Granted Patent B2

US 12,263,345 · App. 17/243,539 · Granted Apr 1, 2025

Inventors: Yi-Jin Huang (New Taipei, TW); Yin-Hsong Hsu (New Taipei, TW); Wei-Hao Chang (New Taipei, TW); Chien-Hung Li (New Taipei, TW)

Assignee: Acer Incorporated

A61N1/36171A61B5/395A61B5/397A61N1/36139

Abstract

Claims (32)

1. An electronic device, comprising:

an electromyography value measurement circuit;

a storage circuit, storing a code;

an electrode patch; and

a processor, coupled to the electromyography value measurement circuit, the storage circuit, and the electrode patch, and configured by the code to execute:

individually applying a corresponding first current to a body part of a user in a plurality of consecutive time intervals through the electrode patch, wherein the plurality of consecutive time intervals comprise an i-th time interval to an (i+N)-th time interval, where i and N are positive integers;

obtaining a plurality of electromyography values of the body part in each of the plurality of consecutive time intervals through the electromyography value measurement circuit;

determining a second current corresponding to an (i+N+1)-th time interval based on the first current corresponding to each of the plurality of consecutive time intervals, the body part, at least one personal information of the user, and the electromyography values of each of the plurality of consecutive time intervals, comprising:

converting the electromyography values in each of the plurality of consecutive time intervals into a first vector;

converting the first current corresponding to each of the plurality of consecutive time intervals, the body part, and the at least one personal information of the user into a second vector, and splicing the first vector and the second vector into a specific matrix;

converting the specific matrix into a third vector, and converting the third vector into a reference coefficient; and

multiplying the reference coefficient by a constant to generate the second current corresponding to the (i+N+1)-th time interval; and

applying the second current to the body part of the user in the (i+N+1)-th time interval through the electrode patch.

2. The electronic device according to claim 1 , wherein the processor is configured to perform:

obtaining a long short term memory model, wherein the long short term memory model comprises a 1-st hidden layer to an (N+1)-th hidden layer connected in series;

respectively inputting the individual electromyography values of the i-th time interval to the (i+N)-th time interval into the 1-st hidden layer to the (N+1)-th hidden layer, wherein the long short term memory model generates the first vector in response to the individual electromyography values of the i-th time interval to the (i+N)-th time interval.

3. The electronic device according to claim 1 , wherein the processor is configured to perform:

inputting the first current corresponding to each of the plurality of consecutive time intervals, the body part, and the at least one personal information of the user into a first deep neural network, wherein the first deep neural network generates the second vector in response to the first current corresponding to each of the plurality of consecutive time intervals, the body part, and the at least one personal information of the user.

4. The electronic device according to claim 1 , wherein the processor is configured to perform:

inputting the specific matrix into a second deep neural network, wherein the second deep neural network generates the third vector in response to the specific matrix.

5. The electronic device according to claim 1 , wherein the processor is configured to perform:

converting the third vector into the reference coefficient based on a hyperbolic tangent function, wherein the reference coefficient is between −1 and 1.

6. The electronic device according to claim 1 , wherein the processor is further configured to perform:

obtaining a plurality of electromyography values of the body part in the (i+N+1)-th time interval through the electromyography value measurement circuit;

determining a third current corresponding to an (i+N+2)-th time interval based on the second current, the body part, the at least one personal information of the user, and the individual electromyography values of the (i+1)-th time interval to the (i+N+1)-th time interval; and

applying the third current to the body part of the user through the electrode patch in the (i+N+2)-th time interval.

7. The electronic device according to claim 1 , wherein before applying the second current to the body part of the user through the electrode patch in the (i+N+1)-th time interval, the processor is further configured to perform:

obtaining a median frequency value of each of the plurality of consecutive time intervals based on the electromyography values of each of the plurality of consecutive time intervals;

determining a plurality of frequency value slopes based on the individual median frequency values of an (i+k)-th time interval to the (i+N)-th time interval in the plurality of consecutive time intervals, where k≤N−1; and

stopping to apply the second current to the body part of the user in response to judging the frequency value slopes as satisfying a first condition or a second condition, otherwise applying the second current to the body part of the user through the electrode patch in the (i+N+1)-th time interval.

8. The electronic device according to claim 7 , wherein in response to judging n consecutive frequency value slopes as all positive and individual absolute values thereof as all less than a first preset value, the frequency value slopes are judged as satisfying the first condition, otherwise the frequency value slopes are judged as not satisfying the first condition.

9. The electronic device according to claim 7 , wherein in response to judging n consecutive frequency value slopes as all negative or individual absolute values thereof as greater than a second preset value, the frequency value slopes are judged as satisfying the second condition, otherwise the frequency value slopes are judged as not satisfying the second condition.

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (16)