CN-121996075-A - Control method and system based on brain-computer interface technology

CN121996075ACN 121996075 ACN121996075 ACN 121996075ACN-121996075-A

Abstract

The embodiment of the invention provides a control method and a control system based on brain-computer interface technology, and relates to the technical field of brain-computer interfaces. The control method based on the brain-computer interface technology comprises the steps of collecting a first brain-computer signal when a current user performs motor imagery based on preset action prompt information, performing identity verification on the current user based on the first brain-computer signal, obtaining a target decoder matched with the current user from a preset decoder if the current user passes the identity verification, collecting a second brain-computer signal when the current user performs motor imagery based on preset task prompt information, comparing a target category obtained by classifying the second brain-computer signal based on the target decoder with a prompt category corresponding to the preset task prompt information, determining whether the activity inspection is passed or not, and classifying the brain-computer signal when the current user performs tasks by the target decoder to obtain a corresponding control instruction if the activity inspection is determined to be passed.

Inventors

QIN CHUAN
LI QINYING
SHU XIAOKANG

Assignees

上海念通智能科技有限公司

Dates

Publication Date: 20260508
Application Date: 20260129

Claims (12)

1. A control method based on brain-computer interface technology, comprising: acquiring a first electroencephalogram signal when a current user performs motor imagery based on preset action prompt information, and performing identity verification on the current user based on the first electroencephalogram signal; if the current user passes the identity verification, a target decoder matched with the current user is obtained from a preset decoder; Acquiring a second electroencephalogram signal when a current user performs motor imagery based on preset task prompt information, and comparing a target class obtained by classifying the second electroencephalogram signal based on the target decoder with a prompt class corresponding to the preset task prompt information to determine whether the activity check is passed; And if the activity check is confirmed to pass, classifying the electroencephalogram signals when the current user executes the task by the target decoder to obtain corresponding control instructions.
2. The brain-computer interface technology-based control method according to claim 1, wherein authenticating the current user based on the first electroencephalogram signal includes: Extracting biological characteristics from the first electroencephalogram signals, comparing the extracted biological characteristics with biological characteristics corresponding to a pre-stored preset user under the preset action prompt information, and determining whether a target user matched with the current user exists in the preset user or not; if so, determining that the current user passes the authentication.
3. The brain-computer interface technology-based control method according to claim 1, wherein said preset task prompt information includes a plurality of preset task prompts; comparing a target category obtained by classifying the second electroencephalogram signals based on the target decoder with a prompt category corresponding to the preset task prompt information, and determining whether the second electroencephalogram signals pass through the activity check comprises the following steps: If the target categories corresponding to the second electroencephalogram signals in the continuous N time windows are detected to be the prompt categories of the corresponding preset task prompts in the preset task prompt information in the preset time, determining that the activity check is passed, wherein N is more than or equal to 2.
4. The brain-computer interface technology-based control method according to claim 1, wherein each preset user is provided with a corresponding plurality of preset decoders; obtaining a target decoder matched with the current user from a preset decoder, wherein the target decoder comprises: Obtaining a matching degree score between each preset decoder and the current user; Selecting the preset decoder with the matching degree meeting the preset condition from all preset decoders corresponding to a target user as the target decoder, wherein the preset condition is that the matching degree score is larger than a preset matching score threshold, and the target user is the user matched with the current user in the preset users.
5. The brain-computer interface technology-based control method according to claim 4, wherein obtaining a matching degree score between each of said preset decoders and said current user comprises: Aiming at each preset decoder, obtaining a task tag matching score between the preset decoder and the current user based on a preset task tag corresponding to the current task and the preset decoder; Determining, for each of the preset decoders, an electrode equivalent score between the preset decoder and the current user based on preset electrode configuration information of the preset decoder and the electrode worn by the current user; and calculating the sum of the task tag matching score and the electrode equivalent score corresponding to each preset decoder to be used as a matching degree score between each preset decoder and the current user.
6. The brain-computer interface technology-based control method according to claim 5, wherein said preset electrode configuration information includes an initial electrode position of said preset decoder and a reference brain electrical signal; Determining an electrode equivalent score between the preset decoder and the current user based on preset electrode configuration information of the preset decoder and the electrode worn by the current user, comprising: acquiring mapping relation information from the initial electrode position to an electrode worn by the current user based on preset electrode configuration information of the preset decoder; Acquiring a third electroencephalogram signal of the current user under the pointed task prompt acquired by the electrode worn by the current user, and reconstructing the third electroencephalogram signal by utilizing the mapping relation information to obtain a calibrated electroencephalogram signal; And obtaining an electrode equivalent score between the preset decoder and the electrode worn by the current user based on the calibration electroencephalogram signal and the reference electroencephalogram signal corresponding to the appointed task prompt.
7. The method for controlling a brain-computer interface technology according to claim 6, wherein, Based on preset electrode configuration information of the preset decoder, obtaining mapping relation information from the initial electrode position to the electrode worn by the current user, including: And constructing a mapping topological graph from the initial electrode position to the electrode worn by the current user based on the initial electrode position and the initial electroencephalogram signal, wherein the mapping relation information comprises the mapping topological graph.
8. The method for controlling a brain-computer interface technology according to claim 6, wherein, Based on preset electrode configuration information of the preset decoder, obtaining mapping relation information from the initial electrode position to the electrode worn by the current user, including: And based on the initial electrode position, the electrode position of the electrode worn by the current user and the initial electroencephalogram signal, inputting the initial electrode position to a pre-trained lead mapping model, obtaining a mapping topological graph from the initial electrode position to the electrode worn by the current user, wherein the mapping relation information comprises the mapping topological graph.
9. The method for controlling a brain-computer interface technology according to claim 1, wherein, Before the target decoder classifies the electroencephalogram signals when the current user executes the task to obtain the corresponding control instructions, the method further comprises the following steps: and updating parameters of the target decoder based on the matching score for carrying out identity verification on the current user and the confidence information when carrying out activity check on the current user.
10. The brain-computer interface technology based control method according to claim 9, wherein said parameter updating said target decoder based on a matching score for authentication of said current user comprises: Obtaining an identity matching score for carrying out identity verification on the current user based on the biological characteristics of the current user and the biological characteristics of a target user, wherein the target user is a user matched with the current user in the preset users; Based on the target category obtained by classifying the second electroencephalogram signals by the target decoder and the prompt category corresponding to the preset task prompt information, obtaining a confidence score of each target category; And respectively adjusting the weight of each target category when the target decoder is classified by using the identity matching score and the confidence coefficient of each target category.
11. The brain-computer interface system is characterized by comprising an electroencephalogram acquisition device and a main control module; The electroencephalogram acquisition device is used for acquiring electroencephalogram signals of a user; The main control module is used for executing the control method based on the brain-computer interface technology according to any one of claims 1-10.
12. A computer-readable storage medium, which is a non-volatile storage medium or a non-transitory storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, performs a control method based on brain-computer interface technology according to any one of claims 1-10.

Description

Control method and system based on brain-computer interface technology Technical Field The invention relates to the technical field of brain-computer interfaces, in particular to a control method and a control system based on brain-computer interface technology. Background Brain-computer interface (BCI) is currently in a key stage of expanding from laboratory to clinical application and from medical scenario to consumer field as a next generation man-machine interaction technology for connecting brain and external devices. The development of the method presents the characteristics of technology diversification, application scene and industrial scale, and simultaneously faces the problems of technology bottleneck, ethical disputes, commercialization challenges and the like. In the future, with further maturation of technology (such as invasive minimally invasive, non-invasive signal quality improvement), further support of policies (such as medical coverage, standard formulation), and further standardization of ethics (such as privacy protection and cognition enhancement criteria), brain-computer interfaces are expected to become core technology for changing human lifestyle, and bring revolutionary changes to the fields of medical treatment, consumption, industry and the like. Currently, a brain-computer interface is generally used by a user as a relatively universal brain-computer device, namely, all users can use the device in a wearing mode and the like, and the safety and the adaptability are lacked. Disclosure of Invention The invention aims to provide a control method and a control system based on a brain-computer interface technology, which are used for performing double authentication of identity verification and activity check before a user uses the brain-computer interface system, and can select a decoder matched with the current user to start, so that the safety and the adaptability of the user using the brain-computer interface system are improved. In order to achieve the above object, the present invention provides a control method based on brain-computer interface technology, including: acquiring a first electroencephalogram signal when a current user performs motor imagery based on preset action prompt information, and performing identity verification on the current user based on the first electroencephalogram signal; if the current user passes the identity verification, a target decoder matched with the current user is obtained from a preset decoder; Acquiring a second electroencephalogram signal when a current user performs motor imagery based on preset task prompt information, and comparing a target class obtained by classifying the second electroencephalogram signal based on the target decoder with a prompt class corresponding to the preset task prompt information to determine whether the activity check is passed; And if the activity check is confirmed to pass, classifying the electroencephalogram signals when the current user executes the task by the target decoder to obtain corresponding control instructions. The invention also provides a brain-computer interface system, which comprises an electroencephalogram acquisition device and a main control module; The electroencephalogram acquisition device is used for acquiring electroencephalogram signals of a user; the main control module is used for executing the control method based on the brain-computer interface technology. The present invention also provides a computer-readable storage medium, which is a non-volatile storage medium or a non-transitory storage medium, having stored thereon a computer program which, when executed by a processor, performs a control method based on brain-computer interface technology as described above. In one embodiment, authenticating the current user based on the first electroencephalogram signal includes: Extracting biological characteristics from the first electroencephalogram signals, comparing the extracted biological characteristics with biological characteristics corresponding to a pre-stored preset user under the preset action prompt information, and determining whether a target user matched with the current user exists in the preset user or not; if so, determining that the current user passes the authentication. In one embodiment, the preset task prompt information includes a plurality of preset task prompts; comparing a target category obtained by classifying the second electroencephalogram signals based on the target decoder with a prompt category corresponding to the preset task prompt information, and determining whether the second electroencephalogram signals pass through the activity check comprises the following steps: If the target categories corresponding to the second electroencephalogram signals in the continuous N time windows are detected to be the prompt categories of the corresponding preset task prompts in the preset task prompt information in the preset time, determining that the a