 113L and 113R is made of a combination of a rigid material and a flexible material, and is attached to the thigh. Each of the arm portions 114L and 114R is made of hard resin or metal. Each of the arm parts 114L and 114R extends downward along the thigh and connects the output shaft of the drive source 104 and the leg supporter 113. That is, subframes 103L and 103R are connected to main frame 102 via drive source 104.

The drive source 104L displaces the subframe 103L attached to the user's left leg with respect to the main frame 102. The drive source 104R displaces the subframe 103R attached to the user's right leg with respect to the main frame 102. Each of the drive sources 104L and 104R is, for example, an actuator such as a motor, and is appropriately equipped with one or both of a deceleration mechanism and a compliance mechanism. Each of drive sources 104L and 104R is controlled by control device 105 to output assist torque. Under the control of control device 105, each of drive sources 104L and 104R applies power to arm portion 114 using electric power from battery 107. The power applied to the arm portion 114 is transmitted to the user's leg via the leg supporter 113.

The control device 105 is housed in the main frame 102, for example. The control device 105 may be attached to or housed in the subframe 103 instead of being housed in the main frame 102, or may be provided separately from the walking aid device 100.

The control device 105 is an electronic circuit unit including, for example, a CPU (Central Processing Unit), a RAM (Random Access Memory), a ROM (Read Only Memory), and the like. Further, the electronic circuit unit includes a wireless communication module such as an antenna, a transmitter, and a receiver.

The control device 105 controls the drive sources 104L and 104L to adjust the assist torque that is applied to the user. For example, the control device 105 calculates the difference angle between the left and right hip joint angles (the angle between the hip joints of the left and right legs) based on the angles of the user's hip joints detected by the hip joint angle sensors 106L and 106R, respectively. do. The control device 105 calculates the phase of the difference angle and the walking frequency based on the calculated difference angle. Then, the control device 105 determines assist torques for the left and right legs based on the phase of the difference angle. Specifically, the control device 105 calculates the phase of a virtual oscillator that synchronizes with the user's walking based on the phase of the calculated difference angle and the walking frequency, and based on the phase of the oscillator, the left and right Determine the assist torque for the leg.

Furthermore, based on the detection results of the hip joint angle sensors 106L and 106R, in addition to the difference angle (incident angle), the control device 105 further calculates the number of steps, average stride length, average walking speed, hip joint angle of motion, extension, and Training parameters to be described later, such as the time elapsed during bending (extension/bending time) and the degree of left-right symmetry during walking, are also calculated.

The hip joint angle sensor 106L detects the relative angle between the subframe 103L and the main frame 102 as the angle of the hip joint of the user's left leg. The hip joint angle sensor 106R detects the relative angle between the subframe 103R and the main frame 102 as the angle of the hip joint of the user's right leg. Each of the hip joint angle sensors 106L and 106R is, for example, an absolute angle sensor, and is placed next to the user's waist. Each of the hip joint angle sensors 106L and 106R outputs a signal representing the detected hip joint angle to the control device 105.

Battery 107 supplies power to drive sources 104L and 104L and control device 105. The battery 107 is housed inside the main frame 102, for example. The battery 107 may be attached to or housed in the subframe 103, or may be provided separately from the walking aid device 100.

In this way, the walking assist device 100 allows the user to walk by applying the power of the drive source 104, which is powered by the battery 107, to the user as a walking assist torque via the main frame 102 and the sub-frames 103L and 103R. Assist with exercise.

[Terminal device configuration]
FIG. 3 is a diagram illustrating an example of the configuration of the terminal device 200 according to the embodiment. The terminal device 200 according to the embodiment includes, for example, a communication section 202, a touch panel 204, a control section 220, and a storage section 230.

The communication unit 202 includes, for example, a wireless communication module such as an antenna, a transmitter, and a receiver. The communication unit 202 wirelessly communicates with the control device 105 of the walking aid device 100 and communicates with the server 300 via the network NW.

The touch panel 204 is a user interface that is a combination of a display device such as an LCD (Liquid Crystal Display) or an organic EL (Electroluminescence) display, and an input device such as a touch pad. The display device and the input device do not need to be integrally configured as the touch panel 204, and may be provided separately.

The control unit 220 is realized, for example, by a processor such as a CPU or a GPU (Graphics Processing Unit) executing a program stored in the storage unit 230. The control unit 220 may be realized by hardware such as LSI (Large Scale Integration), ASIC (Application Specific Integrated Circuit), or FPGA (Field-Programmable Gate Array), or may be realized by collaboration between software and hardware. may be done.

The storage unit 230 is realized by, for example, an HDD (Hard Disk Drive), a flash memory, an EEPROM (Electrically Erasable Programmable Read Only Memory), a ROM, a RAM, or the like. The storage unit 230 stores various programs such as firmware and application programs.

For example, the user operates the touch panel 204 to select from a plurality of applications installed on the terminal device 200 a dedicated application (hereinafter referred to as a walking training application) that supports walking training when the walking assist device 100 is worn. ) is selected. In this case, the control unit 220 executes the walking training application and displays various contents on the touch panel 204 in response to the user's selection operation on the touch panel 204 .

FIG. 4 is a diagram illustrating an example of the content of the gait training application. As illustrated, when the walking training application is executed, a walking training menu for each user is automatically displayed as content on the touch panel 204. The walking training menu presents several training parameters (also referred to as training items) that serve as guidelines or targets during walking training.

The training parameters include, for example, upper-level training parameters that determine a rough training strategy and lower-level training parameters that determine a more detailed training strategy. The upper training parameters include, for example, three types of parameters, A, B, and C. Parameter A is, for example, a parameter related to "how to walk" during walking training. Parameter B is, for example, a parameter related to "speed" during walking training. Parameter C is, for example, a parameter related to "endurance" during walking training.

On the other hand, the lower training parameters include, for example, 15 types of parameters such as a to o. Parameter a is, for example, a parameter related to "measurement time." Parameter b is, for example, a parameter related to "walking time". The parameter c is, for example, a parameter related to the "number of steps." The parameter d is, for example, a parameter related to "average stride length." The parameter e is, for example, a parameter related to "average pace." The parameter f is, for example, a parameter related to "average walking speed." The parameter g is, for example, a parameter related to "average walking ratio." The parameter h is, for example, a parameter related to "walking distance". The parameter i is, for example, a parameter related to "hip joint movement angle." The parameter j is, for example, a parameter related to the "included angle". The parameter k is, for example, a parameter related to "extension/bending time." The parameter l is, for example, a parameter related to "symmetry". The parameter m is, for example, a parameter related to "waveform". The parameter n is, for example, a parameter related to "video". The parameter o is, for example, a parameter related to "waveform and moving image".

The training parameters are not limited to the examples described above, and other parameters may be added, some parameters may be replaced with other parameters, or some parameters may be omitted. Further, the training parameters do not have to have a hierarchical structure such as upper and lower levels.

5 and 6 are diagrams showing other examples of content of the walking training application. For example, when the user selects parameter d as a low-order training parameter, as illustrated in FIG. 5, the measured numerical value related to the "average gait" is displayed on the touch panel 204. Furthermore, when the user selects parameters i, j, and k as the lower training parameters, the touch panel 204 displays "hip joint movement angle," "pinching angle," and "extension/flexion time," as illustrated in FIG. Related measurement values are displayed.

The measured values of these training parameters are acquired from the walking assist device 100. For example, the control device 105 of the walking aid device 100 measures all of the training parameters described above and transmits the measurement results to the terminal device 200. When the control unit 220 of the terminal device 200 receives the measurement results of all training parameters from the walking aid device 100 via the communication unit 202, the control unit 220 selects the touch panel according to the user's parameter selection from among the plurality of measurement results. The measurement results to be displayed in 204 are selected. Then, the control unit 220 displays the selected measurement result on the touch panel 204.

[Server configuration]
The configuration of the server 300 will be described below. The server 300 may be a single device, or may be a system in which a plurality of devices connected via a network NW operate in cooperation with each other. That is, the server 300 may be implemented by multiple computers (processors) included in a distributed computing system or a cloud computing system.

FIG. 7 is a diagram illustrating an example of the configuration of the server 300 according to the embodiment. As illustrated, the server 300 includes, for example, a communication section 302, a control section 320, and a storage section 330.

The communication unit 302 includes, for example, a NIC (Network Interface Card). The communication unit 302 communicates with the terminal device 200 and the like via the network NW.

The control unit 320 includes, for example, an acquisition unit 322, a determination unit 324, and a learning unit 326. These components are realized, for example, by a processor such as a CPU or GPU executing a program stored in the storage unit 330. Some or all of the components of the control unit 320 may be realized by hardware such as LSI, ASIC, or FPGA, or may be realized by cooperation of software and hardware.

The storage unit 330 is realized by, for example, an HDD, a flash memory, an EEPROM, a ROM, a RAM, or the like. The storage unit 330 stores various programs such as firmware and application programs. The storage unit 330 stores model data 332 and the like in addition to programs referenced by the processor. The model data 332 is data (program or data structure) that defines a parameter estimation model MDL, which will be described later.

[Processing flow of information processing device]
The flow of a series of processes performed by the server 300 will be described below with reference to a flowchart. FIG. 8 is a flowchart illustrating an example of a series of processes performed by the server 300 according to the embodiment. The processing in this flowchart may be performed, for example, in conjunction with the number of times the user performs walking training. Specifically, when the user wears the walking assist device 100 and performs walking training once a day, the processing in this flowchart is performed on a daily basis. Furthermore, when the server 300 is implemented by multiple computers included in a distributed computing system or a cloud computing system, part or all of the processing in this flowchart may be processed in parallel by the multiple computers. Hereinafter, as an example, a description will be given assuming that the current walking training is the nth time (n is an arbitrary natural number).

First, the acquisition unit 322 waits until the n-th walking training starts (step S100), and when the n-th walking training starts, the acquisition unit 322 receives the first walking training from the terminal device 200 via the communication unit 302. The n-th questionnaire response data is acquired (step S102).

The questionnaire response data is, for example, data representing the results of the user's actual responses to a questionnaire (also referred to as a survey) that is asked to the user before starting walking training. For example, assume that the user starts a walking training application on the terminal device 200 to start walking training. In this case, for example, the control unit 220 of the terminal device 200 causes the touch panel 204 to display a questionnaire upon activation of the walking training application. Questions in the questionnaire include questions regarding the walking assist device 100, questions regarding the user's own physical condition and health, and the like, which would be asked of a patient by an expert such as a doctor or physical therapist. When the user inputs a questionnaire response into the touch panel 204, the control unit 220 transmits the response result to the server 300 as questionnaire response data via the communication unit 202. Questionnaire response data is an example of "third data."

Next, the determining unit 324 uses the n-th questionnaire response data acquired by the acquiring unit 322 in the process of S102, the walking training measurement data and parameter selection data acquired during the previous (n−1)-th walking training. is input to the learned (trained) parameter estimation model MDL defined by the model data 332 (step S104).

The walking training measurement data is data representing measurement results of various training parameters measured by the walking assist device 100. The parameter selection data is data representing the results of parameters actually selected by the user from among a plurality of training parameters that serve as guidelines for walking training. The walking training measurement data is an example of "first data," and the parameter selection data is an example of "second data."

The parameter estimation model MDL is based on the gait training measurement data and parameter selection data of the user who performed gait training for the n-1st time (that is, the previous time), and the questionnaire of the user who is scheduled to perform gait training for the nth time (that is, this time). This model is trained to estimate training parameters that the user should select when performing walking training for the nth time when response data is input, and to output the estimation results as recommended parameters. A learning method for the parameter estimation model MDL will be described later.

FIG. 9 is a diagram illustrating an example of the parameter estimation model MDL. As illustrated, the parameter estimation model MDL may be implemented by a deep neural network configured with an input layer, a plurality of hidden layers (middle layers), and an output layer. The deep neural network may be an RNN (Recurrent Neural Network) in which part of the hidden layer is replaced with an LSTM (Long short-term memory).

When the parameter estimation model MDL is implemented by a neural network, the model data 332 includes, for example, connection information on how units included in each of a plurality of layers constituting the neural network are connected to each other, and connection information. It includes various information such as coupling coefficients given to data input/output between units.

The connection information includes, for example, information such as the number of units included in each layer, information specifying the type of unit to which each unit is connected, the activation function of each unit, and gates provided between units in the hidden layer. include. The activation function may be, for example, a normalized linear function (ReLU function), a sigmoid function, a step function, or other functions. The gate selectively passes or weights data communicated between units, eg, depending on the value returned by the activation function (eg, 1 or 0). The coupling coefficient includes, for example, a weight given to output data when data is output from a unit in a certain layer to a unit in a deeper layer in a hidden layer of a neural network. Further, the coupling coefficient may include a bias component specific to each layer.

Returning to the explanation of the flowchart in FIG. 8. Next, the determining unit 324 determines recommended parameters that the user should select during the n-th (that is, current) walking training based on the output result of the parameter estimation model MDL (step S106).

Next, the determining unit 324 transmits the determined recommended parameters via the communication unit 302 to the terminal device 200 of the user who has undergone the n-th walking training (step S108). In response to this, the control unit 220 of the terminal device 200 displays the content on the touch panel 204 with the recommended parameter selected in advance, before the user makes a selection. This allows the user to know the menu of walking training to be undertaken this time without the guidance of an expert. At this time, the user does not necessarily have to select the recommended parameters, but can select any other training parameters.

Next, the acquisition unit 322 waits until the n-th walking training is finished (step S110), and when the n-th walking training is finished, the acquisition unit 322 receives the n-th walking training from the terminal device 200 via the communication unit 302. Gait training measurement data and parameter selection data of the user who has performed walking training (that is, this time) are acquired (step S112). The n-th walking training measurement data and parameter selection data acquired in the process of S112 are used in the process of S104 in the next cycle.

Next, the learning unit 326 uses the n-1st walking training measurement data and parameter selection data acquired in the process of S112 of the previous cycle, and the n-th walking training measurement data and parameter selection data acquired in the process of S102 of the current cycle. Teacher data is generated based on the questionnaire response data and the n-th parameter selection data acquired in the process of S112 in the current cycle (step S114).

Teacher data is a data set in which correct output data to be output by a machine learning model is associated with certain input data as a teacher label (also referred to as a target). For example, the learning unit 326 inputs input data that includes the (n-1)th walking training measurement data and parameter selection data, and nth questionnaire response data, and output data that includes the nth parameter selection data. A dataset combining these is generated as training data.

Next, the learning unit 326 learns the parameter estimation model MDL based on the generated teacher data (step S116).

FIG. 10 shows an example of a database that includes walking training measurement data, parameter selection data, and questionnaire response data. For example, when n is 3, the learning unit 326 uses the walking training measurement data and parameter selection data for the second walking training session and the questionnaire response data for the third walking training session as input data of teacher data. Then, the parameter selection data for the third time of walking training is set as the output data of the teacher data.

Then, the learning unit 326 inputs the combination of the second walking training measurement data and parameter selection data, and the third questionnaire response data to the parameter estimation model MDL as input data of teacher data. When the parameter estimation model MDL receives these data, it outputs training parameters to be selected by the user during the third walking training as recommended parameters.

The learning unit 326 learns the parameter estimation model MDL so that the third recommended parameters output by the parameter estimation model MDL match the parameters represented by the parameter selection data obtained during the third walking training. In other words, the learning unit 326 learns the parameter estimation model MDL so that the third recommended parameter output by the parameter estimation model MDL approaches the parameter actually selected by the user during the third walking training. For example, the learning unit 326 calculates the difference between parameters, and learns the parameter estimation model MDL using stochastic gradient descent or the like so that the difference becomes small.

After learning the parameter estimation model MDL as described above, the learning unit 326 updates the model data 332 stored in the storage unit 330. This completes the processing of this flowchart.

According to the embodiment described above, the server 300 receives information from the walking assist device 100, which measures the movement of the user while assisting the user's walking, via the terminal device 200, for the n-th walking training session. Obtain walking training measurement data. The server 300 acquires parameter selection data for the n-th walking training from the terminal device 200. Furthermore, the server 300 acquires questionnaire response data from the (n+1)th walking training session from the terminal device 200. When the server 300 acquires the nth walking training measurement data and parameter selection data, and the n+1st questionnaire response data, it inputs these data into the parameter estimation model MDL and uses the output results of the parameter estimation model MDL. Based on this, recommended parameters to be used as guidelines for the user's (n+1)th walking training are determined. In this way, by using machine learning, guidelines for walking training for the user can be appropriately determined without the guidance of experts such as doctors and physical therapists.

<Modified example of embodiment>
Modifications of the above-described embodiment will be described below. In the embodiment described above, the parameter estimation model MDL is described as being implemented by a deep neural network, but the present invention is not limited to this. For example, the parameter estimation model MDL may be implemented by a combination of a topic model and a Bayesian network.

FIG. 11 is a diagram for explaining a topic model, and FIG. 12 is a diagram showing an example of a Bayesian network. As shown in Figure 11, the topic model considers multiple gait training measurement data collected each time gait training is repeated, multiple parameter selection data, and multiple questionnaire response data as one matrix. Sometimes, techniques such as LDA (Latent Dirichlet Allocation) and PLSA are used to classify each element of a matrix into one of a plurality of topics (clusters) such as T1, T2, and T3.

As illustrated in FIG. 12, each topic classified by the topic model is input to the Bayesian network. A Bayesian network outputs estimated parameters by probabilistic inference from input topics. The determining unit 324 may determine recommended parameters by using a combination of such a topic model and a Bayesian network.

Furthermore, in the embodiment described above, the learning unit 326 determines the recommended parameters for the n-th time from the input data including the (n-1)th walking training measurement data and parameter selection data, and the n-th questionnaire response data. Although the description has been made assuming that the parameter estimation model MDL is learned so as to be output, the present invention is not limited to this.

For example, the learning unit 326 selects the n-th gait training measurement data from the input data including the nk-th walking training measurement data and parameter selection data and the n-th questionnaire response data, which are earlier than the n-1-th walking training training. The parameter estimation model MDL may be trained to output recommended parameters. k is a natural number greater than or equal to 1 and smaller than n. In other words, the n−kth time may include the n−1th time.

Furthermore, the learning unit 326 calculates not only the n-kth training but also the n-th walking training measurement data and parameter selection data from a total of j pieces of walking training measurement data and parameter selection data from the n-kth to the n-kjth training. The parameter estimation model MDL may be trained to output recommended parameters. j is any natural number smaller than n. For example, when n is 10, k is 1, and j is 4, the learning unit 326 acquires the 10th gait training measurement data and parameter selection data for a total of 5 gait training sessions from the 5th to the 9th gait training session. The parameter estimation model MDL is trained to output the recommended parameters for the second time.

The embodiment described above can be expressed as follows.
at least one memory storing a program;
at least one processor;
By the processor executing the program,
Obtaining first data representing a measurement result of the user's movement during the n-th walking training from a walking assist device that measures the movement of the user when walking while assisting the user's walking;
Obtaining second data representing a selection result of at least one parameter selected by the user from a plurality of parameters serving as a guideline for the n-th walking training from a terminal device available to the user;
When at least the first data and the second data of the user who has performed the m-th walking training are input, recommended parameters to be used as guidelines for the m+k-th walking training of the user are output. The acquired first data and second data from the user's n-th walking training are input to the model trained in determining the recommended parameters to be used as guidelines for the user's (n+k)th walking training based on the output results of the model;
An information processing device configured as follows.

Although the mode for implementing the present invention has been described above using embodiments, the present invention is not limited to these embodiments in any way, and various modifications and substitutions can be made without departing from the gist of the present invention. can be added.

DESCRIPTION OF SYMBOLS 1...Walking assistance system, 100...Walking assist device, 102...Main frame, 103...Subframe, 104...Drive source, 105...Control device, 106...Hip joint angle sensor, 107...Battery, 200...Terminal device, 202...Communication Department, 204...Touch panel, 220...Control unit, 230...Storage unit, 300...Server, 302...Communication unit, 320...Control unit, 322...Acquisition unit, 324...Decision unit, 326...Learning unit, 330...Storage unit

Claims (6)

First data representing the measurement result of the user's movement during the n-th walking training is acquired from a walking assist device that measures the movement of the user while assisting the user's walking, and the user an acquisition unit that acquires second data representing a selection result of at least one parameter selected by the user from among a plurality of parameters serving as a guideline for the n-th walking training from a terminal device that can be used;
Teacher data that is a combination of at least the first data and the second data of the user who has performed the m-th walking training, and recommended parameters that should be used as guidelines for the m+k-th walking training of the user. The first data and the second data acquired by the acquisition unit at the time of the user's n-th walking training are input to the model learned based on the model, and the first data and the second data are input to the model learned based on the model. a determining unit that determines the recommended parameters to be used as a guideline for the user's (n+k)th walking training based on the output result of the model into which data has been input;
An information processing device comprising: The acquisition unit further acquires third data representing the user's response to the n+kth walking training questionnaire from the terminal device,
The determining unit inputs the first data and the second data of the user during the n-th walking training and the third data of the user during the n+k-th walking training into the model, determining the recommended parameters to be used as guidelines for the n+kth walking training of the user, based on the output results of the model into which the first data, the second data, and the third data are input;
The information processing device according to claim 1. The model is any one of a deep neural network, a topic model, and a Bayesian network, or a combination of multiple models.
The information processing device according to claim 1 or 2. The recommended parameters for the m-th walking training of the user outputted by the model when the first data and the second data of the user for the m-kth time are input to the model, and the recommended parameters for the m-th walking training of the user. further comprising a learning unit that learns the model so that the parameter selected by the user from among the plurality of parameters matches during walking training;
The information processing device according to any one of claims 1 to 3. The computer is
Obtaining first data representing a measurement result of the user's movement during the n-th walking training from a walking assist device that measures the movement of the user when walking while assisting the user's walking;
Obtaining second data representing a selection result of at least one parameter selected by the user from a plurality of parameters serving as a guideline for the n-th walking training from a terminal device available to the user;
Teacher data that is a combination of at least the first data and the second data of the user who has performed the m-th walking training, and recommended parameters that should be used as guidelines for the m+k-th walking training of the user. The first data and the second data obtained during the n-th walking training of the user are input to the model learned based on the model, and the first data and the second data are input. determining the recommended parameters to be used as guidelines for the user's (n+k)th walking training based on the output results of the model;
Information processing method. to the computer,
acquiring first data representing a measurement result of the user's movement during the n-th walking training from a walking assist device that measures the movement of the user when walking while assisting the user's walking;
acquiring, from a terminal device available to the user, second data representing a selection result of at least one parameter selected by the user from among a plurality of parameters serving as a guideline for the n-th walking training;
Teacher data that is a combination of at least the first data and the second data of the user who has performed the m-th walking training, and recommended parameters that should be used as guidelines for the m+k-th walking training of the user. The first data and the second data obtained during the n-th walking training of the user are input to the model learned based on the model, and the first data and the second data are input. determining the recommended parameters to be used as guidelines for the user's (n+k)th walking training based on the output results of the model;
A program to run.

Images