Multi-link collaborative evaluation and feedback system for upper limb rehabilitation training

Abstract

The invention discloses a multi-link collaborative evaluation and feedback system for upper limb rehabilitation training, and belongs to the technical field of medical rehabilitation, and the system comprises a data collection module which is used for obtaining the related data of the upper limb of a patient in the rehabilitation training process, and the related data comprises the motion posture, the muscle activity condition and the joint activity degree; the data processing module responds to the data acquisition module and is used for preprocessing the acquired related data, including filtering and denoising the related data, acquiring feature information in the preprocessed related data and sending the feature information to the data acquisition module; the feature information comprises movement tracks of joints, contraction intensity and time of muscles and coordination of upper limb movement. Multi-dimensional data such as action postures, muscle movement conditions and joint movement ranges in upper limb rehabilitation training are collected, preprocessing and feature extraction are carried out through the data processing module, the upper limb rehabilitation condition of a patient can be comprehensively and accurately evaluated, and a basis is provided for formulating a personalized rehabilitation scheme.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical rehabilitation, in particular to a multi-link cooperative evaluation and feedback system for upper limb rehabilitation training. BACKGROUND

[0002] With the development of society and the intensification of aging, the number of hemiplegia caused by cardiovascular and nervous system is also increasing year by year, so rehabilitation medicine gradually attracts the attention of society. Studies have shown that stroke patients can obtain sufficient motor and sensory stimulation through long-term rehabilitation training, and then gradually recover motor function.

[0003] For the rehabilitation training of stroke patients, the application file with application number CN201910969686.8 provides an upper limb active and passive rehabilitation training robot system based on force feedback technology. The technical scheme includes a robot body and an active and passive training host computer system, which can carry out active and passive rehabilitation training on the freedom degrees of left and right shoulder joint adduction / abduction, forward flexion / back extension, and left and right elbow joint flexion / extension according to the patient's condition. In the active rehabilitation training mode, the patient holds the end of the robot body with both hands, interacts with the rehabilitation training scene, and can feel real and accurate force feedback. Moreover, it supports real-time training data recording, realizes scientific and quantitative evaluation of rehabilitation training effect, and improves the effect of rehabilitation treatment.

[0004] Another application file with application number CN201811445109.0 provides a two-person cooperative upper limb rehabilitation training system and evaluation method based on virtual reality environment. The technical scheme includes determining the upper limb movement mode according to the upper limb function evaluation results of two patients; guiding two patients to hold handles and operate on the same virtual target on the training plane according to the virtual scene and virtual target generated on the training plane, and recognizing and acquiring the movement data of the two handles on the training plane, and interacting with the virtual reality program to make two patients complete the upper limb rehabilitation training together. The technical scheme judges whether the movement trajectory of the virtual target deviates from the preset movement trajectory according to the movement data of the two handles and the movement trajectory of the virtual target; if it deviates, the error area is counted; and the upper limb rehabilitation conditions of the two patients are evaluated according to the training completion condition and the error area counting result. The present application solves the problem of single-person single-device training in the prior art, and improves the interest of patients in rehabilitation training.

[0005] However, the above technical scheme can only detect part of the rehabilitation indicators, and cannot comprehensively and accurately reflect the rehabilitation conditions of each joint, muscle and other multi-links of the patient's upper limbs. Moreover, the evaluation and training links are relatively independent, and the patient cannot obtain timely targeted feedback during the training process, which is not conducive to improving the training effect and accelerating the rehabilitation process. SUMMARY

[0006] In view of the above problems existing in the prior art of medical rehabilitation technology field, the present application is proposed.

[0007] Therefore, one of the purposes of the present application is to provide a multi-link cooperative evaluation and feedback system for upper limb rehabilitation training, which can comprehensively and accurately evaluate the rehabilitation status of the upper limbs of patients by collecting multi-dimensional data such as action posture, muscle activity and joint activity during upper limb rehabilitation training, and pre-processing and feature extraction through a data processing module, thereby providing a basis for personalized rehabilitation program development.

[0008] To solve the above technical problems, the present application provides the following technical solutions: The present application provides a multi-link cooperative evaluation and feedback system for upper limb rehabilitation training, comprising: A data acquisition module is used to obtain relevant data of the upper limbs of patients during the rehabilitation training process, wherein the relevant data includes action posture, muscle activity and joint activity; A data processing module is responsive to the data acquisition module and is used to pre-process the obtained relevant data, including filtering and denoising the relevant data, and obtaining feature information in the pre-processed relevant data, wherein the feature information includes the motion trajectory of the joint, the contraction strength and time of the muscle and the coordination of the upper limb movement; A data differentiation module is used to obtain a training duration corresponding to the rehabilitation training process according to the relevant data, and to differentiate the training duration into a front training duration, a middle training duration and a rear training duration, and to collect feature changes about the action posture, muscle activity and joint activity in each training duration; A data fusion processing module is used to analyze the associated influence of the extension degree of the action posture and the extension of the training duration on the muscle activity and the joint activity according to the feature changes; the data fusion processing module includes a differentiation unit, a calculation unit and an evaluation and feedback unit; The differentiation unit is used to differentiate the extension degree of the upper limbs of the patient during the training process, including differentiating into fluent and complete extension, intermittent extension and incomplete extension according to the fluency and integrity of action execution; The calculation unit is responsive to the differentiation unit and is used to calculate the difference value of the muscle activity and the joint activity according to the fluent and complete extension, the intermittent extension and the incomplete extension; The evaluation and feedback unit is responsive to the calculation unit and is used to evaluate the influence on the muscle activity and the joint activity according to the size of the difference value, to determine the current rehabilitation stage of the patient according to the influence, and to generate feedback according to the evaluation result.

[0009] As a preferred scheme of the present application, wherein: in the data processing module, further comprising data fusion and synchronization of the related data; the data fusion and synchronization comprises multi-data source fusion and time synchronization; The multi-data source fusion comprises fusing data corresponding to action posture, muscle activity and joint activity to generate a data set; The time synchronization comprises aligning data corresponding to action posture, muscle activity and joint activity according to a unified time sequence through the way of time stamp, and analyzing the correlation and causality between the action posture, muscle activity and joint activity of the upper limb in the same moment or time period; Further comprising data modeling and analysis of the related data, the data modeling and analysis comprises kinematics model analysis and muscle dynamics model analysis; The kinematics model analysis comprises establishing an upper limb kinematics model, in which the data corresponding to joint activity is input into the upper limb kinematics model, and the kinematics parameters of each link of the upper limb are calculated, the kinematics parameters comprising motion trajectory, velocity and acceleration, and the motion coordination and flexibility of the upper limb are analyzed; The muscle dynamics model analysis comprises establishing a muscle dynamics model, and through the data corresponding to muscle activity, the contraction strength, fatigue degree and activation sequence of the muscle, and the synergistic relationship between the muscles are analyzed.

[0010] As a preferred scheme of the present application, wherein: the kinematics parameters of each link of the upper limb are calculated according to the following formula: ; ; ; In the formula, 、 、 represents the initial position coordinates, which are the initial position coordinates of the upper limb of the patient; 、 、 represents the velocity component in each direction, represents time.

[0011] As a preferred scheme of the present application, wherein: further comprising calculating according to the following formula: ; In the formula, represents the average velocity, represents the initial velocity, represents the velocity at time ; ; wherein, denotes the velocity at the moment, denotes the initial velocity, denotes the time interval, denotes the acceleration.

[0012] As a preferred scheme of the present application, wherein: among the calculated kinematic parameters, the stretch degree of the upper limbs of the patient in the training time length of different segments is obtained based on the movement trajectory, and the movement trajectory is divided into , ,..., wherein, denotes the divided th movement trajectory, the maximum stretch degree corresponding to different movement trajectories is obtained in the training time length of different segments, the correlation rule of different movement trajectories and stretch degree changes is calculated, and the following formula is used to calculate: ; wherein, denotes the initial position, denotes the total length of the movement trajectory, and the total length of the movement trajectory is the total length of the straight trajectory, denotes the relative change of the stretch degree, which ranges from 0 to 1, denotes the end position of the movement trajectory.

[0013] As a preferred scheme of the present application, wherein: the following formula is further included: ; wherein, denotes the relative change of the stretch degree, which ranges from 0 to 1, denotes the initial position vector, denotes the total length of the movement trajectory, and the total length of the movement trajectory is the total length of the curve trajectory, denotes the end position vector.

[0014] As a preferred scheme of the present application, wherein: according to the calculated correlation rule, when the patient performs rehabilitation training in the future period, the patient is trained based on the movement trajectory corresponding to the maximum stretch degree, the real-time feedback of the patient is obtained in the rehabilitation training, and the movement trajectory in the rehabilitation training is adjusted according to the result of the real-time feedback. The movement trajectory corresponding to the maximum stretch degree is marked as the reference movement trajectory.

[0015] As a preferred scheme of the present application, wherein: the real-time feedback comprises a patient's sensory stimulation, the sensory stimulation comprising pain; when the patient has sensory stimulation, adjustment is made based on a movement trajectory lower than the reference movement trajectory, the adjustment comprising: An average height of the reference movement trajectory is obtained, and 2-4 movement trajectories are set according to the average height; wherein the height set for each movement trajectory is 3-4% lower than that of the previous movement trajectory, real-time feedback of the set different movement trajectories is obtained, and when the average height corresponding to a certain movement trajectory causes the patient to have no sensory stimulation, the patient is rehabilitated based on the movement trajectory during rehabilitation training, and the movement trajectory is marked as a risk movement trajectory.

[0016] As a preferred scheme of the present application, wherein: the effect of the rehabilitation training is evaluated, and in a future period, real-time feedback is obtained at an average height 2-3% higher than the risk movement trajectory when the patient is rehabilitated, and if the patient has sensory stimulation, the system determines that the rehabilitation effect of the patient is poor; otherwise, it is not determined.

[0017] Beneficial effects: 1. The data division module divides the training duration into early, middle and late stages, respectively collects data of each stage and analyzes the characteristic changes, which helps to understand the rehabilitation progress of the patient in different training stages in detail, find problems in time, and optimize the training arrangement. 2. The data fusion processing module analyzes the correlation between the extension degree of the action posture and the muscle activity and the joint activity, deepens the understanding of the mutual relationship between various factors in the rehabilitation training, and improves the scientificity and pertinence of the rehabilitation training. 3. The multi-data source fusion and time synchronization processing in the data processing module ensure the consistency and correlation of different types of data, make the analysis of the upper limb movement condition more accurate and comprehensive, and avoid misjudgment caused by data deviation. 4. With the help of kinematics and dynamics model analysis, the kinematics parameters of each link of the upper limb are calculated, the coordination and flexibility of the upper limb movement are evaluated, and the rehabilitation effect is predicted, so as to plan the subsequent rehabilitation training in advance. 5. By distinguishing the correlation between the movement trajectory and the extension degree, and marking the reference movement trajectory and the risk movement trajectory, scientific guidance is provided for the rehabilitation training of the patient, invalid or excessive training is avoided, and the rehabilitation efficiency is improved. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort based on these drawings. Among them: Fig. 1 A modular structure schematic diagram of the multi-link cooperative evaluation and feedback system for upper limb rehabilitation training of the embodiments of the present application; Fig. 2 A flow structure schematic diagram of the embodiments of the present application; The figure label: 110-data acquisition module; 120-data processing module; 130-data distinguishing module; 140-data fusion processing module; 1401-distinguishing unit; 1402-computing unit; 1403-evaluation and feedback unit. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions of the embodiments of the present application will be clearly and completely described below in combination with the drawings of the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the described embodiments of the present application, all other embodiments obtained by those skilled in the art belong to the scope of protection of the present application.

[0020] Since the prior art can only detect part of the rehabilitation indicators, it cannot comprehensively and accurately reflect the rehabilitation conditions of various joints, muscles and other multi-links of the upper limbs of the patient; and the evaluation and training links are relatively independent, so that the patient cannot obtain timely targeted feedback during the training process, which is not conducive to the improvement of the training effect and the acceleration of the rehabilitation process.

[0021] Based on this, the present application provides a multi-link cooperative evaluation and feedback system for upper limb rehabilitation training, which can comprehensively and accurately evaluate the rehabilitation conditions of the upper limbs of the patient by collecting multi-dimensional data such as action posture, muscle activity and joint activity during upper limb rehabilitation training, and pre-processing and feature extraction through a data processing module, thereby providing a basis for formulating a personalized rehabilitation plan.

[0022] The present application will be further specifically described below through embodiments and in combination with the drawings.

[0023] Reference Figs. 1-2 For an embodiment of the present application, the embodiment provides a multi-link cooperative evaluation and feedback system for upper limb rehabilitation training, comprising: A data acquisition module 110 is used to acquire relevant data of the upper limbs of the patient during the rehabilitation training process, and the relevant data includes action posture, muscle activity and joint activity; In this embodiment, comprehensive rehabilitation data including action posture, muscle activity and joint range of motion can comprehensively reflect the upper limb rehabilitation state; It should be noted that, in a feasible implementation, the data acquisition module includes action capture sensors, electromyographic signal sensors, pressure sensors, etc., to obtain relevant data such as action posture, muscle activity, joint range of motion, etc. of the patient's upper limb during the training process; Specifically, action capture sensors are worn at key positions of the patient's upper limb (such as shoulder joint, elbow joint, wrist joint, etc.), to capture the motion trajectory and posture change of the upper limb in three-dimensional space in real time. At the same time, electromyographic signal sensors are attached to the surface of the main muscle groups of the upper limb (such as deltoid muscle, biceps brachii, triceps brachii, forearm muscle group, etc.), to detect the electrical activity of the muscles during the training process. In addition, pressure sensors are arranged at the part of the patient's hand that contacts the training equipment, to measure the pressure applied by the hand, so as to evaluate the grasping function and motor coordination of the hand; When the patient starts the upper limb rehabilitation training, the sensors start the data acquisition work synchronously, and transmit the collected data to the data processing module at a certain time frequency (such as 100 Hz); The data processing module 120 is used for pre-processing the acquired relevant data, including filtering and denoising the relevant data, and obtaining feature information in the pre-processed relevant data, the feature information including the motion trajectory of the joint, the contraction strength and time of the muscle and the coordination of the upper limb movement; In this embodiment, the noise and interference are effectively removed, and the key feature information such as the joint motion trajectory, the muscle contraction strength and time and the upper limb movement coordination is extracted, to provide data support for subsequent accurate evaluation; The data division module 130 is used for dividing the training duration corresponding to the rehabilitation training process according to the relevant data, dividing the training duration into a front training duration, a middle training duration and a rear training duration, and collecting the feature changes of the action posture, muscle activity and joint range of motion in each training duration; In this embodiment, the training duration is divided into front, middle and rear sections, and the feature changes of each period are collected in detail, so as to understand the rehabilitation performance and progress of the patient at different training stages, find the rehabilitation key points and problems of each stage, and provide basis for targeted training adjustment; The data fusion processing module 140 is used for analyzing the associated influence of the extension of the training duration and the action posture on the muscle activity and the joint range of motion according to the feature changes. The data fusion processing module 140 includes a division unit 1401, a calculation unit 1402 and an evaluation and feedback unit 1403; The distinguishing unit 1401 is configured to distinguish the stretching degree of the upper limb of the patient during the training process, including distinguishing into fluent complete stretching, intermittent stretching and incomplete stretching according to the fluency and integrity of the action execution; The calculation unit 1402 is configured to calculate the difference between the muscle activity and the joint range of motion according to the fluent complete stretching, the intermittent stretching and the incomplete stretching in response to the distinguishing unit; The evaluation and feedback unit 1403 is configured to evaluate the influence on the muscle activity and the joint range of motion according to the size of the difference, determine the current rehabilitation stage of the patient according to the influence, and generate feedback according to the evaluation result in response to the calculation unit; In the embodiment, the influence of the training duration and the stretching degree on the muscle activity and the joint range of motion is comprehensively analyzed to deeply explore the correlation between the factors, which is helpful to develop a more scientific and reasonable rehabilitation training scheme. The module includes the distinguishing unit, the calculation unit and the evaluation and feedback unit, which progressively distinguish the stretching degree, calculate the difference and evaluate the rehabilitation stage and generate feedback according to the result, so as to realize dynamic monitoring and precise guidance of the rehabilitation training; The rehabilitation stage includes the acute stage, the recovery stage and the sequelae stage; It should be noted that, in a feasible implementation, the feedback is generated in the following manner: in the patient end, intuitive visual images (such as three-dimensional animation showing the correct upper limb movement posture and the actual movement trajectory of the patient, a heat map of muscle activation, etc.) are displayed on the user interaction interface, and voice prompts are given to point out the problems existing in the training process of the patient; Such as "your shoulder joint abduction angle is insufficient, please increase the abduction amplitude, please refer to the correct action in the figure", or "your biceps brachii contraction strength is weak, you need to strengthen the muscle strength training" and the like; For the rehabilitation therapist end, a detailed patient evaluation report is provided, including specific values of each evaluation index, chart analysis and rehabilitation progress trend curve of the patient, etc., and specific training adjustment suggestions are given, such as adjusting the parameters of the training equipment, increasing or decreasing the number of repetitions of specific training actions, changing the order and combination of training, etc. In the data processing module, data fusion and synchronization of related data are also included; the data fusion and synchronization include multi-data source fusion and time synchronization; The multi-data source fusion includes fusing the data corresponding to the action posture, the muscle activity and the joint range of motion to generate a data set; In the embodiment, the three-dimensional coordinate data of the action posture and the electromyographic signal of the corresponding muscle, the angle and angular velocity data of the joint are fused, so as to more accurately analyze the overall situation of the upper limb movement and the mutual relationship between the factors; The time synchronization includes aligning the data corresponding to the action posture, muscle activity and joint activity degree in a unified time sequence through time stamping, and analyzing the correlation and causality between the action posture, muscle activity and joint activity degree of the upper limb at the same time or time period; The data modeling and analysis also includes kinematics model analysis and muscle dynamics model analysis; The kinematics model analysis includes establishing an upper limb kinematics model, inputting the data corresponding to the joint activity degree into the upper limb kinematics model, calculating the kinematics parameters of each link of the upper limb, and analyzing the motion coordination and flexibility of the upper limb, wherein the kinematics parameters include motion trajectory, velocity and acceleration; In this embodiment, the fine action ability and coordination of the hand are evaluated by analyzing the motion trajectory and velocity of the fingers, and the overall function of the upper limb is evaluated according to the kinematics parameters of the shoulder, elbow, wrist and other joints; The muscle dynamics model analysis includes establishing a muscle dynamics model, analyzing the contraction strength, fatigue degree and activation sequence of the muscle, and the synergistic relationship between the muscles according to the data corresponding to the muscle activity; In this embodiment, the synergistic contraction of the muscles in the elbow flexion and extension action is understood by analyzing the electromyographic signals of the biceps brachii and triceps brachii, and the coordination and balance of the muscles are evaluated; It should be noted that the data fusion and synchronization are implemented, the multi-source data is integrated and processed by time synchronization, the consistency of the data in the time sequence is ensured, the correlation and causality of each factor of the upper limb at the same time or time period can be accurately analyzed, the rehabilitation evaluation is more comprehensive, in-depth and accurate, and the misjudgment caused by inconsistent data is avoided; And by developing data modeling and analysis, kinematics and muscle dynamics models are used to calculate kinematics parameters and analyze various characteristics and synergistic relationships of the muscles, respectively. The kinematics model can evaluate the coordination and flexibility of the upper limb motion, and provide a basis for adjusting the training action. The muscle dynamics model is helpful for optimizing the muscle strength and coordination training, and improving the scientificity and individualization level of the rehabilitation training; The kinematics parameters of each link of the upper limb are calculated according to the following formula: ; ; ; In the formula, 、 、 represents the initial position coordinates, which are the initial position coordinates of the upper limb of the patient; 、 , This represents the velocity components in each direction. Indicates time; This embodiment provides specific formulas for calculating the kinematic parameters of each segment of the upper limb, including the position coordinate update formula under the linear motion trajectory. Based on the initial position coordinates, velocity components in each direction, and time, it can quantitatively calculate the positional changes of the upper limb during rehabilitation training, providing basic data for the subsequent calculation of parameters such as velocity and acceleration. Through these precise kinematic parameter calculations, the upper limb movement status can be analyzed more accurately, providing a strong basis for the formulation and adjustment of rehabilitation training programs, and helping to improve the accuracy and effectiveness of rehabilitation training. It also includes calculations based on the following formula: ; In the formula, Indicates average speed. Indicates the initial velocity. Indicates time The speed at that time; ; In the formula, express The speed of time Indicates the initial velocity. Indicates time interval, Indicates acceleration; In this embodiment, the calculation formulas for average speed and instantaneous speed are given. The average speed formula can reflect the average speed of upper limb movement over a period of time, while the instantaneous speed formula can accurately obtain the speed value of the upper limb at a specific moment, providing a more detailed reference for controlling the intensity and rhythm of exercise in rehabilitation training. It should be noted that this embodiment provides two methods for calculating acceleration. One method is used to calculate the acceleration of uniformly accelerated linear motion, which can reflect the acceleration changes of the upper limb under uniformly accelerated conditions. The other method can be used to calculate the tangential and normal acceleration in curvilinear motion, comprehensively analyze the changes in the magnitude and direction of velocity during upper limb movement, help rehabilitation therapists to more accurately grasp the patient's movement status, further optimize rehabilitation training programs, and improve the pertinence and effectiveness of training. Among the calculated kinematic parameters, the extension degree of the patient's upper limb during different training durations is obtained based on the motion trajectory, and the motion trajectory is divided into... , ,..., ,in, The first indicates the distinction The maximum stretching degree corresponding to different movement trajectories is obtained in different training time periods, and the correlation between the different movement trajectories and the stretching degree is calculated according to the following formula: ; In the formula, represents the initial position, represents the total length of the movement trajectory, and the total length of the movement trajectory is the total length of the straight-line trajectory, represents the relative change of the stretching degree, and the range is 0-1, represents the end position of the movement trajectory; In this embodiment, on the basis of calculating the kinematic parameters, the movement trajectories in different training time periods are further distinguished, and the maximum stretching degree corresponding thereto is obtained. The correlation between the different movement trajectories and the stretching degree is calculated by a specific formula, which can deeply understand the stretching of the upper limbs under different movement trajectories, and provide a basis for the selection and adjustment of the movement trajectory in the rehabilitation training. It should be noted that the formula considers key factors such as the initial position, the total length of the movement trajectory, and the relative change of the stretching degree, so that the calculation of the stretching degree is more scientific and practical. In combination with the total length of the straight-line trajectory or the total length of the curved trajectory, the relative change of the stretching degree can be accurately calculated according to different movement trajectory types, which provides a quantitative reference for the personalized development of rehabilitation training, helps the rehabilitation therapists to develop more appropriate rehabilitation training programs according to the specific conditions of the patients, and improves the pertinence and effect of the rehabilitation training. Further comprising calculating according to the following formula: ; In the formula, represents the relative change of the stretching degree, and the range is 0-1, represents the initial position vector, represents the total length of the movement trajectory, and the total length of the movement trajectory is the total length of the curved trajectory, represents the end position vector; In this embodiment, on the basis of the calculation of the stretching degree of the straight-line trajectory, a calculation formula of the stretching degree of the curved trajectory is further provided. This formula is suitable for curved movement trajectories and considers factors such as the initial position vector, the total length of the movement trajectory, and the end position vector, so that the calculation of the stretching degree can adapt to more complex movement trajectory types. It should be noted that through the formula, the change of the extension degree of the upper limb under the curved motion trajectory can be comprehensively understood, and precise quantitative analysis can be provided for the training project involving curved motion in rehabilitation training, which helps the rehabilitation therapist to adjust the rehabilitation training scheme, optimize the training action and path, improve the scientificity and individualization level of the rehabilitation training, better meet the rehabilitation needs of the patient under different motion ability states, promote the recovery of the upper limb function according to the change rule of the extension degree of the patient under the curved motion trajectory; According to the calculated correlation rule, when the patient performs rehabilitation training in the future period, the patient is trained based on the motion trajectory corresponding to the maximum extension degree, the real-time feedback of the patient is obtained in the rehabilitation training, and the motion trajectory is adjusted according to the result of the real-time feedback, and the motion trajectory corresponding to the maximum extension degree is marked as a reference motion trajectory; In this embodiment, the individualized training method based on the correlation rule can accurately select the most suitable motion trajectory for rehabilitation training according to the current rehabilitation state of the patient and the correlation between the motion trajectory and the extension degree; And by introducing the real-time feedback mechanism, the rehabilitation training can adjust the motion trajectory in time according to the real-time reaction of the patient, ensure the effectiveness and comfort of the training, and mark the motion trajectory corresponding to the maximum extension degree as a reference motion trajectory, which is convenient for the rehabilitation therapist to record and analyze the rehabilitation progress of the patient, and provide a reference basis for further optimizing the training scheme. This method helps to improve the pertinence and effect of rehabilitation training and promote the rapid recovery of the upper limb function of the patient; The real-time feedback includes the perceptual stimulus of the patient, and the perceptual stimulus includes pain; when the patient has a perceptual stimulus, the motion trajectory lower than the reference motion trajectory is used as the basis for adjustment, and the adjustment mode includes: The average height of the reference motion trajectory is obtained, and 2-4 motion trajectories are set according to the average height; wherein the height set by each motion trajectory is 3%-4% lower than the previous motion trajectory, the real-time feedback of the set different motion trajectories is obtained, and when the average height corresponding to a certain set motion trajectory does not cause the patient to have a perceptual stimulus, the motion trajectory is used as the basis for rehabilitation training of the patient during rehabilitation training, and the motion trajectory is marked as a risk motion trajectory; In this embodiment, the perceptual stimulus of the patient is included in the real-time feedback of the rehabilitation training, and when the patient has a perceptual stimulus such as pain, the height of the reference motion trajectory is lowered to adjust the motion trajectory, which can effectively reduce the discomfort of the patient and improve the comfort of the rehabilitation training; And setting multiple gradually reduced height movement trajectories, and obtaining real-time feedback under different movement trajectories, until finding the movement trajectory without pain of the patient, that is, the risk movement trajectory, this step-by-step adjustment method can accurately determine the movement range that the patient can bear, avoid injury caused by overtraining, and ensure the continuity and effectiveness of training, which helps the patient better cooperate with the rehabilitation training, enhances the rehabilitation confidence, and improves the overall quality and effect of rehabilitation training. The effect of rehabilitation training is evaluated, and in the future period of rehabilitation training of the patient, real-time feedback is obtained at an average height of 2% to 3% higher than the risk movement trajectory, if the patient has a perceptual stimulus, it is determined that the rehabilitation effect of the patient is poor, otherwise, it is not determined. In this embodiment, the effect of rehabilitation training is evaluated, and in subsequent rehabilitation training, real-time feedback is obtained at a movement trajectory with a certain percentage higher than the risk movement trajectory, which provides a dynamic and quantitative evaluation method for the judgment of rehabilitation effect. If the patient has a perceptual stimulus, it is determined that the rehabilitation effect is poor, otherwise, it is not determined to be poor. This rehabilitation effect evaluation method based on real-time feedback can timely reflect the actual impact of rehabilitation training on the patient, help the rehabilitation therapist adjust the rehabilitation training plan according to the immediate response of the patient, ensure that the rehabilitation training is always within the appropriate range, improve the scientificity and effectiveness of the rehabilitation training, and promote the smooth progress of the patient's rehabilitation process. At the same time, through this evaluation method, the rehabilitation progress of the patient can be better tracked, providing an important reference for the rehabilitation therapist to develop subsequent rehabilitation plans. It should be noted that in reality, after stroke, the upper limb muscle strength is weakened, and rehabilitation training needs to be done with force. Muscle overfatigue will cause soreness, and after stroke, the neural control function is impaired, and the upper limb muscle may become tense, stiff, and form spasm. Spastic muscles are prone to pain when pulled or moved during rehabilitation training. In addition, after stroke, the joint may be caused by long-term braking, unbalanced muscle strength, and other factors, resulting in decreased joint range of motion. Forced joint movement during rehabilitation training can cause pain. At the same time, the upper limb muscle strength of the stroke patient is weakened, and the joint capsule is relaxed, which is prone to shoulder joint subluxation. In the rehabilitation training, the upper limbs of patients with shoulder joint subluxation may have obvious pain when being pulled or weighted. Therefore, the embodiment judges the rehabilitation effect based on whether the patient has a perceptual stimulus, which has practical significance.

[0024] In summary, the present application can comprehensively and accurately evaluate the rehabilitation status of the patient's upper limbs by collecting multi-dimensional data such as action posture, muscle activity, and joint activity during upper limb rehabilitation training, and pre-processing and feature extraction by the data processing module, which provides a basis for personalized rehabilitation plan development.

[0025] It should be noted that the above examples are only used to illustrate the technical solutions of the present application but not to limit the present application. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or equivalently replaced without departing from the spirit and scope of the present application, and all modifications and equivalents should be included in the scope of the claims of the present application.

Claims

1. A multi-link cooperative evaluation and feedback system for upper limb rehabilitation training, characterized in that, The application relates to a data processing method for upper limbs rehabilitation training, which comprises the following steps: a data acquisition module is used to acquire relevant data of a patient's upper limbs in a rehabilitation training process, wherein the relevant data comprises action posture, muscle activity and joint activity; a data processing module is used to pre-process the acquired relevant data, including filtering and denoising the relevant data, and acquiring feature information in the pre-processed relevant data, wherein the feature information comprises joint motion trajectory, muscle contraction strength and time and upper limb motion coordination; a data division module is used to acquire training duration corresponding to the rehabilitation training process according to the relevant data, and divide the training duration into front training duration, middle training duration and rear training duration, and collect feature changes about the action posture, muscle activity and joint activity in each training duration; a data fusion processing module is used to analyze the associated influence of training duration extension and action posture stretching degree on muscle activity and joint activity according to the feature changes; the data fusion processing module comprises a division unit, a calculation unit and an evaluation and feedback unit; the division unit is used to divide the stretching degree of the patient's upper limbs in the training process, including dividing into fluent and complete stretching, intermittent stretching and incomplete stretching according to the fluency and integrity of action execution; the calculation unit is used to calculate the difference value of the muscle activity and joint activity according to the fluent and complete stretching, intermittent stretching and incomplete stretching; the evaluation and feedback unit is used to evaluate the influence on muscle activity and joint activity according to the size of the difference value, determine the current rehabilitation stage of the patient according to the influence, and generate feedback according to the evaluation result.

2. The upper limb rehabilitation multi-link cooperative assessment and feedback system according to claim 1, wherein, In the data processing module, the relevant data is also subjected to data fusion and synchronization; the data fusion and synchronization comprises multi-data source fusion and time synchronization; the multi-data source fusion comprises fusing data corresponding to the action posture, muscle activity and joint activity to generate a data set; the time synchronization comprises aligning the data corresponding to the action posture, muscle activity and joint activity according to a unified time sequence through the time stamp mode, analyzing the association and causality between the action posture, muscle activity and joint activity of the upper limbs in the same moment or time period; the relevant data is also subjected to data modeling and analysis, wherein the data modeling and analysis comprises kinematics model analysis and muscle dynamics model analysis; the kinematics model analysis comprises establishing an upper limb kinematics model, wherein in the upper limb kinematics model, data corresponding to the joint activity is input into the upper limb kinematics model, kinematics parameters of each link of the upper limb are calculated, the kinematics parameters comprise motion trajectory, velocity and acceleration, and the motion coordination and flexibility of the upper limb are analyzed; the muscle dynamics model analysis comprises establishing a muscle dynamics model, and analyzing muscle contraction strength, fatigue degree and activation sequence and the synergistic relationship between muscles through data corresponding to the muscle activity.

3. The upper limb rehabilitation multi-link cooperative assessment and feedback system according to claim 2, wherein, The kinematic parameters of each link of the upper limb are calculated, and are calculated according to the following formula: ； ； ； In the formula, , , represents an initial position coordinate, which is an initial position coordinate of the upper limb of the patient; , , represents a velocity component in each direction, represents time.

4. The upper limb rehabilitation training multi-link cooperative assessment and feedback system according to claim 3, characterized in that, Further comprising calculating according to the following formula: ； wherein denotes the average speed, denotes the initial speed, denotes the time speed at time ； wherein denotes the speed at the moment, denotes the initial speed, denotes the time interval, denotes the acceleration.

5. The multi-link cooperative assessment and feedback system for upper limb rehabilitation training according to any one of claims 3-4, characterized in that, In the calculated kinematic parameters, the stretching degree of the upper limbs of the patient in the training duration of different sections is obtained based on the movement trajectory, and the movement trajectory is divided into , ,..., , wherein represents the first movement trajectory, the maximum stretching degree corresponding to different movement trajectories is obtained in the training duration of different sections, the correlation between the different movement trajectories and the stretching degree change is calculated, and the following formula is used for calculation: ； wherein denotes the initial position, denotes the total length of the motion trajectory, which is the total length of the straight line trajectory, denotes the relative change in the extent of stretching, which ranges between 0 and 1, denotes the end position of the motion trajectory.

6. The upper limb rehabilitation training multi-link cooperative assessment and feedback system according to claim 5, characterized in that, Further comprising calculating according to the following formula: ； wherein denotes the relative change of the extent of stretching, ranging between 0 and 1, denotes the initial position vector, denotes the total length of the motion trajectory, which is the total length of the curvilinear trajectory, denotes the end position vector.

7. The multi-link cooperative assessment and feedback system for upper limb rehabilitation training according to any one of claims 5-6, characterized in that, According to the calculated correlation law, when the patient performs rehabilitation training in the future period, the patient is trained based on the movement trajectory corresponding to the maximum stretching degree, the real-time feedback of the patient is obtained in the rehabilitation training, and the movement trajectory in the rehabilitation training is adjusted according to the result of the real-time feedback, and the movement trajectory corresponding to the maximum stretching degree is marked as a reference movement trajectory.

8. The upper limb rehabilitation multi-link cooperative assessment and feedback system according to claim 7, characterized in that, The real-time feedback includes the patient's sensory stimulation, and the sensory stimulation includes pain; when the patient has sensory stimulation, the adjustment is based on a movement trajectory lower than the reference movement trajectory, and the adjustment includes: Obtaining the average height of the reference movement trajectory, setting 2-4 movement trajectories according to the average height; wherein the height of each movement trajectory is set to be 3%-4% lower than the previous movement trajectory, obtaining the real-time feedback of the set different movement trajectories, when the average height corresponding to a certain set movement trajectory makes the patient not have sensory stimulation, then the patient is trained based on the movement trajectory during rehabilitation training, and the movement trajectory is marked as a risk movement trajectory.

9. The upper limb rehabilitation multi-link cooperative assessment and feedback system according to claim 8, wherein, The effect of the rehabilitation training is evaluated, and when the patient performs rehabilitation training in the future period, the real-time feedback is obtained at an average height higher than the risk movement trajectory by 2%-3%, if the patient has sensory stimulation, the system determines that the rehabilitation effect of the patient is poor; otherwise, it is not determined.

Images