CN-121996056-A - Control method, device and equipment based on electroencephalogram signals

CN121996056ACN 121996056 ACN121996056 ACN 121996056ACN-121996056-A

Abstract

The application provides a control method, a device and equipment based on an electroencephalogram signal. The method comprises the steps of outputting a first visual signal under the condition that a user is connected with signal acquisition equipment, wherein the first visual signal is used for guiding the user to conduct motor imagery related to a first task, receiving an electroencephalogram signal of the motor imagery of the user in the process of outputting the first visual signal, analyzing the electroencephalogram signal by utilizing a pre-trained classification model to obtain a label of the electroencephalogram signal and a first instruction, wherein the first instruction is a control instruction for the first task, sending the first instruction to equipment corresponding to the first task, and training the classification model based on a first fusion signal, wherein the first fusion signal is a signal obtained by fusing the electroencephalogram signal induced by the visual signal, the electroencephalogram signal induced by the auditory signal and a body sign signal. The application can accurately identify the intention of the user, generate a correct control instruction and realize the accurate control of external equipment according to the brain electrical signal.

Inventors

ZHENG ZHIMIN
LIU HAOPENG
Lu Tongchao
CUI CHUNFENG
LIU GUANGYI
WANG QIXING
WANG FEI
LIU JIANJUN
YUAN GEFEI

Assignees

中国移动通信有限公司研究院
中国移动通信集团有限公司

Dates

Publication Date: 20260508
Application Date: 20241104

Claims (11)

1. The control method based on the electroencephalogram signal is characterized by comprising the following steps of: Outputting a first visual signal for guiding a user to perform motor imagery related to a first task under the condition that the user establishes connection with the signal acquisition device; Receiving an electroencephalogram signal of motor imagery of the user in a first visual signal output process; Analyzing the electroencephalogram signals by utilizing a pre-trained classification model to obtain labels of the electroencephalogram signals and first instructions, wherein the first instructions are control instructions for the first task; Sending the first instruction to equipment corresponding to the first task; the classification model is obtained by training based on a first fusion signal, wherein the first fusion signal is a signal obtained by fusing an electroencephalogram signal induced by a visual signal, an electroencephalogram signal induced by an auditory signal and a sign signal.
2. The method of claim 1, wherein prior to analyzing the electroencephalogram signal with a pre-trained classification model, the method further comprises: Judging whether the electroencephalogram signal is in a motion state or not; and if the electroencephalogram signal is in a dynamic state, analyzing the electroencephalogram signal by using a pre-trained classification model.
3. The method according to claim 2, wherein the method further comprises: if the electroencephalogram signal is in an idle state, analyzing the electroencephalogram signal according to a steady-state visual evoked potential SSVEP algorithm to obtain an analysis result; And if the analysis result indicates that the SSVEP response with the preset frequency is included, outputting a first instruction.
4. The method according to claim 1, wherein the method further comprises: acquiring off-line training data of a plurality of users, wherein the off-line training data comprise electroencephalogram signals and sign signals of the users; And classifying and modeling the offline training data to obtain classification models matched with different users.
5. The method according to claim 1 or 4, characterized in that the method further comprises: Outputting a second visual signal and an acoustic signal under the condition of offline training of the user, wherein the second visual signal and the acoustic signal are used for prompting the user to perform motor imagery; Continuously outputting a third visual signal in a first time period, and receiving an electroencephalogram signal and a sign signal of motor imagery of the user in the third visual signal output process, wherein the electroencephalogram signal comprises the electroencephalogram signals of motor imagery of N body parts, the sign signal comprises the sign signals of N body parts in the motor imagery process, and N is a positive integer; Fusing the electroencephalogram signal and the sign signal to obtain a first fused signal; And generating a classification model matched with the user according to the first fusion signal.
6. The method of claim 5, wherein the second visual signal corresponds to images indicating a plurality of directions, and wherein the images in each direction blink at a preset frequency.
7. The method of claim 5, wherein the electroencephalogram signals obtained from offline training of the user have corresponding labels for indicating motor imagery content of the user.
8. An electroencephalogram signal-based control device, characterized by comprising: The first output module is used for outputting a first visual signal under the condition that a user establishes connection with the signal acquisition equipment, and the first visual signal is used for guiding the user to perform motor imagery related to a first task; The first receiving module is used for receiving an electroencephalogram signal of motor imagery of the user in a first visual signal output process; The first processing module is used for analyzing the electroencephalogram signals by utilizing a pre-trained classification model to obtain labels of the electroencephalogram signals and first instructions, wherein the first instructions are control instructions for the first task; The first sending module is used for sending the first instruction to the equipment corresponding to the first task; the classification model is obtained by training based on a first fusion signal, wherein the first fusion signal is a signal obtained by fusing an electroencephalogram signal induced by a visual signal, an electroencephalogram signal induced by an auditory signal and a sign signal.
9. An electronic device comprising a transceiver, a processor, a memory and a program or instructions stored on the memory and executable on the processor, the processor implementing the steps of the electroencephalogram signal based control method according to any one of claims 1 to 7 when the program or instructions are executed by the processor.
10. A readable storage medium having stored thereon a program or instructions, which when executed by a processor, realizes the steps of the electroencephalogram signal based control method according to any one of claims 1 to 7.
11. A computer program product having a program or instructions stored thereon, comprising computer instructions which, when executed by a processor, implement the steps of the electroencephalogram signal based control method according to any one of claims 1 to 7.

Description

Control method, device and equipment based on electroencephalogram signals Technical Field The present application relates to the field of data services, and in particular, to a control method, apparatus, and device based on an electroencephalogram signal. Background Brain waves have unique time-frequency characteristics, and the state of the brain is reflected in the brain waves. The more frequent the brain activity, the more frequent the electrical activity. Brain waves of various senses and activities have unique spatial characteristics. Different areas of the brain have different functions, specific correlation characteristics exist among the areas, and the movement and communication functions of the upper and lower limbs can be controlled based on the brain-computer interface. Electroencephalogram can be stimulated by active imagination, and a scene is motor imagination, namely, when a person imagines the movement of own limbs (or muscles) but does not have actual movement output, a specific brain region of the person is still activated. The user intention can be judged by analyzing the brain electrical signals and detecting and identifying the activation effects of different brain areas, so that the direct communication and control between the human brain and external equipment are realized. Most of the detection equipment related to the brain electricity is still in the stage of academic research and clinical diagnosis at present, and one of the characteristics is that the environmental requirement on signal acquisition is high. The vast majority of brain electrical signals belong to spontaneous random signals, particularly untrained subjects have difficulty in controlling the motor imagery process of the subjects and sending out clean and clear motor imagery signals, so that the signal-to-noise ratio of the acquired signals is low, and the accuracy of the identified user intention is low. Disclosure of Invention The application aims to provide a control method, a control device and control equipment based on an electroencephalogram signal, which solve the problem of low user accuracy identified according to the electroencephalogram signal in the prior art. To achieve the above object, an embodiment of the present application provides a control method based on an electroencephalogram signal, including: Outputting a first visual signal for guiding a user to perform motor imagery related to a first task under the condition that the user establishes connection with the signal acquisition device; Receiving an electroencephalogram signal of motor imagery of the user in a first visual signal output process; Analyzing the electroencephalogram signals by utilizing a pre-trained classification model to obtain labels of the electroencephalogram signals and first instructions, wherein the first instructions are control instructions for the first task; Sending the first instruction to equipment corresponding to the first task; the classification model is obtained by training based on a first fusion signal, wherein the first fusion signal is a signal obtained by fusing an electroencephalogram signal induced by a visual signal, an electroencephalogram signal induced by an auditory signal and a sign signal. Optionally, before analyzing the electroencephalogram signal with the pre-trained classification model, the method further comprises: Judging whether the electroencephalogram signal is in a motion state or not; and if the electroencephalogram signal is in a dynamic state, analyzing the electroencephalogram signal by using a pre-trained classification model. Optionally, the method further comprises: If the electroencephalogram signal is in an idle state, analyzing the electroencephalogram signal according to a Steady-state visual evoked potential (SSVEP) algorithm to obtain an analysis result; And if the analysis result indicates that the SSVEP response with the preset frequency is included, outputting a first instruction. Optionally, the method further comprises: acquiring off-line training data of a plurality of users, wherein the off-line training data comprise electroencephalogram signals and sign signals of the users; And classifying and modeling the offline training data to obtain classification models matched with different users. Optionally, the method further comprises: Outputting a second visual signal and an acoustic signal under the condition of offline training of the user, wherein the second visual signal and the acoustic signal are used for prompting the user to perform motor imagery; Continuously outputting a third visual signal in a first time period, and receiving an electroencephalogram signal and a sign signal of motor imagery of the user in the third visual signal output process, wherein the electroencephalogram signal comprises the electroencephalogram signals of motor imagery of N body parts, the sign signal comprises the sign signals of N body parts in the motor imagery process, and N is a