A hand function rehabilitation training method and device

Abstract

This invention relates to the technical field of device control and provides a method and apparatus for hand function rehabilitation training. The method includes: responding to a user-triggered self-test mode by collecting five-finger flexion data via a flexion sensor and collecting muscle electrical signals via an electromyography (EMG) sensor; the self-test mode is used to perform a maximum grasping motion when the user wears a pneumatic rehabilitation robot glove, where the maximum grasping motion refers to the user's maximum grasping ability; matching a training level based on the EMG signals; matching a tiered training strategy based on the five-finger flexion data and the training level; and controlling a pneumatic structure to perform training operations according to the tiered training strategy. This hand function rehabilitation training method, through intelligent feedback and personalized adjustment, makes rehabilitation training more efficient and precise, and effectively avoids the limitations of traditional methods.

Description

Technical Field

[0001] This invention belongs to the technical field of equipment control, and particularly relates to a method and device for hand function rehabilitation training. Background Technology

[0002] With the advent of an aging society, rehabilitation treatment for hand dysfunction has become an increasingly important concern for patients. Hand dysfunction is usually caused by various factors, including stroke, trauma, and nerve damage. These diseases or injuries can lead to loss or limitation of hand motor function, significantly impacting patients' quality of life. Therefore, hand function rehabilitation training is a crucial part of the treatment process, and how to provide efficient and personalized rehabilitation programs has become an important research topic.

[0003] Currently, hand function rehabilitation training mainly relies on traditional physical therapy methods, such as passive or active hand movement training. However, these traditional methods have certain limitations. For example, physical therapy often requires guidance from a professional rehabilitation therapist, and the rehabilitation training process is relatively monotonous, making it difficult for patients to adjust the training intensity according to their own recovery progress. Furthermore, traditional methods often neglect the individual needs of patients, failing to achieve personalized training goals.

[0004] With the development of technology, rehabilitation robots are gradually entering clinical applications, especially pneumatic rehabilitation robotic gloves. These gloves provide a relatively efficient means of rehabilitation training by simulating natural hand movements. Utilizing pneumatic control technology, these gloves adjust air pressure to simulate hand movements, enabling active or passive training of the patient's hand. Such devices not only provide precise motion control but also adjust training strategies based on real-time patient feedback, thereby improving rehabilitation outcomes.

[0005] However, existing pneumatic rehabilitation robotic gloves still have certain shortcomings, especially in providing personalized training programs for different patients' rehabilitation progress. Although pneumatic rehabilitation robotic gloves can achieve some hand training through mechanical control and sensor feedback, most current devices use relatively simple training methods and lack accurate assessment and targeted adjustments to the patient's hand function recovery level. Therefore, developing a hand function rehabilitation training method that can intelligently and personally adjust according to the patient's real-time status is crucial to improving rehabilitation outcomes. Summary of the Invention

[0006] In view of this, embodiments of the present invention provide a hand function rehabilitation training method and device to solve the technical problem that most current devices have relatively simple training methods and lack accurate assessment and targeted adjustment of the degree of recovery of the patient's hand function.

[0007] A first aspect of this invention provides a hand function rehabilitation training method, which is applied to a pneumatic rehabilitation robot glove. The pneumatic rehabilitation robot glove includes a pneumatic structure, a bending sensor, and an electromyography sensor. The hand function rehabilitation training method includes:

[0008] S1: In response to the user-triggered self-test mode, the bending data of the five fingers is collected by the bending sensor and the electromyography signal is collected by the electromyography sensor; the self-test mode is used to perform maximum gripping action when the user is wearing the pneumatic rehabilitation robot glove, the maximum gripping action refers to the maximum limit of the user's gripping ability.

[0009] S2: Match training levels based on the electromyographic signals;

[0010] S3: Match a step-by-step training strategy based on the five finger bending data and the training level;

[0011] S4: Control the aerodynamic structure to perform training operations according to the stepped training strategy.

[0012] Further, S2 includes:

[0013] S21: Calculate the user's muscle control index based on the electromyographic signal; the muscle control index is used to characterize the user's ability to control muscles.

[0014] S22: Match the training level based on the muscle control index.

[0015] Further, S21 includes:

[0016] S211: Collect signal values ​​corresponding to multiple sampling points in the electromyography signal according to a preset frequency;

[0017] S212: Calculate the average value corresponding to the multiple signal values;

[0018] S213: Count the number of interruptions and the duration of interruptions in the electromyographic signals;

[0019] S214: Calculate the variance between multiple signal values;

[0020] S215: Calculate the muscle control index based on the average value, the number of interruptions, the duration of the interruptions, and the variance.

[0021] Further, S215 includes:

[0022] S2151: Multiply the number of interruptions by the first adjustment parameter to obtain the first value;

[0023] S2152: Multiply the interruption duration by the second adjustment parameter to obtain the second value;

[0024] S2153: Add the first value and the second value to obtain the interrupt parameter;

[0025] S2154: If the average value is greater than the first threshold, the interruption parameter is less than the second threshold, and the variance is less than the third threshold, then the muscle control index is determined to be the first preset value.

[0026] S2155: If the average value is greater than the first threshold, the interruption parameter is not less than the second threshold, and the variance is less than the third threshold, then the muscle control index is determined to be the second preset value.

[0027] S2156: If the average value is greater than the first threshold, the interruption parameter is less than the second threshold, and the variance is not less than the third threshold, then the muscle control index is determined to be the third preset value.

[0028] S2157: If the average value is not greater than the first threshold, the interruption parameter is less than the second threshold, and the variance is less than the third threshold, then the muscle control index is determined to be the fourth preset value.

[0029] S2158: If the average value is not greater than the first threshold, the interruption parameter is not less than the second threshold, and the variance is less than the third threshold, then the muscle control index is determined to be the fifth preset value.

[0030] S2159: If the average value is not greater than the first threshold, the interruption parameter is less than the second threshold, and the variance is not less than the third threshold, then the muscle control index is determined to be the sixth preset value.

[0031] Further, S3 includes:

[0032] S31: Extract the training frequency and multiple step coefficients corresponding to the training level; the multiple step coefficients include a first step coefficient, a second step coefficient, and a third step coefficient;

[0033] S32: Multiply the five-finger bending data with the first step coefficient to obtain the first stage bending data;

[0034] S33: Multiply the first stage bending data by the second step coefficient to obtain the second stage bending data;

[0035] S34: Multiply the second stage bending data with the third step coefficient to obtain the third stage bending data;

[0036] S35: Calculate the pneumatic control data corresponding to the first stage bending data, the second stage bending data, and the third stage bending data;

[0037] S36: The training frequency and the pneumatic control data corresponding to each of the multiple ordered stages are used as the step-by-step training strategy.

[0038] Further, S35 includes:

[0039] S351: Obtain the mapping table between bending data and aerodynamic data;

[0040] S352: Extract the pneumatic control data corresponding to the first stage bending data, the second stage bending data and the third stage bending data respectively from the mapping table.

[0041] Further, S36 includes:

[0042] S361: The training frequency and pneumatic control data corresponding to each of the multiple ordered stages are used as a multi-finger step-by-step training strategy for the five fingers.

[0043] S362: Calculate the difference between the multiple finger bending data;

[0044] S363: Calculate the mean of the differences between multiple differences corresponding to each finger;

[0045] S364: If the mean difference is higher than the fourth threshold, then divide the mean difference by the maximum value in the five-finger bending data to obtain the training coefficient;

[0046] S365: Multiply the training coefficient by the training frequency to obtain the single-finger frequency;

[0047] S366: The training frequency and pneumatic control data corresponding to each of the multiple ordered stages are used as the single-finger stepwise training strategy for the mean difference value corresponding to a single finger.

[0048] S367: Randomly mix the multi-finger step training strategy and the single-finger step training strategy in the same stage to obtain the step training strategy.

[0049] A second aspect of the present invention provides a hand function rehabilitation training device, comprising:

[0050] The acquisition unit is used to respond to the self-test mode triggered by the user, to acquire five-finger bending data through a bending sensor and to acquire muscle electrical signals through an electromyography sensor; the self-test mode is used to perform maximum gripping action when the user wears the pneumatic rehabilitation robot glove, the maximum gripping action refers to the maximum limit of the user's gripping ability.

[0051] A level matching unit is used to match training levels based on the electromyographic signals.

[0052] A strategy matching unit is used to match a step-by-step training strategy based on the five-finger bending data and the training level.

[0053] The control unit is used to control the pneumatic structure to perform training operations according to the stepped training strategy.

[0054] A third aspect of the present invention provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps in the hand function rehabilitation training method described in the first aspect above.

[0055] A fourth aspect of the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps in the hand function rehabilitation training method described in the first aspect.

[0056] The beneficial effects of this invention compared to existing technologies are as follows: By collecting real-time electromyographic signals and finger flexion data, combined with user physiological feedback, training levels and step-by-step training strategies are matched. The intensity and difficulty of training are adjusted according to each user's hand function recovery, achieving targeted rehabilitation training. This personalized training method avoids the "one-size-fits-all" problem of traditional training methods, better meeting the specific needs of each patient and improving the effectiveness of rehabilitation training. This invention utilizes feedback data from electromyographic and flexion sensors to automatically identify the patient's muscle activity and finger flexion state. By analyzing these physiological signals in real time, the training intensity can be dynamically adjusted to ensure that the training process is neither too easy nor too intense, thereby reducing patient discomfort and risks during training. This intelligent training adjustment helps improve the safety and comfort of rehabilitation training. The self-test mode in this invention allows patients to perform a self-test of their maximum gripping ability while wearing pneumatic rehabilitation robot gloves. Through this action, the system can accurately assess the patient's hand gripping ability, serving as an important basis for adjusting training intensity. This function ensures that the rehabilitation process can start from the patient's existing abilities, conducting progressive rehabilitation training, which helps to gradually restore the patient's hand function. This invention, by matching a step-by-step training strategy to the user's physiological signal data, ensures a gradual training process, preventing injury or fatigue caused by overtraining in the early stages. Gradually increasing training intensity helps patients better adapt to the rehabilitation process, progressively restoring hand function and avoiding short-sighted training methods. Because the method can adjust the training strategy according to individual patient differences, it avoids a one-size-fits-all approach, improving rehabilitation effectiveness while effectively shortening rehabilitation time. Personalized training programs make patients more proactive in the rehabilitation process, greatly improving the quality and efficiency of training. In summary, the hand function rehabilitation training method of this invention, through intelligent feedback and personalized adjustments, makes rehabilitation training more efficient and precise, effectively avoiding the limitations of traditional methods. Attached Figure Description

[0057] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0058] Figure 1 A schematic flowchart of a hand function rehabilitation training method provided by the present invention is shown;

[0059] Figure 2 A schematic diagram of a hand function rehabilitation training device according to an embodiment of the present invention is shown;

[0060] Figure 3 A schematic diagram of a terminal device provided in an embodiment of the present invention is shown. Detailed Implementation

[0061] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of the invention. However, those skilled in the art will understand that the invention can be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods are omitted so as not to obscure the description of the invention with unnecessary detail.

[0062] This invention provides a hand function rehabilitation training method and device to address the technical problem that most current devices have relatively simple training methods and lack accurate assessment and targeted adjustment of the patient's hand function recovery level.

[0063] First, this invention provides a method for hand function rehabilitation training. Please refer to [link / reference]. Figure 1 , Figure 1 A schematic flowchart of a hand function rehabilitation training method provided by the present invention is shown. Figure 1 As shown, this hand function rehabilitation training method may include the following steps:

[0064] S1: In response to the user-triggered self-test mode, the bending data of the five fingers is collected by the bending sensor and the electromyography signal is collected by the electromyography sensor; the self-test mode is used to perform maximum gripping action when the user is wearing the pneumatic rehabilitation robot glove, the maximum gripping action refers to the maximum limit of the user's gripping ability.

[0065] The main purpose of this step is to obtain the user's current hand function status, providing basic data for subsequent personalized training.

[0066] When the user wears the pneumatic rehabilitation robot gloves, the system enters self-test mode. The purpose of this mode is to allow the user to exert maximum effort in grasping motions, thereby testing the maximum limit of their grasping ability (i.e., the patient's current maximum grasping force or ability).

[0067] The flexion sensor is used to collect flexion data of the five fingers in real time, reflecting the movement of each finger. This data allows the system to assess the user's finger dexterity and range of motion.

[0068] Electromyography (EMG) sensors are used to capture electrical signals from the muscles of a user during grasping movements. These EMG signals reflect the activity state of the muscles and can indirectly assess muscle strength and control. Therefore, they provide crucial information for analyzing a user's hand muscle function.

[0069] S2: Match training levels based on the electromyographic signals;

[0070] Electromyography (EMG) signals are used to assess a user's muscle control ability, and an appropriate training level is determined based on the assessment results. EMG signals can assess a user's grip strength or muscle control ability based on the intensity of electrical activity in the muscles. This process assigns an appropriate training level to the user, reflecting the patient's current progress or level of hand rehabilitation.

[0071] Specifically, S2 includes S21 to S22:

[0072] S21: Calculate the user's muscle control index based on the electromyographic signal; the muscle control index is used to characterize the user's ability to control muscles.

[0073] The purpose of this step is to quantify the user's muscle control ability by collecting electromyographic signals and generate a numerical value representing the user's level of muscle control—the "muscle control index".

[0074] Electromyography (EMG) sensors acquire electromyographic signals generated when a user performs grasping or other hand movements. EMG signals are essentially electrical fluctuations generated during muscle activity; these signals reflect the intensity, frequency, and pattern of muscle activity.

[0075] By analyzing electromyographic signals (such as filtering, feature extraction, and frequency domain analysis), key information about muscle activity can be extracted. Analysis methods include calculating the root mean square (RMS) value, average voltage (AV), or spectral analysis, which can be used to assess muscle activity levels.

[0076] The extracted feature data are combined to calculate the "muscle control index" based on a pre-defined algorithm or model. This index reflects a user's muscle control ability when performing actions such as grasping. Specifically, the muscle control index may be a numerical value representing the strength or precision of muscle control. For example, a higher muscle control index may indicate stronger muscle control, while a lower index may mean weaker muscle control, potentially requiring more rehabilitation training.

[0077] Specifically, S21 includes S211 to S215:

[0078] S211: Collect signal values ​​corresponding to multiple sampling points in the electromyography signal according to a preset frequency;

[0079] The purpose of this sub-step is to acquire electromyographic signal data from the electromyography sensor at multiple time points and to provide sufficient signal samples for subsequent processing.

[0080] The system sets a fixed sampling frequency (e.g., a sampling rate of 1000Hz, meaning 1000 data points are collected per second) to ensure that a sufficient number of electromyographic (EMG) signal data are acquired within a specified time interval. These signal values ​​comprehensively reflect the real-time state of muscle activity. Following the set sampling frequency, the system continuously collects EMG signals over a certain period. Each sampling point corresponds to the electrical activity intensity value of the muscle at a specific moment. These signal values ​​are the fundamental data for measuring muscle activity, control precision, and stability.

[0081] S212: Calculate the average value corresponding to the multiple signal values;

[0082] This sub-step calculates the average of multiple acquired signal values ​​to obtain an indicator representing the overall level of muscle control. The arithmetic mean of the acquired signal values ​​is calculated (e.g., the sum of the signal values ​​divided by the number of sampling points). This average reflects the overall muscle activity or control strength during the sampling period. A higher average may indicate stronger muscle control in the user, while a lower average may indicate weaker control.

[0083] S213: Count the number of interruptions and the duration of interruptions in the electromyographic signals;

[0084] The purpose of this sub-step is to assess whether there are any abnormal interruptions in muscle signals, which may indicate discontinuity or instability in muscle activity.

[0085] The system analyzes the continuity of signals to identify "interruptions." An interruption refers to a significant weakening or disappearance of the signal over a period of time (e.g., the amplitude of an electrical signal drops below a certain threshold). Counting the number of interruptions reflects frequent instability or brief failures in muscle activity. For each interruption, the system also records its duration. Longer interruptions may indicate a significant decline in muscle control or fatigue during actions such as grasping.

[0086] Interruption duration may be 0-2 times in healthy subjects; 3-10 times in patients with moderate hand dysfunction; and >10 times in patients with severe impairment.

[0087] S214: Calculate the variance between multiple signal values;

[0088] The purpose of this sub-step is to assess the volatility or degree of change in the acquired signals to reflect the stability and accuracy of muscle control.

[0089] Variance is a statistic that measures the degree of change in a signal. By calculating the variance of multiple signal values, the system can assess the stability of electromyographic signals. If the signal value changes significantly and the variance is high, it may indicate unstable muscle control and poor control ability; if the signal change is small and the variance is low, it may indicate relatively smooth and stable muscle control.

[0090] S215: Calculate the muscle control index based on the average value, the number of interruptions, the duration of the interruptions, and the variance.

[0091] The purpose of this sub-step is to comprehensively consider multiple factors and calculate a comprehensive "muscle control index" to characterize the user's overall muscle control ability.

[0092] The mean reflects the overall level of muscle activity; a higher mean can improve the muscle control index. The number and duration of interruptions reflect the stability of muscle control; frequent interruptions and longer interruption times decrease the muscle control index, indicating weaker user control. Variance reflects the precision and stability of control; lower variance indicates more stable muscle control.

[0093] By comprehensively evaluating the above factors, a digital muscle control index is derived, which represents the strength of a user's muscle control ability. A higher index indicates stronger control, and vice versa. This index will be directly used for subsequent training level matching.

[0094] In the embodiments corresponding to S211 to S215, the user's muscle control index is calculated by analyzing and processing electromyographic signal data in detail, comprehensively considering factors such as the average value, fluctuation, stability, and instability of the signal. This index will provide a key basis for subsequent training level matching, ensuring the personalization and effectiveness of the training task.

[0095] Specifically, S215 includes S2151 to S2159:

[0096] S2151: Multiply the number of interruptions by the first adjustment parameter to obtain the first value;

[0097] The purpose of this sub-step is to obtain a value (the first value) representing the impact of interruptions by multiplying the number of interruptions by an adjustment parameter. This value will reflect the effect of the frequency of interruptions on the muscle control index.

[0098] Interruption count: The system has counted the number of interruptions in the electromyographic signal, which represents the number of times the signal interruption occurred.

[0099] First Adjustment Parameter: This parameter is a preset value used to control the weight of the number of interruptions on the muscle control index. A higher number of interruptions suggests potentially weaker muscle control; therefore, the first adjustment parameter helps adjust for this effect. The "first value" is obtained by multiplying the number of interruptions by the first adjustment parameter, which quantifies the impact of interruptions on control ability. The first adjustment parameter can be set to 0.5.

[0100] S2152: Multiply the interruption duration by the second adjustment parameter to obtain the second value;

[0101] This step involves multiplying the interrupt duration by another adjustment parameter to obtain a value (the second value) that reflects the impact of the interrupt duration.

[0102] Interruption duration: This is the duration of each interruption that has been statistically analyzed in the third sub-step, reflecting the discontinuity of muscle activity.

[0103] The second adjustment parameter, similar to the first, is also a preset value used to control the impact of interruption duration on the muscle control index. Generally, a prolonged interruption may indicate instability in muscle control; therefore, the interruption duration adjustment parameter affects the magnitude of the index. The "second value" is obtained by multiplying the interruption duration by the second adjustment parameter. The second adjustment parameter can be set to 0.3.

[0104] S2153: Add the first value and the second value to obtain the interrupt parameter;

[0105] This step combines the effects of the number of interruptions and the duration of interruptions to obtain a comprehensive "interruption parameter," which reflects the overall impact of the interruption. Adding these two values ​​together yields the interruption parameter. The magnitude of the interruption parameter reflects the overall impact of the interruption; a larger value indicates that the frequency and duration of the interruption have a greater influence on muscle control.

[0106] S2154: If the average value is greater than the first threshold, the interruption parameter is less than the second threshold, and the variance is less than the third threshold, then the muscle control index is determined to be the first preset value.

[0107] This step involves a conditional judgment, determining the final muscle control index based on multiple conditions. The first threshold, second threshold, and third threshold are preset standards used to determine whether the condition for the muscle control index to reach the first preset value is met.

[0108] If the average value is greater than the first threshold, the interruption parameter is less than the second threshold, and the variance is less than the third threshold, then the muscle control index is the first preset value. This means that the control ability is strong and the instability is low.

[0109] S2155: If the average value is greater than the first threshold, the interruption parameter is not less than the second threshold, and the variance is less than the third threshold, then the muscle control index is determined to be the second preset value.

[0110] If the average value is greater than the first threshold, but the interruption parameter is not less than the second threshold (indicating a longer number or duration of interruptions), and the variance is less than the third threshold, then the muscle control index is set to the second preset value. This situation may mean that although the control ability is relatively strong, there are certain interruptions, and more training may be needed to further stabilize the control ability.

[0111] S2156: If the average value is greater than the first threshold, the interruption parameter is less than the second threshold, and the variance is not less than the third threshold, then the muscle control index is determined to be the third preset value.

[0112] If the average value is greater than the first threshold, and the interruption parameter is less than the second threshold (indicating fewer interruptions), but the variance is not less than the third threshold (indicating insufficient control stability), then the muscle control index is set to the third preset value. This means that the user may have good control ability, but there are problems with the stability of control, and the accuracy may need to be improved.

[0113] S2157: If the average value is not greater than the first threshold, the interruption parameter is less than the second threshold, and the variance is less than the third threshold, then the muscle control index is determined to be the fourth preset value.

[0114] If the average value is not greater than the first threshold (indicating weak control ability), the interruption parameter is small (indicating fewer interruptions), and the variance is small (indicating good stability), then the muscle control index is the fourth preset value. This situation may indicate that the user has low muscle control ability, but the control process is relatively stable.

[0115] S2158: If the average value is not greater than the first threshold, the interruption parameter is not less than the second threshold, and the variance is less than the third threshold, then the muscle control index is determined to be the fifth preset value.

[0116] If the average value is not greater than the first threshold, the interruption parameter is large (indicating frequent interruptions), and the variance is small, then the muscle control index is set to the fifth preset value. Such users may have weaker and more unstable control, requiring greater training adjustments.

[0117] S2159: If the average value is not greater than the first threshold, the interruption parameter is less than the second threshold, and the variance is not less than the third threshold, then the muscle control index is determined to be the sixth preset value.

[0118] If the average value is not greater than the first threshold (weak control ability) and the interruption parameter is small (few interruptions), but the variance is large (unstable control), then the muscle control index is the sixth preset value. This indicates that the user needs more training to improve control stability and accuracy.

[0119] As an optional embodiment of this application, the muscle control index can also be calculated using the following mathematical model:

[0120]

[0121] in, This indicates the muscle control index. This indicates the number of interruptions (the number of interruption events in the electromuscular signal). Indicates the interrupt duration (the duration of each interrupt, in seconds). This represents the average value of the muscle electrical signal. Represents the variance of the muscle electrical signal. This represents the first weighting coefficient. This represents the second weighting coefficient. This represents the third weighting coefficient. Represents a constant.

[0122] The core idea of ​​the Muscle Control Index (MCI) is to characterize a person's muscle control ability based on several key features of the muscle electrical signal. These features include signal strength (mean), stability (variance), frequency of interruptions (number of interruptions), and duration of each interruption (interruption duration). These features reflect muscle control performance in different dimensions.

[0123] This represents the combined effect of the intensity and instability of the electromyographic (EMG) signal. A larger mean EMG signal indicates stronger control, but a larger variance may indicate weaker control; therefore, a variance-weighted term is introduced.

[0124] This reflects the impact of the number of interruptions and the duration of each interruption on muscle control. The more interruptions, the worse the control; the longer the interruption, the worse the control.

[0125] constant This is used to ensure computational stability and prevent division by zero errors in formulas when the number of interruptions or the duration of interruptions is zero.

[0126] An interruption event is defined as a sustained low-amplitude EMG signal (EMG) envelope amplitude (or RMS value) below 40% of the EMG amplitude corresponding to maximum voluntary contraction force (MVC) during the user's maximal gripping action (S1), with this low amplitude state lasting ≥ 200 milliseconds (ms). A 40% MVC EMG indicates a significant signal attenuation below normal exertion levels. 200ms is sufficient to distinguish between brief noise / jitter and genuine loss of control or force.

[0127] The specific numerical acquisition logic for α, β, γ, and δ is as follows: Under strictly controlled conditions, the user performs multiple self-tests of maximum grip strength while wearing gloves. High-precision electromyography (EMG) signals (for calculating μ, σ, N_interrupt, τ_interrupt), bending data, and clinical gold standard assessment results (such as MRC muscle strength grading, iEMG / MAV of surface EMG, or standard scale scores) are recorded simultaneously. A set of α, β, γ, and δ is found such that the calculated MCI has the optimal correlation (e.g., the highest Pearson / Spearman correlation coefficient) or the strongest discrimination (e.g., the largest difference in MCI between different ability groups) with the clinical assessment results or expert-determined ability level. For example, the values ​​of α, β, γ, and δ can be set as follows: α = -0.15, β = 2.0, γ = 0.25, δ = 1.0.

[0128] The mathematical model described above comprehensively reflects a user's muscle control ability by integrating four key factors: mean, variance, number of interruptions, and interruption duration. This comprehensive evaluation method describes muscle control ability more accurately than analyzing signal strength or stability alone. The coefficients in the formula provide flexibility to adjust the influence of each factor. These coefficients can be adjusted according to different application scenarios or needs to better adapt to different user groups or control systems. This enables personalized assessment, allowing the muscle control index to perform well in different situations. By incorporating factors such as signal variance and interruption duration, the formula effectively reflects the stability of the electromyographic signal. If a user's muscle control is unstable, with high variance or frequent interruptions, the MCI value will decrease significantly, reflecting a control deficiency or problem and helping to identify weak points in muscle control. Since the number and duration of interruptions are also considered, the formula can handle dynamic changes. In practical applications, muscle control performance is not static and may fluctuate with factors such as fatigue, environmental changes, and training. This formula accurately reflects these changes and provides feedback for training or treatment. By incorporating multiple factors, the formula avoids over-reliance on a single dimension (such as solely relying on signal strength or solely on stability). This multi-dimensional comprehensive evaluation makes the MCI more holistic and able to more accurately characterize a person's muscle control ability.

[0129] For example, suppose the input data (from S211-S214) is:

[0130] Average value (Avg): 0.8 (assuming a range of 0-1, where 1 represents the strongest signal);

[0131] Number of interrupts (NumInterrupt): 3;

[0132] Interruption duration (DurInterrupt): 1.5 seconds (can be total duration or average duration, here we assume it is total duration);

[0133] Variance (Var): 0.1 (reflects the degree of signal fluctuation);

[0134] First adjustment parameter (W_num): 0.5

[0135] Second adjustment parameter (W_dur): 0.3

[0136] First threshold (Th_avg): 0.7 (used to determine whether the average electromyographic intensity is sufficient)

[0137] Second threshold (Th_int): 2.0 (Upper limit used to determine the severity of the interruption)

[0138] Third threshold (Th_var): 0.15 (Upper limit for judging the degree of signal fluctuation)

[0139] Preset values: First preset value (MCI_1): 10 (highest control capability), Second preset value (MCI_2): 8, Third preset value (MCI_3): 7, Fourth preset value (MCI_4): 5, Fifth preset value (MCI_5): 3, Sixth preset value (MCI_6): 2 (lowest control capability).

[0140] Calculate the first value = 3 * 0.5 = 1.5, calculate the second value = 1.5 * 0.3 = 0.45, and calculate the interrupt parameter (IntParam) = 1.5 + 0.45 = 1.95.

[0141] In this hypothetical example: the user's average electromyographic (EMG) signal intensity (0.8) is higher than the minimum required threshold (0.7). Although interruptions occurred (3 times, total duration 1.5 seconds), the calculated overall interruption parameter (1.95) is lower than the acceptable upper limit (2.0), indicating that the interruptions were within a controllable range (the judgment criterion is based on the standard of having movement impairment, not on the standard of normality). The fluctuation of the EMG signal (0.1) is relatively small, below the stability threshold (0.15). Based on the above three points, the system determines that the user's muscle control ability is good and assigns the highest muscle control index of 10 (corresponding to S22, this high index will match a higher level of training difficulty).

[0142] Other branch examples (assuming data changes):

[0143] Example A (satisfying S2155):

[0144] Avg = 0.8 (>0.7), IntParam = 2.5 (>=2.0), Var = 0.1 (<0.15)

[0145] Result: MCI = MCI_2 = 8 (Sufficient strength, stable signal, but interruptions are too frequent / too long)

[0146] Example B (satisfying S2156):

[0147] Avg = 0.8 (>0.7), IntParam = 1.5 (<2.0), Var = 0.2 (>=0.15)

[0148] Result: MCI = MCI_3 = 7 (Sufficient strength, few interruptions, but excessive signal fluctuation)

[0149] Example C (satisfying S2157):

[0150] Avg = 0.6 (<=0.7), IntParam = 1.0 (<2.0), Var = 0.05 (<0.15)

[0151] Result: MCI = MCI_4 = 5 (Insufficient strength, but stable control and few interruptions)

[0152] Example D (satisfying S2158):

[0153] Avg = 0.65 (<=0.7), IntParam = 3.0 (>=2.0), Var = 0.12 (<0.15)

[0154] Result: MCI = MCI_5 = 3 (Insufficient strength, severe interruption, signal is still stable)

[0155] Example E (satisfying S2159):

[0156] Avg = 0.55 (<=0.7), IntParam = 1.8 (<2.0), Var = 0.18 (>=0.15)

[0157] Result: MCI = MCI_6 = 2 (Insufficient strength, interruption is acceptable, but signal fluctuation is large - weakest control capability).

[0158] In the embodiments corresponding to S2151 to S2159, a specific muscle control index is determined through a series of conditional judgments, combined with the user's average value, interruption parameters, and variance. Each combination of conditions serves as a judgment criterion, accurately reflecting the user's muscle control ability and the stability of control, thereby providing personalized level matching for subsequent training.

[0159] S22: Match the training level based on the muscle control index.

[0160] The purpose of this step is to determine the appropriate training level for the user based on their muscle control index. The training level determines the intensity and complexity of the training tasks the user will undertake.

[0161] The system pre-sets a series of training levels corresponding to different muscle control indices. Typically, these training levels are divided into multiple stages (such as beginner, intermediate, and advanced), each corresponding to different training goals and intensities. For example, if the muscle control index is low (indicating weak muscle control), the training level might be set to beginner, with training tasks performed at a lower intensity to help the user gradually improve their control. If the muscle control index is high (indicating strong muscle control), the training level can be set to advanced, with training tasks that are more difficult and complex, aiming to further enhance the user's control.

[0162] Based on the calculated muscle control index, the system automatically selects the most suitable training level. For example, if a user's muscle control index falls within a certain range, the system will select the training level corresponding to that range according to preset matching rules. This training level serves as the basis for subsequent training, influencing the intensity, complexity, and specific requirements of the task. If the system detects a significant change in the user's muscle control index (e.g., faster or slower recovery progress), it can dynamically adjust the training level to ensure the effectiveness and personalization of the training. By continuously monitoring and adjusting the training level, the system helps users perform rehabilitation training at an appropriate intensity, avoiding overtraining or undertraining.

[0163] In the embodiments corresponding to S21 and S22, these two steps provide personalized matching for the user's training through electromyography (EMG) signal analysis and muscle control index calculation. First, the system assesses the user's muscle control ability by collecting EMG signals and calculates the muscle control index. Then, the system matches the user with the most suitable training level based on this index. This method not only adjusts the training intensity according to the user's current ability but also dynamically adjusts it as the rehabilitation progresses, thereby ensuring that the rehabilitation process is both effective and safe.

[0164] S3: Match a step-by-step training strategy based on the five finger bending data and the training level;

[0165] This step combines data on finger flexion and training levels to select a suitable tiered training strategy for the user. A tiered training strategy means that the difficulty, intensity, and complexity of the training gradually increase; as the user's ability improves, the training difficulty gradually rises to help the user gradually regain hand function.

[0166] Specifically, S3 includes S31 to S36:

[0167] S31: Extract the training frequency and multiple step coefficients corresponding to the training level; the multiple step coefficients include a first step coefficient, a second step coefficient, and a third step coefficient;

[0168] The purpose of this step is to initialize the parameter configuration in preparation for subsequent calculations. The training level is based on the previous "muscle control index" matching results, such as beginner, intermediate, advanced, etc.

[0169] Each level corresponds to:

[0170] Training frequency refers to the total number of training sessions for each level.

[0171] The step coefficients (K1, K2, K3) are coefficients that control the increase or change of bending data at each stage.

[0172] They can be designed as: incremental coefficients (such as 1.0→1.2→1.5) to enhance training; or custom curves to adapt to the complex needs of the rehabilitation phase.

[0173] S32: Multiply the five-finger bending data with the first step coefficient to obtain the first stage bending data;

[0174] S33: Multiply the first stage bending data by the second step coefficient to obtain the second stage bending data;

[0175] The data from the first stage is further enhanced or modified by multiplying it by a second-order coefficient to generate the target value for the next stage. This process simulates the "progressiveness" of training, transitioning from the basic stage to the reinforcement stage.

[0176] S34: Multiply the second stage bending data with the third step coefficient to obtain the third stage bending data;

[0177] The difficulty is further increased to obtain the third stage of bending data, which is used to improve the intensity or accuracy of later training.

[0178] For example, the five-finger bending data (MaxBend): Assume that in self-test mode, the maximum bending angle (in degrees) of the user's five fingers are as follows: Thumb: 90°, Index: 85°, Middle: 80°, Ring: 75° and Little: 70°.

[0179] The number of repetitions required for each training phase at this level. Assume the training frequency for the current training phase is 10 repetitions per phase.

[0180] This level defines a coefficient for the percentage decrease in training intensity. Let the coefficient for the current training phase be:

[0181] First-stage coefficient (K1) = 0.80 (The first-stage target is 80% of maximum capacity)

[0182] Second-stage coefficient (K2) = 0.60 (the second-stage target is 60% of the first-stage target)

[0183] The third-stage coefficient (K3) = 0.50 (the third-stage target is 50% of the second-stage target).

[0184] Calculation process (based on S31-S36):

[0185] S31 extracts the training frequency and multiple step coefficients corresponding to the training level;

[0186] Training level = 3, training frequency = 10 (times / stage), step coefficients: K1 = 0.80, K2 = 0.60, K3 = 0.50.

[0187] S32 multiplies the five-finger bending data with the first step coefficient to obtain the first stage bending data (Stage1_Bend);

[0188] Thumb: 90° * 0.80 = 72°, Index finger: 85° * 0.80 = 68°, Middle finger: 80° * 0.80 = 64°, Ring finger: 75° * 0.80 = 60°, Little finger: 70° * 0.80 = 56°.

[0189] First-stage bending data = [72, 68, 64, 60, 56]

[0190] S33 multiplies the first-stage bending data by the second step coefficient to obtain the second-stage bending data;

[0191] Thumb: 72° * 0.60 = 43.2°, Index finger: 68° * 0.60 = 40.8°, Middle finger: 64° * 0.60 = 38.4°, Ring finger: 60° * 0.60 = 36.0°, Little finger: 56° * 0.60 = 33.6°.

[0192] Second stage bending data = [43.2, 40.8, 38.4, 36.0, 33.6].

[0193] S34 multiplies the second-stage bending data by the third-step coefficient to obtain the third-stage bending data;

[0194] Thumb: 43.2° * 0.50 = 21.6°, Index finger: 40.8° * 0.50 = 20.4°, Middle finger: 38.4° * 0.50 = 19.2°, Ring finger: 36.0° * 0.50 = 18.0°, Little finger: 33.6° * 0.50 = 16.8°.

[0195] Third-stage bending data = [21.6, 20.4, 19.2, 18.0, 16.8].

[0196] S35: Calculate the pneumatic control data corresponding to the first stage bending data, the second stage bending data, and the third stage bending data;

[0197] Pneumatic control data is the input signal for the training system to ultimately control the pneumatic glove / actuator, and it is mapped or converted based on bending data.

[0198] Specifically, S35 includes S351 and S352:

[0199] S351: Obtain the mapping table between bending data and aerodynamic data;

[0200] A mapping table describes the relationship between bending data (finger bending angles or muscle control strength) and pneumatic control data (air pressure values, airflow velocity, or other pneumatic system control signals). The mapping table's function is to convert data such as finger bending angles into actual control signals that can drive actuators. The mapping table is based on the correspondence between bending data and pneumatic data obtained from laboratory measurements, and the mapping formula is derived through statistical analysis and curve fitting.

[0201] S352: Extract the pneumatic control data corresponding to the first stage bending data, the second stage bending data and the third stage bending data respectively from the mapping table.

[0202] Based on the previously calculated staged bending data (i.e., bending data for the first, second, and third stages), the corresponding pneumatic control data is retrieved from the mapping table. For example, assuming the first stage bending data is 0.4 (i.e., a finger is bent by 40%), the corresponding pneumatic data according to the mapping table might be the air pressure value X1.

[0203] Second-stage bending data: Similarly, the bending data of the second stage is used as the basis for querying the corresponding aerodynamic control data from the mapping table.

[0204] Third-stage bending data: Finally, the third-stage bending data is used to find the corresponding pneumatic control signal.

[0205] The bending data is converted into pneumatic control signals, which drive the pneumatic actuator to achieve the actual bending or movement of the finger.

[0206] In the embodiments corresponding to S351 and S352, the key objective of this process is to ensure that the mapping relationship between bending data and aerodynamic control data is correctly implemented and applied. The bending data at each stage may correspond to control commands of different intensities or fineness, and through the mapping table, you can ensure that the data at each stage can generate appropriate aerodynamic outputs, thereby enabling the training strategy or control system to accurately execute the required actions.

[0207] S36: The training frequency and the pneumatic control data corresponding to each of the multiple ordered stages are used as the step-by-step training strategy.

[0208] The output-step training strategy is a structured training plan with the following characteristics: clear objectives (curved data); reasonable pace (training frequency); and adjustable stages (three-stage strategy).

[0209] In the embodiments corresponding to S31 to S36, strategy matching ensures that each stage of the training process can be adaptively adjusted according to the actual performance of the fingers, avoiding rigidity in training. Through precise strategy matching, the training plan for each finger can be maximized for personalization, improving the accuracy and efficiency of training. The system can adaptively adjust based on the feedback data of the fingers, ensuring that the training strategy for each finger is continuously optimized during the training process. Through the implementation of S3 above, the training process for each finger can be made more precise and efficient, enhancing the coordination of multi-finger training, and ultimately improving the overall training system effect. It is particularly suitable for tasks requiring fine control, such as robot operation, prosthetic control, or finger rehabilitation.

[0210] Specifically, S36 includes S361 to S367:

[0211] S361: The training frequency and pneumatic control data corresponding to each of the multiple ordered stages are used as a multi-finger step-by-step training strategy for the five fingers.

[0212] In the previous steps, training frequency and pneumatic control data for each stage have been generated. The purpose of this step is to organize this data into a multi-finger step-by-step training strategy applicable to all five fingers. Here, each finger has corresponding training frequency and pneumatic control data. Through the step-by-step design, the training goals for each finger are gradually increased, avoiding overtraining while ensuring the hierarchical and progressive nature of the training.

[0213] S362: Calculate the difference between the multiple finger bending data;

[0214] In this sub-step, the difference calculation is used to measure the difference in training progress between different fingers at the same stage. For example, suppose that at a certain stage, the bending data for each finger are: [0.3, 0.5, 0.4, 0.6, 0.7].

[0215] Calculate the difference: The difference between finger 1 and finger 2 is |0.3 - 0.5| = 0.2.

[0216] Similarly, calculate the differences between the other fingers to obtain the differences in finger bending.

[0217] The purpose of this step is to make a horizontal comparison of the five-finger bending data at each stage to determine whether the training of each finger is balanced at the same stage.

[0218] S363: Calculate the mean of the differences between multiple differences corresponding to each finger;

[0219] S364: If the mean difference is higher than the fourth threshold, then divide the mean difference by the maximum value in the five-finger bending data to obtain the training coefficient;

[0220] The fourth threshold can be set to 15°.

[0221] S365: Multiply the training coefficient by the training frequency to obtain the single-finger frequency;

[0222] This step multiplies the previously calculated training coefficients by the original training frequency, thereby adjusting the training frequency for each finger.

[0223] A higher training coefficient indicates greater variation in finger performance, potentially requiring more frequent training sessions; conversely, a lower training coefficient allows for less frequent training. This ensures that the training intensity for each finger is adjusted appropriately based on its performance differences.

[0224] S366: The training frequency and pneumatic control data corresponding to each of the multiple ordered stages are used as the single-finger stepwise training strategy for the mean difference value corresponding to a single finger.

[0225] Based on the single-finger frequency and pneumatic control data obtained from the previous calculations, a separate step-by-step training strategy is developed for each finger.

[0226] This strategy involves personalized training design based on the average difference of each finger and its corresponding training frequency, so that the training intensity and frequency of each finger can be tailored to ensure the best training effect.

[0227] S367: Randomly mix the multi-finger step training strategy and the single-finger step training strategy in the same stage to obtain the step training strategy.

[0228] This step involves randomly mixing the single-finger training strategy for each finger with the overall multi-finger training strategy for all five fingers to obtain the final training plan.

[0229] The purpose of random mixing is to increase the diversity of training and avoid the limitations of finger control caused by a single training mode.

[0230] After mixing, the final step-by-step training strategy will include: independent training intensity and frequency for each finger, as well as overall coordination training of all five fingers.

[0231] In the embodiments corresponding to S361 to S367, the core objective is to generate a complete training program that includes both multi-finger step-by-step training strategies and single-finger step-by-step training strategies through difference analysis and personalized adjustments. This ensures that each finger can be appropriately adjusted according to its performance and training needs at each stage. The multi-finger step-by-step training strategy ensures the coordination of multiple fingers at different stages. The single-finger step-by-step training strategy provides personalized training based on the control differences of each finger. Finally, through random mixing, a more comprehensive and flexible training strategy is generated, maximizing the training effect.

[0232] S4: Control the aerodynamic structure to perform training operations according to the stepped training strategy.

[0233] According to the established training strategy, the glove is controlled via a pneumatic structure to perform specific training movements, ensuring that the training matches the user's abilities. In this step, the pneumatic structure in the pneumatic rehabilitation robot glove is controlled according to the requirements of the tiered training strategy. The pneumatic structure simulates different grasping or relaxing movements by adjusting air pressure or pneumatic actuators, guiding the user's fingers through training. These controls can be automated or may adjust the training intensity based on real-time feedback to help the user gradually recover hand function.

[0234] It should be noted that the numbers S1 to S4 and the specific steps do not constitute a restriction on the order of the method steps. The execution order of the steps can be adjusted based on the actual situation, and no restrictions are imposed here.

[0235] In the embodiments corresponding to S1 to S4, training levels and tiered training strategies are matched by real-time acquisition of electromyographic signals and finger flexion data, combined with the user's physiological feedback. The intensity and difficulty of training are adjusted according to each user's hand function recovery, achieving targeted rehabilitation training. This personalized training method avoids the "one-size-fits-all" problem of traditional training methods, better meeting the specific needs of each patient and improving the effectiveness of rehabilitation training. This invention utilizes feedback data from electromyographic and flexion sensors to automatically identify the patient's muscle activity and finger flexion state. By analyzing these physiological signals in real time, the training intensity can be dynamically adjusted to ensure that the training process is neither too easy nor too intense, thereby reducing patient discomfort and risks during training. This intelligent training adjustment helps improve the safety and comfort of rehabilitation training. The self-test mode in this invention allows patients to perform a self-test of maximum gripping movements while wearing pneumatic rehabilitation robot gloves. Through this action, the system can accurately assess the patient's hand gripping ability, serving as an important basis for adjusting training intensity. This function ensures that the rehabilitation process can start from the patient's existing abilities, conducting progressive rehabilitation training, which helps to gradually restore the patient's hand function. This invention, by matching a step-by-step training strategy to the user's physiological signal data, ensures a gradual training process, preventing injury or fatigue caused by overtraining in the early stages. Gradually increasing training intensity helps patients better adapt to the rehabilitation process, progressively restoring hand function and avoiding short-sighted training methods. Because the method can adjust the training strategy according to individual patient differences, it avoids a one-size-fits-all approach, improving rehabilitation effectiveness while effectively shortening rehabilitation time. Personalized training programs make patients more proactive in the rehabilitation process, greatly improving the quality and efficiency of training. In summary, the hand function rehabilitation training method of this invention, through intelligent feedback and personalized adjustments, makes rehabilitation training more efficient and precise, effectively avoiding the limitations of traditional methods.

[0236] like Figure 2 This invention provides a hand function rehabilitation training device; please refer to [link / reference]. Figure 2 , Figure 2 A schematic diagram of a hand function rehabilitation training device provided by the present invention is shown, as follows: Figure 2 The hand function rehabilitation training device shown includes:

[0237] The acquisition unit 21 is used to respond to the self-test mode triggered by the user, to acquire five-finger bending data through the bending sensor, and to acquire muscle electrical signals through the electromyography sensor; the self-test mode is used to perform maximum gripping action when the user wears the pneumatic rehabilitation robot glove, and the maximum gripping action refers to the maximum limit of the user's gripping ability.

[0238] The level matching unit 22 is used to match the training level according to the electromyographic signal;

[0239] The strategy matching unit 23 is used to match a step-by-step training strategy based on the five-finger bending data and the training level.

[0240] Control unit 24 is used to control the pneumatic structure to perform training operations according to the stepped training strategy.

[0241] This invention provides a hand function rehabilitation training device that matches training levels and a tiered training strategy by real-time acquisition of electromyographic signals and finger flexion data, combined with user physiological feedback. The intensity and difficulty of training are adjusted according to each user's hand function recovery, achieving targeted rehabilitation training. This personalized training method avoids the "one-size-fits-all" problem of traditional training methods, better meeting the specific needs of each patient and improving the effectiveness of rehabilitation training. This invention utilizes feedback data from electromyographic and flexion sensors to automatically identify the patient's muscle activity and finger flexion state. By analyzing these physiological signals in real time, the training intensity can be dynamically adjusted to ensure that the training process is neither too easy nor too intense, thereby reducing patient discomfort and risks. This intelligent training adjustment helps improve the safety and comfort of rehabilitation training. The self-test mode in this invention allows patients to perform a maximum gripping action self-test while wearing pneumatic rehabilitation robotic gloves. Through this action, the system can accurately assess the patient's hand gripping ability, serving as an important basis for adjusting training intensity. This function ensures that the rehabilitation process starts from the patient's existing abilities, conducting progressive rehabilitation training, which helps to gradually restore the patient's hand function. This invention, by matching a step-by-step training strategy to the user's physiological signal data, ensures a gradual training process, preventing injury or fatigue caused by overtraining in the early stages. Gradually increasing training intensity helps patients better adapt to the rehabilitation process, progressively restoring hand function and avoiding short-sighted training methods. Because the method can adjust the training strategy according to individual patient differences, it avoids a one-size-fits-all approach, improving rehabilitation effectiveness while effectively shortening rehabilitation time. Personalized training programs make patients more proactive in the rehabilitation process, greatly improving the quality and efficiency of training. In summary, the hand function rehabilitation training method of this invention, through intelligent feedback and personalized adjustments, makes rehabilitation training more efficient and precise, effectively avoiding the limitations of traditional methods.

[0242] Figure 3 This is a schematic diagram of a terminal device provided in an embodiment of the present invention. Figure 3As shown, a terminal device 3 in this embodiment includes: a processor 30, a memory 31, and a computer program 32 stored in the memory 31 and executable on the processor 30, such as a hand function rehabilitation training program. When the processor 30 executes the computer program 32, it implements the steps described in the various embodiments of the hand function rehabilitation training method above, for example... Figure 1 S1, S2, S3, and S4 are shown. Alternatively, when the processor 30 executes the computer program 32, it implements the functions of each unit in the above-described device embodiments, for example... Figure 2 The function of the unit shown.

[0243] For example, the computer program 32 can be divided into one or more units, which are stored in the memory 31 and executed by the processor 30 to complete the present invention. The one or more units can be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program 32 in the terminal device 3. For example, the specific functions of each unit of the computer program 32 can be divided as follows:

[0244] The acquisition unit is used to respond to the self-test mode triggered by the user, to acquire five-finger bending data through a bending sensor and to acquire muscle electrical signals through an electromyography sensor; the self-test mode is used to perform maximum gripping action when the user wears the pneumatic rehabilitation robot glove, the maximum gripping action refers to the maximum limit of the user's gripping ability.

[0245] A level matching unit is used to match training levels based on the electromyographic signals.

[0246] A strategy matching unit is used to match a step-by-step training strategy based on the five-finger bending data and the training level.

[0247] The control unit is used to control the pneumatic structure to perform training operations according to the stepped training strategy.

[0248] The terminal device includes, but is not limited to, a processor 30 and a memory 31. Those skilled in the art will understand that... Figure 3 This is merely an example of a terminal device 3 and does not constitute a limitation on a terminal device 3. It may include more or fewer components than shown, or combine certain components, or different components. For example, the terminal device may also include input / output devices, network access devices, buses, etc.

[0249] The processor 30 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0250] The memory 31 can be an internal storage unit of the terminal device 3, such as a hard disk or memory of the terminal device 3. The memory 31 can also be an external storage device of the terminal device 3, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the terminal device 3. Furthermore, the memory 31 can include both internal and external storage units of the terminal device 3. The memory 31 is used to store the computer program and other programs and data required by the roaming control device. The memory 31 can also be used to temporarily store data that has been output or will be output.

[0251] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0252] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of the present invention. For details on their specific functions and technical effects, please refer to the method embodiments section, which will not be repeated here.

[0253] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this invention. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0254] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps described in the various method embodiments above.

[0255] This invention provides a computer program product that, when run on a mobile terminal, enables the mobile terminal to implement the steps described in the above-described method embodiments.

[0256] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying the computer program code to a photographing device / terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks.

[0257] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0258] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0259] In the embodiments provided by this invention, it should be understood that the disclosed apparatus / network devices and methods can be implemented in other ways. For example, the apparatus / network device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0260] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units.

[0261] It should be understood that, when used in this specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0262] It should also be understood that the term “and / or” as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0263] As used in this specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if [the described condition or event] is detected" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once [the described condition or event] is detected," or "in response to detection of [the described condition or event]."

[0264] Furthermore, in the description of this invention and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0265] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of the invention include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0266] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A hand function rehabilitation training device, characterized in that, The hand function rehabilitation training device includes a data acquisition unit, a level matching unit, a strategy matching unit, and a control unit, and is used to implement the following steps: The acquisition unit is used to respond to the self-test mode triggered by the user, to acquire five-finger bending data through a bending sensor and to acquire muscle electrical signals through an electromyography sensor; the self-test mode is used to perform maximum gripping action when the user wears the pneumatic rehabilitation robot glove, the maximum gripping action refers to the maximum limit of the user's gripping ability. A level matching unit, used to match training levels based on the electromyographic signals, specifically includes: S21: Calculate the user's muscle control index based on the electromyographic signal; the muscle control index is used to characterize the user's ability to control muscles. S21 specifically includes: S211: Collect signal values ​​corresponding to multiple sampling points in the electromyography signal according to a preset frequency; S212: Calculate the average value corresponding to the multiple signal values; S213: Count the number of interruptions and the duration of interruptions in the electromyographic signals; S214: Calculate the variance between multiple signal values; S215: Calculate the muscle control index based on the average value, the number of interruptions, the duration of the interruptions, and the variance; S22: Match training levels based on the muscle control index; The strategy matching unit is used to match a tiered training strategy based on the five-finger bending data and the training level, specifically including: S31: Extract the training frequency and multiple step coefficients corresponding to the training level; the multiple step coefficients include a first step coefficient, a second step coefficient, and a third step coefficient; S32: Multiply the five-finger bending data with the first step coefficient to obtain the first stage bending data; S33: Multiply the first stage bending data by the second step coefficient to obtain the second stage bending data; S34: Multiply the second stage bending data with the third step coefficient to obtain the third stage bending data; S35: Calculate the pneumatic control data corresponding to the first stage bending data, the second stage bending data, and the third stage bending data; S36: The training frequency and pneumatic control data corresponding to each of the multiple ordered stages are used as the step-by-step training strategy. The control unit is used to control the pneumatic structure to perform training operations according to the stepped training strategy.

2. The hand function rehabilitation training device as described in claim 1, characterized in that, S215 includes: S2151: Multiply the number of interruptions by the first adjustment parameter to obtain the first value; S2152: Multiply the interruption duration by the second adjustment parameter to obtain the second value; S2153: Add the first value and the second value to obtain the interrupt parameter; S2154: If the average value is greater than the first threshold, the interruption parameter is less than the second threshold, and the variance is less than the third threshold, then the muscle control index is determined to be the first preset value. S2155: If the average value is greater than the first threshold, the interruption parameter is not less than the second threshold, and the variance is less than the third threshold, then the muscle control index is determined to be the second preset value. S2156: If the average value is greater than the first threshold, the interruption parameter is less than the second threshold, and the variance is not less than the third threshold, then the muscle control index is determined to be the third preset value. S2157: If the average value is not greater than the first threshold, the interruption parameter is less than the second threshold, and the variance is less than the third threshold, then the muscle control index is determined to be the fourth preset value. S2158: If the average value is not greater than the first threshold, the interruption parameter is not less than the second threshold, and the variance is less than the third threshold, then the muscle control index is determined to be the fifth preset value. S2159: If the average value is not greater than the first threshold, the interruption parameter is less than the second threshold, and the variance is not less than the third threshold, then the muscle control index is determined to be the sixth preset value.

3. The hand function rehabilitation training device as described in claim 1, characterized in that, The step of calculating the pneumatic control data corresponding to the first stage bending data, the second stage bending data, and the third stage bending data includes: S351: Obtain the mapping table between bending data and aerodynamic data; S352: Extract the pneumatic control data corresponding to the first stage bending data, the second stage bending data and the third stage bending data respectively from the mapping table.

4. The hand function rehabilitation training device as described in claim 1, characterized in that, S36 includes: S361: The training frequency and pneumatic control data corresponding to each of the multiple ordered stages are used as a multi-finger step-by-step training strategy for the five fingers. S362: Calculate the difference between the multiple finger bending data; S363: Calculate the mean of the differences between multiple differences corresponding to each finger; S364: If the mean difference is higher than the fourth threshold, then divide the mean difference by the maximum value in the five-finger bending data to obtain the training coefficient; S365: Multiply the training coefficient by the training frequency to obtain the single-finger frequency; S366: The training frequency and pneumatic control data corresponding to each of the multiple ordered stages are used as the single-finger stepwise training strategy for the mean difference value corresponding to a single finger. S367: Randomly mix the multi-finger step training strategy and the single-finger step training strategy in the same stage to obtain the step training strategy.

5. A terminal device, characterized in that, The terminal device includes: a memory, a processor, and a hand function rehabilitation training program stored in the memory and executable on the processor. The hand function rehabilitation training program is configured to perform the following steps: S1: In response to the user-triggered self-test mode, the bending data of the five fingers is collected by the bending sensor and the electromyography signal is collected by the electromyography sensor; the self-test mode is used to perform maximum gripping action when the user is wearing the pneumatic rehabilitation robot glove, the maximum gripping action refers to the maximum limit of the user's gripping ability. S2: Match training levels based on the electromyographic signals; S2 includes: S21: Calculate the user's muscle control index based on the electromyographic signal; the muscle control index is used to characterize the user's ability to control muscles. S21 includes: S211: Collect signal values ​​corresponding to multiple sampling points in the electromyography signal according to a preset frequency; S212: Calculate the average value corresponding to the multiple signal values; S213: Count the number of interruptions and the duration of interruptions in the electromyographic signals; S214: Calculate the variance between multiple signal values; S215: Calculate the muscle control index based on the average value, the number of interruptions, the duration of the interruptions, and the variance; S22: Match training levels based on the muscle control index; S3: Match a step-by-step training strategy based on the five finger bending data and the training level; S3 includes: S31: Extract the training frequency and multiple step coefficients corresponding to the training level; the multiple step coefficients include a first step coefficient, a second step coefficient, and a third step coefficient; S32: Multiply the five-finger bending data with the first step coefficient to obtain the first stage bending data; S33: Multiply the first stage bending data by the second step coefficient to obtain the second stage bending data; S34: Multiply the second stage bending data with the third step coefficient to obtain the third stage bending data; S35: Calculate the pneumatic control data corresponding to the first stage bending data, the second stage bending data, and the third stage bending data; S36: The training frequency and pneumatic control data corresponding to each of the multiple ordered stages are used as the step-by-step training strategy. S4: Control the aerodynamic structure to perform training operations according to the stepped training strategy.

6. The terminal device as described in claim 5, characterized in that, S215 includes: S2151: Multiply the number of interruptions by the first adjustment parameter to obtain the first value; S2152: Multiply the interruption duration by the second adjustment parameter to obtain the second value; S2153: Add the first value and the second value to obtain the interrupt parameter; S2154: If the average value is greater than the first threshold, the interruption parameter is less than the second threshold, and the variance is less than the third threshold, then the muscle control index is determined to be the first preset value. S2155: If the average value is greater than the first threshold, the interruption parameter is not less than the second threshold, and the variance is less than the third threshold, then the muscle control index is determined to be the second preset value. S2156: If the average value is greater than the first threshold, the interruption parameter is less than the second threshold, and the variance is not less than the third threshold, then the muscle control index is determined to be the third preset value. S2157: If the average value is not greater than the first threshold, the interruption parameter is less than the second threshold, and the variance is less than the third threshold, then the muscle control index is determined to be the fourth preset value. S2158: If the average value is not greater than the first threshold, the interruption parameter is not less than the second threshold, and the variance is less than the third threshold, then the muscle control index is determined to be the fifth preset value. S2159: If the average value is not greater than the first threshold, the interruption parameter is less than the second threshold, and the variance is not less than the third threshold, then the muscle control index is determined to be the sixth preset value.

7. The terminal device as described in claim 5, characterized in that, The S35 includes: S351: Obtain the mapping table between bending data and aerodynamic data; S352: Extract the pneumatic control data corresponding to the first stage bending data, the second stage bending data and the third stage bending data respectively from the mapping table.

8. The terminal device as described in claim 5, characterized in that, S36 includes: S361: The training frequency and pneumatic control data corresponding to each of the multiple ordered stages are used as a multi-finger step-by-step training strategy for the five fingers. S362: Calculate the difference between the multiple finger bending data; S363: Calculate the mean of the differences between multiple differences corresponding to each finger; S364: If the mean difference is higher than the fourth threshold, then divide the mean difference by the maximum value in the five-finger bending data to obtain the training coefficient; S365: Multiply the training coefficient by the training frequency to obtain the single-finger frequency; S366: The training frequency and pneumatic control data corresponding to each of the multiple ordered stages are used as the single-finger stepwise training strategy for the mean difference value corresponding to a single finger. S367: Randomly mix the multi-finger step training strategy and the single-finger step training strategy in the same stage to obtain the step training strategy.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it performs the following steps: S1: In response to the user-triggered self-test mode, the bending data of the five fingers is collected by the bending sensor and the electromyography signal is collected by the electromyography sensor; the self-test mode is used to perform maximum gripping action when the user is wearing the pneumatic rehabilitation robot glove, the maximum gripping action refers to the maximum limit of the user's gripping ability. S2: Match training levels based on the electromyographic signals; S2 includes: S21: Calculate the user's muscle control index based on the electromyographic signal; the muscle control index is used to characterize the user's ability to control muscles. S21 includes: S211: Collect signal values ​​corresponding to multiple sampling points in the electromyography signal according to a preset frequency; S212: Calculate the average value corresponding to the multiple signal values; S213: Count the number of interruptions and the duration of interruptions in the electromyographic signals; S214: Calculate the variance between multiple signal values; S215: Calculate the muscle control index based on the average value, the number of interruptions, the duration of the interruptions, and the variance; S22: Match training levels based on the muscle control index; S3: Match a step-by-step training strategy based on the five finger bending data and the training level; S3 includes: S31: Extract the training frequency and multiple step coefficients corresponding to the training level; the multiple step coefficients include a first step coefficient, a second step coefficient, and a third step coefficient; S32: Multiply the five-finger bending data with the first step coefficient to obtain the first stage bending data; S33: Multiply the first stage bending data by the second step coefficient to obtain the second stage bending data; S34: Multiply the second stage bending data with the third step coefficient to obtain the third stage bending data; S35: Calculate the pneumatic control data corresponding to the first stage bending data, the second stage bending data, and the third stage bending data; S36: The training frequency and pneumatic control data corresponding to each of the multiple ordered stages are used as the step-by-step training strategy. S4: Control the aerodynamic structure to perform training operations according to the stepped training strategy.

10. The computer-readable storage medium as claimed in claim 9, characterized in that, S215 includes: S2151: Multiply the number of interruptions by the first adjustment parameter to obtain the first value; S2152: Multiply the interruption duration by the second adjustment parameter to obtain the second value; S2153: Add the first value and the second value to obtain the interrupt parameter; S2154: If the average value is greater than the first threshold, the interruption parameter is less than the second threshold, and the variance is less than the third threshold, then the muscle control index is determined to be the first preset value. S2155: If the average value is greater than the first threshold, the interruption parameter is not less than the second threshold, and the variance is less than the third threshold, then the muscle control index is determined to be the second preset value. S2156: If the average value is greater than the first threshold, the interruption parameter is less than the second threshold, and the variance is not less than the third threshold, then the muscle control index is determined to be the third preset value. S2157: If the average value is not greater than the first threshold, the interruption parameter is less than the second threshold, and the variance is less than the third threshold, then the muscle control index is determined to be the fourth preset value. S2158: If the average value is not greater than the first threshold, the interruption parameter is not less than the second threshold, and the variance is less than the third threshold, then the muscle control index is determined to be the fifth preset value. S2159: If the average value is not greater than the first threshold, the interruption parameter is less than the second threshold, and the variance is not less than the third threshold, then the muscle control index is determined to be the sixth preset value.

11. The computer-readable storage medium as claimed in claim 9, characterized in that, The S35 includes: S351: Obtain the mapping table between bending data and aerodynamic data; S352: Extract the pneumatic control data corresponding to the first stage bending data, the second stage bending data and the third stage bending data respectively from the mapping table.

12. The computer-readable storage medium as claimed in claim 9, characterized in that, S36 includes: S361: The training frequency and pneumatic control data corresponding to each of the multiple ordered stages are used as a multi-finger step-by-step training strategy for the five fingers. S362: Calculate the difference between the multiple finger bending data; S363: Calculate the mean of the differences between multiple differences corresponding to each finger; S364: If the mean difference is higher than the fourth threshold, then divide the mean difference by the maximum value in the five-finger bending data to obtain the training coefficient; S365: Multiply the training coefficient by the training frequency to obtain the single-finger frequency; S366: The training frequency and pneumatic control data corresponding to each of the multiple ordered stages are used as the single-finger stepwise training strategy for the mean difference value corresponding to a single finger. S367: Randomly mix the multi-finger step training strategy and the single-finger step training strategy in the same stage to obtain the step training strategy.

Images