Rehabilitation training parameter optimization method and system based on neural feedback and athletic performance

Abstract

The invention relates to the technical field of rehabilitation training data processing, in particular to a rehabilitation training parameter optimization method and system based on neural feedback and motor performance, and the method comprises the steps: obtaining neural data and trajectory error data; obtaining a brain activation level parameter index and an athletic performance parameter index, and constructing a task parameter adjustment model according to the brain activation level parameter index and the athletic performance parameter index; and the neural data and the trajectory error data are input into the task parameter adjustment model for analysis to obtain task adjustment parameters, so that the flexibility and adaptability of rehabilitation training are improved, and the rehabilitation training effect is improved.

Description

Technical Field

[0001] The present application relates to the technical field of rehabilitation training data processing, and in particular to a method and system for optimizing rehabilitation training parameters based on neural feedback and motor performance. Background Art

[0002] Stroke, also known as apoplexy, is a common acute cerebrovascular disease. The brain damage it causes can lead to loss of neurological function, various functional disorders, especially motor dysfunction, which seriously affects the quality of life. Effective rehabilitation treatment not only depends on the active participation of the subjects in the rehabilitation training process, but also requires the cooperation of relevant technologies and equipment.

[0003] At present, bilateral rehabilitation training is considered to be a new type of rehabilitation training method suitable for stroke, involving symmetrical or asymmetrical repetitive movements of the upper limbs, which can be practiced in combination with external equipment. According to research, bilateral training is divided into three categories, including bilateral functional task training, bilateral arm training with rhythmic auditory cues, and bilateral robot-assisted training. All of them utilize the coupling mechanism of the corpus callosum and interhemispheric connection during rehabilitation, and all achieve functional improvement by recruiting the ipsilateral corticospinal pathway, strengthening the control of the contralateral hemisphere, and normalizing the inhibitory mechanism.

[0004] However, the traditional bilateral rehabilitation training method focuses on passive activation of the limbs and achieves the excitement of neurotransmitters through repetitive training, and its long-term effect is controversial. In addition, the corresponding equipment is simple in function and usually only uses the subject's task completion accuracy as the evaluation standard. The single training form affects the subject's training enthusiasm and training effect. The above problems need to be solved. Summary of the invention

[0005] In order to improve the flexibility and adaptability of rehabilitation training, thereby improving the rehabilitation training effect, the present application provides a method and system for optimizing rehabilitation training parameters based on neurofeedback and motor performance, which adopts the following technical solutions:

[0006] In a first aspect, the present application provides a method for optimizing rehabilitation training parameters based on neurofeedback and motor performance, comprising:

[0007] Obtain neural data and trajectory error data;

[0008] Acquire a brain activation level parameter index and a motor performance parameter index, and construct a task parameter adjustment model according to the brain activation level parameter index and the motor performance parameter index;

[0009] The neural data and trajectory error data are input into the task parameter adjustment model for analysis to obtain the task adjustment parameters.

[0010] Preferably, the specific steps of obtaining neural data are:

[0011] Acquire optical density signals, convert and process the optical density signals to obtain hemodynamic signals, extract features of the hemodynamic signals, and obtain oxygenated hemoglobin information;

[0012] The concentration change analysis of oxygenated hemoglobin information is performed to obtain the concentration change mean data.

[0013] Preferably, the specific steps of the trajectory error data are:

[0014] The grip force tracking task completion information is obtained, and the trajectory error is calculated for the grip force tracking task completion information to obtain trajectory error data.

[0015] Preferably, the specific steps of inputting the neural data and trajectory error data into the task parameter adjustment model for analysis to obtain the task adjustment parameters are:

[0016] The concentration change mean data and trajectory error data were input into the task parameter adjustment model for analysis to obtain the grip force asymmetry coefficient used to adjust the horizontal interference offset;

[0017] The concentration change mean data and trajectory error data are input into the task parameter adjustment model for analysis to obtain the trajectory complexity used to adjust the target trajectory.

[0018] In a second aspect, the present application provides a rehabilitation training parameter optimization system based on neurofeedback and motor performance, comprising:

[0019] Information acquisition module, used to obtain neural data and trajectory error data;

[0020] A model building module, used to obtain brain activation level parameter indicators and motor performance parameter indicators, and to build a task parameter adjustment model according to the brain activation level parameter indicators and the motor performance parameter indicators;

[0021] The parameter adjustment module is used to input the neural data and trajectory error data into the task parameter adjustment model for analysis to obtain the task adjustment parameters.

[0022] Preferably, the specific steps of the information acquisition module for acquiring neural data are:

[0023] Acquire optical density signals, convert and process the optical density signals to obtain hemodynamic signals, extract features of the hemodynamic signals, and obtain oxygenated hemoglobin information;

[0024] The concentration change analysis of oxygenated hemoglobin information is performed to obtain the concentration change mean data.

[0025] Preferably, the specific steps of the information acquisition module for acquiring trajectory error data are:

[0026] The grip force tracking task completion information is obtained, and the trajectory error is calculated for the grip force tracking task completion information to obtain trajectory error data.

[0027] Preferably, the parameter adjustment module is used to input the neural data and trajectory error data into the task parameter adjustment model for analysis, and the specific steps of obtaining the task adjustment parameters are:

[0028] The concentration change mean data and trajectory error data were input into the task parameter adjustment model for analysis to obtain the grip force asymmetry coefficient used to adjust the horizontal interference offset;

[0029] The concentration change mean data and trajectory error data are input into the task parameter adjustment model for analysis to obtain the trajectory complexity used to adjust the target trajectory.

[0030] In a third aspect, the present application provides a rehabilitation training parameter optimization device based on neurofeedback and motor performance, comprising a memory and a processor, the memory storing a computer program, the processor being configured to run the computer program to execute the rehabilitation training parameter optimization method based on neurofeedback and motor performance as described above.

[0031] In a fourth aspect, the present application provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the rehabilitation training parameter optimization method based on neurofeedback and motor performance as described above when running.

[0032] In summary, compared with the prior art, the technical solution provided by this application has at least the following beneficial effects:

[0033] The present application obtains neural data reflecting the user's brain activation level and trajectory error data reflecting the user's motor performance, and then constructs a task parameter adjustment model based on the brain activation level parameter index and the motor performance parameter index. The neural data and trajectory error data are analyzed through the task parameter adjustment model to obtain task adjustment parameters for adjusting the training task. The task content is adjusted through neural feedback and motor performance, thereby improving the flexibility and adaptability of rehabilitation training and thus improving the rehabilitation training effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 It is a flow chart of a method for optimizing rehabilitation training parameters based on neurofeedback and motor performance described in an embodiment of the present application.

[0035] Figure 2 It is a schematic diagram of the fuzzy set of input variables and output variables described in the embodiment of the present application.

[0036] Figure 3 It is a flowchart of the rehabilitation training described in the embodiment of the present application.

[0037] Figure 4 It is a module schematic diagram of a rehabilitation training parameter optimization system based on neural feedback and motor performance described in an embodiment of the present application.

[0038] Description of reference numerals:

[0039] 1. Information acquisition module; 2. Model building module; 3. Parameter adjustment module. DETAILED DESCRIPTION

[0040] The following combination Figure 1-Figure 4 The present application is described in further detail. The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments and are not intended to be limiting.

[0041] Reference Figure 1 The present application relates to a method for optimizing rehabilitation training parameters based on neurofeedback and motor performance, which specifically includes:

[0042] Step S1: Obtain neural data and trajectory error data;

[0043] Step S2: obtaining a brain activation level parameter index and a motor performance parameter index, and constructing a task parameter adjustment model according to the brain activation level parameter index and the motor performance parameter index;

[0044] Step S3: Input the neural data and trajectory error data into the task parameter adjustment model for analysis to obtain the task adjustment parameters.

[0045] Specifically, unilateral movement causes the ipsilateral cerebral hemisphere to be inhibited by the contralateral hemisphere to prevent mirror activation of the contralateral upper limb; while bilateral movement activates both hemispheres and can reduce inter-hemispheric and intra-hemispheric inhibition. Stroke can lead to an imbalance in the interaction between the two hemispheres, that is, the lateralization of inter-hemispheric balance. The effect of neural crosstalk depends in part on the level of force applied, with higher force levels leading to stronger crosstalk effects and lower force levels producing lower effects. Therefore, based on the theoretical basis of the imbalance in the interaction between the hemispheres of stroke users and the effect of force level on the strength of inter-hemispheric neural crosstalk, a personalized bilateral asymmetric grip strength training program was planned to be designed.

[0046] The user is trained according to the set training plan. During the training process, the present application scheme obtains the optical density signal for conversion to obtain the hemodynamic signal, extracts the oxygenated hemoglobin information based on the hemodynamic signal, analyzes the oxygenated hemoglobin information to obtain its concentration change mean data, i.e., neural data, thereby reflecting the user's brain activation level, and calculates the trajectory error of the grip tracking task completion information to obtain the trajectory error data, thereby reflecting the user's motor performance, and then constructs a task parameter adjustment model based on the brain activation level parameter index and the motor performance parameter index, analyzes the concentration change mean data and the trajectory error data through the task parameter adjustment model, and obtains the task adjustment parameters for adjusting the training task, and uses neural feedback and motor performance to feedback and adjust the task content, thereby improving the flexibility and adaptability of rehabilitation training, thereby improving the rehabilitation training effect.

[0047] This application first needs to select evaluation parameters that reflect brain activation levels and evaluation parameters for motor performance.

[0048] As one implementation method, the specific steps of extracting features from hemodynamic signals to obtain oxygenated hemoglobin information are as follows:

[0049] The resting period data and the task period data in the hemodynamic signal are extracted, and the oxygenated hemoglobin information is obtained by subtracting the task period data from the rest period data.

[0050] Specifically, the brain activation level, BAL, and evaluation parameters are characterized by cerebral blood oxygen signal. The optical density signal is detected in real time by a functional near-infrared spectroscopy device, which sends the detected optical density signal to a parameter optimization device for processing. According to the Beer-Lambert Law, the optical density signal is converted into a hemodynamic signal. Among them, oxygenated hemoglobin, HbO, is the most sensitive indicator, which can directly reflect the activation of the cortical area. Therefore, the embodiment of the present application uses the HbO signal for further data analysis. After preprocessing the HbO signal, it is divided into a resting period and a task period according to the stage of each tracking experiment. The HbO signal in the resting period refers to the signal collected within 5 seconds before the start of the experiment, which is HbO baseline The HbO signal during the task period refers to the entire tracking phase from the beginning of the experiment to the beginning of the tracking task, that is, HbO tracking The HbO concentration change ΔHbO caused by the task in a certain channel can be obtained by subtracting the HbO signal during the task period from the HbO signal during the rest period. task =HbO tracking -HbO baseline .

[0051] As one implementation method, the specific steps of analyzing the concentration change of oxygenated hemoglobin information and obtaining the concentration change mean data are as follows:

[0052] The oxygenated hemoglobin information is classified according to the brain region type information of the oxygenated hemoglobin information, and the mean of several pieces of oxygenated hemoglobin information of the same brain region type is calculated to obtain the concentration change mean data.

[0053] Specifically, in the embodiment of the present application, in the case of right-hand bias, the values ​​measured in each channel in the left primary motor cortex are averaged, and in the case of left-hand bias, the values ​​measured in each channel in the right primary motor cortex are averaged. The mean blood oxygen concentration mean_ΔHbO of the selected brain area can be obtained. task As a parameter reflecting the level of brain activation activity. task It reflects the average activation level of the corresponding brain area during the task. The larger the value, the higher the activation level.

[0054] Through neuroimaging technology, such as functional near-infrared spectroscopy, fNIRS technology monitors the brain's neurophysiological signals in real time, and combines optimization algorithms to dynamically adjust training parameters, making the training process more efficient and personalized. The real-time feedback mechanism can adjust the training intensity and difficulty according to the user's immediate neural response, significantly improving the training effect.

[0055] The grip force tracking task completion information is obtained, and the trajectory error is calculated for the grip force tracking task completion information to obtain trajectory error data.

[0056] Specifically, the grip force tracking task completion information of the embodiment of the present application includes left and right grip force signals, left and right grip force target signals and the number of sampling points. The trajectory error, TTE, during the two-hand grip force tracking task is calculated as an evaluation index of sports performance. The calculation formula of the trajectory error data is as follows:

[0057]

[0058] Among them, F iL 、F iR are the left and right grip force signals of the i-th sampling point, F il 、F ir are the left and right grip force target signals of the i-th sampling point, and N is the total number of sampling points.

[0059] As one implementation method, a brain activation level parameter index and a motor performance parameter index are obtained, and a task parameter adjustment model is constructed according to the brain activation level parameter index and the motor performance parameter index.

[0060] Specifically, after collecting evaluation indicators reflecting brain activation level and motor performance, the embodiment of the present application uses an adaptive algorithm to establish a mathematical model between the evaluation indicators and the task parameter adjustment, and when the user's evaluation indicator value changes, the task difficulty is adjusted according to the mathematical model. The mathematical model can be calculated by an adaptive algorithm such as a fuzzy logic algorithm and Bayesian optimization.

[0061] Reference Figure 2 ,When the fuzzy logic algorithm is used in the mathematical model, the fuzzy logic regulator can fuzzy the input parameters, thus being more robust to the interference factors caused by the differences of different subjects.,A dual-input and dual-output fuzzy logic optimization structure is adopted, with the activation of the motor cortex and the trajectory tracking error as input, and the grip asymmetry coefficient and the trajectory complexity as output.

[0062] First, the fuzzy sets defining the input variables and output variables are defined by triangular membership functions. The input variables include brain activation level and trajectory tracking error. Brain activation level (BAL) includes low, medium, and high; trajectory tracking error (TTE) includes small, medium, and large. The output variables include grip asymmetry coefficient and trajectory complexity. Grip asymmetry coefficient (K) includes low, medium, and high; trajectory complexity (Tcomplexity) includes simple, moderate, and complex.

[0063] According to the brain activation level parameter index and the motor performance parameter index, a fuzzy reasoning correspondence is formulated, namely, the task parameter adjustment model, which is as follows:

[0064]

[0065] The embodiments of the present application combine optimization algorithms such as fuzzy logic algorithms to dynamically adjust training parameters, making the training process more efficient and personalized. The real-time feedback mechanism can adjust the training intensity and difficulty according to the user's immediate neural response, significantly improving the rehabilitation effect.

[0066] As one implementation method, the neural data and trajectory error data are input into the task parameter adjustment model for analysis, and the specific steps of obtaining the task adjustment parameters are as follows:

[0067] The concentration change mean data and trajectory error data were input into the task parameter adjustment model for analysis to obtain the grip force asymmetry coefficient used to adjust the horizontal interference offset;

[0068] The concentration change mean data and trajectory error data are input into the task parameter adjustment model for analysis to obtain the trajectory complexity used to adjust the target trajectory.

[0069] Specifically, in the embodiments of the present application, the condition parameters in the rehabilitation training experimental paradigm are adjusted, that is, the grip strength asymmetry coefficient and the trajectory complexity are adjusted, so as to provide a personalized rehabilitation training plan to ensure that each user can obtain training parameters targeted to their training needs.

[0070] The adjustment of the grip strength asymmetry coefficient K is achieved by adjusting the horizontal interference offset related to the left and right hand grip strengths (FL, FR) during the control of the slider movement in the experiment. Adjusting the gain coefficient K can change the proportion of the left and right hand grip strengths participating in the task. After each task is completed, the embodiments of the present application will adjust the grip strength asymmetry coefficient K according to the brain activation level. The left offset interference is: fL = α1 × FL; the right offset interference is: fR = α2 × FR; the grip strength asymmetry coefficient:

[0071] where FL and FR are the left and right hand grip strengths; α1 and α2 are the left and right hand horizontal offset interference coefficients; fL and fR are the left and right direction offsets. In the embodiments of the present application, a larger K represents more participation of the left hand grip strength in the task, and a smaller K represents more participation of the right hand grip strength in the task.

[0072] The trajectory complexity, Tcomplexity, is changed by the probability of adding noise to the target trajectory. The specific process is to perform interference processing on the original trajectory and add interference containing the noise probability. In the task difficulty adjuster, after each task is completed, the algorithm will adjust the task trajectory according to the brain activation level:

[0073] Y i = Y orin_i + aZ i R i (1 ≤ i ≤ N)

[0074] where N is the number of equally spaced discrete points in the initial preset task trajectory, Y orin_i represents the position of the i-th discrete point in the initial preset trajectory, a (a > 0) represents a constant of the interference amplitude, R i is a uniformly distributed random variable within [-0.5, 0.5] that follows an independent and identical distribution, and Z i is also a random variable with an independent and identical distribution. Among the elements included in Z, there is a probability of p (0 < p < 1) being 1 and a probability of 1 - p being 0. In the embodiments of the application, a larger p can represent a more complex generated trajectory, and thus a higher difficulty of the training task. Therefore, p is defined as the trajectory complexity T complexity .

[0075] Refer to Figure 3In this application, the initial grip asymmetry K and trajectory complexity Tcomplexity are first set; training of the subject is started; the trajectory tracking task under the current task parameter conditions is completed and the user's brain activation level and motor performance parameters are collected at the same time to determine the evaluation score of the parameters; the task condition parameter adjustment is calculated by a fuzzy logic algorithm; it is determined whether the training cycle is completed, and if the training cycle is not completed, the steps are repeated; if the training cycle is completed, the training cycle is ended.

[0076] This application realizes dynamic adjustment of rehabilitation training task parameters by real-time monitoring of brain blood oxygen or voltage signals. It includes steps such as signal acquisition, processing, analysis and parameter adjustment. Through real-time monitoring and analysis of brain neural activity signals, the training tasks are dynamically adjusted according to the feedback data to adapt to the user's rehabilitation needs and progress. According to the difference in grip strength of the user's hands and real-time neural feedback data, adaptive adjustment of the difficulty of the training task is achieved. Adjust the grip asymmetry ratio coefficient K and the task trajectory difficulty p so that the difficulty and requirements of the training task match the user's ability and progress. By real-time monitoring of the user's hand grip strength and neural feedback data, specific algorithms and methods are used to dynamically adjust the task difficulty and provide a personalized rehabilitation training experience.

[0077] Reference Figure 4 , an embodiment of the present application provides a rehabilitation training parameter optimization system based on neurofeedback and sports performance, the system comprising:

[0078] Information acquisition module 1, used to acquire neural data and trajectory error data;

[0079] Model building module 2, used to obtain brain activation level parameter indicators and sports performance parameter indicators, and build a task parameter adjustment model according to the brain activation level parameter indicators and sports performance parameter indicators;

[0080] The parameter adjustment module 3 is used to input the neural data and trajectory error data into the task parameter adjustment model for analysis to obtain the task adjustment parameters.

[0081] Specifically, the system achieves dynamic adjustment of the contribution ratio of the left and right hands in rehabilitation training tasks by acquiring brain neuroelectrophysiological signals and performing steps such as signal acquisition, processing, analysis, and algorithm optimization and adaptive adjustment. At the same time, according to the difference in grip strength between the patient's hands, real-time neural feedback data, and kinematic performance, specific algorithms and methods are used to adaptively adjust the difficulty of the training tasks. The adjustment process involves adjusting the grip asymmetry ratio coefficient K and the task trajectory difficulty p so that the training tasks match the patient's ability and progress. The system provides a personalized rehabilitation training experience to meet the patient's rehabilitation needs and progress, improve the flexibility and adaptability of rehabilitation training, and thus improve the rehabilitation training effect.

[0082] As one implementation manner, the information acquisition module 1 is used to extract features of hemodynamic signals, and the specific steps of obtaining oxygenated hemoglobin information are as follows:

[0083] The resting period data and the task period data in the hemodynamic signal are extracted, and the oxygenated hemoglobin information is obtained by subtracting the task period data from the rest period data.

[0084] As one implementation manner, the information acquisition module 1 is used to analyze the concentration change of the oxygenated hemoglobin information, and the specific steps of obtaining the concentration change mean data are as follows:

[0085] The oxygenated hemoglobin information is classified according to the brain region type information of the oxygenated hemoglobin information, and the mean of several pieces of oxygenated hemoglobin information of the same brain region type is calculated to obtain the concentration change mean data.

[0086] As one implementation method, the parameter adjustment module 3 is used to input the neural data and trajectory error data into the task parameter adjustment model for analysis, and the specific steps of obtaining the task adjustment parameters are as follows:

[0087] The concentration change mean data and trajectory error data were input into the task parameter adjustment model for analysis to obtain the grip force asymmetry coefficient used to adjust the horizontal interference offset;

[0088] The concentration change mean data and trajectory error data are input into the task parameter adjustment model for analysis to obtain the trajectory complexity used to adjust the target trajectory.

[0089] An embodiment of the present application provides a rehabilitation training parameter optimization device based on neural feedback and motor performance, including a memory and a processor, the memory storing a computer program, and the processor being configured to run the computer program to execute the rehabilitation training parameter optimization method based on neural feedback and motor performance as described above.

[0090] An embodiment of the present application provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the above-mentioned method for optimizing rehabilitation training parameters based on neural feedback and motor performance when running.

[0091] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described device and product can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0092] In several embodiments provided in this application, it should be understood that the disclosed methods, systems, devices and program products may be implemented in other ways.

[0093] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0094] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for optimizing rehabilitation training parameters based on neurofeedback and motor performance, It is characterized in that include: Obtain neural data and trajectory error data; Acquire a brain activation level parameter index and a motor performance parameter index, and construct a task parameter adjustment model according to the brain activation level parameter index and the motor performance parameter index; The neural data and trajectory error data are input into the task parameter adjustment model for analysis to obtain the task adjustment parameters.

2. The method for optimizing rehabilitation training parameters based on neurofeedback and motor performance according to claim 1, It is characterized in that The specific steps of obtaining neural data are: Acquire optical density signals, convert and process the optical density signals to obtain hemodynamic signals, extract features of the hemodynamic signals, and obtain oxygenated hemoglobin information; The concentration change analysis of oxygenated hemoglobin information is performed to obtain the concentration change mean data.

3. The method for optimizing rehabilitation training parameters based on neurofeedback and motor performance according to claim 1, It is characterized in that The specific steps of the trajectory error data are: The grip force tracking task completion information is obtained, and the trajectory error is calculated for the grip force tracking task completion information to obtain trajectory error data.

4. The method for optimizing rehabilitation training parameters based on neurofeedback and motor performance according to claim 3, It is characterized in that The specific steps of inputting the neural data and trajectory error data into the task parameter adjustment model for analysis to obtain the task adjustment parameters are: The concentration change mean data and trajectory error data were input into the task parameter adjustment model for analysis to obtain the grip force asymmetry coefficient used to adjust the horizontal interference offset; The concentration change mean data and trajectory error data are input into the task parameter adjustment model for analysis to obtain the trajectory complexity used to adjust the target trajectory.

5. A rehabilitation training parameter optimization system based on neurofeedback and motor performance, It is characterized in that include: Information acquisition module, used to obtain neural data and trajectory error data; A model building module, used to obtain brain activation level parameter indicators and motor performance parameter indicators, and to build a task parameter adjustment model according to the brain activation level parameter indicators and the motor performance parameter indicators; The parameter adjustment module is used to input the neural data and trajectory error data into the task parameter adjustment model for analysis to obtain the task adjustment parameters.

6. The rehabilitation training parameter optimization system based on neurofeedback and sports performance according to claim 5, It is characterized in that The specific steps of the information acquisition module for acquiring neural data are: Acquire optical density signals, convert and process the optical density signals to obtain hemodynamic signals, extract features of the hemodynamic signals, and obtain oxygenated hemoglobin information; The concentration change analysis of oxygenated hemoglobin information is performed to obtain the concentration change mean data.

7. The rehabilitation training parameter optimization system based on neurofeedback and sports performance according to claim 5, It is characterized in that The specific steps of the information acquisition module for acquiring trajectory error data are as follows: The grip force tracking task completion information is obtained, and the trajectory error is calculated for the grip force tracking task completion information to obtain trajectory error data.

8. The rehabilitation training parameter optimization system based on neurofeedback and sports performance according to claim 7, It is characterized in that The parameter adjustment module is used to input the neural data and trajectory error data into the task parameter adjustment model for analysis. The specific steps of obtaining the task adjustment parameters are as follows: The concentration change mean data and trajectory error data were input into the task parameter adjustment model for analysis to obtain the grip force asymmetry coefficient used to adjust the horizontal interference offset; The concentration change mean data and trajectory error data are input into the task parameter adjustment model for analysis to obtain the trajectory complexity used to adjust the target trajectory.

9. A rehabilitation training parameter optimization device based on neurofeedback and sports performance, It is characterized in that The method comprises a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the method for optimizing rehabilitation training parameters based on neurofeedback and sports performance according to any one of claims 1 to 4.

10. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores a computer program, wherein the computer program is configured to execute the method for optimizing rehabilitation training parameters based on neurofeedback and motor performance as described in any one of claims 1 to 4 when running.

Images