Application US20200405189

LEARNING SYSTEM, WALKING TRAINING SYSTEM, METHOD, PROGRAM, AND TRAINED MODEL
[+] Show Details

US20200405189

1. A learning system comprising: (4) (3)

a data acquisition unit configured to acquire rehabilitation data from a walking training system comprising an actuator configured to assist a walking motion of a trainee, a sensor configured to detect data regarding the walking motion assisted by the actuator, and a control unit configured to control the actuator in accordance with a setting parameter;

a data generation unit configured to generate the rehabilitation data as learning data, the rehabilitation data comprising detection data, which is based on the results of detection by the sensor, and the setting parameter; and

a learning unit configured to perform machine learning using the learning data, thereby generating a learning model that receives the detection data and outputs a recommended value of the setting parameter.

2. The learning system according to claim 1, wherein the learning unit performs supervised learning using an actual setting value of the setting parameter actually set by a training staff member as teacher data. (0)

3. The learning system according to claim 1, wherein (0) (3)

4. The learning system according to claim 1, wherein (0) (3)

10. A non-transitory computer readable medium storing a trained model for causing a computer to function so as to output a recommended value of a setting parameter in a walking training system based on rehabilitation data for evaluation acquired by the walking training system, (1) (1)

5. A learning method comprising the steps of: (4) (3)

acquiring rehabilitation data from a walking training system comprising an actuator configured to assist a walking motion of a trainee who performs walking training, a sensor configured to detect data regarding the walking motion assisted by the actuator, and a control unit configured to control the actuator in accordance with a setting parameter;

generating rehabilitation data as learning data, the rehabilitation data comprising detection data, which is based on the results of the detection by the sensor, and a setting parameter regarding setting of the walking training system; and

performing machine learning using the learning data, thereby generating a learning model that receives the detection data and outputs the setting parameter.

6. The learning method according to claim 5, wherein supervised learning is performed using an actual setting value of the setting parameter actually set by a training staff member as teacher data. (0)

7. The learning method according to claim 5, wherein (0) (3)

8. The learning method according to claim 5, wherein (0) (3)

9. A non-transitory computer readable medium storing a program for causing a computer to execute the learning method according to claim 5. (0)

11. A walking training system comprising: (3) (4)

an actuator configured to assist a walking motion of a trainee;

a sensor configured to detect data regarding the walking motion assisted by the actuator;

a control unit configured to control the actuator in accordance with a setting parameter; and

a trained model that receives detection data in accordance with the results of the detection by the sensor and outputs a recommended value of the setting parameter.

12. The walking training system according to claim 11, wherein (0) (3)

13. The walking training system according to claim 11, wherein (0) (2)

14. The walking training system according to claim 11, wherein the recommended value of the setting parameter is updated based on the detection data sequentially acquired during the training of the trainee. (0)

15. An operation method of a walking training system comprising: (2) (5)

an actuator configured to assist a walking motion of a trainee;

a sensor configured to detect data regarding the walking motion assisted by the actuator; and

a control unit configured to control the actuator in accordance with a setting parameter, the operation method comprising the steps of:

acquiring detection data in accordance with results of the detection by the sensor; and

receiving detection data in accordance with results of the detection by the sensor and outputting a recommended value of the setting parameter.

16. The operation method according to claim 15, wherein (1) (3)

the sensor is provided to detect a plurality of motion amounts in the walking motion of the trainee,

the walking training system determines that the walking motion corresponds to abnormal walking when at least one of the motion amounts matches one of predetermined abnormal walking criteria, and

the detection data includes the results of the evaluation regarding whether the walking motion corresponds to the abnormal walking.

18. The operation method according to claim 16, wherein the recommended value of the setting parameter is updated based on the detection data sequentially acquired during the training of the trainee. (0)

17. The operation method according to claim 15, wherein (0) (2)

View Abstract and Specification Size

PDF with Images and Document Face >

Full Text Publication >

Application US20200405189

LEARNING SYSTEM, WALKING TRAINING SYSTEM, METHOD, PROGRAM, AND TRAINED MODEL

Patent Matrix® Search