CN-115607168-B - Control method and device based on brain electrical signals, electronic equipment and storage medium

CN115607168BCN 115607168 BCN115607168 BCN 115607168BCN-115607168-B

Abstract

The invention discloses a control method and device based on an electroencephalogram signal, electronic equipment and a storage medium. The method comprises the steps of obtaining an electroencephalogram signal of a target object, extracting target class identification feature parameters corresponding to target class identification features in the electroencephalogram signal, determining a violation identification result in the electroencephalogram signal based on the target class identification feature parameters and target class reference parameters, wherein the target class identification features and the target class reference parameters are determined in advance based on feature classification results of sample electroencephalogram signals, determining an action state of the target object based on the violation identification results, and executing processing operation corresponding to the action state. The signal artifacts of the electroencephalogram signals are classified through the predetermined target class identification features and the target class reference parameters, so that the complexity of the algorithm is reduced, the problem that the conventional myoelectricity classification algorithm cannot be embedded into a chip is solved, and the control operation based on the electroencephalogram signal artifact classes is realized.

Inventors

QIAN JINHUI
WU HANFENG
WANG XIAOAN

Assignees

脑陆(重庆)智能科技研究院有限公司

Dates

Publication Date: 20260505
Application Date: 20221031

Claims (8)

1. The control method based on the electroencephalogram signal is characterized by comprising the following steps of: acquiring an electroencephalogram signal of a target object, and extracting target class identification characteristic parameters corresponding to target class identification characteristics in the electroencephalogram signal, wherein the target class is at least one of a body myoelectricity class, a face myoelectricity class and an eye myoelectricity class; Determining an artifact identification result in the electroencephalogram signal based on the target class identification characteristic parameter and the target class reference parameter, wherein the target class identification characteristic and the target class reference parameter are determined in advance based on a characteristic classification result of a sample electroencephalogram signal, wherein the sample electroencephalogram signal is the electroencephalogram signal containing different signal artifacts; Determining the action state of the target object based on the artifact identification result, and executing processing operation corresponding to the action state; The extracting the target class identification characteristic parameters corresponding to the target class identification characteristics in the electroencephalogram signal comprises: Extracting the characteristics of the target class identification characteristics from the electroencephalogram signals to obtain extracted electroencephalogram characteristics; Performing dimension reduction processing on the extracted brain electrical characteristics to obtain the target class identification characteristic parameters; The target category reference parameters include category reference parameters corresponding to a target category and non-category reference parameters corresponding to a non-target category, and the determining an artifact identification result in the electroencephalogram signal based on the target category identification feature parameters and the target category reference parameters includes: Determining a first distance between the target class identification feature parameter and the class reference parameter, and a second distance between the target class identification feature parameter and the non-class reference parameter; and taking the category corresponding to the smaller distance in the first distance and the second distance as the artifact identification result.
2. The method of claim 1, wherein the determining of the target class identification feature and the target class reference parameter comprises: acquiring a sample electroencephalogram signal and a marking category of the sample electroencephalogram signal, wherein the marking category of the sample electroencephalogram signal is determined based on the category of signal artifacts in the sample electroencephalogram signal; Extracting sample category identification characteristic parameters in the sample electroencephalogram signals to obtain sample electroencephalogram characteristic points of the sample electroencephalogram signals; Determining category reference point position information corresponding to each of the marking categories based on the marking category of each of the sample electroencephalogram signals and the sample electroencephalogram characteristic points of each of the sample electroencephalogram signals; Determining the distance between the marking categories according to the category reference point position information corresponding to each marking category; When the distance between the marking categories is larger than a set threshold value, the sample category identification feature is used as the target category identification feature, and category reference point position information corresponding to each marking category is used as the target category reference parameter; And when the distance between the mark categories is not greater than a set threshold, repeating the steps until the distance between the mark categories determined based on the extracted sample category identification feature parameters is greater than the set threshold, taking the sample category identification feature as the target category identification feature, and taking the category reference point position information corresponding to the current mark category as the target category reference parameter.
3. The method according to claim 2, wherein determining the target class reference parameter based on the spatial distribution region of the sample electroencephalogram feature points corresponding to each of the marker classes includes: and taking the coordinate characteristic values of the sample electroencephalogram characteristic points corresponding to the marking categories as target category reference parameters corresponding to the marking categories.
4. The method of claim 1, wherein the performing the processing operation corresponding to the action state comprises: determining posture adjustment prompt information according to the action state, and outputting the posture adjustment prompt information; And acquiring an electroencephalogram signal of the target object after executing the posture adjustment mode corresponding to the posture adjustment prompt information as a target electroencephalogram signal.
5. The method of claim 1, wherein the performing the processing operation corresponding to the action state comprises: And determining an action executing mechanism corresponding to the action state, and controlling the action executing mechanism to execute corresponding movement operation.
6. An electroencephalogram signal-based control device, characterized by comprising: The device comprises an identification feature extraction module, a target class identification feature parameter extraction module and a target class identification feature extraction module, wherein the identification feature extraction module is used for obtaining an electroencephalogram signal of a target object and extracting target class identification feature parameters corresponding to target class identification features in the electroencephalogram signal, and the target class is at least one of a body myoelectricity class, a face myoelectricity class and an eye myoelectricity class; the artifact identification result determining module is used for determining an artifact identification result in the electroencephalogram signal based on the target category identification characteristic parameter and the target category reference parameter, wherein the target category identification characteristic and the target category reference parameter are determined in advance based on a characteristic classification result of a sample electroencephalogram signal; the processing operation execution module is used for determining the action state of the target object based on the artifact identification result and executing the processing operation corresponding to the action state; The identification feature extraction module is specifically configured to: Performing feature extraction of target class identification features on the electroencephalogram signals to obtain extracted electroencephalogram features; Performing dimension reduction processing on the extracted brain electrical characteristics to obtain target category identification characteristic parameters; the target category reference parameters comprise category reference parameters corresponding to target categories and non-category reference parameters corresponding to non-target categories, and the artifact identification result determining module is specifically configured to: Determining a first distance between the target class identification feature parameter and the class reference parameter and a second distance between the target class identification feature parameter and the non-class reference parameter; And taking the category corresponding to the smaller distance in the first distance and the second distance as an artifact identification result.
7. An electronic device, the electronic device comprising: at least one processor, and A memory communicatively coupled to the at least one processor, wherein, The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the electroencephalogram-based control method of any one of claims 1-5.
8. A computer readable storage medium, characterized in that the computer readable storage medium stores computer instructions for causing a processor to implement the electroencephalogram signal based control method according to any one of claims 1 to 5 when executed.

Description

Control method and device based on brain electrical signals, electronic equipment and storage medium Technical Field The present invention relates to the technical field of electroencephalogram signal analysis and processing, and in particular, to a control method, an apparatus, an electronic device, and a storage medium based on an electroencephalogram signal. Background The brain electrical signal is very weak relative to other types of physiological signals, with amplitude on the order of microvolts. In the process of acquiring the brain electrical signals, environmental interference or artificial interference is inevitably introduced to influence the quality of the brain electrical signals. At present, most of common myoelectricity classification algorithms are based on a wireless surface myoelectricity test system to finish fine myoelectricity classification tasks, such as judgment of arm moment and direction, distinction of grabbing target shapes and the like. However, the existing myoelectricity analysis algorithm needs a complete myoelectricity signal acquisition system, the cost is high, and the myoelectricity classification algorithm is developed mostly based on a common machine learning or deep learning model, so that the myoelectricity classification algorithm for meeting the power demand cannot be embedded into a chip. Therefore, it is difficult to realize control based on an electroencephalogram signal in a computer apparatus. Disclosure of Invention The technical problem to be solved by the embodiment of the invention is that the existing myoelectricity classification algorithm cannot be embedded into a chip, so that control based on brain electrical signals is difficult to realize. According to an aspect of the present invention, there is provided a control method based on an electroencephalogram signal, including: acquiring an electroencephalogram signal of a target object, and extracting target class identification feature parameters corresponding to target class identification features in the electroencephalogram signal; Determining a violation identification result in the electroencephalogram signal based on the target class identification characteristic parameter and the target class reference parameter, wherein the target class identification characteristic and the target class reference parameter are determined in advance based on a characteristic classification result of the sample electroencephalogram signal; And determining the action state of the target object based on the violation identification result, and executing the processing operation corresponding to the action state. According to another aspect of the present invention, there is provided an electroencephalogram signal-based control apparatus including: the identification feature extraction module is used for acquiring the electroencephalogram signal of the target object and extracting target category identification feature parameters corresponding to the target category identification features in the electroencephalogram signal; The system comprises a violation identification result determining module, a target class identification characteristic parameter determining module and a target class reference parameter determining module, wherein the violation identification result determining module is used for determining a violation identification result in an electroencephalogram signal based on the target class identification characteristic parameter and the target class reference parameter, and the target class identification characteristic and the target class reference parameter are determined in advance based on a characteristic classification result of a sample electroencephalogram signal; And the processing operation execution module is used for determining the action state of the target object based on the violation identification result and executing the processing operation corresponding to the action state. According to another aspect of the present invention, there is provided an electronic apparatus including: at least one processor, and A memory communicatively coupled to the at least one processor, wherein, The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the electroencephalogram-based control method of any one of the embodiments of the present invention. According to another aspect of the present invention, there is provided a computer readable storage medium storing computer instructions for causing a processor to implement the electroencephalogram signal-based control method of any one of the embodiments of the present invention when executed. According to the technical scheme, the target class identification characteristic parameters corresponding to the target class identification characteristics in the electroencephalogram signals are extracted by acquiring the electroencephalogram signals of the target object, the illegal id