A lower limb rehabilitation exercise control system based on acupoint electric stimulation

Abstract

The application provides a lower limb rehabilitation exercise control system based on acupoint electric stimulation, and relates to the technical field of data processing.The system comprises an acquisition module for acquiring lower limb state data of a patient, a recommendation module for recommending a lower limb rehabilitation exercise scheme to the patient according to the lower limb state data, a decomposition module for decomposing the lower limb rehabilitation exercise scheme to obtain a rehabilitation exercise action, an execution module for making the patient perform a corresponding rehabilitation exercise action by applying electric stimulation at a corresponding acupoint according to the correlation between the rehabilitation exercise action and the acupoint, an establishment module for establishing a system dynamics model according to the correlation between the rehabilitation exercise action and the electric stimulation, an adjustment module for adaptively adjusting the electric stimulation through a RISE-based control algorithm, and a repetition module for repeating the adjustment module until the rehabilitation exercise action is a desired action, thereby completing the control of the lower limb rehabilitation exercise.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a lower limb rehabilitation exercise control system based on acupoint electrical stimulation. BACKGROUND

[0002] Acupoint refers to the "acupoint" in traditional Chinese medicine theory, which is a special part of the human meridian system, and can regulate qi and blood and visceral function through stimulation. Electrical stimulation, also known as "electrical nerve stimulation", activates the activity of nerves or muscles by applying current to the skin or muscles, and lower limb rehabilitation exercise refers to physical training movements designed to restore or improve lower limb function, such as leg lifting, gait training, joint flexion and extension, etc. It is often used in postoperative or post-neurological injury rehabilitation process. The lower limb rehabilitation exercise control system based on acupoint electrical stimulation refers to a technical method of using electrical stimulation of human acupoints to guide and control patients to complete lower limb rehabilitation exercise.

[0003] By stimulating specific acupoints, the relevant muscle groups can be activated to achieve active or passive exercise control. By integrating traditional Chinese meridian theory with modern automatic control and artificial intelligence, the modern application of traditional medicine is realized, and the scientific nature and international influence of treatment are improved.

[0004] However, the existing lower limb rehabilitation exercise control method relies on manual assistance or mechanical driving, lacks self-adaptive ability to individual differences, and the training method is relatively rigid, which is difficult to accurately match the actual functional state of the patient. Secondly, most methods cannot achieve closed-loop control, lack real-time feedback and dynamic adjustment of rehabilitation effect, which may lead to unstable training effect or low efficiency, in addition, traditional physical rehabilitation consumes a large amount of human resources, is not suitable for large-scale promotion, and is also difficult to sustain high-frequency training. SUMMARY

[0005] In order to solve the technical problems that the existing lower limb rehabilitation exercise control method relies on manual assistance or mechanical driving, lacks self-adaptive ability to individual differences, and the training method is relatively rigid, which is difficult to accurately match the actual functional state of the patient. Secondly, most methods cannot achieve closed-loop control, lack real-time feedback and dynamic adjustment of rehabilitation effect, which may lead to unstable training effect or low efficiency, not suitable for large-scale promotion, and difficult to sustain high-frequency training, the present application provides a lower limb rehabilitation exercise control system based on acupoint electrical stimulation.

[0006] The technical scheme provided by the embodiments of the present application is as follows:

[0007] First aspect:

[0008] The lower limb rehabilitation exercise control system based on acupoint electrical stimulation provided by the embodiments of the present application comprises:

[0009] The acquisition module is configured to acquire lower limb state data of the patient.

[0010] recommendation module, configured to recommend a lower limb rehabilitation exercise scheme to the patient according to the lower limb state data through a random forest model;

[0011] decomposition module, configured to decompose the lower limb rehabilitation exercise scheme to obtain a rehabilitation exercise action;

[0012] execution module, configured to make the patient perform a corresponding rehabilitation exercise action by applying electric stimulation at a corresponding acupoint according to an association relationship between the rehabilitation exercise action and the acupoint;

[0013] establishment module, configured to establish a system dynamics model according to a relationship between the rehabilitation exercise action and the electric stimulation;

[0014] adjustment module, configured to adaptively adjust the electric stimulation through a RISE-based control algorithm according to a lower limb response output by the system dynamics model;

[0015] repetition module, configured to repeat the adjustment module until the rehabilitation exercise action is a desired action, and complete the control of the lower limb rehabilitation exercise.

[0016] The technical scheme provided by the embodiment of the present application has at least the following beneficial effects:

[0017] In the embodiment of the present application, the lower limb state data of the patient is obtained, and a lower limb rehabilitation exercise scheme is recommended to the patient according to the lower limb state data through a random forest model, thereby providing a personalized rehabilitation exercise scheme for the patient. Then, the lower limb rehabilitation exercise scheme is decomposed to obtain a rehabilitation exercise action. Meanwhile, the patient performs a corresponding rehabilitation exercise action by applying electric stimulation at a corresponding acupoint according to an association relationship between the rehabilitation exercise action and the acupoint. Further, a system dynamics model is established according to a relationship between the rehabilitation exercise action and the electric stimulation, which quantifies the relationship between the lower limb exercise and the electric stimulation, making the subsequent exercise control more accurate. Finally, the electric stimulation is adaptively adjusted through a RISE-based control algorithm according to a lower limb response output by the system dynamics model until the rehabilitation exercise action is a desired action, and the control of the lower limb rehabilitation exercise is completed. The personalized, accurate and efficient rehabilitation training is realized, the rehabilitation experience and treatment effect of the patient are improved, the human resources are greatly saved, the adaptive adjustment is realized, the action is more stable, the training is safer, and the rehabilitation quality and safety are improved. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed in the embodiment description. Obviously, the drawings in the following description only show some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative effort.

[0019] Figure 1 A structural schematic diagram of a lower limb rehabilitation exercise control system based on acupoint electrical stimulation provided by the embodiment of the present application is shown. DETAILED DESCRIPTION

[0020] The technical solutions in the present application will be described below with reference to the drawings.

[0021] In the embodiments of the present application, the words such as "example", "for example" are used to represent an example, illustration or description. Any embodiment or design scheme described as "example" in the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the word "example" is intended to present the concept in a specific manner. In addition, in the embodiments of the present application, the meaning expressed by "and / or" can be both, or can be one of the two.

[0022] In the embodiments of the present application, "image" and "picture" can be used interchangeably at times. It should be pointed out that when the distinction is not emphasized, the meanings expressed are consistent. "Of", "corresponding" and "corresponding" can be used interchangeably at times. It should be pointed out that when the distinction is not emphasized, the meanings expressed are consistent.

[0023] In the embodiments of the present application, sometimes the subscript such as W1 can be written in the form of non-subscript such as W1. When the distinction is not emphasized, the meanings expressed are consistent.

[0024] In order to make the technical problems, technical solutions and advantages to be solved by the present application more clear, the following will be described in detail with reference to the drawings and specific embodiments.

[0025] Reference is made to the drawings attached Figure 1 A flowchart schematic diagram of a lower limb rehabilitation exercise control system based on acupoint electrical stimulation provided by the embodiment of the present application is shown.

[0026] The embodiment of the present application provides a lower limb rehabilitation exercise control system based on acupoint electrical stimulation. The system can be realized by a lower limb rehabilitation exercise control device based on acupoint electrical stimulation. The lower limb rehabilitation exercise control device based on acupoint electrical stimulation can be a terminal or a server. The processing flow of the lower limb rehabilitation exercise control system based on acupoint electrical stimulation can include the following steps:

[0027] an acquisition module configured to acquire lower limb state data of a patient.

[0028] The lower limb state data refers to various physiological parameters or information reflecting the function of the patient's lower limbs, such as joint angles, muscle electrical signals, etc., for describing and evaluating the patient's motor ability, rehabilitation progress, etc.

[0029] It should be noted that by acquiring the lower limb state data of the patient, the physiological state of the patient can be monitored in real time, and the functional recovery of the patient can be accurately evaluated. Unlike traditional manual evaluation, the data-driven method can provide more objective and quantitative information to ensure that the treatment process is more accurate and personalized.

[0030] In one possible implementation, the lower limb state data specifically includes: knee joint angle, electromyography signal, knee joint stiffness, knee joint elasticity, lower limb force line, muscle strength level, muscle tension, and gait data.

[0031] The knee joint angle refers to the angle formed when the knee is bent or straightened, which reflects the range of joint movement and is often measured by an angle sensor.

[0032] Optionally, the knee joint angle is acquired by an angle sensor.

[0033] The electromyography signal (EMG) is a recording of the electrical signals generated by muscles during activity, reflecting the degree of muscle excitation and activation state.

[0034] Optionally, the size of the electromyography signal is measured by an electrode patch.

[0035] The knee joint stiffness measures the ability of the knee joint to resist bending under external force, affecting movement stability and support.

[0036] The knee joint elasticity reflects the ability of the knee joint to return to its original state after being stretched, which is related to the state of soft tissues.

[0037] The lower limb force line is a mechanical characteristic describing the load transmission path from the hip to the foot, and is an important indicator for evaluating gait and posture balance.

[0038] The muscle strength level reflects the ability of muscles to generate strength, which is an important parameter for evaluating muscle function and training effect.

[0039] The muscle tension describes the tension of muscles in a static or dynamic state, and high or low tension can affect the quality of movement.

[0040] The gait data includes step length, step speed, step frequency, etc., which is an important reference for reflecting walking function.

[0041] It is worth noting that these data provide a reliable basis for subsequent exercise recommendation and control, enabling the entire rehabilitation system to adapt to the specific needs of patients, optimize rehabilitation effects, and reduce unnecessary risks. In addition, real-time data acquisition also makes the rehabilitation process more dynamic, enabling timely adjustment of treatment plans, thereby accelerating the recovery process of patients.

[0042] a recommendation module configured to recommend a lower limb rehabilitation exercise plan to the patient based on the lower limb state data through a random forest model.

[0043] wherein the random forest model is a machine learning algorithm based on decision tree ensemble, which improves the accuracy and robustness of classification and prediction by training multiple tree models for voting or averaging. The lower limb rehabilitation exercise plan refers to a set of training actions or processes customized for the patient by the model based on the analysis results, such as gait training, leg lifting training, etc., to help them recover lower limb function.

[0044] It is worth noting that combining individual state data of patients with machine learning algorithms achieves "precision recommendation" of rehabilitation training. Compared with traditional methods that rely on experience or fixed templates, the random forest model can learn the complex mapping relationship between different rehabilitation states and exercise types through a large number of training samples, thereby matching the most suitable rehabilitation plan for each patient. This not only improves the relevance of training, but also helps to improve rehabilitation efficiency and safety.

[0045] In one possible implementation, the recommendation module is specifically configured to:

[0046] extract core kinematic features from the lower limb state data.

[0047] wherein the core kinematic features refer to the most representative and most reflective key data features of exercise ability and rehabilitation state extracted from the lower limb state data of the patient. For example, the angle change of the knee joint, the regularity of gait, the intensity of electromyography signals, etc. These features can effectively represent the exercise function of the patient.

[0048] preprocess the core kinematic features.

[0049] wherein preprocessing refers to cleaning, standardizing, denoising, etc. of the extracted kinematic features before data analysis, to ensure higher data quality and better suitability for subsequent analysis and modeling.

[0050] determine the rehabilitation exercise category based on the preprocessed core kinematic features through the random forest model:

[0051]

[0052] wherein, represents the rehabilitation exercise category, and argmax represents the maximum value.C k represents the first k candidate movement category, I() represents an indicator function, h t represents the first t decision tree, t =1,2,… T , T represents the total number of decision trees, X represents the core kinematic feature vector.

[0053] wherein the rehabilitation movement category refers to a training scheme type suitable for the patient determined by the model according to the patient's kinematic features, such as gait training, flexion and extension movement, leg lifting training, etc. These categories represent different movement patterns, aiming to restore lower limb function through specific training.

[0054] According to the rehabilitation movement category, a standard training library is mapped to recommend a lower limb rehabilitation movement scheme to the patient.

[0055] wherein the standard training library refers to a database of rehabilitation movement schemes prepared in advance, which contains various rehabilitation movement categories and their corresponding specific actions. Through mapping, the most suitable rehabilitation training scheme can be recommended to the patient according to the movement category determined by the model.

[0056] It should be noted that by extracting and preprocessing the kinematic features, a random forest model is used for classification, and finally the most suitable rehabilitation movement scheme for the patient is recommended according to the classification result. This process realizes the intelligent transformation from data to action, providing a scientific basis for lower limb rehabilitation.

[0057] In one possible implementation, the lower limb rehabilitation movement scheme includes: gait training, active flexion and extension movement, passive movement, and leg lifting training.

[0058] wherein gait training refers to a series of movements and training methods to help patients restore or improve their ability to walk. Gait refers to the coordination and movement pattern of body parts such as legs and torso during walking.

[0059] wherein active flexion and extension movement refers to the patient actively controlling the muscles of the lower limbs to complete the flexion and extension of the knee joint during rehabilitation training. Flexion and extension movement involves the bending (flexion) and stretching (extension) of the joint.

[0060] wherein passive movement refers to the patient's lower limbs completing movement under the action of external force, without the need for active effort by the patient, usually provided by a rehabilitation therapist or equipment (such as a rehabilitation robot) to provide external force for joint flexion, extension, rotation, etc.

[0061] Among them, the leg lifting training refers to training the patient to enhance the lower limb strength, joint flexibility and gait coordination through the action of bending the knee and lifting the thigh, knee, and even completely lifting the foot.

[0062] The decomposition module is configured to decompose the lower limb rehabilitation exercise scheme to obtain the rehabilitation exercise action.

[0063] Among them, the rehabilitation exercise action refers to each specific executable exercise instruction, such as "bend the knee to 45 degrees", "stretch the leg for 3 seconds", "lift the leg by 10 centimeters", etc. Each action contains the execution mode, joint angle, involved muscle group, corresponding acupoint and stimulation parameter, which is the smallest control unit for executing rehabilitation training.

[0064] It should be noted that by decomposing the recommended scheme into single rehabilitation exercise action, the system can accurately locate the target area of each stimulation in combination with the acupoint distribution, muscle group composition and electric stimulation site. This action level control helps to achieve a highly personalized training path, while improving the efficiency and accuracy of stimulation.

[0065] In one possible implementation, the decomposition module is specifically configured to: in combination with the action-acupoint-muscle group mapping relationship table, decompose the lower limb rehabilitation exercise scheme to obtain a plurality of rehabilitation exercise action combinations, wherein the rehabilitation exercise action combination includes action number, rehabilitation exercise action, acupoint and electric stimulation site.

[0066] Among them, the action-acupoint-muscle group mapping relationship table is a multi-dimensional mapping table for associating information, which establishes a corresponding relationship between a specific rehabilitation exercise action and the Chinese medicine acupoint and muscle group involved. Its role is to let the system know: when completing a certain rehabilitation exercise action, which acupoint needs to be stimulated, which muscle group needs to be activated, so as to achieve efficient and scientific rehabilitation guidance.

[0067] Among them, the action number is a unique identification number assigned to each basic rehabilitation exercise action, which is used for system scheduling, recording, tracking and feedback management.

[0068] Among them, the electric stimulation site refers to the position where the electrode is actually attached and the electric pulse is applied, which is usually highly consistent with the acupoint position, or consistent with the area where the target muscle group nerve pathway is located. It is the physical interface point of system execution control.

[0069] It should be noted that by using an association table, a complex rehabilitation scheme is refined into a series of controllable unit actions, each action is associated with the action target, the acupoint for stimulation and the target muscle group, and is executed and controlled through electric stimulation, so as to realize a precise and personalized rehabilitation process. The fineness and executability of this way is the key embodiment of the intelligentization of the rehabilitation system.

[0070] The execution module is configured to cause the patient to perform a corresponding rehabilitation movement action by applying electrical stimulation at a corresponding acupoint according to an association between the rehabilitation movement action and the acupoint.

[0071] The association refers to a functional correspondence between the rehabilitation movement action and the acupoint established through a mapping table. For example, a certain lower limb flexion and extension movement may need to activate a certain muscle group, and the control nerve pathway of the muscle group corresponds to a certain acupoint, and the target action can be triggered by stimulating the acupoint.

[0072] It should be noted that by applying electrical stimulation on a specific acupoint, the system can induce the target muscle or nerve to produce a response, so that the patient can complete the preset rehabilitation movement action, which is of great significance especially for patients who cannot move autonomously. In addition, this method combines traditional Chinese medicine meridians with modern bioelectric stimulation technology, improves the physiological efficiency and functional specificity of stimulation, and reduces the dependence on the active cooperation of patients.

[0073] The establishment module is configured to establish a system dynamics model according to a relationship between the rehabilitation movement action and the electrical stimulation.

[0074] The system dynamics model is a mathematical model used to describe the relationship between the input (such as electrical stimulation) and the output (such as joint angle change) of the system. It includes the inertia, damping, elasticity and other characteristics of the body joints, and may introduce disturbance terms or neuromuscular responses, etc. The purpose is to quantify the behavior characteristics of the entire control system, and provide a calculation basis for subsequent control algorithms (such as RISE control).

[0075] It should be noted that by establishing a system dynamics model between the rehabilitation movement action and the electrical stimulation, the entire rehabilitation system is given “predictability” and “controllability”. The model abstracts the human biological system as a physical control system, and can accurately simulate the dynamic response of electrical stimulation by modeling the inertia, damping, elasticity, gravity effect and disturbance term of the joint.

[0076] In one possible implementation, the system dynamics model is specifically:

[0077]

[0078]

[0079]

[0080]

[0081]

[0082] wherein, J represents the inertia of the system, i.e. the inertia of the lower limbs, represents t angular acceleration of the knee joint at time t, represents the effect of gravity, θ ( t ) represents t angular position of the knee joint at time t, represents the effect of elasticity, represents the effect of viscous damping, represents t angular velocity of the knee joint at time t, represents t disturbance term at time t, represents t torque generated by the electrical stimulation at time t, m represents the total mass of the shank and foot, g represents the gravitational acceleration, l represents the distance from the knee joint to the center of mass of the shank and foot, , and all represent the relevant positive coefficients of joint stiffness, e represents the natural constant, k 1, k 2, and k 3 all represent the relevant parameters of viscous damping effect, represents the joint torque, represents a nonlinear function, u ( t ) represents t electrical stimulation signal at time t.

[0083] It should be noted that this modeling not only helps to understand the internal mechanism of patient motion generation, but also provides a theoretical basis for intelligent control algorithms, enabling the system to maintain high precision and high stability of output control when facing physiological differences and external disturbances. In short, by shifting the entire rehabilitation process from experience-driven to scientific modeling and predictive control, it is the key to achieving automated and personalized rehabilitation.

[0084] The adjustment module is configured to adjust the electrical stimulation adaptively according to the lower limb response output by the system dynamics model through the RISE-based control algorithm.

[0085] The lower limb response refers to the movement response of the patient's lower limb after receiving the electrical stimulation, such as knee bending, leg lifting, etc. It is an observation result of the system output and a key data for evaluating the execution effect of rehabilitation movement action. The RISE (Robust Integral of the Sign of the Error) control algorithm is a robust nonlinear control algorithm, which is particularly suitable for complex systems with model uncertainty and external disturbance. The algorithm combines the tracking error integral term and the sign function term to dynamically adjust the input control (i.e., electrical stimulation), so that the system output approaches the target trajectory. Adaptive adjustment means that the system continuously adjusts the electrical stimulation parameters according to the actual response, so that the control signal dynamically adapts to the current state of the patient. This way does not need to preset fixed parameters, but updates in real time through feedback, improving the flexibility and control accuracy of the system.

[0086] It should be noted that the introduction of the adaptive control mechanism based on the RISE algorithm enables closed-loop intelligent adjustment throughout the rehabilitation process. By monitoring the lower limb response output by the system dynamics model in real time, the system can identify the deviation between the target action and the actual action and automatically adjust the electrical stimulation signal to correct the error. The RISE algorithm is particularly suitable for handling biological systems with strong uncertainty and large disturbances, so it can effectively cope with physiological differences, posture changes or external disturbances of patients during rehabilitation, improving the accuracy and stability of rehabilitation movement actions. In addition, the system does not need human intervention, and can continuously optimize itself according to the results of each training, so as to realize high-precision and high-robustness personalized rehabilitation control, which helps to improve rehabilitation efficiency and enhance patient experience.

[0087] In one possible implementation, the adjustment module is specifically configured to:

[0088] According to the difference between the actual knee joint angle and the expected knee joint angle trajectory in the system dynamics model, the tracking error is determined:

[0089]

[0090] wherein, e 1( t ) represents t the difference between the expected position and the actual position at the moment, i.e., the tracking error, represents t the expected knee joint angle to be achieved at the moment.

[0091] Wherein, the actual knee joint angle refers to the bending or stretching angle of the knee joint at time t measured by the sensor in real time, which is the actual output of the system movement, the expected knee joint angle trajectory is the preset ideal movement trajectory, i.e. the target angle change process that the patient's knee joint should reach, which is usually set based on the rehabilitation target or normal gait standard. The tracking error represents the difference between the expected angle and the actual angle at time t, which is used to measure the execution deviation of the rehabilitation movement action and is the basis signal for control adjustment.

[0092] The tracking error is filtered:

[0093]

[0094] Wherein, e 2 represents the filtered tracking error at time t, t represents the derivative of the tracking error at time t, t 1 and 2 both represent control gains, t represents the filtered derivative of the tracking error at time t. α α Wherein, the purpose of filtering is to smooth the original error signal and remove high-frequency noise, so that the control system is more stable. R t According to the filtered tracking error, combined with the inertia of the lower limbs, the error dynamic equation is calculated: t

[0095]

[0096]

[0097]

[0098]

[0099]

[0100] Wherein, r represents the derivative of the filtered tracking error, Y represents an output function, represents the expected movement speed of the knee joint, represents the expected knee joint angle, represents the actual measured knee joint angle, represents the derivative of the tracking error, e 2 represents the filtered tracking error, Ψ represents a function related to the joint angle, u represents the electrical stimulation signal, represents the expected knee joint acceleration.

[0101] ​​​​​Lower limb inertia refers to the patient's lower limbs (mainly the lower legs and feet) resisting changes in acceleration during movement, usually denoted by J. The error dynamic equation is a mathematical model describing the process of error change over time; it reveals the mechanism of how error evolves with changes in control signals, electrical stimulation, and system state.

[0102] The error dynamic equation is analyzed to obtain the error evolution model.

[0103] The error evolution model, derived from the error dynamic equation, describes how the error evolves over time. Specifically, it demonstrates how the error evolves in response to adjustments in control signals (such as electrical stimulation).

[0104] Based on the error evolution model, the electrical stimulation is adaptively adjusted:

[0105]

[0106] in, u ( t )express t The electrical stimulation signal at any time, k s Indicates control gain. β The constant representing the adjustment sign function. sgn ( ) represents a sign function. dt Represents the differential element of the integral.

[0107] It should be noted that by comparing the actual knee joint angle with the desired trajectory in real time, the system can quantify the accuracy of the current movement execution and dynamically filter the error to remove interference and fluctuations, ensuring stable and reliable feedback data. Based on this, an error dynamic equation is established by combining the patient's lower limb dynamic characteristics, thereby deriving an error evolution model, giving the control process a physical basis and predictive capability. Finally, through a sign function and integral adjustment mechanism, the electrical stimulation signal is adaptively adjusted, allowing the system to automatically converge to the desired movement, maintaining robustness and stability even in the face of individual differences and external disturbances. This closed-loop, self-regulating control strategy not only improves the accuracy and consistency of rehabilitation exercises but also enhances the reliability and intelligence of the system in practical clinical applications.

[0108] In one possible implementation, adaptive adjustment of the electrical stimulation specifically involves adaptive adjustment of the parameters of the electrical stimulation.

[0109] The parameters specifically include: voltage amplitude, pulse width, pulse frequency, stimulation mode, and activation time window.

[0110] The voltage amplitude refers to the voltage size of the electrical stimulation signal, usually measured in volts (V). The voltage amplitude controls the intensity of the current and affects the strength of muscle or nerve activation. Too high a voltage can cause pain or damage, while too low a voltage may not produce sufficient stimulation effects.

[0111] The pulse width refers to the duration of each electrical pulse, usually measured in microseconds (μs) or milliseconds (ms). The pulse width affects the degree of activation of nerves or muscles. A longer pulse width can result in stronger muscle contractions, while a shorter pulse width is suitable for more delicate control.

[0112] The pulse frequency refers to the number of electrical pulses applied within a certain time, usually measured in hertz (Hz). The pulse frequency affects the rhythm and duration of stimulation. Higher pulse frequencies help activate fast-reacting muscle groups, while lower frequencies are suitable for long-term muscle endurance training.

[0113] The stimulation pattern refers to the modulation of electrical pulses, including continuous stimulation, intermittent stimulation, or other complex stimulation patterns. Different stimulation patterns can be optimized for different treatment goals, such as intermittent patterns to reduce fatigue and continuous patterns to stimulate muscles more persistently.

[0114] The activation time window refers to the duration or time period during which the electrical stimulation signal is applied, i.e., the electrical stimulation is activated within this time window, usually measured in milliseconds or seconds. The activation time window is related to the rhythm of movement execution and the requirements of the target task.

[0115] It should be noted that by adjusting various parameters of electrical stimulation, the rehabilitation process can be precisely and flexibly controlled to meet individual treatment needs and improve patient rehabilitation efficiency and treatment experience. Different parameters (such as frequency, pulse width, etc.) can be optimized according to specific rehabilitation goals (such as restoring muscle strength, improving nerve function, relieving muscle fatigue, etc.) to achieve diverse treatment goals.

[0116] The repetition module is used to repeat the adjustment module until the rehabilitation movement is the desired action, completing the control of the lower limb rehabilitation movement.

[0117] The desired action is the standard rehabilitation movement action in the ideal state, which is set by the system according to medical standards or individual patient goals, and is used for comparison with the actual action to evaluate the execution quality.

[0118] It needs to be explained that through continuously repeating error analysis and electric stimulation adjustment of the electric stimulation, the system can gradually reduce the motion execution deviation and approach the expected trajectory. The "self-learning type" rehabilitation control mechanism has strong adaptability and can cope with real-time changes of the patient state, such as muscle fatigue, unstable motion or different neural recovery progress. It not only improves the accuracy and consistency of the rehabilitation motion execution, but also automatically optimizes the electric stimulation parameters according to the feedback of each training, so as to realize highly personalized and dynamic rehabilitation guidance. Finally, it ensures the goal achievement ability of the whole rehabilitation system and is a key step to promote the transformation from "passive rehabilitation" to "active intelligent rehabilitation".

[0119] The technical scheme provided by the embodiment of the application has at least the following beneficial effects:

[0120] In the embodiment of the application, the lower limb state data of the patient is acquired, and a lower limb rehabilitation exercise scheme is recommended to the patient according to the lower limb state data through a random forest model, so as to provide a personalized rehabilitation exercise scheme for the patient. Then, the lower limb rehabilitation exercise scheme is decomposed to obtain a rehabilitation exercise action. Meanwhile, according to the correlation between the rehabilitation exercise action and the acupoints, electric stimulation is applied at the corresponding acupoints to make the patient perform the corresponding rehabilitation exercise action. Further, a system dynamics model is established according to the relationship between the rehabilitation exercise action and the electric stimulation, the relationship between the lower limb exercise and the electric stimulation is quantified, and the subsequent motion control is more accurate. Finally, according to the lower limb response output by the system dynamics model, the electric stimulation is adaptively adjusted through the control algorithm based on RISE until the rehabilitation exercise action is the expected action, the control of the lower limb rehabilitation exercise is completed, and personalized, accurate and efficient rehabilitation training is realized. The rehabilitation experience and treatment effect of the patient are improved, the human resources are greatly saved, the adaptive adjustment is realized, the motion is more stable, the training is safer, and the rehabilitation quality and safety are improved.

[0121] The accompanying drawings are referred to in the description of the application. Figure 1 Fig. 1 shows a structure schematic diagram of a lower limb rehabilitation exercise control system based on acupoint electric stimulation provided by the application.

[0122] The technical scheme provided by the embodiment of the application has at least the following beneficial effects:

[0123] In the embodiment of the present application, the lower limb state data of the patient is acquired, and a lower limb rehabilitation exercise scheme is recommended to the patient according to the lower limb state data through a random forest model, thereby providing the patient with a personalized rehabilitation exercise scheme. Then, the lower limb rehabilitation exercise scheme is decomposed to obtain a rehabilitation exercise action. Meanwhile, according to the correlation between the rehabilitation exercise action and the acupoints, an electric stimulation is applied at the corresponding acupoints to enable the patient to perform the corresponding rehabilitation exercise action. Further, a system dynamics model is established according to the relationship between the rehabilitation exercise action and the electric stimulation, thereby quantifying the relationship between the lower limb movement and the electric stimulation, and making the subsequent movement control more accurate. Finally, according to the lower limb response output by the system dynamics model, the electric stimulation is adaptively adjusted through a control algorithm based on RISE until the rehabilitation exercise action is the expected action, thereby completing the control of the lower limb rehabilitation exercise and realizing personalized, accurate and efficient rehabilitation training, improving the rehabilitation experience and treatment effect of the patient, greatly saving the human resources, realizing adaptive adjustment, making the action more stable, the training safer, and improving the rehabilitation quality and safety.

[0124] It should be understood that the processor in the embodiment of the present application can be a central processing unit (CPU), and the processor can also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), ready programmable gate arrays (FPGAs) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0125] It should also be understood that the memory in the embodiments of the present application can be volatile or nonvolatile memory, or can include both volatile and nonvolatile memory. Nonvolatile memory can be read-only memory (ROM), programmable ROM (PROM), erasable PROM (EPROM), electrically EPROM (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), which is used as external cache. By way of example, and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous dynamic RAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0126] The above-described embodiments can be implemented in whole or in part by software, hardware (such as a circuit), firmware, or any combination thereof. When implemented in software, the above-described embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions according to the embodiments of the present application are wholly or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center through a wired (for example, infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server, data center, etc. containing one or more available medium collections. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state disk.

[0127] It should be understood that the term "and / or" herein merely describes an association relationship of associated objects, which means that there can be three relationships, for example, A and / or B can represent three cases of A alone, A and B together, and B alone, where A and B can be singular or plural. In addition, the character " / " herein generally represents an "or" relationship between the front and rear associated objects, but can also represent an "and / or" relationship, which can be understood in the context.

[0128] In the present application, "at least one" means one or more, and "multiple" means two or more. "At least one of the following" or the like means any combination of the items, including any combination of single or multiple items. For example, at least one of a, b, or c can represent a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be single or multiple.

[0129] It should be understood that in various embodiments of the present application, the size of the sequence number of the above-described processes does not mean the order of execution, and the execution order of the processes should be determined by their functions and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0130] Those skilled in the art can clearly understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed 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 implementation should not be considered beyond the scope of the present application.

[0131] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the devices, apparatuses and units described above can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0132] In several embodiments provided by the present application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely schematic, for example, the division of units is only a logical function division, and actual implementation can have another division manner, for example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0133] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0134] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically independently, or two or more units can be integrated into one unit.

[0135] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or parts of the present application that essentially contribute to the prior art or parts of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various storage medium capable of storing program codes.

[0136] The embodiment of the present application provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to realize the lower limb rehabilitation exercise control system based on acupoint electric stimulation of the method embodiment.

[0137] The computer readable storage medium provided by the present application can realize the steps and effects of the lower limb rehabilitation exercise control system based on acupoint electric stimulation of the above-mentioned method embodiment. To avoid repetition, the present application will not be described again.

[0138] The technical solutions provided by the embodiments of the present application have at least the following beneficial effects:

[0139] In the embodiments of the present application, the state data of the lower limbs of the patient is acquired, and the lower limb rehabilitation exercise scheme is recommended to the patient through the random forest model according to the lower limb state data, so as to provide the patient with a personalized rehabilitation exercise scheme. Then, the lower limb rehabilitation exercise scheme is decomposed to obtain a rehabilitation exercise action. At the same time, according to the correlation between the rehabilitation exercise action and the acupoint, electric stimulation is applied at the corresponding acupoint to make the patient perform the corresponding rehabilitation exercise action. Further, according to the relationship between the rehabilitation exercise action and the electric stimulation, a system dynamics model is established to quantify the relationship between the lower limb movement and the electric stimulation, so that the subsequent movement control is more accurate. Finally, according to the lower limb response output by the system dynamics model, the electric stimulation is adaptively adjusted through the RISE-based control algorithm until the rehabilitation exercise action is the expected action, the control of the lower limb rehabilitation exercise is completed, the personalized, accurate and efficient rehabilitation training is realized, the rehabilitation experience and treatment effect of the patient are improved, the human resources are greatly saved, the adaptive adjustment is realized, the action is more stable, the training is safer, and the rehabilitation quality and safety are improved.

[0140] The above merely illustrates the specific embodiments of the present application, and the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present application, which should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0141] The following points need to be explained:

[0142] (1) The drawings of the embodiments of the present application only involve the structures involved in the embodiments of the present application, and other structures can refer to the usual design.

[0143] (2) In order to be clear, the thickness of the layer or region is enlarged or reduced in the drawings used to describe the embodiments of the present application, that is, the drawings are not drawn according to the actual proportion. It can be understood that when an element such as a layer, a film, a region or a substrate is referred to as being located "on" or "under" another element, the element can be "directly" located on or under another element or there can be an intermediate element.

[0144] (3) In the case of no conflict, the embodiments of the present application and the features in the embodiments can be combined with each other to obtain new embodiments.

[0145] The above merely illustrates the specific embodiments of the present application, and the protection scope of the present application is not limited thereto, and the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A lower limb rehabilitation exercise control system based on acupoint electrical stimulation, characterized in that, include: The acquisition module is used to acquire data on the patient's lower limb status. The recommendation module is used to recommend lower limb rehabilitation exercise programs to the patient based on the lower limb status data using a random forest model. The decomposition module is used to decompose the lower limb rehabilitation exercise plan to obtain rehabilitation exercise movements; The execution module is used to enable the patient to perform the corresponding rehabilitation exercise by applying electrical stimulation at the corresponding acupoints, based on the correlation between the rehabilitation exercise and the acupoints. A module is established to create a system dynamics model based on the relationship between the rehabilitation exercises and the electrical stimulation. The system dynamics model is specifically as follows: ； ； ； ； ； in, J This represents the inertia of the system, specifically the inertia of the lower limbs. express t The angular acceleration of the knee joint at any given moment. Indicates the effect of gravity. θ ( t )express t The angle position of the knee joint at all times. Indicates elastic effect, This indicates the viscous damping effect. express t The angular velocity of the knee joint at any given moment. express t The perturbation term at time, express t The torque generated by constant electrical stimulation m This indicates the total mass of the lower leg and foot. g Represents gravitational acceleration. l It indicates the distance from the knee joint to the center of gravity of the lower leg and foot. , and All of these represent positive correlation coefficients for joint stiffness. e Represents the natural constant. k 1. k 2 and k 3 represents parameters related to the viscous damping effect. Indicates joint torque. Represents a nonlinear function. u ( t )express t The electrical stimulation signal at any given moment; The adjustment module is used to adaptively adjust the electrical stimulation based on the lower limb response output by the system dynamics model and a RISE-based control algorithm. The repetition module is used to repeat the adjustment module until the rehabilitation exercise is the desired movement, thereby completing the control of the lower limb rehabilitation exercise.

2. The lower limb rehabilitation exercise control system based on acupoint electrical stimulation according to claim 1, characterized in that, The lower limb status data specifically includes: knee joint angle, electromyography signal, knee joint stiffness, knee joint elasticity, lower limb force line, muscle strength level, muscle tension, and gait data.

3. The lower limb rehabilitation exercise control system based on acupoint electrical stimulation according to claim 1, characterized in that, The recommendation module is specifically used for: Extract the core kinematic features from the lower limb state data; The core kinematic features are preprocessed; Based on the preprocessed core kinematic features, the category of rehabilitation exercise is determined using the random forest model. Based on the rehabilitation exercise category, the lower limb rehabilitation exercise program is recommended to the patient by mapping a standard training library.

4. The lower limb rehabilitation exercise control system based on acupoint electrical stimulation according to claim 1, characterized in that, The lower limb rehabilitation exercise program specifically includes: gait training, active flexion and extension exercises, passive exercises, and leg raising exercises.

5. The lower limb rehabilitation exercise control system based on acupoint electrical stimulation according to claim 1, characterized in that, The decomposition module is specifically used to: decompose the lower limb rehabilitation exercise program by combining the action-acupoint-muscle group mapping relationship table to obtain multiple rehabilitation exercise action combinations, wherein the rehabilitation exercise action combination includes the action number, the rehabilitation exercise action, the acupoint, and the electrical stimulation site.

6. The lower limb rehabilitation exercise control system based on acupoint electrical stimulation according to claim 1, characterized in that, The adjustment module is specifically used for: The tracking error is determined based on the difference between the actual knee joint angle and the expected knee joint angle trajectory in the system dynamics model. The tracking error is filtered out; Based on the filtered tracking error and combined with lower limb inertia, the error dynamic equation is calculated. The error dynamic equation is analyzed to obtain the error evolution model; The electrical stimulation is adaptively adjusted based on the error evolution model.

7. The lower limb rehabilitation exercise control system based on acupoint electrical stimulation according to claim 6, characterized in that, The adaptive adjustment of the electrical stimulation specifically involves: adaptively adjusting the parameters of the electrical stimulation; The parameters specifically include: voltage amplitude, pulse width, pulse frequency, stimulation mode, and activation time window.

Images