Learning system, walking training system, system, method, program, and learning completion model

A walking training and learning system technology, applied in the field of learning completed models, can solve problems such as difficult settings for training staff

Active Publication Date: 2020-12-29
TOYOTA JIDOSHA KK
View PDF7 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, it is difficult to train staff to effectively set

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Learning system, walking training system, system, method, program, and learning completion model
  • Learning system, walking training system, system, method, program, and learning completion model
  • Learning system, walking training system, system, method, program, and learning completion model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach 1

[0054] Hereinafter, Embodiment 1 will be described with reference to the drawings.

[0055] (system structure)

[0056] figure 1 It is an overall schematic diagram showing a configuration example of the rehabilitation support system according to the first embodiment. The rehabilitation support system (rehabilitation system) of this embodiment is mainly composed of a walking training device 100 , an external communication device 300 , and a server (server device) 500 .

[0057] Walking training device 100 is a specific example of a rehabilitation assisting device that assists a trainer (user) 900 in rehabilitation (rehabilitation exercise). The gait training device 100 is a device for a trainer 900 who is a hemiplegic patient with one leg paralyzed to perform gait training in accordance with the guidance of a training staff 901 . Here, the training worker 901 may be a therapist (physiotherapist) or a doctor, and may also be called a training instructor, a training helper, or...

Embodiment approach 2

[0196] In Embodiment 1, the actual measurement value of the walking FIM was used as the index showing the degree of recovery, but in this embodiment, the estimated value of the walking FIM is used as the index showing the degree of recovery. For example, as input data for the learned model described in Embodiment 1, an estimated value of walking FIM is used. Hereinafter, the processing of the gait training system of this embodiment will be described.

[0197] (Inference of walking FIM)

[0198] First, processing of the server 500 will be described. The server 500 generates not only the learned model described in Embodiment 1, but also a learning model that outputs an estimated value of walking FIM. Hereinafter, for clarity of description, a learning model for outputting recommended setting parameters is referred to as a first learning model or a learning model for recommended setting parameters. On the other hand, the learning model for outputting the estimated value of wal...

Embodiment approach 3

[0230] In Embodiment 3, server 500 divides trainers 900 into a plurality of groups. Furthermore, the server 500 constructs a learning model for each group. Specifically, server 500 clusters trainers based on trainer data. In addition, since the basic configuration and processing of the system of Embodiment 3 are the same as those of Embodiments 1 and 2, description thereof will be appropriately omitted. In addition, the control unit 510 generates at least one of the first learning model and the second learning model for each group.

[0231] use Figure 12 The processing method of this embodiment will be described. Figure 12 It is a flowchart for explaining the processing of the control unit 510. First, similarly to Embodiment 1, the control unit 510 acquires rehabilitation data (S21). Then, the control unit 510 groups the trainers (S22). As grouped training data, the values ​​of the initial walking FIM and SIAS can be used. For example, trainers whose initial walking F...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The present invention provides a learning system, a walking training system, method, system, program, and a learning completion model for performing walking training with appropriate setting parameters. The learning system according to an embodiment of the present invention is provided with: a data acquisition unit that acquires rehabilitation data from a walking training system provided with an actuator that assists a walking action of a trainee, and a control unit that controls the actuator on the basis of a set parameter; a data generation unit that generates rehabilitation data including an index indicating the degree of recovery of the trainee and a setting parameter as learning data; and a learning unit that uses the learning data to perform machine learning, thereby generating a learning model in which the recommended value of the setting parameter is output using the index as an input.

Description

technical field [0001] The present invention relates to a learning system, a walking training system, a method, a system, a program and a learned model. Background technique [0002] In order to perform avoidance actions against falls, a technique is known in which a subject wears a multi-joint structure for detecting a motion state and detects the start of a fall. (For example, Japanese Patent Application Laid-Open No. 2010-22439). [0003] When a patient (hereinafter referred to as trainer) undergoes rehabilitation, FIM (Functional Independence Measure: Functional Independence Measure) is included as an index indicating the degree of recovery of the trainer. For example, with regard to walking training for patients with paralyzed legs, FIM walking on level ground is used as an index showing the degree of recovery. The FIM is represented by values ​​in seven stages of 1 to 7 corresponding to the assist amount. In addition, the level walking FIM represents the walking abi...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): A61H3/00A61H1/02A63B21/00A63B22/02A63B24/00G16H20/30G16H40/63
CPCA61H3/00A61H1/0218A61H1/0237A63B22/0235A63B21/00181A63B24/0087G16H20/30G16H40/63A61H2003/006A61H2003/007A61H2201/5058A61H2201/5069A61H2201/5084A61H2201/5097A61H2201/165A61H2230/105A61H2201/5064A61H2201/5092G06N3/084G16H50/20G16H50/30G06N3/044G06N3/045A61H3/008
Inventor 大槻将久太场裕昌中岛一诚小林诚今井田昌幸
Owner TOYOTA JIDOSHA KK
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products