Finger rehabilitation electrical stimulation parameter control method and system

Abstract

The invention relates to the technical field of medical rehabilitation, and particularly discloses a finger rehabilitation electrical stimulation parameter control method and system, and the method comprises the steps: obtaining a multi-channel surface electromyogram signal and finger joint kinematics data of a patient; according to the multi-channel surface electromyogram signals, target fine actions of the patient are recognized; according to the target fine motion and the finger joint kinematics data, a multi-muscle group cooperative activation mode and an expected motion trail are obtained through analysis; generating an electrical stimulation parameter combination for different muscle groups according to a multi-muscle group collaborative activation mode; outputting multi-channel electrical stimulation to the patient based on the electrical stimulation parameter combination, and continuously adjusting the electrical stimulation parameter combination on line according to the deviation between the kinematics data of the finger joints and the expected motion trail; the method solves the problems that an existing method is difficult to effectively simulate complex multi-muscle group coordination, complex in parameter adjustment and difficult to adapt to dynamic changes of a patient, and the effect of assisting the patient in complex and fine finger action training is achieved.

Description

Technical Field

[0001] The present application relates to the field of medical rehabilitation technology, and in particular to a method and system for controlling electrical stimulation parameters for finger rehabilitation. Background Art

[0002] In home rehabilitation settings, functional electrical stimulation devices are widely used for rehabilitation training for patients with finger dysfunction. These devices utilize electrodes attached to the forearm surface to apply preset electrical stimulation pulses, driving target muscles to contract and assisting patients in completing basic extension or flexion movements. This training model aims to regenerate neural pathways between the brain and muscles through repetitive, patterned movements, gradually helping patients regain independent movement ability. This reflects the trend toward more convenient and home-based rehabilitation technology.

[0003] However, existing electrical stimulation methods for finger rehabilitation have significant limitations when it comes to achieving complex and fine finger movements. For complex functional movements that require the coordination of multiple muscle groups, multiple channels, and timing, such as pinching or writing, the device cannot effectively simulate changes in muscle activation patterns, including the coordinated process of different muscle groups contracting and relaxing at different intensities at different time points. The parameter adjustment process is complex and requires repeated trial and error and manual configuration by professional rehabilitation therapists. It is also difficult to adapt to the dynamic changes in muscle response and neural plasticity during the patient's rehabilitation process, which limits the patient's ability to resume the precise operations required in daily life, affecting functional independence and rehabilitation effects.

[0004] There is currently no effective technical solution to the above problems. Summary of the Invention

[0005] The purpose of this application is to provide a method and system for controlling finger rehabilitation electrical stimulation parameters to solve the problems that existing methods are difficult to effectively simulate complex multi-muscle coordination, parameter adjustment is complex and difficult to adapt to dynamic changes of patients, so as to achieve the effect of assisting patients in complex and fine finger movement training.

[0006] In a first aspect, the present application provides a method for controlling finger rehabilitation electrical stimulation parameters for assisting patients in training complex and fine finger movements, the method comprising the following steps: S1. Acquire the patient's multi-channel surface electromyography signals and finger joint kinematic data; S2. identifying the patient's target fine movements based on the multi-channel surface electromyography signals; S3. Analyze and obtain the multi-muscle group coordinated activation pattern and expected movement trajectory based on the target fine movement and finger joint kinematic data; S4. generating electrical stimulation parameter combinations for different muscle groups according to the multi-muscle group coordinated activation pattern; S5. Output multi-channel electrical stimulation to the patient based on the electrical stimulation parameter combination, and continuously adjust the electrical stimulation parameter combination online according to the deviation between the finger joint kinematic data and the expected motion trajectory.

[0007] The finger rehabilitation electrical stimulation parameter control method of the present application combines multi-channel surface electromyography signals with finger joint kinematic data to achieve comprehensive perception of the patient's movement intention, muscle activation status and actual movement performance, and based on this, analyzes personalized multi-muscle group collaborative activation patterns and expected movement trajectories, and then generates and adjusts electrical stimulation parameter combinations online. This solves the problems that existing methods are difficult to effectively simulate complex multi-muscle group collaboration, and the parameter adjustment is complex and difficult to adapt to the dynamic changes of patients, thereby achieving the effect of assisting patients in complex and fine finger movement training.

[0008] The finger rehabilitation electrical stimulation parameter control method, wherein step S2 includes: S21, extracting time domain features, frequency domain features, and inter-channel collaborative features from the multi-channel surface electromyography signals to obtain multi-dimensional electromyography features representing the activation state of the muscle group; S22. Compare the multi-dimensional electromyographic features with a preset fine movement feature pattern library to determine the target fine movement, wherein the fine movement feature pattern library contains multi-dimensional electromyographic features corresponding to different target fine movements.

[0009] Through the above processing, the method of the present application can accurately capture the unique muscle group activation patterns corresponding to different fine movements, effectively deal with the influence of noise and individual differences, improve the accuracy and robustness of fine movement recognition, and provide a reliable basis for the subsequent generation and adjustment of electrical stimulation parameters, thereby effectively assisting patients in complex fine finger movement training.

[0010] The finger rehabilitation electrical stimulation parameter control method, wherein step S3 includes: S31, according to the target fine movement, obtaining an initial multi-muscle group coordinated activation pattern and an initial expected movement trajectory corresponding to the target fine movement from a preset movement pattern library; S32. Evaluate the patient's current range of motion and exercise ability of the finger joints based on the finger joint kinematic data; S33. According to the range of motion and the motion ability, adjust the initial multi-muscle group coordinated activation mode to obtain the multi-muscle group coordinated activation mode, and adjust the initial expected motion trajectory to obtain the expected motion trajectory.

[0011] The finger rehabilitation electrical stimulation parameter control method, wherein step S32 includes: S321, analyzing the finger joint kinematic data to obtain the maximum motion angle and the minimum motion angle of each finger joint within a preset motion cycle to determine the motion range; S322: Analyze the finger joint kinematic data to obtain the movement speed, movement smoothness, and movement coordination between multiple joints of each finger joint within a preset movement cycle to determine the movement ability.

[0012] The finger rehabilitation electrical stimulation parameter control method, wherein step S33 includes: S331. Obtaining rehabilitation progress status; S332, generating a progressive challenge factor according to the rehabilitation progress status, the range of motion, and the exercise ability; S333. Based on the progressive challenge factor, the initial multi-muscle group coordinated activation pattern is adjusted, and the initial expected motion trajectory is adjusted to obtain the multi-muscle group coordinated activation pattern and the expected motion trajectory.

[0013] The finger rehabilitation electrical stimulation parameter control method, wherein the multi-muscle group collaborative activation mode includes the activation intensity ratio and activation timing relationship of each muscle group required to achieve the target fine movement, and the electrical stimulation parameter combination includes the stimulation intensity, pulse width, frequency of each channel and the timing relationship between channels.

[0014] The finger rehabilitation electrical stimulation parameter control method, wherein step S4 includes: S41. Determine the initial stimulation intensity, initial pulse width, and initial frequency of each channel according to the activation intensity ratio and in combination with preset muscle group electrical stimulation response characteristics; S42, determining the stimulation start delay and stimulation duration of each channel according to the activation timing relationship, so as to form a timing relationship between the channels; S43. Obtain the patient's electrical stimulation tolerance threshold and the electrophysiological impedance of each muscle group, and adjust the initial stimulation intensity, initial pulse width and initial frequency according to the tolerance threshold and the electrophysiological impedance to form the electrical stimulation parameter combination in combination with the timing relationship between the channels.

[0015] In the finger rehabilitation electrical stimulation parameter control method, the electrical stimulation tolerance threshold and the electrophysiological impedance are both pre-measured data, and the electrical stimulation tolerance threshold measurement process includes: A1. Applying a test stimulus of gradually increasing intensity to the patient through the electrical stimulation device, and recording the intensity of the test stimulus at which the patient reports reaching the upper limit of comfort tolerance as the electrical stimulation tolerance threshold; The electrophysiological impedance measurement process includes: A2. Apply a test current to each muscle group through the electrical stimulation output channel, measure the voltage across the channel, and calculate the electrophysiological impedance based on the voltage and the test current.

[0016] The finger rehabilitation electrical stimulation parameter control method, wherein step S5 comprises: S51, outputting multi-channel electrical stimulation to the patient based on the combination of electrical stimulation parameters; S52. During the process of outputting multi-channel electrical stimulation to the patient, continuously calculating the motion deviation between the kinematic data and the expected motion trajectory; S53, determining an adjustment amount and an adjustment direction for the electrical stimulation parameter combination at a next moment according to the movement deviation; S54. When the target fine movement remains unchanged, adjust the electrical stimulation parameter combination to be used at the next moment based on the adjustment amount and adjustment direction.

[0017] In a second aspect, the present application further provides a finger rehabilitation electrical stimulation parameter control system for assisting patients in performing complex and fine finger movement training, the system comprising: An acquisition module, used to acquire the patient's multi-channel surface electromyography signals and finger joint kinematics data; an identification module, configured to identify the patient's target fine movements based on the multi-channel surface electromyography signals; An analysis module is used to analyze and obtain the multi-muscle group coordinated activation pattern and expected movement trajectory based on the target fine movement and finger joint kinematic data; a parameter configuration module, configured to generate electrical stimulation parameter combinations for different muscle groups according to the multi-muscle group coordinated activation mode; The stimulation module is used to output multi-channel electrical stimulation to the patient based on the electrical stimulation parameter combination, and continuously adjust the electrical stimulation parameter combination online according to the deviation between the finger joint kinematic data and the expected motion trajectory.

[0018] The finger rehabilitation electrical stimulation parameter control method of the present application combines multi-channel surface electromyography signals with finger joint kinematic data to achieve comprehensive perception of the patient's movement intention, muscle activation status and actual movement performance, and based on this, analyzes the personalized multi-muscle group collaborative activation pattern and expected movement trajectory, and then generates and adjusts the electrical stimulation parameter combination online, solving the problems that the existing system is difficult to effectively simulate complex multi-muscle group collaboration, the parameter adjustment is complex and difficult to adapt to the dynamic changes of the patient, and achieves the effect of assisting patients in complex and fine finger movement training.

[0019] From the above, it can be seen that the present application provides a finger rehabilitation electrical stimulation parameter control method and system, wherein the finger rehabilitation electrical stimulation parameter control method of the present application combines multi-channel surface electromyography signals with finger joint kinematic data to achieve comprehensive perception of the patient's movement intention, muscle activation status and actual movement performance, and based on this, analyzes personalized multi-muscle group collaborative activation patterns and expected movement trajectories, and then generates and adjusts electrical stimulation parameter combinations online. It can generate personalized multi-muscle group collaborative activation patterns and expected movement trajectories according to the patient's movement intentions and actual abilities, and generate electrical stimulation parameters based on this, and can dynamically adapt to the patient's movement performance and rehabilitation process, to achieve effective auxiliary training of complex and fine finger movements, thereby solving the problem that existing methods are difficult to effectively simulate complex multi-muscle group coordination, and parameter adjustment is complex and difficult to adapt to dynamic changes in patients, and achieves the effect of assisting patients in complex and fine finger movement training. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a flow chart of the finger rehabilitation electrical stimulation parameter control method provided in an embodiment of the present application.

[0021] Figure 2 This is a structural diagram of the finger rehabilitation electrical stimulation parameter control system provided in an embodiment of the present application.

[0022] Reference numerals: 201, acquisition module; 202, identification module; 203, analysis module; 204, parameter configuration module; 205, stimulation module. DETAILED DESCRIPTION

[0023] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work fall within the scope of protection of the present application.

[0024] It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and should not be understood as indicating or implying relative importance.

[0025] First, please refer to Figure 1Some embodiments of the present application provide a method for controlling finger rehabilitation electrical stimulation parameters to assist patients in training complex and fine finger movements. The method comprises the following steps: S1. Acquire the patient's multi-channel surface electromyography signals and finger joint kinematic data; S2, identifying the patient's target fine movements based on multi-channel surface electromyography signals; S3. Analyze and obtain the multi-muscle group coordinated activation pattern and expected movement trajectory based on the target fine movement and finger joint kinematic data; S4, generating electrical stimulation parameter combinations for different muscle groups based on the multi-muscle group coordinated activation pattern; S5. Output multi-channel electrical stimulation to the patient based on the electrical stimulation parameter combination, and continuously adjust the electrical stimulation parameter combination online according to the deviation between the finger joint kinematic data and the expected motion trajectory.

[0026] Specifically, obtaining the patient's multi-channel surface electromyographic signals and finger joint kinematic data refers to collecting the patient's physiological electrical signals and joint motion status information when trying to perform finger movements through sensors. It can use surface electrodes to collect electromyographic signals, such as electrode patches attached to the patient's forearm or key muscle areas of the hand, and use kinematic sensors to collect motion data, such as angle sensors or inertial measurement units worn at the finger joints. Its main purpose is to obtain objective data reflecting the patient's movement intention, muscle activation status and actual movement performance, and provide input for subsequent motion recognition, pattern analysis and parameter control.

[0027] More specifically, in step S2, identifying the patient's target fine movements based on the multi-channel surface electromyographic signals refers to analyzing the collected electromyographic signal characteristics and determining the specific type of finger fine movements that the patient is currently attempting to perform. This can be achieved using signal processing and pattern recognition technology, such as extracting the time domain, frequency domain or time-frequency features of the electromyographic signals and matching them with a preset motion feature pattern library. This is mainly to understand the patient's movement intentions so that rehabilitation training can respond to the patient's active attempts.

[0028] More specifically, step S3 is used to determine the ideal muscle coordination mode and the motion path that the finger joints should follow required to complete the target fine movement and the finger joint kinematic data. It can be achieved by adjusting the preset model or by personalized modeling based on the patient's historical data. For example, the basic pattern and trajectory are obtained from the standard movement pattern library, and then adjusted according to the patient's range of motion and ability. It is mainly to generate personalized training goals that are in line with the patient's current rehabilitation stage and can guide him to complete the target movement.

[0029] More specifically, step S4 is used to convert the analyzed multi-muscle group coordinated activation pattern into a specific electrical stimulation output instruction. This process can be implemented using mapping rules or algorithms. For example, the stimulation intensity and pulse width are determined according to the muscle group activation intensity ratio, and the stimulation start delay and duration are determined according to the activation timing relationship. It is used to convert the abstract muscle coordination pattern into an executable electrical stimulation signal to drive the patient's muscles to contract according to the desired pattern.

[0030] More specifically, step S5 is used to apply the generated electrical stimulation signal to the patient through the multi-channel electrodes, while monitoring the patient's actual finger movement in real time, and comparing the actual movement with the expected trajectory, and dynamically modifying the electrical stimulation parameters according to the difference between the two. It can be implemented by closed-loop control or adaptive control algorithm, such as proportional-integral-derivative (PID) controller or fuzzy controller, which is mainly to guide the patient's movement closer to the expected trajectory through real-time feedback adjustment, thereby improving the accuracy and adaptability of training.

[0031] Specifically, the method of this application first collects multi-channel surface electromyographic (SEM) signals and finger joint kinematic data while the patient attempts a movement. The SEM signals reflect the patient's movement intention and muscle electrical activity, while the kinematic data reflects the actual movement state of the fingers. Next, the SEM signals are analyzed to identify the target fine movement the patient is attempting. Then, based on the identified target movement and the patient's current kinematic data, the personalized multi-muscle group co-activation pattern and desired motion trajectory required to achieve the movement are analyzed. The multi-muscle group co-activation pattern describes the activation intensity ratio and timing relationship of different muscle groups, while the desired motion trajectory describes the path that the finger joints should follow. Subsequently, based on the analyzed multi-muscle group co-activation pattern, multi-channel electrical stimulation parameter combinations for different muscle groups are generated. Finally, the generated electrical stimulation is applied to the patient, and the finger joint kinematic data is continuously monitored during the stimulation process. The deviation between the actual movement and the desired trajectory is calculated, and the electrical stimulation parameter combination is adjusted online in real time based on the deviation to guide the patient's movement toward the desired trajectory. The entire process forms a closed-loop control system of perception-decision-execution-feedback, enabling electrical stimulation to intelligently respond to the patient's condition and training needs.

[0032] The finger rehabilitation electrical stimulation parameter control method of the present application combines multi-channel surface electromyography signals with finger joint kinematic data to achieve comprehensive perception of the patient's movement intention, muscle activation status and actual movement performance, and based on this, analyzes personalized multi-muscle group collaborative activation patterns and expected movement trajectories, and then generates and adjusts electrical stimulation parameter combinations online. It can generate personalized multi-muscle group collaborative activation patterns and expected movement trajectories according to the patient's movement intentions and actual abilities, and generate electrical stimulation parameters based on this, and can dynamically adapt to the patient's movement performance and rehabilitation process, to achieve effective auxiliary training of complex and fine finger movements, thereby solving the problem that existing methods are difficult to effectively simulate complex multi-muscle group coordination, and parameter adjustment is complex and difficult to adapt to dynamic changes in patients, thereby achieving the effect of assisting patients in complex and fine finger movement training.

[0033] In some preferred embodiments, step S2 includes: S21, extracting time domain features, frequency domain features, and inter-channel collaborative features from multi-channel surface electromyographic signals to obtain multi-dimensional electromyographic features representing the activation state of muscle groups; S22. Compare the multi-dimensional electromyographic features with a preset fine movement feature pattern library to determine the target fine movement, where the fine movement feature pattern library contains multi-dimensional electromyographic features corresponding to different target fine movements.

[0034] Specifically, time-domain features refer to the properties of myoelectric signals in the time dimension, such as amplitude and energy. Frequency-domain features refer to the properties of myoelectric signals in the frequency dimension, such as frequency distribution and power spectral density. These can be implemented using methods such as Fourier transform and power spectrum analysis. Inter-channel collaborative features refer to the interrelated properties between different myoelectric signal channels, such as their correlation, synchronization, or timing relationship. These can be implemented by calculating the cross-correlation coefficient, coherence, or time delay of signals from different channels. Multidimensional myoelectric features are vectors or matrices that combine time-domain features, frequency-domain features, and inter-channel collaborative features extracted from multiple channels. They are used to comprehensively quantify the activation state and collaborative patterns of muscle groups. A fine motor feature library is a pre-established collection of typical or standard multi-dimensional myoelectric feature patterns corresponding to various known fine motor movements (such as pinching, writing, and grasping). These libraries can be established by collecting data from healthy individuals or patients before rehabilitation training, extracting features, and storing patterns.

[0035] Specifically, the method of the present application extracts multi-dimensional features from multi-channel surface electromyographic signals and compares the extracted features with a preset fine motion feature pattern library, thereby achieving accurate recognition of the patient's target fine motions, overcoming the limitations of directly processing the original electromyographic signals, and providing reliable input for subsequent electrical stimulation parameter control. The original multi-channel electromyographic signals contain rich timing and frequency information, and also reflect the collaborative working relationship between different muscle groups. Step S21 can convert the original, complex electromyographic signals into more representative and easier to process multi-dimensional feature vectors by extracting these multi-dimensional features. Step S22 compares the multi-dimensional electromyographic features with a preset fine motion feature pattern library to determine the target fine motion. The fine motion feature pattern library contains multi-dimensional electromyographic features corresponding to different target fine motions. The preset fine motion feature pattern library is established before rehabilitation training or through training data, and stores typical or standard multi-dimensional electromyographic feature patterns corresponding to known different fine motions. By comparing the currently extracted patient's EMG feature vector with the feature patterns corresponding to various fine movements stored in the fine movement feature pattern library, the pattern that best matches the patient's current EMG signature is found. The fine movement corresponding to this best-matching pattern is then identified as the target fine movement the patient is currently attempting. This feature comparison-based recognition method leverages the distinguishability of different fine movements in a multidimensional EMG feature space, enabling effective recognition of complex fine movements.

[0036] Through the above processing, the method of the present application can accurately capture the unique muscle group activation patterns corresponding to different fine movements, effectively deal with the influence of noise and individual differences, improve the accuracy and robustness of fine movement recognition, and provide a reliable basis for the subsequent generation and adjustment of electrical stimulation parameters, thereby effectively assisting patients in complex fine finger movement training.

[0037] In some preferred embodiments, step S3 includes: S31, according to the target fine movement, obtaining the initial multi-muscle group coordinated activation pattern and the initial expected movement trajectory corresponding to the target fine movement from a preset movement pattern library; S32. Assess the patient's current range of motion and exercise ability of the finger joints based on the finger joint kinematic data; S33. According to the range of motion and the motion ability, the initial multi-muscle group coordinated activation pattern is adjusted to obtain the multi-muscle group coordinated activation pattern, and the initial expected motion trajectory is adjusted to obtain the expected motion trajectory.

[0038] Specifically, the preset action pattern library refers to a data set that stores standard or ideal multi-muscle group coordinated activation patterns and expected motion trajectories for a variety of fine finger movements, and is implemented in the form of a database or structured file. The initial multi-muscle group coordinated activation pattern refers to the standard or ideal muscle activation timing and relative strength pattern corresponding to the target fine movement obtained from the preset action pattern library. The initial expected motion trajectory refers to the standard or ideal finger joint motion path and time series corresponding to the target fine movement obtained from the preset action pattern library. The range of motion refers to the maximum range of motion angles that the finger joints can reach, which can be determined by analyzing the maximum and minimum joint angles in the finger joint kinematic data. Movement ability refers to the quality characteristics of finger joint movement, such as the speed, smoothness and coordination between multiple joints of the movement, which can be evaluated by analyzing the speed curve, smoothness index or correlation between joint movements in the finger joint kinematic data.

[0039] Specifically, the method of the present application first obtains the initial multi-muscle co-activation pattern and initial desired motion trajectory corresponding to the identified target fine movement from a preset motion pattern library. Simultaneously, by analyzing the patient's current finger joint kinematic data, the patient's current actual range of motion and motor ability of the finger joints are assessed, thereby obtaining objective information about the patient's current physiological state. Then, based on the assessed patient's current range of motion and motor ability, the initial multi-muscle co-activation pattern and initial desired motion trajectory are adjusted. This adjustment process personalizes the universal or ideal pattern and trajectory to better suit the patient's current actual ability level. For example, if the patient's range of motion is limited, the amplitude of the desired motion trajectory is adjusted; if motor ability is insufficient, the intensity ratio or timing of muscle group activation may be adjusted. This dynamic adjustment based on the patient's current state ensures that the generated training targets and electrical stimulation parameters are more closely aligned with the patient's needs. The adjusted multi-muscle co-activation pattern and desired motion trajectory are then used to generate electrical stimulation parameters and make online adjustments, allowing the entire rehabilitation process to adapt to the individual differences and progress of the patient.

[0040] Through the above processing, the method of the present application generates personalized training goals and stimulation patterns that match the patient's current motor ability and rehabilitation progress, effectively improving the effectiveness and adaptability of rehabilitation training, enabling the rehabilitation process to be adjusted according to the patient's actual situation, and supporting the patient to gradually restore finger function.

[0041] In some preferred embodiments, step S32 includes: S321, analyzing the kinematic data of the finger joints to obtain the maximum motion angle and the minimum motion angle of each finger joint within a preset motion cycle to determine the motion range; S322: Analyze the kinematic data of the finger joints to obtain the movement speed, movement smoothness, and movement coordination between multiple joints of each finger joint within a preset movement cycle to determine the movement ability.

[0042] Specifically, the preset motion cycle refers to a time window set for analyzing the kinematic data of the finger joints, which can be achieved by completing a specific target fine movement (for example, grasping, pinching), or by performing a standardized assessment movement. Motion smoothness refers to the smoothness of the changes in velocity and acceleration during the movement of the finger joints. It can be quantified by analyzing the volatility of the velocity or acceleration curve in the kinematic data, and whether there are spikes or mutations. The coordination of movement between multiple joints refers to the degree of coordination of the movements of multiple finger joints in time and space when performing an action. It can be evaluated by analyzing the temporal relationship or correlation between the motion angles, velocity or acceleration curves of different joints.

[0043] Specifically, the method of the present application analyzes the collected finger joint kinematic data, and first obtains the maximum and minimum motion angles of each finger joint in step S321 within a preset motion cycle, thereby determining the patient's joint motion range in the current state. Subsequently, in step S322, the kinematic data within the same motion cycle is further analyzed to extract dynamic indicators such as motion speed, motion smoothness, and motion coordination between multiple joints to determine the patient's motor ability. By combining the evaluation of motion range (static indicators) and motor ability (dynamic indicators), a comprehensive and objective data basis is provided for the subsequent adjustment of the initial multi-muscle group coordinated activation pattern and the initial expected motion trajectory according to the evaluation results in step S33. This detailed evaluation method is combined with the overall process of obtaining the initial pattern and trajectory in step S31 and adjusting in step S33, so that the personalized adjustment of rehabilitation training can more accurately reflect the patient's current actual movement disorder type and degree, thereby overcoming the problem of insufficient evaluation in the prior art.

[0044] Through the above processing, the method of the present application can accurately and comprehensively evaluate the patient's range of motion and exercise ability based on the finger joint kinematic data, providing a more comprehensive and accurate basis for subsequent personalized adjustment of the multi-muscle coordinated activation mode and expected movement trajectory.

[0045] In some preferred embodiments, step S33 includes: S331. Obtaining rehabilitation progress status; S332. Generate progressive challenge factors based on rehabilitation progress, range of motion, and exercise capacity; S333. Based on the progressive challenge factor, the initial multi-muscle group synergistic activation pattern is adjusted, and the initial expected motion trajectory is adjusted to obtain the multi-muscle group synergistic activation pattern and the expected motion trajectory.

[0046] Specifically, the rehabilitation progress status refers to the patient's improvement trajectory over time based on historical and current performance data. It can be obtained in advance based on the patient's historical finger joint kinematic data and historical rehabilitation training performance data. The rehabilitation progress status can include data such as movement completion, movement smoothness, and the extent of improvement in range of motion. The progressive challenge factor refers to a value or indicator used to quantify the theoretical increase in training difficulty determined based on the patient's rehabilitation progress status, current range of motion, and current motor ability. It can be implemented as a scaling factor, an additive value, or an index derived from a function or lookup table, and represents the degree of increase in training difficulty.

[0047] It should be noted that the progressive challenge factor is used to adjust the activation intensity ratio of each muscle group in the initial multi-muscle coordinated activation pattern and to adjust the movement amplitude or movement speed of the initial desired movement trajectory.

[0048] Specifically, the method of the present application combines the patient's rehabilitation progress status, range of motion and motor ability to generate a progressive challenge factor. This factor quantifies the degree of increase in training difficulty determined based on the patient's rehabilitation progress status, range of motion and motor ability. This factor is used to adjust the training goals to match the patient's ability and provide appropriate challenges. Finally, based on the progressive challenge factor, the initial multi-muscle group co-activation pattern and the initial expected motion trajectory obtained from the preset action pattern library are adjusted so that the generated multi-muscle group co-activation pattern and the expected motion trajectory adapt to the patient's current rehabilitation stage, provide training goals, and promote the recovery and improvement of functional fine motor skills. By incorporating historical rehabilitation data into the adjustment process of training parameters and introducing a quantitative progressive challenge factor, the solution of the present application can more accurately grasp the patient's rehabilitation rhythm and potential, thereby generating a training pattern and trajectory that is more in line with the patient's actual situation, overcoming the limitations of relying solely on current data for adjustment, and promoting the continuous improvement of fine motor skills.

[0049] In some preferred embodiments, the multi-muscle group coordinated activation mode includes the activation intensity ratio and activation timing relationship of each muscle group required to achieve the target fine movement, and the electrical stimulation parameter combination includes the stimulation intensity, pulse width, frequency of each channel and the timing relationship between channels.

[0050] Specifically, the activation intensity ratio refers to the relative size relationship of the contraction force or activation electrical signal amplitude of different muscle groups when performing the same action. The activation timing relationship refers to the activation start time, duration, and start delay or synchronization relationship between different muscle groups when performing the same action. Stimulation intensity refers to the voltage or current amplitude of the applied electrical stimulation pulse. Pulse width refers to the duration of a single electrical stimulation pulse. Frequency refers to the number of electrical stimulation pulses applied per unit time. The timing relationship between channels refers to the synchronous or asynchronous relationship of the start, duration, or end time of stimulation of each channel when electrical stimulation pulses are applied through different electrode channels.

[0051] Specifically, the method of the present application solves the problem of vague pattern and parameter definitions by clarifying the specific composition of the multi-muscle group coordinated activation pattern and the electrical stimulation parameter combination, providing a specific technical basis for achieving effective auxiliary training of complex and fine finger movements, enabling electrical stimulation to more accurately simulate the muscle coordination required for complex and fine movements, thereby improving the effectiveness of electrical stimulation-assisted training and helping patients better restore their ability to perform complex and fine finger movements.

[0052] In some preferred embodiments, step S4 includes: S41. Determine the initial stimulation intensity, initial pulse width, and initial frequency of each channel based on the activation intensity ratio and the preset muscle group electrical stimulation response characteristics; S42. Determine the stimulation start delay and stimulation duration of each channel according to the activation timing relationship to form a timing relationship between the channels; S43. Obtain the patient's electrical stimulation tolerance threshold and the electrophysiological impedance of each muscle group, and adjust the initial stimulation intensity, initial pulse width and initial frequency according to the tolerance threshold and electrophysiological impedance to form an electrical stimulation parameter combination in combination with the timing relationship between channels.

[0053] Specifically, the preset muscle group electrical stimulation response characteristics refer to data or models determined in advance through experiments or experience that describe the response of a typical muscle group to different electrical stimulation parameters (such as contraction force or activation level). The electrical stimulation tolerance threshold refers to the upper limit of the electrical stimulation intensity that a patient can comfortably tolerate. Electrophysiological impedance refers to the electrical impedance encountered by the electrical stimulation current when it passes through the electrodes, skin, and subcutaneous tissue to reach the target muscle group, affecting the current passing through or the voltage generated by a given current at a given voltage.

[0054] Specifically, step S4 generates the electrical stimulation parameter combination in a phased process. First, the initial stimulation intensity, initial pulse width, and initial frequency are calculated for each electrical stimulation channel using the activation intensity ratios of each muscle group defined in the multi-muscle coordinated activation model and reference to pre-established muscle group electrical stimulation response characteristic data. This step initially maps the desired relative muscle activation degree to the electrical stimulation parameters. Next, based on the activation timing relationships within the multi-muscle coordinated activation model, the timing of stimulation on each channel (start delay) and duration (duration) are determined. This establishes a timing relationship between the channels, ensuring that the order and duration of electrical stimulation meet the muscle synergy requirements of the target movement. Finally, to ensure that the generated parameters are suitable for the specific patient and ensure safety, the patient's individual electrical stimulation tolerance threshold and electrophysiological impedance data for each muscle group are obtained. Based on this individual data, the previously determined initial stimulation intensity, initial pulse width, and initial frequency are adjusted. Adjustments based on the tolerance threshold ensure that the stimulation intensity does not exceed the patient's safe and comfortable range; adjustments based on electrophysiological impedance compensate for the effects of tissue resistance differences on current conduction, helping to maintain the desired stimulation effect. Ultimately, the individually adjusted stimulation intensity, pulse width, and frequency are combined with the determined timing relationship between channels to form a complete electrical stimulation parameter combination to drive the patient's muscles.

[0055] Through the above processing, the method of this application can convert abstract muscle group co-activation patterns into specific electrical stimulation parameter combinations, and taking into account individual physiological differences in patients, generate personalized, safe, and effective electrical stimulation parameters for specific patients and target movements. This overcomes the limitations of existing technologies, which rely on experience for parameter generation and are difficult to personalize and adapt to complex movements. It improves the accuracy and effectiveness of rehabilitation training and helps patients better complete complex and fine finger movement training.

[0056] In some preferred embodiments, the electrical stimulation tolerance threshold and the electrophysiological impedance are both pre-measured data, and the process of measuring the electrical stimulation tolerance threshold includes: A1. Apply a test stimulus of gradually increasing intensity to the patient using an electrical stimulation device, and record the intensity of the test stimulus at which the patient reports reaching the upper limit of comfort as the electrical stimulation tolerance threshold; The electrophysiological impedance measurement process includes: A2. Apply test current to each muscle group through the electrical stimulation output channel, measure the voltage at both ends of the channel, and calculate the electrophysiological impedance based on the voltage and test current.

[0057] Specifically, an electrical stimulation device refers to a device that can generate and output electrical stimulation signals, which may include a stimulation pulse generator, a current or voltage control circuit, and an output channel connected to the electrode. A test stimulation with gradually increasing intensity refers to a stimulation sequence in which the stimulation intensity starts from a lower level and gradually increases according to a preset step size or rate. The upper limit of comfort tolerance refers to the maximum level at which the patient feels the stimulation intensity has reached that he or she can accept without causing obvious discomfort or pain. The electrical stimulation output channel refers to the physical or electrical pathway in the electrical stimulation device used to transmit the electrical stimulation signal to the electrode and apply it to the patient's muscle group.

[0058] Specifically, the above measurement process provides a method for determining a patient's electrical stimulation tolerance threshold and muscle group electrophysiological impedance, thereby providing a reliable data foundation for subsequent personalized adjustment of electrical stimulation parameters. The electrical stimulation tolerance threshold is determined by applying test stimulation of increasing intensity to the patient and recording the intensity at which the patient reports reaching the upper limit of comfort. This method can determine the patient's subjective upper limit of electrical stimulation tolerance, preventing discomfort or pain caused by excessive stimulation intensity. Electrophysiological impedance is measured by applying a test current to each muscle group, measuring the voltage across the channel, and calculating the impedance based on the voltage and test current. The electrophysiological impedance of a muscle group affects the distribution of the electrical stimulation current in tissue and its actual effect. By measuring the electrophysiological impedance of a specific muscle group, we can understand the current contact between the electrode and the skin and the conductive properties of the subcutaneous tissue. Obtaining electrophysiological impedance data allows subsequent adjustments to electrical stimulation parameters to account for changes in tissue impedance, such as by adjusting the voltage or current to maintain a preset current density or charge. This ensures that the target muscle group receives the expected level of effective stimulation across different patients or across different training sessions for the same patient. These pre-determined tolerance thresholds and electrophysiological impedance data serve as input for electrical stimulation parameter adjustment, enabling the parameter adjustment process to better adapt to individual differences and changes in physiological states of patients.

[0059] In some preferred embodiments, step S43 includes: S431. Determine an adjustment factor according to the electrophysiological impedance value; S432. Adjust the initial stimulation intensity, initial pulse width, and initial frequency based on the adjustment factor, and use the electrical stimulation tolerance threshold as the intensity upper limit to clip the adjusted initial stimulation intensity, obtain the stimulation intensity, pulse width, and frequency of each channel, and combine them with the timing relationship between the channels to form an electrical stimulation parameter combination.

[0060] Specifically, an adjustment factor refers to one or a group of coefficients used to modify the initial electrical stimulation parameters (such as intensity, pulse width, and frequency). It can be determined by the ratio of the actual measured electrophysiological impedance value to the preset or nominal impedance value, or by looking up the electrophysiological impedance value through a table or calculation formula. It is mainly used to maintain the preset current density or preset charge amount of the corresponding muscle group. Intensity capping refers to comparing the adjusted stimulation intensity with the electrical stimulation tolerance threshold and limiting the final stimulation intensity to within the electrical stimulation tolerance threshold.

[0061] Specifically, step S431 calculates an adjustment factor for adjusting the initial stimulation parameters based on the patient's current electrophysiological impedance values for each muscle group. Changes in electrophysiological impedance can affect the current or charge actually applied to a muscle group at a given voltage or current, thereby affecting the stimulation effect. By calculating the adjustment factor and applying it to the initial stimulation intensity, pulse width, and frequency, fluctuations in stimulation intensity caused by impedance changes can be compensated for, allowing the effective stimulation amount (preset current density or preset charge amount) applied to the target muscle group to remain relatively stable. For example, if the impedance increases, the adjustment factor will increase the stimulation intensity or pulse width accordingly to maintain the preset current density or charge amount. Next, step S432 compares the impedance-adjusted stimulation intensity with the patient's electrical stimulation tolerance threshold. If the adjusted intensity exceeds the patient's electrical stimulation tolerance threshold, the final stimulation intensity is set to the electrical stimulation tolerance threshold. This tailoring step ensures the safety of electrical stimulation and avoids excessive stimulation or discomfort to the patient. Ultimately, the stimulation intensity, pulse width, and frequency, after impedance adjustment and electrical stimulation tolerance threshold clipping, are combined with the predetermined timing relationship between channels (stimulation start delay and duration) to form the final electrical stimulation parameter combination for output.

[0062] The above process incorporates the individual patient's electrophysiological state and tolerance into parameter generation, allowing electrical stimulation to better adapt to the patient's real-time situation, ensuring that electrical stimulation is always within the range that the patient can safely and comfortably tolerate, and enabling electrical stimulation to more accurately simulate natural muscle activation patterns and adapt to the patient's dynamic changes during the rehabilitation process.

[0063] In some preferred embodiments, step S5 includes: S51, outputting multi-channel electrical stimulation to the patient based on the combination of electrical stimulation parameters; S52. During the process of delivering multi-channel electrical stimulation to the patient, continuously calculating the motion deviation between the kinematic data and the expected motion trajectory; S53, determining the adjustment amount and direction of the electrical stimulation parameter combination at the next moment according to the movement deviation; S54. When the target fine motor movement remains unchanged, adjust the electrical stimulation parameter combination used at the next moment based on the adjustment amount and adjustment direction.

[0064] Specifically, the method of this application provides a specific implementation method for online adjustment of electrical stimulation parameter combinations, aiming to improve the accuracy and effectiveness of electrical stimulation in assisting patients with complex and fine movements through real-time feedback control. First, step S51 delivers multi-channel electrical stimulation to the patient based on the electrical stimulation parameter combination. This is the foundation of rehabilitation training. Preset or preliminarily determined parameter combinations drive the patient's muscle groups to contract, attempting to guide the fingers to complete the target movement. Next, while delivering multi-channel electrical stimulation to the patient, step S52 continuously calculates the motion deviation between the kinematic data and the desired motion trajectory. This step is crucial as it obtains feedback signals by monitoring the difference between the patient's actual finger joint movement and the preset ideal motion path in real time. Then, step S53 determines the amount and direction of adjustment to the electrical stimulation parameter combination at the next moment based on the motion deviation. This step is the core decision-making process of feedback control. By analyzing the magnitude and direction of the current motion deviation, the system can determine the extent and direction of the patient's actual movement deviation from the desired trajectory, and then calculate the extent and direction of the electrical stimulation parameter adjustment required to correct the deviation and guide movement back to the desired trajectory. Finally, step S53 adjusts the electrical stimulation parameter combination used at the next moment based on the adjustment amount and adjustment direction while the target fine movement remains unchanged. This means that while the patient is trying to complete the same target fine movement, the system dynamically modifies the electrical stimulation parameter combination being used based on the adjustment amount and direction calculated in real time, and applies the modified parameters to the electrical stimulation output at the next moment. This online, real-time parameter adjustment mechanism enables electrical stimulation to provide instant feedback and correction based on the patient's current actual motor performance, overcoming the limitations of static or offline parameter settings, and improving the electrical stimulation's auxiliary accuracy for complex fine movements and its adaptability to changes in patient movement, thereby more effectively helping patients complete their desired motion trajectory.

[0065] Through the above processing, the method of the present application can adjust the electrical stimulation parameters in real time according to the deviation between the patient's actual movement and the expected trajectory, so that the electrical stimulation assistance can more accurately guide the patient to complete complex and fine movements, thereby improving the effectiveness and adaptability of rehabilitation training, and overcoming the limitations of the existing technology that the parameters are difficult to adjust and difficult to adapt to the dynamic changes of patients.

[0066] In some preferred embodiments, step S52 includes: S521, performing time synchronization and spatial alignment on the kinematic data at the current moment and the expected motion trajectory; S522, extracting motion features based on the synchronized and aligned kinematic data; S523: Calculate the difference between the motion feature and the corresponding feature in the expected motion trajectory to obtain a motion deviation.

[0067] Specifically, step S521 is used to synchronize the current patient's finger joint kinematic data with the preset desired motion trajectory in both time and space. Temporal synchronization can be achieved using a dynamic time warping algorithm, which aligns two time series through nonlinear mapping, even if their speeds or durations differ. Spatial alignment can be achieved using an iterative closest point algorithm, which maps the actual motion data to the coordinate system of the desired trajectory through rotational and translational transformations.

[0068] More specifically, step S522 is used to extract key motion features based on the kinematic data that have been synchronized and aligned. The motion features include the instantaneous angle, instantaneous velocity and instantaneous position of the finger joints. The instantaneous angle refers to the bending or extension angle of the finger joints at a certain moment, which can be directly measured or calculated by the kinematic sensor worn on the patient's finger joints. The instantaneous velocity refers to the rate of change of the finger joint angle or position at a certain moment, which can be obtained by performing time differentiation calculation on the instantaneous angle or instantaneous position data. The instantaneous position refers to the coordinates of the finger joints in three-dimensional space, which can be calculated by the kinematic sensor in combination with the kinematic model.

[0069] More specifically, step S523 is used to calculate the difference between the extracted motion features and the corresponding features in the expected motion trajectory, thereby obtaining a multi-dimensional motion deviation, which specifically includes angle deviation, velocity deviation, and position deviation. Angle deviation refers to the difference between the actual instantaneous angle and the expected instantaneous angle, and specifically, the Euclidean distance or absolute difference between the two can be directly calculated. Velocity deviation refers to the difference between the actual instantaneous speed and the expected instantaneous speed, and specifically, the Euclidean distance or absolute difference between the two can be directly calculated. Position deviation refers to the difference between the actual instantaneous position and the expected instantaneous position, and specifically, the Euclidean distance between the two in three-dimensional space can be directly calculated.

[0070] More specifically, by calculating angle deviation, it is possible to assess whether the patient has achieved the correct joint posture; by calculating speed deviation, it is possible to assess whether the patient's movement fluency and rhythm meet the requirements; and by calculating position deviation, it is possible to assess the precision of the patient's fingers in space. This multi-dimensional deviation information can provide rich and accurate feedback for subsequent online adjustment of electrical stimulation parameters, enabling the system to specifically adjust parameters such as stimulation intensity, pulse width, and frequency to correct specific deficiencies in the patient's angle, speed, or position, thereby more effectively guiding the patient to complete complex and fine motor training and improving rehabilitation outcomes.

[0071] More specifically, this precise and comprehensive deviation calculation method, combined with the online adjustment of electrical stimulation parameters, forms a closed-loop online adjustment mechanism. This enables the system to monitor the patient's motor performance in real time and dynamically adjust the electrical stimulation parameters based on precise deviation information. This overcomes the existing issues of complex parameter adjustment processes and their difficulty adapting to the dynamic changes in muscle response and neural plasticity during the patient's rehabilitation process. This improves the refinement and adaptability of rehabilitation training, effectively assisting patients in recovering complex and fine finger movements.

[0072] In some preferred embodiments, step S53 includes: S531. Determine the adjustment amount and direction of the stimulation intensity, pulse width, and frequency based on the angle deviation, speed deviation, and position deviation, and in combination with preset adjustment rules.

[0073] Specifically, after obtaining multi-dimensional motion deviation information, the method of the present application enters the key step of adjusting the electrical stimulation parameters. This step determines the adjustment amount and adjustment direction of the stimulation intensity, pulse width and frequency in the electrical stimulation parameter combination at the next moment based on these specific angle deviations, speed deviations and position deviations, and in combination with the preset adjustment rules. For example, if a large angle deviation is detected, it indicates that the muscle contraction amplitude may be insufficient or too large. The system will increase or decrease the stimulation intensity accordingly according to the adjustment rules to adjust the muscle contraction force. If a speed deviation is detected, such as the movement speed is too slow, the system may increase the stimulation frequency or pulse width according to the rules to improve the smoothness and speed of muscle contraction. If there is a position deviation, it may be necessary to comprehensively adjust the stimulation intensity, pulse width and frequency to guide the finger to move to the desired position.

[0074] More specifically, pre-set adjustment rules are the core of this refined adjustment. They map the specific type and degree of movement deviation to a specific adjustment strategy for the electrical stimulation parameters. These rules can be constructed based on professional knowledge and clinical experience in rehabilitation medicine to ensure the scientific and effective adjustment. In this way, the system can more comprehensively and accurately understand the specific differences between the patient's current movement and the desired movement trajectory, thereby specifically determining the amount and direction of adjustment for specific electrical stimulation parameters such as stimulation intensity, pulse width, and frequency.

[0075] As a preferred embodiment, step S531 is specifically implemented as follows: The patient is undergoing rehabilitation training for a pinching movement, with the goal of achieving precise contact between the thumb and index fingertips. During the training, the system continuously collects kinematic data of the finger joints.

[0076] At a given moment, the system calculates the current finger joint motion deviation. The angle deviation is obtained by comparing the real-time acquired thumb and index finger joint angles with the desired pinching angles; the velocity deviation is obtained by comparing the joint motion speed with the desired speed; and the position deviation is obtained by comparing the spatial position of the fingertips with the desired contact point position.

[0077] For example, the system detected the following deviations: - Angulation deviation: The thumb interphalangeal joint angle is 5 degrees less than the desired value (indicating insufficient flexion).

[0078] - Speed deviation: The index finger moves 20% slower than the expected speed when approaching the target point (indicating bradykinesia).

[0079] - Positional deviation: The relative position of the thumb tip and index finger tip deviates by 3 mm from the expected contact point (indicating inaccurate spatial positioning).

[0080] At this point, the system will adjust the parameters according to the preset adjustment rules. Based on the above detected deviations and the preset rules, the system determines the amount and direction of adjustment of the electrical stimulation parameters at the next moment: - Increased the intensity of the thumb flexor muscles by 5%.

[0081] - Increase the stimulation frequency of the index finger flexor muscles by 2 Hz.

[0082] - Fine-tune the pulse width of the relevant muscle groups, for example, by increasing it by 0.05ms.

[0083] These adjustment amounts and directions are then applied to the electrical stimulation parameter combination at the next moment, thereby correcting the patient's movement in real time and guiding them to complete the pinching action more accurately.

[0084] Second, please refer to Figure 2 Some embodiments of the present application further provide a finger rehabilitation electrical stimulation parameter control system for assisting patients in performing complex and fine finger movement training, the system comprising: An acquisition module 201 is used to acquire multi-channel surface electromyographic signals and finger joint kinematic data of a patient; Recognition module 202, for recognizing the patient's target fine movements based on multi-channel surface electromyography signals; An analysis module 203 is used to analyze and obtain the multi-muscle group coordinated activation pattern and expected movement trajectory based on the target fine movement and finger joint kinematic data; Parameter configuration module 204, for generating electrical stimulation parameter combinations for different muscle groups according to the multi-muscle group coordinated activation pattern; The stimulation module 205 is used to output multi-channel electrical stimulation to the patient based on the electrical stimulation parameter combination, and continuously adjust the electrical stimulation parameter combination online according to the deviation between the finger joint kinematic data and the expected motion trajectory.

[0085] The finger rehabilitation electrical stimulation parameter control system of the present application combines multi-channel surface electromyography signals with finger joint kinematic data to achieve comprehensive perception of the patient's movement intention, muscle activation status and actual movement performance, and based on this, analyzes personalized multi-muscle group collaborative activation patterns and expected movement trajectories, and then generates and adjusts electrical stimulation parameter combinations online. It can generate personalized multi-muscle group collaborative activation patterns and expected movement trajectories according to the patient's movement intentions and actual abilities, and generate electrical stimulation parameters based on this, and can dynamically adapt to the patient's movement performance and rehabilitation process, to achieve effective auxiliary training of complex and fine finger movements, thereby solving the problem that the existing system is difficult to effectively simulate complex multi-muscle group coordination, the parameter adjustment is complex and difficult to adapt to the dynamic changes of patients, and achieves the effect of assisting patients in complex and fine finger movement training.

[0086] In addition, the units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0087] Furthermore, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0088] In this document, relational terms such as first and second, etc. are used merely to distinguish one entity or operation from another entity or operation, but do not necessarily require or imply any actual relationship or order between these entities or operations.

[0089] The above description is merely an embodiment of the present application and is not intended to limit the scope of protection of the present application. For those skilled in the art, various modifications and variations of the present application are possible. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A method for controlling finger rehabilitation electrical stimulation parameters, used to assist patients in training complex and fine finger movements, characterized in that: The method comprises the following steps: S1. Acquire the patient's multi-channel surface electromyography signals and finger joint kinematic data; S2. identifying the patient's target fine movements based on the multi-channel surface electromyography signals; S3. Analyze and obtain the multi-muscle group coordinated activation pattern and expected movement trajectory based on the target fine movement and finger joint kinematic data; S4. generating electrical stimulation parameter combinations for different muscle groups according to the multi-muscle group coordinated activation pattern; S5. Output multi-channel electrical stimulation to the patient based on the electrical stimulation parameter combination, and continuously adjust the electrical stimulation parameter combination online according to the deviation between the finger joint kinematic data and the expected motion trajectory.

2. The finger rehabilitation electrical stimulation parameter control method according to claim 1, characterized in that: Step S2 includes: S21, extracting time domain features, frequency domain features, and inter-channel collaborative features from the multi-channel surface electromyography signals to obtain multi-dimensional electromyography features representing the activation state of the muscle group; S22. Compare the multi-dimensional electromyographic features with a preset fine movement feature pattern library to determine the target fine movement, wherein the fine movement feature pattern library contains multi-dimensional electromyographic features corresponding to different target fine movements.

3. The finger rehabilitation electrical stimulation parameter control method according to claim 1, characterized in that: Step S3 includes: S31, according to the target fine movement, obtaining an initial multi-muscle group coordinated activation pattern and an initial expected movement trajectory corresponding to the target fine movement from a preset movement pattern library; S32. Evaluate the patient's current range of motion and exercise ability of the finger joints based on the finger joint kinematic data; S33. According to the range of motion and the motion ability, adjust the initial multi-muscle group coordinated activation mode to obtain the multi-muscle group coordinated activation mode, and adjust the initial expected motion trajectory to obtain the expected motion trajectory.

4. The finger rehabilitation electrical stimulation parameter control method according to claim 3, characterized in that: Step S32 includes: S321, analyzing the finger joint kinematic data to obtain the maximum motion angle and the minimum motion angle of each finger joint within a preset motion cycle to determine the motion range; S322: Analyze the finger joint kinematic data to obtain the movement speed, movement smoothness, and movement coordination between multiple joints of each finger joint within a preset movement cycle to determine the movement ability.

5. The finger rehabilitation electrical stimulation parameter control method according to claim 3, characterized in that: Step S33 includes: S331. Obtaining rehabilitation progress status; S332, generating a progressive challenge factor according to the rehabilitation progress status, the range of motion, and the exercise ability; S333. Based on the progressive challenge factor, the initial multi-muscle group coordinated activation pattern is adjusted, and the initial expected motion trajectory is adjusted to obtain the multi-muscle group coordinated activation pattern and the expected motion trajectory.

6. The finger rehabilitation electrical stimulation parameter control method according to claim 1, characterized in that: The multi-muscle group coordinated activation mode includes the activation intensity ratio and activation timing relationship of each muscle group required to achieve the target fine movement, and the electrical stimulation parameter combination includes the stimulation intensity, pulse width, frequency of each channel and the timing relationship between channels.

7. The finger rehabilitation electrical stimulation parameter control method according to claim 6, characterized in that: Step S4 includes: S41. Determine the initial stimulation intensity, initial pulse width, and initial frequency of each channel according to the activation intensity ratio and in combination with preset muscle group electrical stimulation response characteristics; S42, determining the stimulation start delay and stimulation duration of each channel according to the activation timing relationship, so as to form a timing relationship between the channels; S43. Obtain the patient's electrical stimulation tolerance threshold and the electrophysiological impedance of each muscle group, and adjust the initial stimulation intensity, initial pulse width and initial frequency according to the tolerance threshold and the electrophysiological impedance to form the electrical stimulation parameter combination in combination with the timing relationship between the channels.

8. The finger rehabilitation electrical stimulation parameter control method according to claim 7, characterized in that: The electrical stimulation tolerance threshold and the electrophysiological impedance are both pre-measured data. The process of measuring the electrical stimulation tolerance threshold includes: A1. Applying a test stimulus of gradually increasing intensity to the patient through the electrical stimulation device, and recording the intensity of the test stimulus at which the patient reports reaching the upper limit of comfort tolerance as the electrical stimulation tolerance threshold; The electrophysiological impedance measurement process includes: A2. Apply a test current to each muscle group through the electrical stimulation output channel, measure the voltage across the channel, and calculate the electrophysiological impedance based on the voltage and the test current.

9. The finger rehabilitation electrical stimulation parameter control method according to claim 1, characterized in that: Step S5 includes: S51, outputting multi-channel electrical stimulation to the patient based on the combination of electrical stimulation parameters; S52. During the process of outputting multi-channel electrical stimulation to the patient, continuously calculating the motion deviation between the kinematic data and the expected motion trajectory; S53, determining an adjustment amount and an adjustment direction for the electrical stimulation parameter combination at a next moment according to the movement deviation; S54. When the target fine movement remains unchanged, adjust the electrical stimulation parameter combination to be used at the next moment based on the adjustment amount and adjustment direction.

10. A finger rehabilitation electrical stimulation parameter control system, used to assist patients in complex and fine finger movement training, characterized in that: The system comprises: An acquisition module, used to acquire the patient's multi-channel surface electromyography signals and finger joint kinematics data; an identification module, configured to identify the patient's target fine movements based on the multi-channel surface electromyography signals; An analysis module is used to analyze and obtain the multi-muscle group coordinated activation pattern and expected movement trajectory based on the target fine movement and finger joint kinematic data; a parameter configuration module, configured to generate electrical stimulation parameter combinations for different muscle groups according to the multi-muscle group coordinated activation mode; The stimulation module is used to output multi-channel electrical stimulation to the patient based on the electrical stimulation parameter combination, and continuously adjust the electrical stimulation parameter combination online according to the deviation between the finger joint kinematic data and the expected motion trajectory.

Images