A brain-computer interface interaction system and method for cerebral infarction rehabilitation training
By extracting features from electroencephalogram (EEG) signals and performing comprehensive feedback processing, the interference problem of brain-computer interface systems in cerebral infarction rehabilitation training was solved, enabling personalized rehabilitation plans and improving rehabilitation outcomes.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- HEILONGJIANG ACAD OF TCM
- Filing Date
- 2026-02-09
- Publication Date
- 2026-05-29
AI Technical Summary
Existing brain-computer interface systems are susceptible to interference from electrooculography, electromyography, electrocardiography, and the environment during cerebral infarction rehabilitation training, leading to increased errors in feature extraction and classification. Furthermore, they lack visual and auditory interactive feedback, which affects rehabilitation outcomes.
By receiving and preprocessing EEG signal data, spatial, temporal, and frequency domain features are extracted. Combined with the patient's visual, auditory, and tactile feedback data, a comprehensive rehabilitation assessment is conducted to generate a personalized rehabilitation treatment plan.
It improves the suitability and effectiveness of rehabilitation training, enhances patients' concentration through comprehensive signal feedback, and improves rehabilitation outcomes.
Smart Images
Figure CN122117231A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of EEG feature processing technology, specifically a brain-computer interface interaction system and method for rehabilitation training of cerebral infarction. Background Technology
[0002] Brain-computer interface (BCI) is an intelligent interactive system that uses special electrodes to collect neural signals and then uses computers to extract, classify, and decode them to obtain specific brain activity information and instructions such as plans contained in the neural signals. It eliminates the need for peripheral nerves and muscle tissue and enables people to communicate with the external environment. It is currently a hot research topic in the field of rehabilitation and is gradually being applied to prosthetic limb control and rehabilitation training for patients with motor dysfunction.
[0003] However, existing brain-computer interfaces have the following problems:
[0004] Because EEG signals are easily affected by electrooculography, electromyography, electrocardiography, and environmental interference, the errors in feature extraction and classification increase, thus affecting the rehabilitation effect. Furthermore, the system's feedback is only provided through a single visual or auditory sense, lacking the ability to integrate visual and auditory feedback, which makes patients unable to concentrate during rehabilitation, resulting in mediocre rehabilitation outcomes. Summary of the Invention
[0005] To address the shortcomings mentioned in the background section, the present invention aims to provide a brain-computer interface interaction system and method for rehabilitation training of cerebral infarction.
[0006] Firstly, the objective of this invention can be achieved through the following technical solution: a brain-computer interface interaction method for rehabilitation training of cerebral infarction, the method comprising the following steps:
[0007] Receive EEG signal data, preprocess the EEG signal data to obtain processed EEG signal data, wherein the EEG signal data includes μ wave signal data and β wave signal data;
[0008] Feature extraction is performed on the processed EEG signal data to obtain EEG feature data. Based on the EEG feature data, feature weighted fusion calculation is performed to obtain the comprehensive EEG feature fusion coefficient. The EEG feature data includes spatial domain features, temporal domain features, and frequency domain features.
[0009] The system receives patient feedback data, performs comprehensive calculations on the feedback signals based on the patient feedback data, and obtains a comprehensive signal feedback coefficient. The patient feedback data includes visual data, auditory data, and tactile data. Based on the comprehensive signal feedback coefficient and the comprehensive EEG feature fusion coefficient, a comprehensive rehabilitation assessment is performed to obtain a comprehensive rehabilitation assessment coefficient. Based on the comprehensive rehabilitation assessment coefficient, a rehabilitation treatment plan is generated for the patient.
[0010] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: the spatial domain features are extracted by a common spatial mode algorithm, the time domain features are the mean and variance of the signal amplitude, and the frequency domain features are the power spectral density of a preset specific frequency band.
[0011] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: the calculation process of feature weighted fusion calculation based on EEG feature data includes:
[0012] The EEG feature data are labeled as follows: spatial features are labeled as Ki, time-domain features are labeled as Si, and frequency-domain features are labeled as Pi; where i is the data index of the EEG feature data, and i = 1, 2, 3, ..., n, and n is the total number of EEG feature data.
[0013] The calculation formula is as follows:
[0014]
[0015] In the formula, The fusion coefficients of comprehensive EEG features are defined as follows: K0 is the spatial weight matrix, S0 is the temporal weight matrix, P0 is the frequency weight matrix, α, β, and γ are all preset weight coefficients, and satisfy α+β+γ=1; G() is the feature quality assessment function.
[0016] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: the process of comprehensively calculating feedback signals based on patient feedback data includes the following steps:
[0017] The patient feedback data is labeled, with visual data labeled as Vj, auditory data labeled as Tj, and tactile data labeled as Cj, where j is the number of patient feedback data and j = 1, 2, 3, ..., m, and m is the total number of patient feedback data.
[0018] Using formula The comprehensive signal feedback coefficient is calculated. Where V0 is the original visual intensity coefficient, T0 is the original auditory intensity coefficient, C0 is the original tactile intensity coefficient, a is the adaptive adjustment coefficient, R1 is the physiological response index coefficient, and R2 is the behavioral performance index coefficient.
[0019] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: the process of performing comprehensive rehabilitation assessment processing based on comprehensive signal feedback coefficients and comprehensive EEG feature fusion coefficients to obtain comprehensive rehabilitation assessment coefficients, including:
[0020]
[0021] In the formula, Z is the comprehensive rehabilitation assessment coefficient. and This is the preset scaling factor.
[0022] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: the process of acquiring the electroencephalogram (EEG) signal data includes:
[0023] A wireless computer-controlled electroencephalogram (EEG) acquisition system was used. The patient wore an EEG cap and was injected with conductive gel. The signal quality was ensured by fixing reference electrodes and electrooculogram (EOG) electrodes. After the patient's brain was affected by the external device, μ-wave and β-wave signal data were collected simultaneously as EEG signal data.
[0024] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: the process of preprocessing the electroencephalogram (EEG) signal data includes:
[0025] The raw EEG signal is filtered, rereferenced, and artifacts are detected and removed to obtain processed EEG signal data.
[0026] Secondly, in order to achieve the above objectives, the present invention discloses a brain-computer interface interaction system for rehabilitation training of cerebral infarction, comprising:
[0027] The data processing module is used to receive EEG signal data, preprocess the EEG signal data, and obtain processed EEG signal data, wherein the EEG signal data includes μ wave signal data and β wave signal data.
[0028] The feature extraction and fusion module is used to extract features from the processed EEG signal data to obtain EEG feature data, and to perform feature weighted fusion calculation based on the EEG feature data to obtain a comprehensive EEG feature fusion coefficient. The EEG feature data includes spatial domain features, temporal domain features and frequency domain features.
[0029] The rehabilitation assessment module is used to receive patient feedback data, perform comprehensive calculations on the feedback signals based on the patient feedback data, and obtain a comprehensive signal feedback coefficient; wherein, the patient feedback data includes visual data, auditory data, and tactile data; perform comprehensive rehabilitation assessment processing based on the comprehensive signal feedback coefficient and the comprehensive EEG feature fusion coefficient to obtain a comprehensive rehabilitation assessment coefficient; and generate a rehabilitation treatment plan for the patient based on the comprehensive rehabilitation assessment coefficient.
[0030] In another aspect of the present invention, in order to achieve the above-mentioned objective, a terminal device is disclosed, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor. The memory stores the computer program capable of running on the processor. When the processor loads and executes the computer program, it employs a brain-computer interface interaction method for cerebral infarction rehabilitation training as described above.
[0031] In another aspect of the present invention, in order to achieve the above-mentioned objective, a computer-readable storage medium is disclosed, wherein a computer program is stored in the computer program, and when the computer program is loaded and executed by a processor, a brain-computer interface interaction method for cerebral infarction rehabilitation training as described above is employed.
[0032] The beneficial effects of this invention are:
[0033] This invention extracts features from electroencephalogram (EEG) signal data, performs feature weighting and fusion calculations based on the EEG feature data to obtain a comprehensive EEG feature fusion coefficient, performs comprehensive feedback signal calculations based on patient feedback data to obtain a comprehensive signal feedback coefficient, performs comprehensive rehabilitation assessment processing based on the comprehensive signal feedback coefficient and the comprehensive EEG feature fusion coefficient to obtain a comprehensive rehabilitation assessment coefficient, and finally determines the most suitable rehabilitation treatment plan for the patient based on the comprehensive rehabilitation assessment coefficient, making the rehabilitation process more suitable for the patient's actual situation and improving the rehabilitation effect. Attached Figure Description
[0034] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0035] Figure 1 This is a schematic diagram of the method flow of the present invention;
[0036] Figure 2 This is a schematic diagram of the system structure of the present invention. Detailed Implementation
[0037] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0038] Example 1:
[0039] like Figure 1As shown, a brain-computer interface interaction method for rehabilitation training of cerebral infarction includes the following steps:
[0040] S101: Receive EEG signal data, preprocess the EEG signal data to obtain processed EEG signal data, wherein the EEG signal data includes μ wave signal data and β wave signal data;
[0041] Specifically, the EEG signal data refers to the EEG signals generated by the patient during motor imagery.
[0042] The process of acquiring electroencephalogram (EEG) signal data includes:
[0043] A wireless computer-controlled EEG acquisition system is used. The patient wears an EEG cap and is injected with conductive gel. Signal quality is ensured by fixing reference electrodes (fixed behind the ear) and electrooculography (EOG) electrodes (placed around the eyes to monitor eye movement interference). Then, external devices are used to influence the patient's brain. Specifically, this application involves the patient watching a video of motion imagery played on a screen for a period of time, and then simultaneously acquiring μ-wave and β-wave signal data as EEG signal data. If eye or other interference is detected during the acquisition process, the patient is alerted and the acquisition is repeated.
[0044] The preprocessing of EEG signal data includes:
[0045] To convert the raw, noisy EEG signals into clean signals capable of feature extraction, this embodiment adds a preprocessing step for the EEG signal data. Specifically, the raw EEG signal is filtered to remove frequency band interference unrelated to the target EEG rhythm. The filtering includes bandpass filtering and notch filtering; the bandpass filtering includes high-pass filtering and low-pass filtering. A rereference process is then performed on the filtered EEG signal, specifically an average reference: by subtracting the average signal from each electrode's signal, the EEG signal is made closer to brain activity. Artifact detection and removal are then performed on the rereferenced EEG signal to remove some physiological traces remaining after filtering, making the signal cleaner and purer, ultimately yielding the processed EEG signal data.
[0046] S102: Extract features from the processed EEG signal data to obtain EEG feature data, and perform feature weighted fusion calculation based on the EEG feature data to obtain a comprehensive EEG feature fusion coefficient. The EEG feature data includes spatial domain features, temporal domain features, and frequency domain features.
[0047] Specifically, in this embodiment, the spatial features are features extracted by the co-space pattern algorithm. Furthermore, the spatial features focus on the distribution relationship of signals between different electrodes (spatial locations), reflecting the collaborative working mode of various brain regions.
[0048] The temporal characteristics are the mean and variance of the signal amplitude, which are directly obtained from the time series of the EEG signal.
[0049] Frequency domain features are the power spectral density of a specific preset frequency band, which reflects the energy distribution of EEG signals in different frequency domains and corresponds to different functional states of the brain.
[0050] The computational process of feature weighting and fusion calculation based on EEG feature data includes the following steps:
[0051] The EEG feature data are labeled as follows: spatial features are labeled as Ki, time-domain features are labeled as Si, and frequency-domain features are labeled as Pi; where i is the data index of the EEG feature data, and i = 1, 2, 3, ..., n, and n is the total number of EEG feature data.
[0052] Calculations based on labeled EEG feature data:
[0053]
[0054] In the formula, For the comprehensive EEG feature fusion coefficient, K0 is the spatial weight matrix, S0 is the temporal weight matrix, P0 is the frequency weight matrix, α, β, and γ are all preset weight coefficients, and satisfy α+β+γ=1; G() is the feature quality evaluation function. Therefore, G(Ki) is the spatial feature quality evaluation coefficient, G(Si) is the temporal feature quality evaluation coefficient, and G(Pi) is the frequency feature quality evaluation coefficient.
[0055] Furthermore, in the specific implementation process, the spatial domain weight matrix, the temporal domain weight matrix, and the frequency domain weight matrix are obtained by collecting spatial domain features, temporal domain features, and frequency domain features daily, and then evaluating the features and allocating them based on preset weight coefficients.
[0056] The preset weighting coefficients were obtained through multiple simulations based on the historical quality assessment process, taking into account the proportion of the weighted influence of spatial, temporal, and frequency domain features on EEG signal features.
[0057] S103: Receive patient feedback data, perform comprehensive calculation of feedback signals based on the patient feedback data, and obtain a comprehensive signal feedback coefficient; wherein, the patient feedback data includes visual data, auditory data, and tactile data; perform comprehensive rehabilitation assessment processing based on the comprehensive signal feedback coefficient and the comprehensive EEG feature fusion coefficient to obtain a comprehensive rehabilitation assessment coefficient; generate a rehabilitation treatment plan for the patient based on the comprehensive rehabilitation assessment coefficient.
[0058] Specifically, the process of collecting patient feedback data includes:
[0059] Influencing the patient's visual perception by playing partial videos on an externally installed display screen; capturing the patient's eye movement trajectory and frequency using an eye tracker as visual data;
[0060] Partial prompts are played through an externally installed microphone, and the patient's reaction to the prompts is collected as auditory data.
[0061] The patient is given partial electromyography stimulation by an externally installed surface electromyography sensor, and then the electrical signals of the patient's skin contraction after stimulation are recorded.
[0062] The specific process of comprehensively calculating feedback signals based on patient feedback data includes the following steps:
[0063] The patient feedback data is labeled, with visual data labeled as Vj, auditory data labeled as Tj, and tactile data labeled as Cj, where j is the number of patient feedback data and j = 1, 2, 3, ..., m, and m is the total number of patient feedback data.
[0064] Using formula The comprehensive signal feedback coefficient is calculated. Where V0 is the original visual intensity coefficient, T0 is the original auditory intensity coefficient, C0 is the original tactile intensity coefficient, a is the adaptive adjustment coefficient, R1 is the physiological response index coefficient, and R2 is the behavioral performance index coefficient.
[0065] Furthermore, in the specific implementation process, the original visual intensity coefficient, the preset standard auditory intensity coefficient, and the original tactile intensity coefficient are obtained by comprehensively and dynamically adjusting the data based on the patient's feedback after collecting visual, auditory, and tactile data daily.
[0066] In this embodiment, the physiological response index coefficient and the behavioral performance index coefficient are calculated by comprehensively evaluating the physiological and behavioral responses of patients in daily life, based on the influence of external factors.
[0067] The process of obtaining the comprehensive rehabilitation assessment coefficient Z based on the comprehensive signal feedback coefficient and the comprehensive EEG feature fusion coefficient includes:
[0068]
[0069] In the formula, and The preset proportional coefficient is a coefficient determined based on a comprehensive assessment of EEG characteristics and patient feedback, applicable to the assessment of the proportion of the impact of both factors on rehabilitation.
[0070] By determining the comprehensive rehabilitation assessment coefficient Z, a specific rehabilitation treatment plan can be obtained. This allows for a comprehensive assessment of the rehabilitation plan, taking into account the influence of the patient's brain waves and the patient's own feedback, making the rehabilitation process more suitable for the patient's actual situation.
[0071] Example 2: A brain-computer interface interaction system for rehabilitation training of cerebral infarction, such as... Figure 2 As shown, it includes:
[0072] Data processing module 11 is used to receive EEG signal data, preprocess the EEG signal data, and obtain processed EEG signal data, wherein the EEG signal data includes μ wave signal data and β wave signal data;
[0073] The feature extraction and fusion module 12 is used to extract features from the processed EEG signal data to obtain EEG feature data, and to perform feature weighted fusion calculation based on the EEG feature data to obtain a comprehensive EEG feature fusion coefficient. The EEG feature data includes spatial domain features, temporal domain features and frequency domain features.
[0074] The rehabilitation assessment module 13 is used to receive patient feedback data, perform comprehensive calculations on the feedback signals based on the patient feedback data, and obtain a comprehensive signal feedback coefficient; wherein, the patient feedback data includes visual data, auditory data, and tactile data; perform comprehensive rehabilitation assessment processing based on the comprehensive signal feedback coefficient and the comprehensive EEG feature fusion coefficient to obtain a comprehensive rehabilitation assessment coefficient; and generate a rehabilitation treatment plan for the patient based on the comprehensive rehabilitation assessment coefficient.
[0075] Based on the same inventive concept, this invention also provides a computer device, comprising: one or more processors, and a memory for storing one or more computer programs; the programs include program instructions, and the processor executes the program instructions stored in the memory. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, used to implement one or more instructions, specifically for loading and executing one or more instructions stored in a computer storage medium to implement the above-described method.
[0076] It should be further explained that, based on the same inventive concept, the present invention also provides a computer storage medium storing a computer program, which, when executed by a processor, performs the above-described method. This storage medium can be any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In the present invention, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
[0077] The above formulas are all numerical calculations after removing dimensions. The formulas are obtained by software simulation based on a large amount of data and are closest to the real situation. The preset parameters and preset thresholds in the formulas are set by those skilled in the art according to the actual situation or obtained by simulation based on a large amount of data.
[0078] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this disclosure. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.
[0079] The foregoing has shown and described the basic principles, main features, and advantages of this disclosure. Those skilled in the art should understand that this disclosure is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of this disclosure. Various changes and modifications can be made to this disclosure without departing from its spirit and scope, and all such changes and modifications fall within the scope of this disclosure as claimed.
Claims
1. A brain-computer interface interaction method for rehabilitation training of cerebral infarction, characterized in that, The method includes the following steps: Receive EEG signal data, preprocess the EEG signal data to obtain processed EEG signal data, wherein the EEG signal data includes μ wave signal data and β wave signal data; Feature extraction is performed on the processed EEG signal data to obtain EEG feature data. Based on the EEG feature data, feature weighted fusion calculation is performed to obtain the comprehensive EEG feature fusion coefficient. The EEG feature data includes spatial domain features, temporal domain features, and frequency domain features. The system receives patient feedback data, performs comprehensive calculations on the feedback signals based on the patient feedback data, and obtains a comprehensive signal feedback coefficient. The patient feedback data includes visual data, auditory data, and tactile data. Based on the comprehensive signal feedback coefficient and the comprehensive EEG feature fusion coefficient, a comprehensive rehabilitation assessment is performed to obtain a comprehensive rehabilitation assessment coefficient. Based on the comprehensive rehabilitation assessment coefficient, a rehabilitation treatment plan is generated for the patient.
2. The brain-computer interface interaction method for cerebral infarction rehabilitation training according to claim 1, characterized in that, The spatial features are extracted using a common-space mode algorithm, the time-domain features are the mean and variance of the signal amplitude, and the frequency-domain features are the power spectral density of a preset specific frequency band.
3. The brain-computer interface interaction method for cerebral infarction rehabilitation training according to claim 1, characterized in that, The calculation process for feature weighted fusion based on EEG feature data includes: The EEG feature data are labeled as follows: spatial features are labeled as Ki, time-domain features are labeled as Si, and frequency-domain features are labeled as Pi; where i is the data index of the EEG feature data, and i = 1, 2, 3, ..., n, and n is the total number of EEG feature data. The calculation formula is as follows: In the formula, The fusion coefficients of comprehensive EEG features are defined as follows: K0 is the spatial weight matrix, S0 is the temporal weight matrix, P0 is the frequency weight matrix, α, β, and γ are all preset weight coefficients, and satisfy α+β+γ=1; G() is the feature quality assessment function.
4. The brain-computer interface interaction method for cerebral infarction rehabilitation training according to claim 1, characterized in that, The process of comprehensively calculating feedback signals based on patient feedback data includes the following steps: The patient feedback data is labeled, with visual data labeled as Vj, auditory data labeled as Tj, and tactile data labeled as Cj, where j is the number of patient feedback data and j = 1, 2, 3, ..., m, and m is the total number of patient feedback data. Using formula The comprehensive signal feedback coefficient is calculated. Where V0 is the original visual intensity coefficient, T0 is the original auditory intensity coefficient, C0 is the original tactile intensity coefficient, a is the adaptive adjustment coefficient, R1 is the physiological response index coefficient, and R2 is the behavioral performance index coefficient.
5. A brain-computer interface interaction method for cerebral infarction rehabilitation training according to claim 1, characterized in that, The process of obtaining the comprehensive rehabilitation assessment coefficient based on the comprehensive signal feedback coefficient and the comprehensive EEG feature fusion coefficient includes: In the formula, Z is the comprehensive rehabilitation assessment coefficient. and This is the preset scaling factor.
6. A brain-computer interface interaction method for cerebral infarction rehabilitation training according to claim 1, characterized in that, The process of acquiring the electroencephalogram (EEG) signal data includes: A wireless computer-controlled electroencephalogram (EEG) acquisition system was used. The patient wore an EEG cap and was injected with conductive gel. The signal quality was ensured by fixing reference electrodes and electrooculogram (EOG) electrodes. After the patient's brain was affected by the external device, μ-wave and β-wave signal data were collected simultaneously as EEG signal data.
7. A brain-computer interface interaction method for cerebral infarction rehabilitation training according to claim 1, characterized in that, The preprocessing of the EEG signal data includes: The raw EEG signal is filtered, rereferenced, and artifacts are detected and removed to obtain processed EEG signal data.
8. A brain-computer interface interaction system for rehabilitation training of cerebral infarction, employing the brain-computer interface interaction method for rehabilitation training of cerebral infarction as described in any one of claims 1 to 7, characterized in that, include: The data processing module is used to receive EEG signal data, preprocess the EEG signal data, and obtain processed EEG signal data, wherein the EEG signal data includes μ wave signal data and β wave signal data. The feature extraction and fusion module is used to extract features from the processed EEG signal data to obtain EEG feature data, and to perform feature weighted fusion calculation based on the EEG feature data to obtain a comprehensive EEG feature fusion coefficient. The EEG feature data includes spatial domain features, temporal domain features and frequency domain features. The rehabilitation assessment module is used to receive patient feedback data, perform comprehensive calculations on the feedback signals based on the patient feedback data, and obtain a comprehensive signal feedback coefficient; wherein, the patient feedback data includes visual data, auditory data, and tactile data; perform comprehensive rehabilitation assessment processing based on the comprehensive signal feedback coefficient and the comprehensive EEG feature fusion coefficient to obtain a comprehensive rehabilitation assessment coefficient; and generate a rehabilitation treatment plan for the patient based on the comprehensive rehabilitation assessment coefficient.
9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that, The memory stores a computer program that can run on a processor. When the processor loads and executes the computer program, it employs a brain-computer interface interaction method for cerebral infarction rehabilitation training as described in any one of claims 1 to 7.
10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is loaded and executed by the processor, it employs a brain-computer interface interaction method for cerebral infarction rehabilitation training as described in any one of claims 1 to 7.