Closed-loop brain computer interface-based rehabilitation training method and apparatus, device, and storage medium

Abstract

The present application relates to a closed-loop brain computer interface-based rehabilitation training method and apparatus, a device, and a storage medium. The method comprises: assessing fine motor skills of a hand of a subject, and setting a target training force range on the basis of an assessment result; collecting electroencephalogram signals of the subject during actual hand-grasping or motor imagery of hand-grasping, and collecting, by means of an electromyographic signal collection module, electromyographic signals of the hand of the subject during hand-grasping; acquiring a movement intention force of the subject as an actual force; calculating a difference between the actual force and a target training force, and generating a control instruction on the basis of the difference to control a rehabilitation training device; and providing, to the subject by means of the rehabilitation training device, a haptic feedback force equal to the difference such that the subject adjusts the force of motor imagery or actual hand-grasping, and generating a training action for rehabilitation training. In the present application, by integrating brain computer interface technology with 3D games, the interactivity and enjoyment are enhanced for subjects, thereby improving the enthusiasm and initiative for training.

Description

Closed-loop brain-computer interface rehabilitation training methods, devices, equipment, and storage media Technical Field

[0001] This application belongs to the field of EEG signal application technology, and specifically relates to a closed-loop brain-computer interface rehabilitation training method, device, equipment, and storage medium. Background Technology

[0002] Stroke is a group of acute diseases caused by impaired blood circulation to the brain, leading to brain tissue damage. Stroke causes brain cells to die from oxygen deprivation, resulting in various clinical symptoms such as limb paralysis and motor dysfunction. It is the second leading cause of death worldwide and the third leading cause of death and disability. Therefore, rehabilitation training after a stroke is particularly important.

[0003] Currently, traditional rehabilitation training methods for stroke include physical therapy, occupational therapy, and speech therapy. These methods stimulate the brain and nervous system to remodel and adapt through repetitive and systematic exercise, thereby improving impaired neurological function. While traditional methods can help patients regain basic function to some extent, their relatively monotonous training environment and methods make it difficult to increase patient participation and interest. Furthermore, they lack targeted and individualized design, failing to meet the personalized needs of different patients. Real-time monitoring and precise feedback are also difficult to achieve, making it challenging to accurately quantify and evaluate treatment effectiveness.

[0004] BCI (Brain-Computer Interface) refers to a hardware and software communication system that enables information exchange between the human or animal brain and external devices by connecting the brain and the external environment, without relying on the conventional neuromuscular physiological system. When applied to stroke rehabilitation training, the BCI system can utilize the user's brain activity as a communication medium between the person and the environment, allowing the subject to operate external devices through brain activity, independent of peripheral nerve or muscle control. In existing technologies, BCI-based rehabilitation methods typically use 2D planes such as computer screens as visual cues or feedback, enabling real-time monitoring and analysis of the subject's cerebral cortex's electrophysiological signals to provide immediate physiological feedback for adjusting training difficulty and feedback methods. The disadvantages of this method are: tactile feedback cannot be precisely adjusted according to the subject's actual needs, affecting rehabilitation effectiveness; and it suffers from weak immersion, poor interactivity, and low engagement, making it difficult to motivate the subject's initiative and enthusiasm for rehabilitation training. Summary of the Invention

[0005] This application provides a closed-loop brain-computer interface rehabilitation training method, device, equipment, and storage medium, aiming to at least partially solve one of the aforementioned technical problems in the prior art.

[0006] To address the above problems, this application provides the following technical solution:

[0007] A closed-loop brain-computer interface rehabilitation training method includes:

[0008] Assess the trainee's fine motor skills and set training target intensity ranges based on the assessment results;

[0009] The EEG signal acquisition module collects the trainee's EEG signals during actual movement / motor imagination of hand grasping, and the EMG signal acquisition module collects the trainee's EMG signals during hand grasping.

[0010] The electroencephalogram (EEG) and electromyogram (EMG) signals are synchronized with the game scene of the user interface module, and the EEG and EMG signals are processed online to obtain the intensity value of the trainee's movement intention, which is used as the actual intensity value.

[0011] The difference between the actual force value and the training target force value is calculated as the residual force, and a control command is generated based on the residual force; the training target force value is any value within the training target force range.

[0012] The rehabilitation training device is controlled by the control commands to provide the trainee with tactile feedback force equal to the residual force, so that the trainee can adjust the motor imagination / actual grip strength according to the tactile feedback force and generate training movements. The game scene is changed according to the training movements until the training ends; wherein, the rehabilitation training device is worn on the trainee's hand.

[0013] The technical solution adopted in this application embodiment further includes: before the step of collecting the EEG signals of the trainee's actual hand grasping during movement / motor imagination through the EEG signal acquisition module, and collecting the electromyographic signals of the trainee's hand grasping during the process through the electromyographic signal acquisition module, the method further includes:

[0014] After the trainee puts on the rehabilitation training equipment, the user interface module receives the training mode selected by the trainee and displays the game scene to the trainee.

[0015] The technical solution adopted in this application embodiment also includes: the user interface module includes a scene display unit, a user prompt unit, and a user information unit. The scene display unit is used to display the game scene to the trainee. The user prompt unit is used to prompt the trainee to select the training mode, display information during the training process, and training steps according to the game rules. The user information unit is used to display the trainee's brain topography, actual force value, and remaining force value during the training process in a real-time information visualization interface.

[0016] The technical solution adopted in this application embodiment further includes: acquiring the EEG signals of the trainee during actual movement / motor imagination hand grasping through the EEG signal acquisition module, and acquiring the electromyographic signals of the trainee during hand grasping through the electromyographic signal acquisition module, specifically:

[0017] The EEG signal acquisition module is arranged on a flexible, wearable, and detachable EEG cap, which is worn on the head of the trainee.

[0018] The electromyography (EMG) signal acquisition module includes four pairs of EMG electrodes and ten hand electrodes. The four pairs of EMG electrodes are respectively attached to the bilateral frontalis muscles, left and right temporalis-masseter muscles, and bilateral posterior cervical trapezius muscles of the trainee, and are used to collect facial EMG signals during the trainee's hand grasping. The ten hand electrodes are placed on the upper half of the trainee's forearm and are arranged in a uniform circumference, and are used to collect upper limb EMG signals during the trainee's grasping.

[0019] The technical solution adopted in this application embodiment also includes:

[0020] The online processing of the electroencephalogram (EEG) and electromyogram (EMG) signals to obtain the intensity value of the trainee's movement intention also includes:

[0021] The EEG signal is preprocessed by using a bandpass filter to retain the signal of the frequency band of interest, and using ICA to remove electrooculography, electromyography, electrocardiography, power supply interference and motion artifacts to obtain a clean EEG signal.

[0022] Motion state features are extracted from the preprocessed EEG signals to obtain a state feature vector matrix;

[0023] The state feature vector matrix is ​​input into LSSVM for motion state decoding to generate the trainer's motion intention.

[0024] The technical solution adopted in this application embodiment further includes: obtaining the trainee's intention force value as the actual force value, including:

[0025] A force sensor is worn on the trainee's hand, and the actual force applied by the trainee's hand when grasping is directly obtained through the force sensor;

[0026] Alternatively, the actual force applied by the trainee's hand when grasping can be predicted using the electroencephalogram (EEG) and electromyogram (EMG) signals.

[0027] Alternatively, the electroencephalogram (EEG), electromyogram (EMG), and actual force values ​​acquired by the force sensor can be fused according to a set ratio to predict the force applied by the trainee's hand when grasping, and the final actual force value can be inferred by Bayesian posterior probability.

[0028] The technical solution adopted in this application embodiment further includes: controlling the rehabilitation training equipment through the control command to provide the trainee with a tactile feedback force equal to the residual force, so that the trainee adjusts the motor imagination / actual gripping force according to the tactile feedback force and generates training movements, and controlling the change of game scene according to the training movements, specifically:

[0029] The rehabilitation training equipment provides the trainee with tactile feedback force equal to the residual force, allowing the trainee to adjust the motor imagination / actual gripping force according to the tactile feedback force until the training target force value is reached and the duration is maintained for the preset duration, thus generating a successful training movement.

[0030] When a successful training action is generated, the user interface module controls the change of the game scene according to the training action, and provides game training prompts to the trainee according to the game rules until the training ends.

[0031] Another technical solution adopted in this application embodiment is: a closed-loop brain-computer interface rehabilitation training device, comprising:

[0032] Target value setting module: used to assess the trainee's fine motor skills and set the training target intensity range based on the assessment results;

[0033] EEG signal acquisition module: used to acquire EEG signals when the trainee is actually moving / imagining their hand grasping;

[0034] Electromyography (EMG) signal acquisition module: used to acquire EMG signals during the trainee's hand grasping process;

[0035] The motion intent acquisition module is used to synchronize the electroencephalogram (EEG) and electromyogram (EMG) signals with the game scene of the user interface module, and to process the EEG and EMG signals online to obtain the intensity value of the trainee's motion intent as the actual intensity value.

[0036] Control output module: used to calculate the difference between the actual force value and the training target force value as the residual force, and generate control commands based on the residual force; the training target force value is any value in the training target force range;

[0037] Training feedback module: used to control the rehabilitation training device through the control commands, providing the trainee with tactile feedback force equal to the residual force, so that the trainee can adjust the motor imagination / actual grip strength according to the tactile feedback force and generate training movements, and control the change of game scene according to the training movements until the training ends; wherein, the rehabilitation training device is worn on the trainee's hand.

[0038] Another technical solution adopted in this application embodiment is: a device, the device including a processor and a memory coupled to the processor, wherein,

[0039] The memory stores program instructions for implementing the closed-loop brain-computer interface rehabilitation training method;

[0040] The processor is used to execute the program instructions stored in the memory to control the closed-loop brain-computer interface rehabilitation training method.

[0041] Another technical solution adopted in this application embodiment is: a storage medium storing program instructions that can be run by a processor, the program instructions being used to execute the closed-loop brain-computer interface rehabilitation training method.

[0042] Compared to existing technologies, the beneficial effects of the embodiments of this application are as follows: The closed-loop brain-computer interface rehabilitation training method, device, equipment, and storage medium of the embodiments of this application integrate brain-computer interface technology with 3D games. Utilizing virtual game scenes, it guides trainees to grasp objects with varying degrees of force during actual movement / motor imagination. Simultaneously, it collects EEG and EMG signals from the trainee's actual movement / motor imagination, extracts the trainee's movement intention, obtains the actual force value, and monitors the trainee's actual force value and the difference from the target force value in real time to obtain residual force. Based on the residual force, it generates control commands to control the rehabilitation training equipment, providing corresponding tactile feedback to the trainee, inducing the trainee to optimize motor performance, improving the trainee's fine motor skills, and thus enhancing the rehabilitation effect. The embodiments of this application activate the motor sensory areas of the trainee's brain through actual movement / motor imagination, using the rehabilitation training equipment to provide tactile feedback to help the trainee train hand function. Personalized visual and tactile feedback is provided based on the motor performance of each training session, greatly enhancing the interactivity and enjoyment of the trainee, and increasing the trainee's training enthusiasm and initiative. Attached Figure Description

[0043] Figure 1 is a flowchart of a closed-loop brain-computer interface rehabilitation training method according to an embodiment of this application;

[0044] Figure 2 is a schematic diagram of the structure of the closed-loop brain-computer interface rehabilitation training device according to an embodiment of this application;

[0045] Figure 3 is a schematic diagram of the device structure according to an embodiment of this application;

[0046] Figure 4 is a schematic diagram of the structure of the storage medium according to an embodiment of this application. Detailed Implementation

[0047] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0048] The terms "first," "second," and "third" in this application are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined as "first," "second," or "third" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified. All directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of this application are only used to explain the relative positional relationships and movements between components in a specific orientation (as shown in the figures). If the specific orientation changes, the directional indications also change accordingly. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0049] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0050] Specifically, please refer to Figure 1, which is a flowchart of the closed-loop brain-computer interface rehabilitation training method according to an embodiment of this application. The closed-loop brain-computer interface rehabilitation training method according to an embodiment of this application includes the following steps:

[0051] S100: Before training begins, assess the trainee's fine motor skills and set the training target intensity range based on the assessment results.

[0052] In this step, fine motor skills of the hand can be assessed based on information such as the trainee's gender, age, and degree of motor impairment, so as to set reasonable training target intensity ranges for different individuals and meet their training needs.

[0053] S110: After the trainee puts on the rehabilitation training equipment, it receives the training mode selected by the trainee through the user interface module and displays the game scene to the trainee.

[0054] In this step, the rehabilitation training device is a flexible wearable glove robot, worn on the trainee's hand. The user interface module includes a scene display unit, a user prompt unit, and a user information unit. The scene display unit is used to show the trainee the game scene; the user prompt unit is used to prompt the trainee to select the training mode according to the game rules, display information for each trial during training, and guide the trainee through the preparation, actual movement / movement visualization, and rest steps of each training session; the user information unit displays the trainee's brain topography map and actual force value, as well as the difference between the actual force value and the preset training target force value, in real time through a real-time information visualization interface, providing the trainee with timely visual feedback to help them quickly identify and correct deficiencies in force. It is understood that the rehabilitation training device can also use other wearable flexible devices that focus on hand movement and perception, such as flexible wearable finger cot robots.

[0055] Specifically, this application uses an archery game developed based on the Unity 3D platform as an example. The game scene is set in a rural area with a small bridge, flowing water, and forest. Multiple targets are set up, each representing different target strengths and positions. The targets are arranged according to the target strength, from smallest to largest, and from farthest to closest. Before starting training, the trainee can freely choose a suitable training mode based on information such as age, gender, and degree of motor impairment through user prompts. It is understood that any other game format that can effectively provide feedback on the trainee's ability to maintain target strength can also be used.

[0056] S120: After training begins, the EEG signal acquisition module collects the EEG signals of the trainee during actual movement / motor imagination hand grasping in real time, and the EMG signal acquisition module collects the EMG signals of the trainee during hand grasping in real time.

[0057] In this step, the EEG signal acquisition module is mounted on a 64-channel flexible wearable and detachable EEG cap, which is worn on the trainee's head. Semi-dry electrodes are used, with the impedance reduced to an appropriate value by lubricating the electrodes with saline solution. Channel positions are determined according to the 10-10 international standard lead system to ensure the highest possible EEG signal acquisition quality. After the EEG cap is worn and the EEG signal acquisition module is activated, it uses a 1000Hz sampling rate to acquire EEG signals during different gripping forces of the trainee's actual movement / motor imagery. The EMG signal acquisition module consists of four pairs of EMG electrodes and ten hand electrodes. The four pairs of EMG electrodes are respectively attached to the trainee's bilateral frontalis muscles, left and right temporalis-masseter muscles, and bilateral posterior cervical trapezius muscles to acquire facial EMG signals during hand gripping. The ten hand electrodes are placed on the upper half of the trainee's forearm, arranged in a uniform circular pattern, to acquire upper limb EMG signals during gripping.

[0058] S130: After synchronizing the collected EEG and EMG signals with the scene display unit of the user interface module, the collected EEG signals are processed online through the EEG signal processing module to extract the motion state features in the EEG signals, and the motion state is decoded according to the motion state features to generate the trainee's motion intention and obtain the actual force value.

[0059] In this step, the online processing of brain signals by the EEG signal processing module includes the following steps:

[0060] S131: The collected 64-channel EEG signals were preprocessed. Bandpass filters were used to retain signals in the frequency bands of interest. ICA (Independent Components Analysis) was used to remove electrooculography, electromyography, electrocardiography, power supply interference, and motion artifacts to obtain clean EEG signals.

[0061] S132: Extract motion state features from the preprocessed EEG signals to obtain a state feature vector matrix;

[0062] S133: Input the state feature vector matrix into LSSVM (least squares support vector machine) for motion state decoding to generate the trainer's motion intention; other algorithms with higher decoding accuracy and faster speed can also be used for motion state decoding.

[0063] In this embodiment, the actual force value of the trainee is obtained in three ways: First, a force sensor is worn on the trainee's hand to directly acquire the actual force value applied when the trainee grasps the object; second, the actual force value applied when the trainee grasps the object is predicted by the electroencephalogram (EEG) signal acquired by the EEG signal acquisition module and the electromyogram (EMG) signal acquired by the EMG signal acquisition module; third, the EEG signal, EMG signal, and the actual force value acquired by the force sensor are fused according to a certain fusion ratio to predict the force applied when the trainee grasps the object, and the final actual force value is inferred by Bayesian posterior probability. The fusion ratio can be set according to the trainee's age, gender, and degree of motor impairment.

[0064] S140: Calculate the difference between the actual force value and the training target force value as the residual force, generate corresponding control commands based on the residual force value, and transmit the control commands to the rehabilitation training equipment through the control output module;

[0065] In this step, the control output module includes an identification information unit and an output device unit. The identification information unit is used to acquire the residual force value, generate corresponding control commands based on the residual force value, and transmit the control commands to the output device unit (i.e., the rehabilitation training device), controlling the rehabilitation training device to provide tactile feedback to the trainee. The training target force value is any value within the training target force range.

[0066] S150: The rehabilitation training equipment provides the trainee with tactile feedback force equal to the residual force, so that the trainee can adjust the motor imagination / actual gripping force according to the tactile feedback force until the training target force value is reached and the duration is maintained for the preset duration, then a successful training movement is generated.

[0067] In this step, after the trainee receives tactile feedback from the glove robot, they adjust their imagined / actual grip strength based on the tactile feedback and continue the training until the actual strength value reaches the training target strength value and can be maintained for a preset duration. This is considered a successful training movement. Conversely, if the trainee's imagined / actual hand grip strength does not reach the training target strength value, or reaches the training target strength value but does not maintain it for the preset duration, the training movement is considered a failure, and steps S100 to S140 are repeated. It is understood that if the difference between the trainee's actual strength value and the target strength value is small, the tactile feedback provided by the glove robot is weaker; conversely, if the difference is large, the tactile feedback provided by the glove robot is stronger. This application successfully provides a tactile feedback experience of hand strength through the tactile feedback provided by the flexible wearable glove robot, helping trainees quickly identify and correct deficiencies in strength, and providing a potential means to promote the plasticity and learning of the motor sensory system.

[0068] S160: When a successful training action is generated, the user interface module controls the change of the game scene according to the training action, and provides game training prompts to the trainee according to the game rules until the training ends.

[0069] In this step, taking an archery game as an example, when a successful training action is generated, the user interface module controls the scene display unit to transform the game scene into an arrow being shot and accurately hitting a set target. If the trainee fails to reach the training target force value within the specified time, the game scene will show an arrow being shot but failing to hit the target. Each training session includes ten actions. After the ten training actions are completed, the number of hits on each target and the start time of the training are counted, and a training record is generated and saved. After each training session, the trainee can freely select the training mode for the next training session through the user prompt unit. It can be understood that this embodiment of the application, by combining training content with a 3D game and providing real-time tactile and visual feedback to the trainee, greatly enhances the interactivity and fun of the training process, and improves the trainee's training enthusiasm and initiative.

[0070] Based on the above, the closed-loop brain-computer interface rehabilitation training method of this application integrates brain-computer interface technology with 3D games. Utilizing virtual game scenes, it guides trainees to grasp objects with varying degrees of force through actual movement / motor imagery. Simultaneously, it collects EEG and EMG signals from the trainee's actual movement / motor imagery, extracts the trainee's actual force value, and monitors the actual force value and its difference from the target force value in real time as residual force. Based on this residual force, control commands are generated to control the rehabilitation training equipment to provide corresponding tactile feedback to the trainee, inducing the trainee to optimize motor performance and improve their fine motor skills, thereby enhancing the rehabilitation effect. This application embodiment activates the motor sensory areas of the trainee's brain through actual movement / motor imagery, uses rehabilitation training equipment to provide tactile feedback, helps trainees train hand function, and provides personalized visual and tactile feedback based on the motor performance of each training session, greatly enhancing the interactivity and enjoyment of the training, and increasing the trainee's enthusiasm and initiative.

[0071] Please refer to Figure 2, which is a schematic diagram of the structure of the closed-loop brain-computer interface rehabilitation training device according to an embodiment of this application. The closed-loop brain-computer interface rehabilitation training method device 40 according to an embodiment of this application includes:

[0072] Target value setting module 41: Used to assess the trainee's fine motor skills and set the training target intensity range based on the assessment results;

[0073] EEG signal acquisition module 42: used to acquire EEG signals when the trainee is actually moving / imagining the hand grasping;

[0074] Electromyography signal acquisition module 43: used to acquire electromyography signals during the trainee's hand grasping process;

[0075] The motion intention acquisition module 44 is used to synchronize the electroencephalogram (EEG) signals and electromyogram (EMG) signals with the game scene of the user interface module, and to process the EEG signals and EMG signals online to obtain the motion intention strength value of the trainee as the actual strength value.

[0076] Control output module 45: used to calculate the difference between the actual force value and the training target force value as the residual force, and generate control commands based on the residual force; the training target force value is any value in the training target force range;

[0077] Training feedback module 46: used to control the rehabilitation training device through the control command, provide the trainee with tactile feedback force equal to the residual force, so that the trainee can adjust the motor imagination / actual gripping force according to the tactile feedback force and generate training movements, and control the change of game scene according to the training movements until the training ends; wherein, the rehabilitation training device is worn on the trainee's hand.

[0078] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0079] The apparatus provided in this application can be applied to the foregoing method embodiments. For details, please refer to the description of the above method embodiments, which will not be repeated here.

[0080] Please refer to Figure 3, which is a schematic diagram of the device structure according to an embodiment of this application. The device 50 includes:

[0081] Memory 51 storing executable program instructions;

[0082] Processor 52 connected to memory 51;

[0083] The processor 52 is used to call the executable program instructions stored in the memory 51 and perform the following steps: assess the trainee's fine motor skills and set the training target strength range value according to the assessment results; collect the EEG signals of the trainee during actual movement / motor imagination hand grasping through the EEG signal acquisition module, and collect the EMG signals of the trainee during hand grasping through the EMG signal acquisition module; synchronize the EEG signals and EMG signals with the game scene of the user interface module, and process the EEG signals and EMG signals online to obtain the trainee's intention strength value as the actual strength value; calculate the difference between the actual strength value and the training target strength value as the residual force, and generate control instructions based on the residual force; the training target strength value is any value in the training target strength range value; control the rehabilitation training device through the control instructions to provide the trainee with tactile feedback force equal to the residual force, so that the trainee adjusts the motor imagination / actual grasping force according to the tactile feedback force and generates training actions, and controls the game scene to change according to the training actions until the training ends; wherein, the rehabilitation training device is worn on the trainee's hand.

[0084] The processor 52 can also be referred to as a CPU (Central Processing Unit). The processor 52 may be an integrated circuit chip with signal processing capabilities. The processor 52 can also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor can be a microprocessor or any conventional processor.

[0085] Please refer to Figure 4, which is a schematic diagram of the structure of the storage medium according to an embodiment of this application. The storage medium of this application embodiment stores program instructions 61 capable of implementing the following steps: assessing the trainee's fine motor skills and setting a training target strength range value based on the assessment results; acquiring EEG signals during the trainee's actual hand movement / motor imagery grasping using an EEG signal acquisition module, and acquiring EMG signals during the trainee's hand grasping using an EMG signal acquisition module; synchronizing the EEG and EMG signals with the game scene of the user interface module, and processing the EEG and EMG signals online to obtain the trainee's intention strength value as the actual strength value; calculating the difference between the actual strength value and the training target strength value as the residual force, and generating control instructions based on the residual force; the training target strength value is any value within the training target strength range value; controlling the rehabilitation training device through the control instructions to provide the trainee with a tactile feedback force equal to the residual force, so that the trainee adjusts the motor imagery / actual grasping force based on the tactile feedback force and generates training actions, and controlling the game scene to change based on the training actions until the training ends; wherein, the rehabilitation training device is worn on the trainee's hand.

[0086] The program instructions 61 can be stored in the aforementioned storage medium in the form of a software product. These instructions include several instructions to cause a device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program instructions, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks, or terminal devices such as computers, servers, mobile phones, and tablets. The server can be an independent server or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0087] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interfaces, apparatuses, or units, and may be electrical, mechanical, or other forms.

[0088] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated units described above can be implemented in hardware or as software functional units. The above are merely embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made based on the description and drawings of this application, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A closed-loop brain-computer interface rehabilitation training method, characterized in that, include: Assess the trainee's fine motor skills and set training target intensity ranges based on the assessment results; The EEG signal acquisition module collects the trainee's EEG signals during actual movement / motor imagination of hand grasping, and the EMG signal acquisition module collects the trainee's EMG signals during hand grasping. The electroencephalogram (EEG) and electromyogram (EMG) signals are synchronized with the game scene of the user interface module, and the EEG and EMG signals are processed online to obtain the intensity value of the trainee's movement intention, which is used as the actual intensity value. The difference between the actual force value and the training target force value is calculated as the residual force, and a control command is generated based on the residual force; the training target force value is any value within the training target force range. The rehabilitation training device is controlled by the control commands to provide the trainee with tactile feedback force equal to the residual force, so that the trainee can adjust the motor imagination / actual grip strength according to the tactile feedback force and generate training movements. The game scene is changed according to the training movements until the training ends; wherein, the rehabilitation training device is worn on the trainee's hand.

2. The closed-loop brain-computer interface rehabilitation training method according to claim 1, characterized in that, Before acquiring the EEG signals of the trainee during actual hand grasping via the EEG signal acquisition module, and acquiring the electromyography (EMG) signals of the trainee during hand grasping via the EMG signal acquisition module, the method further includes: After the trainee puts on the rehabilitation training equipment, the user interface module receives the training mode selected by the trainee and displays the game scene to the trainee.

3. The closed-loop brain-computer interface rehabilitation training method according to claim 2, characterized in that, The user interface module includes a scene display unit, a user prompt unit, and a user information unit. The scene display unit is used to display the game scene to the trainee, and the user prompt unit is used to prompt the trainee to select the training mode, display information during the training process, and training steps according to the game rules. The user information unit is used to display the trainee's brain topography, actual force value, and remaining force value in a real-time information visualization interface during the training process.

4. The closed-loop brain-computer interface rehabilitation training method according to claim 1, characterized in that, The process involves acquiring EEG signals from the trainee during actual hand grasping using an EEG signal acquisition module, and acquiring electromyographic (EMG) signals from the trainee during hand grasping using an EMG signal acquisition module. Specifically: The EEG signal acquisition module is arranged on a flexible, wearable, and detachable EEG cap, which is worn on the head of the trainee. The electromyography (EMG) signal acquisition module includes four pairs of EMG electrodes and ten hand electrodes. The four pairs of EMG electrodes are respectively attached to the bilateral frontalis muscles, left and right temporalis-masseter muscles, and bilateral posterior cervical trapezius muscles of the trainee, and are used to collect facial EMG signals during the trainee's hand grasping. The ten hand electrodes are placed on the upper half of the trainee's forearm and are arranged in a uniform circumference, and are used to collect upper limb EMG signals during the trainee's grasping.

5. The closed-loop brain-computer interface rehabilitation training method according to claim 4, characterized in that, The online processing of the electroencephalogram (EEG) and electromyogram (EMG) signals to obtain the intensity value of the trainee's movement intention also includes: The EEG signal is preprocessed by using a bandpass filter to retain the signal of the frequency band of interest, and using ICA to remove electrooculography, electromyography, electrocardiography, power supply interference and motion artifacts to obtain a clean EEG signal. Motion state features are extracted from the preprocessed EEG signals to obtain a state feature vector matrix; The state feature vector matrix is ​​input into LSSVM for motion state decoding to generate the trainer's motion intention.

6. The closed-loop brain-computer interface rehabilitation training method according to any one of claims 1 to 5, characterized in that, The process of obtaining the trainee's intended force value as the actual force value includes: A force sensor is worn on the trainee's hand, and the actual force applied by the trainee's hand when grasping is directly obtained through the force sensor; Alternatively, the actual force applied by the trainee's hand when grasping can be predicted using the electroencephalogram (EEG) and electromyogram (EMG) signals. Alternatively, the electroencephalogram (EEG), electromyogram (EMG), and actual force values ​​acquired by the force sensor can be fused according to a set ratio to predict the force applied by the trainee's hand when grasping, and the final actual force value can be inferred by Bayesian posterior probability.

7. The closed-loop brain-computer interface rehabilitation training method according to claim 6, characterized in that, The control commands control the rehabilitation training equipment, providing the trainee with tactile feedback force equal to their residual force. This allows the trainee to adjust their motor imagination / actual grip strength based on the tactile feedback force and generate training movements. The game scene is then changed based on these training movements. Specifically: The rehabilitation training equipment provides the trainee with tactile feedback force equal to the residual force, allowing the trainee to adjust the strength of motor imagination / actual grasping according to the tactile feedback force until the training target strength value is reached and the duration is maintained for the preset time, thus generating a successful training movement. When a successful training action is generated, the user interface module controls the change of the game scene according to the training action, and provides game training prompts to the trainee according to the game rules until the training ends.

8. A closed-loop brain-computer interface rehabilitation training device, characterized in that, include: Target value setting module: used to assess the trainee's fine motor skills and set the training target intensity range based on the assessment results; EEG signal acquisition module: used to acquire EEG signals when the trainee is actually moving / imagining their hand grasping; Electromyography (EMG) signal acquisition module: used to acquire EMG signals during the trainee's hand grasping process; The motion intent acquisition module is used to synchronize the electroencephalogram (EEG) and electromyogram (EMG) signals with the game scene of the user interface module, and to process the EEG and EMG signals online to obtain the intensity value of the trainee's motion intent as the actual intensity value. Control output module: used to calculate the difference between the actual force value and the training target force value as the residual force, and generate control commands based on the residual force; the training target force value is any value in the training target force range; Training feedback module: used to control the rehabilitation training device through the control commands, providing the trainee with tactile feedback force equal to the residual force, so that the trainee can adjust the motor imagination / actual grip strength according to the tactile feedback force and generate training movements, and control the change of game scene according to the training movements until the training ends; wherein, the rehabilitation training device is worn on the trainee's hand.

9. A device, characterized in that, The device includes a processor and a memory coupled to the processor, wherein, The memory stores program instructions for implementing the closed-loop brain-computer interface rehabilitation training method according to any one of claims 1-7; The processor is used to execute the program instructions stored in the memory to control the closed-loop brain-computer interface rehabilitation training method.

10. A storage medium, characterized in that, The device stores processor-executable program instructions for performing the closed-loop brain-computer interface rehabilitation training method according to any one of claims 1 to 7.

Images