Motion control method and related equipment based on brain-computer interface

Abstract

The embodiments of the present application provide a motion control method based on a brain-computer interface and related equipment, which relate to the fields of brain-computer interface and motion control. The method includes: when displaying or broadcasting information related to the target motion, collecting EEG signals of the user performing motion imagination; performing signal recognition on the EEG signals to determine the user's motion intention; collecting the first electrophysiological variable corresponding to the user performing motion related to the motion intention; estimating the second electrophysiological variable corresponding to the user performing the target motion under the motion intention based on the preset electrophysiological neural mechanism; based on the difference between the first electrophysiological variable and the second electrophysiological variable, determining the control strategy for performing the target motion, so as to control the user to perform the target motion under the motion intention based on the control strategy. The implementation of the present application realizes motion control of the human body based on the electrophysiological neural mechanism, which is conducive to improving the control accuracy.

Description

Technical Field

[0001] The present application relates to the field of brain-computer interface and artificial intelligence technology. Specifically, the present application relates to a motion control method based on brain-computer interface and related equipment. Background Art

[0002] With the development of neuroscience and computer technology, brain-computer interface (BCI) technology has made great progress. The direct purpose of brain-computer interface is to directly convert human brain signals into different control commands to achieve control of external devices.

[0003] Researchers have done a lot of research on the problem of achieving multi-degree-of-freedom control based on brain-computer interface technology. However, due to the complexity and uncertainty of brain structure, the accuracy of motion control based on brain-computer interface technology is very low in some specific EEG patterns. Summary of the invention

[0004] The embodiment of the present application provides a motion control method based on a brain-computer interface and related equipment, which can solve the problem of low precision of motion control based on EEG interface technology in the prior art. The technical solution is as follows:

[0005] According to one aspect of an embodiment of the present application, a motion control method is provided, the method comprising:

[0006] When displaying or broadcasting information related to the target movement, the EEG signals of the user performing movement imagination are collected;

[0007] Performing signal recognition on the EEG signal to determine the user's movement intention;

[0008] collecting a first electrophysiological variable corresponding to the user performing an exercise related to the exercise intention;

[0009] estimating a second electrophysiological variable corresponding to the target movement performed by the user under the movement intention based on a preset electrophysiological neural mechanism; the electrophysiological neural mechanism reflects changes in each electrophysiological variable when a normal user correctly performs the corresponding movement under each movement intention;

[0010] Based on the difference between the first electrophysiological variable and the second electrophysiological variable, a control strategy for performing the target movement is determined, so as to control the user to perform the target movement under the movement intention based on the control strategy.

[0011] In a feasible embodiment, the estimating the second electrophysiological variable corresponding to the user performing the target movement under the movement intention based on the preset electrophysiological neural mechanism includes:

[0012] estimating, by means of a pre-built electrophysiological representation model based on the learned electrophysiological neural mechanism, a second electrophysiological variable corresponding to the target movement performed by the user under the movement intention;

[0013] The steps of constructing the electrophysiological characterization model include:

[0014] Acquiring training data, wherein the training data includes association information between a movement task determined based on a preset limb movement task and an electrophysiological variable; wherein the electrophysiological variable represents measurement information of cortical activity of a user when performing movement;

[0015] The electrophysiological characterization model is trained based on the training data so that the electrophysiological characterization model learns at least one of a first electrophysiological neural mechanism related to unilateral limb rhythm and speed control and a second electrophysiological neural mechanism related to bilateral limb coordinated movement.

[0016] In a feasible embodiment, determining the association information between the movement task and the electrophysiological variable based on the preset limb movement task includes at least one of the following:

[0017] For a unilateral limb movement task, the electromyographic signals of a user with unilateral limb hemiplegia and a normal user during the movement are obtained; based on the electromyographic signal analysis, the behavioral difference information of the user with unilateral limb hemiplegia and the normal user during the movement is obtained; based on the behavioral difference information, the correlation information between the movement and electrophysiological variables of the unilateral limb rhythm and speed is determined by at least one of electrical stimulation and transcranial magnetic stimulation;

[0018] For bilateral limb coordinated movement tasks, the EEG signals of a user with unilateral limb hemiplegia during the movement are obtained; based on the EEG signal analysis, the brain activity state of the user with unilateral limb hemiplegia and the performance change information of bilateral limb coordinated movement are obtained; based on the performance change information, the correlation information between bilateral limb coordinated movement and electrophysiological variables under visual feedback intervention is determined through transcranial magnetic stimulation.

[0019] In a feasible embodiment, the exercise task for a unilateral limb obtains electromyographic signals of a user with unilateral limb hemiplegia and a normal user during exercise; obtains behavioral difference information between the user with unilateral limb hemiplegia and the normal user when exercising based on the electromyographic signals; and determines the association information between the movement and electrophysiological variables of the unilateral limb rhythm and speed through at least one of electrical stimulation and transcranial magnetic stimulation based on the behavioral difference information, including at least one of the following:

[0020] For the tapping movement of a unilateral limb, a first electromyographic signal of a user with unilateral limb hemiplegia and a normal user during the movement is obtained; based on the first electromyographic signal, first behavioral difference information when the user with unilateral limb hemiplegia and the normal user perform the tapping movement is obtained; based on the first behavioral difference information, a correlation relationship between the cortex and the electromyographic onset time under different rhythmic movements and the rhythmic tone start time is determined; based on the correlation relationship, correlation information between each electrophysiological variable when the unilateral limb performs different rhythmic movements is determined through at least one of electrical stimulation and transcranial magnetic stimulation;

[0021] For the abduction movement of a unilateral limb, second electromyographic signals of a user with unilateral hemiplegia and a normal user during the movement are obtained; second behavioral difference information of the user with unilateral hemiplegia and the normal user when performing abduction movement is obtained based on the analysis of the second electromyographic signals; a correlation between the response speed of the cortex and the abduction muscle is determined based on the second behavioral difference information; and based on the correlation, correlation information between various electrophysiological variables when the unilateral limb performs movements at different speeds is determined through at least one of electrical stimulation or transcranial magnetic stimulation.

[0022] In a feasible embodiment, the determining of the correlation information between the coordinated movement of bilateral limbs and electrophysiological variables under visual feedback intervention through transcranial magnetic stimulation based on the performance change information includes:

[0023] determining an electrophysiological indicator of brain electrical connectivity based on the performance change information;

[0024] Based on the electrophysiological indicators, transcranial magnetic stimulation is used for movement intervention during exercise to determine the correlation information between the coordinated movement of bilateral limbs under visual feedback intervention and various electrophysiological variables.

[0025] In a feasible embodiment, determining the control strategy for performing the target movement based on the difference between the first electrophysiological variable and the second electrophysiological variable includes:

[0026] Determining that a difference between the first electrophysiological variable and the second electrophysiological variable is greater than a preset difference value, and determining a control strategy for performing the target movement based on the difference value by using a pre-constructed electrophysiological characterization model;

[0027] Wherein, the control strategy includes at least one of a visual feedback intervention strategy and a transcranial magnetic stimulation strategy;

[0028] The controlling the user to perform the target movement under the movement intention based on the control strategy includes:

[0029] Executing a control step and collecting a first electrophysiological variable of the user under motion control;

[0030] cyclically executing the step of determining a control strategy for performing the target movement based on a difference between the first electrophysiological variable and the second electrophysiological variable;

[0031] Wherein, the control step includes at least one of the following:

[0032] Displaying a picture corresponding to the visual feedback intervention strategy through a display device, and controlling the user to perform the target movement based on the movement intention;

[0033] A stimulation signal corresponding to the transcranial magnetic stimulation strategy is outputted through a motion control device worn by the user to control the user to perform the target motion based on the motion intention.

[0034] According to another aspect of an embodiment of the present application, a motion control device based on a brain-computer interface is provided, the device comprising:

[0035] A signal acquisition module, used to collect EEG signals of the user performing motor imagery when displaying or broadcasting information related to the target movement;

[0036] An intention determination module, used to perform signal recognition on the EEG signal to determine the user's movement intention;

[0037] A variable collection module, used for collecting a first electrophysiological variable corresponding to the user performing a movement related to the movement intention;

[0038] a variable determination module, for estimating a second electrophysiological variable corresponding to the user performing the target movement under the movement intention based on a preset electrophysiological neural mechanism; the electrophysiological neural mechanism reflects the changes of each electrophysiological variable when a normal user correctly performs the corresponding movement under each movement intention;

[0039] A strategy determination module is used to determine a control strategy for performing the target movement based on a difference between the first electrophysiological variable and the second electrophysiological variable, so as to control the user to perform the target movement under the movement intention based on the control strategy.

[0040] According to another aspect of an embodiment of the present application, an electronic device is provided. The electronic device includes a memory, a processor, and a computer program stored in the memory, and the processor executes the computer program to implement the steps of the above-mentioned motion control method.

[0041] According to another aspect of the embodiments of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned motion control method are implemented.

[0042] According to one aspect of an embodiment of the present application, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned motion control method are implemented.

[0043] The beneficial effects of the technical solution provided by the embodiment of the present application are:

[0044] The present application provides a motion control method and related equipment based on a brain-computer interface. Specifically, the present application uses brain-computer interface technology to collect EEG signals of the user performing motion imagination when displaying or broadcasting information related to the target motion to the user, and performs signal recognition on the collected EEG signals to determine the motion intention reflected by the user's cerebral cortex; then, a series of first electrophysiological variables corresponding to the user performing motion related to the motion intention can be collected at the same time, that is, the electrophysiological variables of the motor cortex are measured in real time; and based on a preset electrophysiological neural mechanism, a second electrophysiological variable corresponding to the user performing the target motion under the motion intention is estimated, wherein the preset electrophysiological neural mechanism can be a mechanism obtained by exploring and learning the electrophysiological neural mechanism of motion control, which reflects the changes in each electrophysiological variable when a normal user correctly performs the corresponding motion under each motion intention, that is, the second electrophysiological variable is the electrophysiological variable predicted for the motion intention; then, based on the difference between the first electrophysiological variable and the second electrophysiological variable, a control strategy for performing the target motion can be determined, so as to control the user to perform the target motion under the motion intention based on the control strategy. The implementation of this application determines the control strategy through electrophysiological neural mechanisms to coordinate the consistency between brain consciousness and actual motor behavior through the control strategy, which is conducive to improving the accuracy of motion control based on brain-computer interface technology and improving the safety performance of human-machine integration. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in describing the embodiments of the present application are briefly introduced below.

[0046] Figure 1a A flowchart of a motion control method based on a brain-computer interface provided in an embodiment of the present application;

[0047] Figure 1b A schematic diagram of the timing of the execution process of a motion control method based on a brain-computer interface provided in an embodiment of the present application;

[0048] Figure 2 A schematic diagram of a process for learning a first electrophysiological neural mechanism provided in an embodiment of the present application;

[0049] Figure 3 A schematic diagram of a process for learning a second electrophysiological neural mechanism provided in an embodiment of the present application;

[0050] Figure 4 A schematic diagram of a learning framework for brain-computer interaction and human-computer fusion provided in an embodiment of the present application;

[0051] Figure 5 A schematic diagram of a flow chart of a motion control method based on a brain-computer interface provided in an embodiment of the present application for rehabilitation training of stroke patients;

[0052] Figure 6 A schematic diagram of a motion task of bilateral limb coordinated motion provided in an embodiment of the present application;

[0053] Figure 7 A schematic diagram of the architecture of a motion control based on an electrophysiological neural mechanism provided in an embodiment of the present application;

[0054] Figure 8 A schematic diagram of the structure of a motion control device based on a brain-computer interface provided in an embodiment of the present application;

[0055] Fig. 9 A schematic diagram of the structure of an electronic device for motion control based on a brain-computer interface provided in an embodiment of the present application;

[0056] Fig.10 An optional structural diagram of a distributed system provided in an embodiment of the present application applied to a blockchain system;

[0057] Fig.11 An optional schematic diagram of the block structure provided in an embodiment of the present application. DETAILED DESCRIPTION

[0058] The embodiments of the present application are described below in conjunction with the drawings in the present application. It should be understood that the implementation methods described below in conjunction with the drawings are exemplary descriptions for explaining the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions of the embodiments of the present application.

[0059] It will be understood by those skilled in the art that, unless specifically stated, the singular forms "one", "said", and "the" used herein may also include plural forms. It should be further understood that the terms "including" and "comprising" used in the embodiments of the present application refer to that the corresponding features can be implemented as the presented features, information, data, steps, operations, elements and / or components, but do not exclude the implementation as other features, information, data, steps, operations, elements, components and / or combinations thereof supported by the technical field. It should be understood that when we say that an element is "connected" or "coupled" to another element, the one element may be directly connected or coupled to the other element, or it may refer to that the one element and the other element establish a connection relationship through an intermediate element. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein indicates at least one of the items defined by the term, for example, "A and / or B" may be implemented as "A", or as "B", or as "A and B".

[0060] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0061] Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology in computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a similar way to human intelligence. Artificial intelligence is to study the design principles and implementation methods of various intelligent machines so that machines have the functions of perception, reasoning and decision-making.

[0062] Artificial intelligence technology is a comprehensive discipline that covers a wide range of fields, including both hardware-level and software-level technologies. The basic technologies of artificial intelligence generally include sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics and other technologies. Artificial intelligence software technology mainly includes computer vision technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0063] In the embodiments of the present application, machine learning technology may be involved. Machine Learning (ML) is a multi-disciplinary cross-disciplinary subject involving probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and other disciplines. It specializes in how computers simulate or implement human learning behavior to acquire new knowledge or skills and reorganize existing knowledge structures to continuously improve their performance. Machine learning is the core of artificial intelligence and the fundamental way to make computers intelligent. Its applications are spread across all fields of artificial intelligence. Machine learning and deep learning generally include artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and learning by teaching.

[0064] With the research and advancement of artificial intelligence technology, artificial intelligence technology has been studied and applied in many fields, such as common smart homes, smart wearable devices, virtual assistants, smart speakers, smart marketing, unmanned driving, automatic driving, drones, robots, smart medical care, smart customer service, etc. I believe that with the development of technology, artificial intelligence technology will be applied in more fields and play an increasingly important role.

[0065] In the problem of achieving multi-degree-of-freedom control based on brain-computer interface technology, relevant researchers have done a lot of exploratory work. For example, different rhythms of motor imagery are used to achieve two-dimensional and three-dimensional cursor control; brain-computer interface based on motor imagery is used to achieve the flight of virtual aircraft in three-dimensional space. However, these methods are simple extensions of BCI systems based on a single EEG pattern, and cannot overcome inherent bottlenecks such as low control accuracy of specific EEG patterns.

[0066] To this end, people have begun to study multi-dimensional and multi-functional control based on a single EEG mixed with different paradigms. For example, a multimodal brain-computer interface designed and implemented using the motor imagery paradigm visually evoked P300 potential (a type of event-related potential, an endogenous special evoked potential related to cognitive function) completes two-dimensional cursor control and can move the cursor on the screen from any initial position to any target position. For example, a hybrid brain-computer interface system based on event-related desynchronization and visual excitation potential is established. The above experimental results show that the hybrid brain-computer interface system can effectively eliminate the "BCI blindness" phenomenon; among them, in some BCI experiments, a certain proportion of users are called "BCI blind", and they do not have obvious "event-related desynchronization / event-related synchronization" phenomena.

[0067] However, due to the complexity and uncertainty of brain structure, the accuracy of motion control based on EEG interface technology is very low in some specific EEG patterns.

[0068] In response to at least one of the above-mentioned technical problems or areas that need improvement in the relevant technology, the present application proposes a motion control method and related equipment based on brain-computer interface. Specifically, the implementation of the present application controls the movement of physiological parts of the human body based on electrophysiological neural mechanisms to improve the control accuracy of motion control based on brain-computer interface technology.

[0069] The following describes several exemplary embodiments to illustrate the technical solutions of the embodiments of the present application and the technical effects produced by the technical solutions of the present application. It should be noted that the following embodiments can refer to, draw on or combine with each other, and the same terms, similar features and similar implementation steps in different embodiments will not be described repeatedly.

[0070] The present application provides a motion control method based on a brain-computer interface. Figure 1a As shown, the method includes the following steps S100-S104:

[0071] Step S100: When displaying or broadcasting information related to the target movement, the EEG signal of the user performing movement imagination is collected.

[0072] Specifically, a brain-computer interface (BCI) refers to a direct connection created between a human or animal brain and an external device to achieve information exchange between the brain and the device. In the technical context of the brain-computer interface, an embodiment of the present application provides a motion control method for controlling a user to perform a specific motion. Optionally, the motion control can be multi-degree-of-freedom.

[0073] In which, when implementing the embodiments of the present application, the user wears an external device, which may include a motion control device, a display device, a collection device, a main control device, etc.; wherein the collection device is used to collect various electrophysiological variables of the user during the motion control process; the display device can be used to display a picture of a target movement, and the device can be a virtual reality head-mounted display device (such as VR glasses), a display screen of a device, etc.; the motion control device is used to output a stimulation signal according to a control strategy to control the user to perform a corresponding movement action; the main control device is used to output a control strategy based on a learned electrophysiological neural mechanism.

[0074] Wherein, the information related to the target motion may be sent by an external device worn by the user, or may be sent by other external devices or other users; when the information related to the target motion is sent by other external devices or other users, the external device worn by the user may be started while displaying or broadcasting the information. Optionally, the target motion may be a limb motion, such as stretching, tapping, bending and the like. Wherein, the information related to the target motion may be displayed through a display device of an external device, or may be displayed through other external devices, or may be broadcasted through other external devices; that is, the source of information related to the target motion may be multimedia data; if it is audio data or text data, it may be broadcasted by voice to convey to the user the relevant information of the target motion to be performed; if it is video data, it may be displayed on the screen to convey to the user the relevant information of the target motion to be performed.

[0075] Among them, motor imagery (MI) refers to the corresponding activation properties of specific brain regions when a person imagines his or her limbs (or muscles) moving but has no actual movement output. Optionally, the user's intention can be judged by analyzing EEG signals and detecting and identifying the activation effects of different brain regions, thereby achieving direct communication and control between the human brain and external devices. EEG signals are the overall reflection of the electrophysiological activities of brain nerve tissue on the surface of the cerebral cortex; specifically, the changing activity data of electrical signals during brain activity can form an electroencephalogram (EEG). The electrical activity of the cerebral cortex can include spontaneous EEG activity and induced EEG activity; among them, spontaneous EEG activity refers to the corresponding brain wave frequency fluctuations exhibited by people in different autonomous states, while the potential corresponding to induced EEG activity is generated by external stimulation.

[0076] In step S100, the collected EEG signal may refer to the EEG signal corresponding to spontaneous EEG activity, such as the EEG signal generated when the human body spontaneously determines that it wants to perform a certain movement (performing motor imagination) through a given external movement task (information related to the target movement displayed or broadcasted) during rehabilitation training. Among them, the EEG signal collection method can be either embedded collection or non-embedded collection; embedded collection refers to opening the brain and implanting sensors inside; and non-embedded collection is to collect EEG signals by placing electrode sensors outside the cerebral cortex. The collection method of EEG signals is not limited in this application.

[0077] Step S101: performing signal recognition on the EEG signal to determine the user's movement intention.

[0078] Among them, movement intention is the result obtained by identifying EEG signals; specifically, when identifying human movement intention through EEG signals (electrophysiological signals), a deep learning convolutional neural network (CNN) can be used to extract feature information in the EEG signals, and then classify the feature information to determine the current spontaneous movement intention of the human body, that is, a certain movement task that the human body wants to complete (based on the set movement task to induce the human body to move spontaneously).

[0079] Optionally, different movement imaginations correspond to different EEG signals, such as different EEG signals corresponding to tapping movement imagination (movement intention is tapping) and elbow bending movement imagination (movement intention is bending the elbow). Based on this, the embodiments of the present application can also classify EEG signals through a classification algorithm, extract feature information corresponding to each set network indicator, classify EEG signals based on the feature information, and determine the corresponding movement intention with the classification label.

[0080] Step S102: collecting first electrophysiological variables corresponding to the user performing exercise related to the exercise intention.

[0081] Specifically, step S102 is to collect the first electrophysiological variable through an external device (such as a collection device) when the human body actively sends out a movement intention, which belongs to the measurement and processing of the electrophysiological variable; for example, according to the set electrophysiological indicators, the excitation or inhibition of the cortical or subcortical pathway is measured to determine the first electrophysiological variable (characterizing the motor cortex emission) under the movement intention.

[0082] Step S103: estimating the second electrophysiological variable corresponding to the user's target movement under the movement intention based on the preset electrophysiological neural mechanism, wherein the electrophysiological neural mechanism reflects the changes of each electrophysiological variable when a normal user correctly performs the corresponding movement under each movement intention.

[0083] Specifically, the preset electrophysiological neural mechanism is a mechanism obtained through research and exploration, which can be determined by setting a series of motor tasks, analyzing the effects of each motor task on the activity of the cortical and subcortical pathways, and then determining the information of the electrophysiological neural mechanism when performing each motor task. On this basis, it can be determined that when a human body spontaneously intends to perform a certain motor task, a predicted electrophysiological variable (second electrophysiological variable) is given for the motor task and the set electrophysiological index, that is, the electrophysiological variable of a normal human body in the actual situation when performing a certain motor task.

[0084] Among them, due to the diversity of movements that the human body can perform, it is difficult to analyze all movements when exploring the electrophysiological neural mechanism. Therefore, the electrophysiological neural mechanism can be explored for the scene, and a specific limited number of target movements can be analyzed to improve the accuracy of the estimated second electrophysiological variable; for example, for the application scenario of human rehabilitation treatment, it can be divided into rehabilitation treatment of unilateral limbs and rehabilitation treatment of bilateral limbs, and N movements that need to be performed are set to adapt to different treatment plans, and only the electrophysiological neural mechanism corresponding to the N movements is explored; then, the corresponding target movement in step S100 is at least one of the N movements. Optionally, the electrophysiological neural mechanism can also be explored for users. Due to the uniqueness of individuals, each user needs to perform different movement control situations. Therefore, M movements that are suitable for a specific user can be set for the user, and the electrophysiological neural mechanism corresponding to the M movements can be explored. Then, when the movement control is performed for the user, the corresponding target movement in step S100 is at least one of the M movements.

[0085] Step S104: determining a control strategy for performing a target movement based on a difference between the first electrophysiological variable and the second electrophysiological variable, so as to control the user to perform the target movement under the movement intention based on the control strategy.

[0086] Specifically, if the difference between the first electrophysiological variable actually measured and the second electrophysiological variable predicted is large, a control strategy for motion control can be determined for the difference, so as to control the user to complete the corresponding target motion when performing motor imagination based on the control strategy (that is, when the user cannot complete the target motion independently, the user is assisted to complete the target motion with the help of external force). If the difference between the first physiological variable and the second physiological variable is small, it is characterized that the current motion intention is consistent with the motor behavior, and there is no need to perform motion control through additional control strategies. For example, in rehabilitation training, the second electrophysiological variable can be regarded as the standard of motor behavior. When the difference between the first electrophysiological variable and the second electrophysiological variable is large, the control strategy can be output so that the external device can assist the specific physiological part of the human body to perform the motion task corresponding to the motion intention based on the control strategy; when the difference between the first electrophysiological variable and the second electrophysiological variable is small, it is characterized that the current rehabilitation treatment is good, and the human body can complete the specific training task spontaneously without the assistance of external equipment.

[0087] Combine the following Figure 1b The motion control method based on brain-computer interface provided in an embodiment of the present application is described.

[0088] like Figure 1b As shown, when implementing the brain-computer interface-based motion control method provided by the present application, the user needs to wear an external device (such as Figure 1bStep S0), the external device may include a collection device installed on the head (such as a portable EEG signal device), a collection device installed on the part where the movement is controlled (such as an electromyography signal collection device), and a motion control device installed on the part where the movement is controlled (such as a multi-channel signal output device); wherein the collection device may transmit the collected data to the main control device included in the external device, and the main control device processes the data and outputs the control strategy to the motion control device, and the motion control device controls the user to perform the corresponding target movement. Among them, the main control device and the collection device, and the main control device and the motion control device in the external device may be connected by wire or wirelessly. When it is a wired connection, the collection device, the main control device and the motion control device are an integrated external device.

[0089] In addition, the external devices worn by the user may also include AR glasses, etc., which can display information related to the target movement. When the user views the information related to the target movement through the AR glasses, the user can imagine the movement. In addition, the information related to the target movement can be displayed or broadcasted through devices unrelated to the external devices worn by the user, such as placing a tablet computer in front of the user to play a video related to the target movement, and other staff can speak the information related to the target movement in natural language around the user.

[0090] When information related to the target motion is displayed or broadcasted to the user, the external device worn by the user for motion control is simultaneously started, and the following steps are performed:

[0091] Step S1, the collection device collects the EEG signals of the user performing motor imagery while displaying or broadcasting information related to the target movement; in step S1, the collection device may include an EEG signal collection module to collect the user's motor imagery EEG signals.

[0092] Step S2: the acquisition device transmits the EEG signal to the main control device.

[0093] Step S3, the main control device identifies the EEG signal to determine the user's movement intention; specifically, the main control device may include a movement intention identification module for identifying and processing the obtained motor imagery EEG signal to determine the user's current movement intention; optionally, the movement intention identification module may classify the EEG signal, identify the classification result by label, that is, directly determine the movement intention in the form of a label, and transmit it to the control strategy module of the main control device;

[0094] Step S4, the main control device feeds back the motion intention to the acquisition device. Optionally, since for the user, when performing motion imagination, the user performs motion synchronously, and the motion intention is used by the external device to distinguish the motion that the user wants to perform, the execution of step S4 can be omitted.

[0095] Step S5, the acquisition device acquires the first electrophysiological variable corresponding to the user performing exercise related to the exercise intention; in step S5, the acquisition device may include an electromyography signal acquisition module, and a signal acquisition module related to each electrophysiological variable, and integrates the signals collected by each independent module when the user performs exercise into the first electrophysiological variable and transmits it to the main control device.

[0096] Step S6: the acquisition device transmits the first electrophysiological variable to the main control device.

[0097] In step S7, the control strategy module included in the main control device first estimates the second electrophysiological variable corresponding to the target movement of the user under the movement intention based on the preset electrophysiological neural mechanism (using this variable as a standard to measure whether the first electrophysiological variable meets the standard), and then determines the control strategy based on the received first electrophysiological variable and the estimated second electrophysiological variable. Specifically, the control strategy for the target movement to be performed is determined based on the difference (such as the absolute difference) between the first electrophysiological variable and the second electrophysiological variable.

[0098] Step S8, the main control device outputs the determined control strategy to the motion control device; wherein the control strategy may include a strategy for controlling the user to perform the target motion, and may also include instruction information indicating that the user does not need to be assisted to perform the target motion (a normal user can complete the target motion independently);

[0099] In step S9, the motion control device controls the user to perform the target motion under the motion intention according to the received control strategy (step S8 does not need to be executed when the instruction information is received). Specifically, the motion control device may include a display module and a signal output module; wherein, the display module (such as AR glasses worn by the user) may display a screen corresponding to the visual feedback intervention strategy to control the user to perform the target motion based on the motion intention; and the signal output module may output a stimulation signal corresponding to the transcranial magnetic stimulation strategy to control the user to perform the target motion based on the motion intention.

[0100] Among them, the data between the acquisition device, the main control device and the motion control device can be transmitted via wired or wireless transmission.

[0101] Taking into account that brain-computer interface (BCI) technology has a wide range of application scenarios in the real world, in order to better illustrate the present application, the following takes assisting patients with nervous system injuries in rehabilitation treatment as an application scenario, and explains the technology of realizing multi-degree-of-freedom control based on the use of external devices to implement brain-computer interface technology for limb motor function rehabilitation treatment, and then using limb robots to assist spinal cord injury (SCI) patients in rehabilitation treatment or performing tasks.

[0102] In a feasible embodiment, the step S103 of estimating the second electrophysiological variable corresponding to the target movement performed by the user under the movement intention based on the preset electrophysiological neural mechanism includes the following steps:

[0103] A second electrophysiological variable corresponding to the user's target movement under the movement intention is estimated through a pre-constructed electrophysiological representation model based on the learned electrophysiological neural mechanism.

[0104] Specifically, the present application can explore electrophysiological neural mechanisms through artificial intelligence technology. For example, the experimental data obtained from electrophysiological experiments can be used as training data for an electrophysiological characterization model to train the model. The model can be trained using an unsupervised learning method to learn the electrophysiological changes under different motor behaviors of the human body.

[0105] The construction of the electrophysiological characterization model includes the following steps A1-A2:

[0106] Step A1: Acquire training data, wherein the training data includes association information between a movement task determined based on a preset limb movement task and an electrophysiological variable; wherein the electrophysiological variable represents measurement information (such as measurement results) of the user's cortical activity when performing exercise.

[0107] Step A2: Train the electrophysiological characterization model based on the training data so that the electrophysiological characterization model learns at least one of a first electrophysiological neural mechanism related to unilateral limb rhythm and speed control and a second electrophysiological neural mechanism related to bilateral limb coordinated movement.

[0108] Specifically, in the interactive process of daily life, the motor functions required usually include unilateral limb movement control and bilateral limb coordinated movement control, both of which are very important for improving the quality of life of stroke patients. In the embodiment of the present application, the movement task can be set according to the actual application scenario, such as setting a limb movement task, which can be a unilateral hand movement task set for the hemiplegic unilateral hand, or a bimanual coordinated movement task set for the hemiplegic unilateral hand. For the set movement task, the measurement results of the excitement or inhibition of the cortical or subcortical pathway can be recorded for the set electrophysiological indicators during the movement control process, and then the measurement results are used as training data for model training, so that the model can analyze the effects of each specific movement task on the activity of the cortical and subcortical pathways, and then learn the corresponding electrophysiological neural mechanism.

[0109] As research on the body's endogenous repair mechanism after brain injury deepens, more and more evidence shows that changes in neural plasticity are the basis for motor function recovery after brain injury. Therefore, exploring efficient brain-computer interaction and fusion methods and increasing intervention and rehabilitation methods for neural function plasticity will be more helpful for motor function recovery in stroke patients. Figure 4 As shown, in the learning framework provided in the embodiment of the present application, brain-controlled TMS (Transcranial Magnetic Stimulation) intervention technology and visual feedback intervention technology are applied in the method of promoting the recovery of limb movement control.

[0110] Among them, the brain-controlled TMS intervention technology targets the characteristics of the neural pathways corresponding to the rhythm and speed functions in motor control, and develops a non-invasive TMS intervention paradigm for synaptic late input to the corticospinal neuronal pathway, including studies on stimulation sequences (such as early I waves or late I waves), stimulation intensity, etc., especially the regulatory effects of different paradigms on the residual cortical, subcortical and corticospinal connection activities after stroke, and establishes cortical targets for improving rhythm and speed control in motor activities after stroke. Targeting this cortical target, combined with the changes in specific rhythmic synchronization activities after movement induced by tasks, a brain-controlled TMS intervention paradigm for rhythm and speed functions in motor control is developed, exploring the effects of TMS intervention under different brain activity states on the plasticity of residual cortical, subcortical and corticospinal connection activities after stroke, and achieving auxiliary treatment and rehabilitation of rhythm and speed control functions in motor activities after stroke.

[0111] Among them, the visual feedback intervention technology can use immersive virtual human technology to apply the established game-like interactive system to the recovery of the coordination function of unilateral limb hemiplegia based on the electrophysiological effect of visual feedback on the coordination of bilateral limbs (such as both hands). For example, in an immersive virtual environment, the non-injured hand controls the same-side hand of the virtual person to coordinate movement training with the other hand of the virtual person, providing visual feedback for the coordination training of both hands for stroke patients. In the embodiments of this application, the automatic matching technology of the color and size of virtual hands for different subjects is also studied. By adjusting the authenticity of the virtual hand, the effect of enhancing the coordination of both hands when improving user participation is explored. The influence of these technologies on the plasticity of neural functions during visual feedback training will also be explored.

[0112] Combine the following Figure 2 and Figure 7 The learning process of the electrophysiological representation model in this application for unilateral limb movement is explained.

[0113] In a feasible embodiment, the electrophysiological representation model may adopt the following steps B1-B3 when learning the association between the motion task and the electrophysiological variable:

[0114] Step B1: For a unilateral limb movement task, the electromyographic signals of a user with unilateral limb hemiplegia and a normal user during movement are obtained.

[0115] Specifically, considering that most SCI patients lack limb motor function, their muscles are not necrotic, that is, when the brain sends out movement intentions, the muscles can still contract slightly. Therefore, analysis can be performed by obtaining the electromyographic signals corresponding to the limbs that perform movement tasks during the movement process.

[0116] Among them, electromyographic signal (EMG) is the superposition of motor unit action potential (MUAP) in many muscle fibers in time and space. Surface electromyographic signal (SEMG) is the comprehensive effect of superficial muscle EMG and electrical activity on nerve trunks on the skin surface, which can reflect neuromuscular activity to a certain extent; surface electromyographic signal is the electrical signal accompanying muscle contraction.

[0117] Among them, the movement task of a unilateral limb can be a movement task set for the left limb or the right limb, such as setting movement tasks such as tapping and abduction for a unilateral hand of the upper limb.

[0118] Step B2: obtaining information on behavioral differences between a user with unilateral hemiplegia and a normal user when exercising based on the electromyographic signal analysis.

[0119] Specifically, when exploring the first electrophysiological neural mechanisms of unilateral limb movement control, such as Figure 2As shown, the analysis can be performed based on the unilateral limb movement of stroke patients (unilateral limb hemiplegia users) and healthy people (normal users). The electromyographic signals of normal users during exercise are used as the standard to analyze the difference between the movement behavior of unilateral limb hemiplegia users during exercise and the standard movement behavior (electrophysiological variable abnormality measurement).

[0120] Step B3: Determine the correlation information between the movement and electrophysiological variables of the unilateral limb rhythm and speed through at least one of electrical stimulation and transcranial magnetic stimulation based on the behavioral difference information.

[0121] Among them, electrical stimulation (FES), also known as functional electrical stimulation, is a treatment method that uses electric current to stimulate organs or limbs that have lost their functions to compensate for or correct functional disorders; it includes diaphragm pacing, bladder electrical stimulation, and functional limb electrical stimulation. Transcranial magnetic stimulation (TMS) is a painless, non-invasive, green treatment method. The magnetic signal can penetrate the skull without attenuation and stimulate the brain nerves. In addition to stimulating the brain, peripheral nerves and muscles can also be stimulated, so it is also called "magnetic stimulation."

[0122] Among them, the rhythm and speed of movement are two important components of unilateral limb movement control, which have a very important impact on learning and mastering daily sports skills (such as playing tennis, playing the piano, etc.). Rhythm and speed usually appear at the same time in the same action. For example, movements with different rhythms not only involve rhythm, but also involve the speed of control.

[0123] Herein, cortical activity may refer to the neural activity of the cortical and subcortical pathways.

[0124] In a feasible embodiment, the specific process of applying the above steps B1-B3 to the tapping movement of a unilateral limb to explore the rhythmic factors is described.

[0125] For the tapping movement of a unilateral limb, the first electromyographic signal of a user with unilateral hemiplegia and a normal user during the movement is obtained; based on the analysis of the first electromyographic signal, the first behavioral difference information when the user with unilateral hemiplegia and the normal user perform the tapping movement is obtained; based on the first behavioral difference information, the correlation between the cortex and the electromyographic onset time under different rhythmic movements and the rhythmic tone start time is determined; based on the correlation relationship, the correlation information between the unilateral limb performing different rhythmic movements and various electrophysiological variables is determined through at least one of electrical stimulation and transcranial magnetic stimulation.

[0126] Specifically, taking the unilateral limb as a unilateral hand as an example, the above process steps for exploring rhythmic factors are explained:

[0127] (1) Recording electromyographic signals (which may also include force signals) during the finger tapping exercise of the hemiplegic hand of stroke patients and the finger tapping exercise of healthy people;

[0128] (2) Analyzing the behavioral differences between the hemiplegic hand and the normal hand when performing slow-rhythm or fast-rhythm tapping movements based on the recorded electromyographic signals (which may also include force signals);

[0129] (3) Based on behavioral differences, explore the influence of corticospinal neural pathways on the relationship between the onset time of electromyography and the onset time of rhythmic tone during different rhythmic movements.

[0130] (4) Through electrical stimulation and TMS technology, explore the role of cortical and subcortical pathways in slow-rhythmic and fast-rhythmic finger movements, respectively.

[0131] In a feasible embodiment, the specific process of applying the above steps B1-B3 to the abduction movement of a unilateral limb to explore the speed factor is described.

[0132] For the abduction movement of a unilateral limb, second electromyographic signals of a user with unilateral hemiplegia and a normal user during the movement are obtained; second behavioral difference information of the user with unilateral hemiplegia and the normal user when performing abduction movement is obtained based on the analysis of the second electromyographic signals; a correlation between the response speed of the cortex and the abduction muscle is determined based on the second behavioral difference information; and based on the correlation, correlation information between various electrophysiological variables when the unilateral limb performs movements at different speeds is determined through at least one of electrical stimulation or transcranial magnetic stimulation.

[0133] Specifically, taking the unilateral limb as a unilateral hand as an example, the above process steps for exploring the speed factor are explained as follows:

[0134] (1) When stroke patients use the fingers or elbows of unilateral hemiplegia to perform abduction exercises and healthy people use the fingers or elbows of unilateral hands to perform abduction exercises, record the electromyographic signals (which may also include force signals);

[0135] (2) Analyze the behavioral differences between the hemiplegic hand and the normal hand in response to fast and slow movements based on the recorded electromyographic signals (which may also include force signals), and explore the influence of subcortical pathways on the response speed of distal muscles (such as index finger abduction) during fast and slow movements;

[0136] (3) explore the role of cortical and subcortical pathways in movement at different speeds through electrical stimulation and TMS techniques;

[0137] (4) Record high-resolution multi-channel EEG signals and combine them with TMS technology to study the neural mechanism of post-exercise beta rhythm synchronization activity (ERS) induced by different movement speeds and explore the interaction pattern of bilateral primary motor areas;

[0138] (5) Combined with brain-computer interface online control and feedback technology, explore the functional effects of changes in beta rhythm synchronization activity (ERS) after exercise on the next movement (e.g. Figure 7 shown).

[0139] Among them, beta rhythm is the oscillatory brain activity observed in different frequency bands in brain waves. These different forms of oscillatory electrical activities are closely related to different functional states of the brain. According to physiological characteristics and frequency band range, EEG oscillation activities can be mainly divided into delta (<3Hz), theta (3-8Hz), alpha (8-12Hz), beta (β, 12-30Hz) and gamma (γ, 30-100Hz) frequency band oscillation activities.

[0140] Among them, ERS (Event-Related Synchronization) means event-related synchronization.

[0141] In the embodiment of the present application, when studying the electrophysiological neural mechanism of unilateral hand movement, in order to establish an electrophysiological representation model of the rhythm and speed control process in movement activities, the following movement tasks can be used.

[0142] Motor task 1: The index finger performs tapping movements with a slow rhythm (such as 0.5, 0.75, 1 Hz) or a fast rhythm (such as 3, 4 Hz);

[0143] Movement task 2: The elbow joint performs a flexion movement as fast as possible and the index finger performs abduction movement as fast as possible and in a self-paced manner.

[0144] During the above-mentioned movement control process, the excitation or inhibition of the cortical or subcortical pathways is measured according to the set electrophysiological indicators.

[0145] Specifically, electrophysiological variables are measured, that is, the study of motor cortical firing, and the measured electrophysiological variables include:

[0146] 1) Resting motor threshold (RMT): TMS will be used to determine the motor brain areas corresponding to the main hand muscles to measure the resting motor threshold. RMT is the minimum required TMS intensity required to induce 5 or more motor evoked potentials (MEPs) of at least 50 μV in 10 consecutive TMS trials. Among them, motor evoked potentials are a non-invasive detection method. Motor evoked potentials (MEPs) are muscle movement compound potentials recorded in the contralateral target muscle by stimulating the motor cortex; they check the transmission of motor nerves from the cortex to the muscles, the overall synchronization and integrity of the conduction pathway.

[0147] 2) MEPs generated by stimulating the cortex: The primary motor cortex was stimulated with a TMS intensity of 120% RMT to test the MEPs of the hand muscles. Each condition was stimulated 30 times, and the MEPs of the 30 times were averaged.

[0148] 3) MEP (CMEP) produced by stimulating the cervical cord: Electrodes are fixed to the skin behind the mastoid process on both sides of the cervical cord, and then a high-voltage current meter stimulates the corticospinal tract pathway. The stimulation intensity is set to about 10% of the stimulation intensity that causes the maximum motor response in the muscle.

[0149] 4) Short-interval intracortical inhibition: This is a method for recording intracortical inhibition. The stimulus intensity of the conditioned stimulus will be the TMS subthreshold intensity that causes approximately 50% inhibition in the resting state. The stimulus intensity of the test stimulus is adjusted to a TMS intensity that causes approximately 50% of the MEP-Max.

[0150] Combine the following Figure 3 , Figure 6 and Figure 7 The learning process of the electrophysiological representation model in this application for coordinated movement of bilateral limbs is explained.

[0151] In a feasible embodiment, the electrophysiological representation model may adopt the following steps C1-C3 when learning the association between the motor task and the cortical activity:

[0152] Step C1: For the bilateral limb coordinated movement task, the EEG signal of the user with unilateral limb hemiplegia during the movement is obtained.

[0153] Among them, the bilateral limb coordination movement task can be to control the left hand to draw Figure 6 While drawing a symbol in the middle, control your right hand to draw Figure 6 Another symbol in .

[0154] Among them, cerebral stroke, also known as "stroke" or "cerebral vascular accident" (CVA), is an acute cerebrovascular disease, which is a group of diseases that cause brain tissue damage due to sudden rupture of brain blood vessels or blood vessel blockage that prevents blood from flowing into the brain; common symptoms of stroke patients are inability to control the movement of one side of the face, arm or leg. Therefore, in the application of the embodiment of the present application, stroke patients belong to a type of unilateral limb hemiplegia users.

[0155] Specifically, since the bilateral limb coordination movement task requires the synchronous movement control of the bilateral limbs, only users with unilateral limb hemiplegia can be used as analysis objects for the movement task. Optionally, in order to improve the accuracy of the data, healthy people can also be used as analysis objects simultaneously.

[0156] Specifically, the motor task of drawing a three-sided square with both hands simultaneously can be used to study the influence of stroke patients' coordination in time and space when drawing symmetrical and asymmetrical tasks with both hands.

[0157] Step C2: obtaining information on the brain activity state and performance changes of bilateral limb coordinated movements of the user with unilateral limb hemiplegia based on the EEG signal analysis.

[0158] Specifically, an evaluation network of brain activity state can be constructed to analyze performance change information based on recorded EEG signals. Specifically, the size of the network required for the EEG signals obtained from the original recording can be divided into time windows, and a graph network can be constructed for the EEG signals corresponding to each time window. The graph network and the movement actions performed at each time node in the coordinated movement of the bilateral limbs are analyzed to evaluate the performance change information of the brain activity state as each movement action in the coordinated movement is performed.

[0159] Step C3: Determine the correlation information between the coordinated movements of bilateral limbs and electrophysiological variables under visual feedback intervention through transcranial magnetic stimulation based on the performance change information.

[0160] Specifically, in a virtual environment, when coordinated movements are performed by interacting with a single hand and a virtual hand, TMS technology can be used to study the effect of visual feedback on the activity of the ipsilateral cortical motor area of ​​the moving hand, such as Figure 7 shown.

[0161] Optionally, in step C3, determining the association information between the coordinated movement of bilateral limbs and cortical activity under visual feedback intervention through transcranial magnetic stimulation based on the performance change information includes the following steps C31-C32:

[0162] Step C31: Determine electrophysiological indicators of EEG connectivity based on the performance change information.

[0163] Specifically, while analyzing information on performance changes, it is possible to explore whether EEG connectivity can be used as an electrophysiological indicator of bimanual coordinated motor performance.

[0164] Step C32: Based on the electrophysiological indicators, transcranial magnetic stimulation is used to perform movement intervention during the movement process to determine the correlation information between the coordinated movement of bilateral limbs under visual feedback intervention and various electrophysiological variables.

[0165] Specifically, the establishment of physiological indicators of EEG connectivity related to changes in the coordination performance of bilateral limbs (such as both hands) can provide a direct means to quickly reflect the effects of neurointervention technology, which will help the subsequent research and exploration of neurointervention and regulation technology.

[0166] Specifically, when exploring the second electrophysiological neural mechanism of bilateral limb movement control, such as Figure 3 As shown, the analysis can be performed based on the bilateral limb movements of stroke patients and healthy people (normal users). The electromyographic signals of normal users during exercise are used as the standard to analyze the difference between the movement behavior of stroke patients during exercise and the standard movement behavior (electrophysiological variable abnormality measurement).

[0167] In this application, when studying the electrophysiological neural mechanism technology of bimanual coordinated movement, in order to establish an electrophysiological representation model of the coordinated control process in movement activities, the following movement tasks can be used.

[0168] A 3D virtual environment was used for stimulus presentation and online visual feedback. Stimuli were presented in the form of a three-sided square above a virtual table, with the open side facing up, right, down, or left (e.g. Figure 6 ). Each side of the square spanned 10 cm. A stimulus set of 16 patterns was created by factorial combinations of these four patterns for the left and right hands. Six of these pairs had translational or reflectional symmetry along the vertical axis and were called symmetric patterns. The other 10 pairs were called incongruent patterns. A training set was created for each participant by randomly selecting three congruent and five incongruent patterns. The other eight patterns (three congruent and five incongruent) formed the set for the pre-training test and the post-training test. All finger movements were generated on the table surface. When the imperative signal appeared, the subjects were required to draw the target shape on the table surface with their index finger simultaneously and as quickly and accurately as possible. The subjects could generate the target shape starting from any endpoint of the three-sided square by moving the index finger along the table surface. The end point of the shape was when the subject lifted the finger from the table.

[0169] During the above-mentioned coordinated movement control process, cortical activity is measured according to set electrophysiological indicators.

[0170] Specifically, the measurement of electrophysiological variables, that is, the study of motor cortical firing, can refer to the electrophysiological variables measured during unilateral limb movement.

[0171] During the exercise, EEG data were collected from 64 scalp sites (extended 10-20 system) using an active Ag / AgCl electrode cap. Wet electrodes were used in the cap, and the reference electrodes were on the bilateral mastoids. Neuroscan Synamps2 amplifiers were used to record EEG signals.

[0172] In combination with the research results of the electrophysiological neural mechanisms corresponding to the rhythm and speed functions in motor control in the above embodiments, the key parameters of the non-invasive TMS intervention paradigm, including the stimulation sequence (such as late I wave) and the stimulation intensity, are studied to investigate the intervention effect on the specific pathways of the late synaptic input to the corticospinal neurons, and obtain the cortical targets of the non-invasive TMS intervention; and in the control of bimanual coordinated movement, TMS and EEG are combined to analyze the changes in cerebral cortical activity and brain connections when using a game-like interactive system to enhance the bimanual coordination function, so as to obtain electrophysiological indicators related to the bimanual coordination function.

[0173] Among them, Figure 7 As shown, the present application can use brain-computer interface technology to identify and feedback brain activity status online, thereby providing trigger conditions for TMS and providing a basis for realizing TMS driven by brain activity status. Because the rhythmic activity of the brain is related to the brain activity status, the first thing to be solved here is how the rhythmic activity of the brain changes regularly with the movement task during the rhythm and speed control process of the movement activity, so as to establish an online brain-computer interface system and use its judgment output command of a certain brain activity status to trigger and control TMS.

[0174] like Figure 4 As shown, the first electrophysiological neural mechanism and the second electrophysiological neural mechanism explored in the embodiment of the present application may coexist.

[0175] Combine the following Figure 5 The specific process of determining the control strategy in the embodiment of the present application is described.

[0176] In a feasible embodiment, determining a control strategy for performing target movement based on the difference between the first electrophysiological variable and the second electrophysiological variable in step S104 includes the following steps D1:

[0177] Step D1: Determine that the difference between the first electrophysiological variable and the second electrophysiological variable is greater than a preset difference value, and determine a control strategy for target movement based on the difference value through a pre-constructed electrophysiological characterization model; wherein the control strategy includes at least one of a visual feedback intervention strategy and a transcranial magnetic stimulation strategy.

[0178] Specifically, Figure 5 As shown, when the motion control method provided by the present application is applied to the rehabilitation training of stroke patients, when the patient is induced to perform a motor task, the patient's EEG signal can be first collected to determine the corresponding motor intention, and at the same time, the first electrophysiological variable in the process of executing the motor action can be collected (the collected electrophysiological indicators are determined in the process of studying the electrophysiological neural mechanism), and then the second electrophysiological variable is predicted through the electrophysiological neural mechanism obtained by the study; on this basis, the first electrophysiological variable and the second electrophysiological variable are compared. If the difference between the two is greater than the preset difference, the control strategy can be determined based on the difference through a pre-constructed electrophysiological characterization model, such as at which time node to output which degree of transcranial magnetic stimulation (transcranial magnetic stimulation strategy), or, a real-time simulation of the execution of the motor task can be displayed through a display device (visual feedback intervention strategy).

[0179] In a feasible embodiment, in step S104, controlling the user to perform the target movement under the movement intention based on the control strategy includes the following steps E1-E2:

[0180] Step E1: Execute the control step and collect the first electrophysiological variable of the user under motion control.

[0181] Specifically, for different control strategies involved in step D1, the embodiment of the present application can provide different output control methods. The difference between the first electrophysiological variable collected in step E1 and the first electrophysiological variable collected in step S102 is that the first electrophysiological variable collected in step E1 is the electrophysiological variable when the coordinated control is performed through the solution of the embodiment of the present application; the first electrophysiological variable collected in step S102 is the electrophysiological variable when the user exercises autonomously.

[0182] Optionally, the controlling step includes at least one of the following (1) and (2):

[0183] (1) Displaying a screen corresponding to the visual feedback intervention strategy through a display device, and controlling the user to perform the target movement based on the movement intention.

[0184] Specifically, when applied to the movement of bilateral limbs, the visual feedback intervention strategy may be a video screen that guides the user to control the output device (such as the control device installed on the impaired hand) through the non-impaired hand to perform coordinated movement. In the coordinated movement, the brain can receive the corresponding movement of the limbs under the movement intention to assist the user's brain in understanding the corresponding movement intention, so as to better spontaneously and actively control the impaired hand to move.

[0185] (2) Outputting a stimulation signal corresponding to the transcranial magnetic stimulation strategy through a motion control device worn by the user, thereby controlling the user to perform the target motion based on the motion intention.

[0186] Specifically, the transcranial magnetic stimulation strategy may include the frequency, strength, and time of the output stimulation signal, and then apply the stimulation signal to the physiological part corresponding to the movement intention through several stimulation points on the motion control device, so that the user can perform the target movement according to the movement intention, thereby increasing the user's movement feeling. Among them, the stimulation signal can also be an electrical stimulation signal applied to the muscle.

[0187] Step E2: loopingly executing the step of determining a control strategy for performing the target movement based on the difference between the first electrophysiological variable and the second electrophysiological variable.

[0188] Specifically, the target motion may correspond to one action or a motion behavior composed of multiple actions.

[0189] Optionally, when the target motion corresponds to an action, the first electrophysiological variable collected in step S102 is the electrophysiological variable of the user's active motion (the first time the target motion is executed), and the first electrophysiological variable collected in step E1 is the electrophysiological variable of the motion performed with the assistance of the outside world (the second time the target motion is executed); at this time, step S104 can be executed repeatedly to determine whether the motion performed under the influence of the outside world meets the expectations. If it still cannot meet the expectations, motion control can continue (that is, the third or nth time of executing the target motion), so that the user can feel real motion feedback corresponding to the motion intention.

[0190] Optionally, when the target motion corresponds to a motion behavior composed of multiple actions, the first electrophysiological variable collected in step S102 is the electrophysiological variable of the user's active motion (performing the first action), and the first electrophysiological variable collected in step E1 is the electrophysiological variable of the motion performed with the assistance of the outside world (performing the second action); at this time, step S104 can be executed repeatedly to determine whether the motion performed under the influence of the outside world meets the expectations. If it still does not meet the expectations, the motion control can be continued (performing the third action until the target motion is completed), so that the user can feel the real motion feedback corresponding to the motion intention. Among them, the motion behavior composed of multiple actions can be knocking on the same position of the table multiple times, and the multiple actions all correspond to the same knocking action.

[0191] In a feasible embodiment, the motion control method based on the brain-computer interface provided in the embodiment of the present application can be executed cyclically. For example, in rehabilitation training, for the same target movement, the motion control method based on the brain-computer interface provided in the embodiment of the present application can be cyclically implemented multiple times until the difference between the first electrophysiological variable collected in step S102 and the second electrophysiological variable estimated in step S103 is within an acceptable range (i.e., the user can spontaneously complete the target movement without external assistance).

[0192] In a feasible embodiment, the embodiment of the present application is performed by a set of intelligent medical equipment, which includes a device for collecting EEG signals, a device for collecting a first electrophysiological variable, and a device for controlling the physiological part of the intended movement to move based on a control strategy; wherein the medical device may also include a memory and a processor; wherein the processor is configured to determine a second electrophysiological variable and an output control strategy. Optionally, the motion control method provided in the embodiment of the present application can be specifically applied to auxiliary rehabilitation training for patients with motor dysfunction.

[0193] In the embodiments of the present application, the potential safety hazards brought by neural engineering and brain-computer interface technologies in the field of information security are also taken into consideration. In order to effectively improve the safety of implementation, the embodiments of the present application effectively improve the accuracy of the output control strategy through the exploration of effective electrophysiological neural mechanisms, and can also effectively avoid malicious use by illegal technicians (it is difficult to accurately know the control strategy output by external devices based on electrophysiological neural mechanisms), thereby effectively reducing the safety hazards brought to users by neural engineering devices (external devices described in the above embodiments).

[0194] Among them, the data related to the electrophysiological neural mechanism explored in the embodiments of the present application can be saved on the blockchain; such as electrophysiological indicators, measured electrophysiological variables, training data, etc. can be stored through the blockchain.

[0195] In the specific implementation of this application, data related to user information, EEG signals, movement intentions, electrophysiological variables, etc. are involved. When the above embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0196] The present application embodiment provides a motion control device based on a brain-computer interface, such as Figure 8 As shown, the motion control device 800 may include: a signal acquisition module 800 , an intention determination module 801 , a variable acquisition module 802 , a variable determination module 803 , and a strategy determination module 804 .

[0197] Among them, the signal acquisition module 800 is used to collect the EEG signals of the user performing movement imagination when displaying or broadcasting information related to the target movement; the intention determination module 801 is used to perform signal recognition on the EEG signals to determine the user's movement intention; the variable acquisition module 802 is used to collect the first electrophysiological variable corresponding to the user performing movement related to the movement intention; the variable determination module 803 is used to estimate the second electrophysiological variable corresponding to the user's target movement under the movement intention based on the preset electrophysiological neural mechanism; the strategy determination module 804 is used to determine the control strategy for performing the target movement based on the difference between the first electrophysiological variable and the second electrophysiological variable, so as to control the user to perform the target movement under the movement intention based on the control strategy.

[0198] Among them, the electrophysiological neural mechanism reflects the changes in various electrophysiological variables when a normal user correctly performs the corresponding movement under various movement intentions.

[0199] In a feasible embodiment, the variable determination module 803 is used to perform the estimation of the second electrophysiological variable corresponding to the user performing the target movement under the movement intention based on the preset electrophysiological neural mechanism, specifically for:

[0200] The pre-constructed electrophysiological representation model is used to estimate a second electrophysiological variable corresponding to the target movement performed by the user under the movement intention based on the learned electrophysiological neural mechanism.

[0201] The steps of constructing the electrophysiological characterization model include:

[0202] Acquiring training data, wherein the training data includes association information between a movement task determined based on a preset limb movement task and an electrophysiological variable; wherein the electrophysiological variable represents measurement information of cortical activity of a user when performing movement;

[0203] The electrophysiological characterization model is trained based on the training data so that the electrophysiological characterization model learns at least one of a first electrophysiological neural mechanism related to unilateral limb rhythm and speed control and a second electrophysiological neural mechanism related to bilateral limb coordinated movement.

[0204] In a feasible embodiment, determining the association information between the movement task and the electrophysiological variable based on the preset limb movement task includes at least one of the following:

[0205] For a unilateral limb movement task, the electromyographic signals of a user with unilateral limb hemiplegia and a normal user during the movement are obtained; based on the electromyographic signal analysis, the behavioral difference information of the user with unilateral limb hemiplegia and the normal user during the movement is obtained; based on the behavioral difference information, the correlation information between the movement and electrophysiological variables of the unilateral limb rhythm and speed is determined by at least one of electrical stimulation and transcranial magnetic stimulation;

[0206] For bilateral limb coordinated movement tasks, the EEG signals of a user with unilateral limb hemiplegia during the movement are obtained; based on the EEG signal analysis, the brain activity state of the user with unilateral limb hemiplegia and the performance change information of bilateral limb coordinated movement are obtained; based on the performance change information, the correlation information between bilateral limb coordinated movement and electrophysiological variables under visual feedback intervention is determined through transcranial magnetic stimulation.

[0207] In a feasible embodiment, for a unilateral limb movement task, myoelectric signals of a user with unilateral limb hemiplegia and a normal user during movement are obtained; behavioral difference information of the user with unilateral limb hemiplegia and the normal user when they are exercising is obtained based on the myoelectric signals; and association information between movement and electrophysiological variables of unilateral limb rhythm and speed is determined through at least one of electrical stimulation and transcranial magnetic stimulation based on the behavioral difference information, including at least one of the following:

[0208] For the tapping movement of a unilateral limb, a first electromyographic signal of a user with unilateral limb hemiplegia and a normal user during the movement is obtained; based on the first electromyographic signal, first behavioral difference information when the user with unilateral limb hemiplegia and the normal user perform the tapping movement is obtained; based on the first behavioral difference information, a correlation relationship between the cortex and the electromyographic onset time under different rhythmic movements and the rhythmic tone start time is determined; based on the correlation relationship, correlation information between each electrophysiological variable when the unilateral limb performs different rhythmic movements is determined through at least one of electrical stimulation and transcranial magnetic stimulation;

[0209] For the abduction movement of a unilateral limb, second electromyographic signals of a user with unilateral hemiplegia and a normal user during the movement are obtained; second behavioral difference information of the user with unilateral hemiplegia and the normal user when performing abduction movement is obtained based on the analysis of the second electromyographic signals; a correlation between the response speed of the cortex and the abduction muscle is determined based on the second behavioral difference information; and based on the correlation, correlation information between various electrophysiological variables when the unilateral limb performs movements at different speeds is determined through at least one of electrical stimulation or transcranial magnetic stimulation.

[0210] In a feasible embodiment, determining the correlation information between the coordinated movement of bilateral limbs and electrophysiological variables under visual feedback intervention through transcranial magnetic stimulation based on the performance change information includes:

[0211] determining an electrophysiological indicator of brain electrical connectivity based on the performance change information;

[0212] Based on the electrophysiological indicators, transcranial magnetic stimulation is used for movement intervention during exercise to determine the correlation information between the coordinated movement of bilateral limbs under visual feedback intervention and various electrophysiological variables.

[0213] In a feasible embodiment, the strategy determination module 804 is used to determine the control strategy for target movement based on the difference between the first electrophysiological variable and the second electrophysiological variable, and is specifically used to: determine that the difference between the first electrophysiological variable and the second electrophysiological variable is greater than a preset difference value, and determine the control strategy for target movement based on the difference value through a pre-constructed electrophysiological characterization model; wherein the control strategy includes at least one of a visual feedback intervention strategy and a transcranial magnetic stimulation strategy;

[0214] The device 800 further includes a motion control module, which is used to control the user to perform the target motion under the motion intention based on the control strategy, specifically for:

[0215] Executing a control step and collecting a first electrophysiological variable of the user under motion control;

[0216] cyclically executing the step of determining a control strategy for performing the target movement based on a difference between the first electrophysiological variable and the second electrophysiological variable;

[0217] Wherein, the control step includes at least one of the following:

[0218] Displaying a picture corresponding to the visual feedback intervention strategy through a display device, and controlling the user to perform the target movement based on the movement intention;

[0219] A stimulation signal corresponding to the transcranial magnetic stimulation strategy is outputted through a motion control device worn by the user to control the user to perform the target motion based on the motion intention.

[0220] The device of the embodiments of the present application can execute the method provided by the embodiments of the present application, and the implementation principles are similar. The actions performed by each module in the device of each embodiment of the present application correspond to the steps in the method of each embodiment of the present application. For the detailed functional description of each module of the device, please refer to the description in the corresponding method shown in the previous text, which will not be repeated here.

[0221] The blockchain referred to in this application is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods, each of which contains a certain amount of processed data to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0222] In an embodiment of the present application, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory, the processor executes the above-mentioned computer program to implement the steps of the motion control method, and compared with the related art, the following can be achieved: when displaying or broadcasting information related to the target motion to the user, the present application uses brain-computer interface technology to collect EEG signals of the user performing motion imagination, and performs signal recognition on the collected EEG signals to determine the motion intention reflected by the user's cerebral cortex; then, a series of first electrophysiological variables corresponding to the user performing motion related to the motion intention can be collected at the same time, that is, the electrophysiological variables of the motor cortex are measured in real time; and based on a preset electrophysiological neural mechanism, a second electrophysiological variable corresponding to the user performing the target motion under the motion intention is estimated, wherein the preset electrophysiological neural mechanism can be a mechanism obtained by exploring and learning the electrophysiological neural mechanism of motion control, which reflects the changes in each electrophysiological variable when a normal user correctly performs the corresponding motion under each motion intention, that is, the second electrophysiological variable is the electrophysiological variable predicted for the motion intention; then, based on the difference between the first electrophysiological variable and the second electrophysiological variable, a control strategy for performing the target motion can be determined, so as to control the user to perform the target motion under the motion intention based on the control strategy. The implementation of this application determines the control strategy through electrophysiological neural mechanisms to coordinate the consistency between brain consciousness and actual motor behavior through the control strategy, which is conducive to improving the accuracy of motion control based on brain-computer interface technology and improving the safety performance of human-machine integration.

[0223] In an alternative embodiment, an electronic device is provided, such as Fig. 9As shown, Fig. 9 The electronic device 4000 shown includes: a processor 4001 and a memory 4003. The processor 4001 and the memory 4003 are connected, such as through a bus 4002. Optionally, the electronic device 4000 may also include a transceiver 4004, which may be used for data interaction between the electronic device and other electronic devices, such as data transmission and / or data reception. It should be noted that in actual applications, the transceiver 4004 is not limited to one, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of the present application.

[0224] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. Processor 4001 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0225] The bus 4002 may include a path to transmit information between the above components. The bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 4002 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig. 9 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0226] The memory 4003 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), magnetic disk storage media, other magnetic storage devices, or any other medium that can be used to carry or store computer programs and can be read by a computer, without limitation herein.

[0227] The memory 4003 is used to store the computer program for executing the embodiment of the present application, and the execution is controlled by the processor 4001. The processor 4001 is used to execute the computer program stored in the memory 4003 to implement the steps shown in the above method embodiment.

[0228] Among them, electronic devices include but are not limited to: user terminals, VR devices, and auxiliary sports equipment.

[0229] The system involved in the embodiments of the present application may be a distributed system formed by connecting a client and multiple nodes (any form of computing devices in the access network, such as servers, user terminals, vehicle terminals, VR devices, auxiliary sports equipment) through network communication. Fig.10 , Fig.10 It is an optional structural diagram of the distributed system 100 provided in the embodiment of the present application applied to the blockchain system, which is formed by multiple nodes (any form of computing devices in the access network, such as servers, user terminals) and clients, and the nodes form a peer-to-peer (P2P, Peer To Peer) network. The P2P protocol is an application layer protocol running on the Transmission Control Protocol (TCP, Transmission Control Protocol) protocol. In a distributed system, any machine such as a server or a terminal can join and become a node, and the node includes a hardware layer, an intermediate layer, an operating system layer, and an application layer.

[0230] See also Fig.10 The functions of each node in the blockchain system shown may include:

[0231] 1) Routing: a basic function of a node, used to support communication between nodes.

[0232] In addition to the routing function, the node can also have the following functions:

[0233] 2) Applications are deployed in the blockchain to implement specific businesses based on actual business needs, record data related to the implementation of functions to form record data, carry digital signatures in the record data to indicate the source of the task data, and send the record data to other nodes in the blockchain system for other nodes to add the record data to a temporary block when they successfully verify the source and integrity of the record data.

[0234] 3) Blockchain, including a series of blocks that are connected to each other in the order of their generation. Once a new block is added to the blockchain, it will not be removed. The block records the record data submitted by the nodes in the blockchain system.

[0235] See also Fig.11 , Fig.11 This is an optional schematic diagram of the block structure provided by the embodiment of the present application. Each block includes the hash value of the transaction record stored in this block (the hash value of this block) and the hash value of the previous block. Each block is connected by the hash value to form a blockchain. In addition, the block can also include information such as the timestamp when the block was generated. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains relevant information for verifying the validity of its information (anti-counterfeiting) and generating the next block.

[0236] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps and corresponding contents of the aforementioned method embodiment can be implemented.

[0237] The embodiment of the present application also provides a computer program product, including a computer program, which can implement the steps and corresponding contents of the aforementioned method embodiment when executed by a processor.

[0238] The terms "first", "second", "third", "fourth", "1", "2", etc. (if any) in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than that shown or described in the drawings.

[0239] It should be understood that, although each operation step is indicated by arrows in the flowchart of the embodiment of the present application, the implementation order of these steps is not limited to the order indicated by the arrows. Unless clearly stated herein, in some implementation scenarios of the embodiment of the present application, the implementation steps in each flowchart can be performed in other orders according to demand. In addition, some or all of the steps in each flowchart may include multiple sub-steps or multiple stages based on actual implementation scenarios. Some or all of these sub-steps or stages may be executed at the same time, and each sub-step or stage in these sub-steps or stages may also be executed at different times respectively. In different scenarios of execution time, the execution order of these sub-steps or stages may be flexibly configured according to demand, and the embodiment of the present application does not limit this.

[0240] The above is only an optional implementation method for some implementation scenarios of the present application. It should be pointed out that for ordinary technicians in this technical field, without departing from the technical concept of the solution of the present application, other similar implementation methods based on the technical ideas of the present application are also within the protection scope of the embodiments of the present application.

Claims

1. A motion control method based on brain-computer interface, characterized in that: include: When displaying or broadcasting information related to the target movement, the EEG signals of the user performing movement imagination are collected; Performing signal recognition on the EEG signal to determine the user's movement intention; collecting a first electrophysiological variable corresponding to the user performing a movement related to the movement intention; the first electrophysiological variable is collected when the target movement is performed for the first time; The second electrophysiological variable corresponding to the target movement performed by the user under the movement intention is estimated by using a pre-constructed electrophysiological representation model; the electrophysiological representation model is obtained by training the association information between the movement task and the electrophysiological variable determined based on the preset limb movement task; If the difference between the first electrophysiological variable and the second electrophysiological variable is greater than a preset difference value, performing the following control operations: determining a control strategy for performing the target movement based on the difference value, controlling the user to perform the target movement under the movement intention based on the control strategy, and collecting a third electrophysiological variable when the user performs the target movement under the control; If the difference between the third electrophysiological variable and the second electrophysiological variable is greater than the preset difference, the control operation is executed in a loop.

2. The method according to claim 1, characterized in that The determining and estimating the second electrophysiological variable corresponding to the target movement performed by the user under the movement intention based on the preset electrophysiological neural mechanism includes: estimating, by means of a pre-built electrophysiological representation model based on the learned electrophysiological neural mechanism, a second electrophysiological variable corresponding to the target movement performed by the user under the movement intention; The steps of constructing the electrophysiological characterization model include: Acquiring training data, wherein the training data includes association information between a movement task determined based on a preset limb movement task and an electrophysiological variable; wherein the electrophysiological variable represents measurement information of cortical activity of a user when performing movement; The electrophysiological characterization model is trained based on the training data so that the electrophysiological characterization model learns at least one of a first electrophysiological neural mechanism related to unilateral limb rhythm and speed control and a second electrophysiological neural mechanism related to bilateral limb coordinated movement.

3. The method according to claim 2, characterized in that Determining the correlation information between the movement task and the electrophysiological variable based on the preset limb movement task, including at least one of the following: For unilateral limb movement tasks, the electromyographic signals of users with unilateral limb hemiplegia and normal users during movement are obtained; Based on the electromyographic signal analysis, the behavioral difference information between the user with unilateral limb hemiplegia and the normal user when exercising is obtained; based on the behavioral difference information, the correlation information between the movement of the unilateral limb rhythm and speed and the electrophysiological variables is determined by at least one of electrical stimulation and transcranial magnetic stimulation; For bilateral limb coordination movement tasks, obtain the EEG signals of users with unilateral limb hemiplegia during movement; Based on the EEG signal analysis, the brain activity state of the user with unilateral hemiplegia and the performance change information of the coordinated movement of bilateral limbs are obtained; based on the performance change information, the correlation information between the coordinated movement of bilateral limbs and electrophysiological variables under the intervention of visual feedback is determined through transcranial magnetic stimulation.

4. The method according to claim 3, characterized in that For the unilateral limb movement task, the electromyographic signals of the unilateral limb hemiplegic user and the normal user during the movement are obtained; The method includes obtaining behavioral difference information between a user with unilateral limb hemiplegia and a normal user when exercising based on the electromyographic signal analysis; determining the association information between the movement of the unilateral limb rhythm and speed and the electrophysiological variables through at least one of electrical stimulation and transcranial magnetic stimulation based on the behavioral difference information, including at least one of the following: For the tapping movement of a unilateral limb, a first electromyographic signal of a user with unilateral limb hemiplegia and a normal user during the movement is obtained; based on the first electromyographic signal, first behavioral difference information when the user with unilateral limb hemiplegia and the normal user perform the tapping movement is obtained; based on the first behavioral difference information, a correlation relationship between the cortex and the electromyographic onset time under different rhythmic movements and the rhythmic tone start time is determined; based on the correlation relationship, correlation information between each electrophysiological variable when the unilateral limb performs different rhythmic movements is determined through at least one of electrical stimulation and transcranial magnetic stimulation; For the abduction movement of unilateral limbs, the second electromyographic signals of the users with unilateral limb hemiplegia and the normal users during the movement are obtained; Obtaining second behavior difference information when a user with unilateral limb hemiplegia and a normal user perform abduction movement based on the second electromyographic signal analysis; Based on the second behavioral difference information, the correlation between the response speed of the cortex and the abductor muscle is determined; based on the correlation, the correlation information between each electrophysiological variable when the unilateral limb moves at different speeds is determined through at least one of electrical stimulation or transcranial magnetic stimulation.

5. The method according to claim 3, characterized in that: The method of determining the correlation information between the coordinated movement of bilateral limbs and electrophysiological variables under visual feedback intervention through transcranial magnetic stimulation based on the performance change information includes: determining an electrophysiological indicator of brain electrical connectivity based on the performance change information; Based on the electrophysiological indicators, transcranial magnetic stimulation is used for movement intervention during exercise to determine the correlation information between the coordinated movement of bilateral limbs under visual feedback intervention and various electrophysiological variables.

6. The method according to claim 1, characterized in that The control strategy includes at least one of a visual feedback intervention strategy and a transcranial magnetic stimulation strategy; The electrophysiological characterization model is configured with an electrophysiological neural mechanism, and the electrophysiological neural mechanism reflects the changes of various electrophysiological variables when a normal user correctly performs corresponding movements under various movement intentions; The control strategy comprises at least one of the following steps: Displaying a picture corresponding to the visual feedback intervention strategy through a display device, and controlling the user to perform the target movement based on the movement intention; A stimulation signal corresponding to the transcranial magnetic stimulation strategy is outputted through a motion control device worn by the user to control the user to perform the target motion based on the motion intention.

7. A motion control device based on a brain-computer interface, characterized in that: include: A signal acquisition module, used to collect EEG signals of the user performing motor imagery when displaying or broadcasting information related to the target movement; An intention determination module, used to perform signal recognition on the EEG signal to determine the user's movement intention; A variable collection module, used for collecting a first electrophysiological variable corresponding to the user performing a movement related to the movement intention; the first electrophysiological variable is collected when the target movement is performed for the first time; A variable determination module, used to estimate a second electrophysiological variable corresponding to the user performing the target movement under the movement intention by using a pre-constructed electrophysiological representation model; the electrophysiological representation model is obtained by training the association information between the movement task determined based on a preset limb movement task and the electrophysiological variable; A strategy determination module is used to perform the following control operation if the difference between the first electrophysiological variable and the second electrophysiological variable is greater than a preset difference value: determine the control strategy for performing the target movement based on the difference value, control the user to perform the target movement under the movement intention based on the control strategy, and collect the third electrophysiological variable when the user performs the target movement under control; if the difference between the third electrophysiological variable and the second electrophysiological variable is greater than the preset difference value, then loop the control operation.

8. An electronic device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images