207 results about "Joint angulation" patented technology

The invention discloses an upper limb exoskeleton rehabilitation robot control system and method, and relates to the technical field of rehabilitation robot upper limb control, and the method comprises the steps: collecting multi-modal data such as multi-channel myoelectricity, joint angles, angular velocity and interactive torque; constructing a sliding window feature vector, predicting a next joint angle increment through TCN and Bi-LSTM deep networks, and outputting intention confidence; and based on the confidence coefficient and the muscle fatigue factor, dynamically adjusting an impedance parameter, and combining an impedance control model to generate a power-assisted torque in real time so as to realize power-assisted torque output. By introducing an impedance adjustment mechanism of multi-modal perception, deep time sequence learning and myoelectricity driving, the bottleneck of a traditional upper limb rehabilitation robot in the aspects of intention prediction, parameter adjustment and training individuation is broken through, and the accuracy, safety and active participation degree in the rehabilitation training process are remarkably improved; wide clinical application prospects and industrial transformation values are realized.

The invention discloses a lower limb exoskeleton rehabilitation robot joint torque prediction method and device based on an electromyographic signal, and the method comprises the steps: firstly collecting the electromyographic, joint angle, angular velocity and joint torque data of a user, and carrying out the modeling of four muscles related to a knee joint through a neuromusculoskeletal model; and identifying physiological parameters used in the model by using a sparrow optimization algorithm, and outputting an optimal solution to obtain an estimated torque. Then, the real torque and the estimated torque are endowed with the weights of # imgabs0 # respectively, and a fusion torque is obtained; and training a neural network model by using the collected data and the fusion moment, and meanwhile, enabling the neuromusculoskeletal model to participate in the training process of the neural network model by adopting a method of bringing the neuromusculoskeletal model into a loss function, so that the constraint of the model is increased. And finally, storing the trained model for subsequent calling. The method has the advantages of high precision and strong generalization, and model training can converge more quickly under the condition of less data volume.

The invention relates to the technical field of spine rehabilitation training, and discloses a computer vision recognition and guidance system for spine rehabilitation training actions. The system comprises a data acquisition module for acquiring user spine motion three-dimensional dynamic image data by using a multi-camera array; the action recognition module tracks bone joint points based on an improved algorithm to generate a real-time action sequence; the posture evaluation module is used for extracting spine curvature and joint angle features through a multi-scale convolutional neural network; the guidance instruction generation module inputs the features into a reinforcement learning model to generate a personalized instruction; and the feedback execution module constructs a fuzzy self-adaptive control model to correct the motion trail of the spine. According to the system, training actions can be accurately recognized, personalized guidance is provided, real-time correction is achieved, the spine rehabilitation training effect is effectively improved, subjectivity and errors of manual evaluation are reduced, and rehabilitation requirements of different patients are met.

The invention provides a lower limb joint angle prediction method and system based on space-time attention in the technical field of exoskeleton robot control, and the method comprises the steps: S1, collecting a large number of I MU historical signals through a single-node IMU sensor disposed at a shank, carrying out the preprocessing of each IMU historical signal, and constructing a data set; s2, creating a joint angle prediction model based on a multi-scale convolution module, a space-time attention module and a long-term memory module; s3, dividing the data set into a training set, a verification set and a test set based on a preset proportion, training the joint angle prediction model through the training set, verifying the trained joint angle prediction model through the verification set, and testing the joint angle prediction model passing verification through the test set; and S4, performing lower limb joint angle prediction on the joint angle prediction model passing the test. The lower limb joint angle prediction method has the advantages that the lower limb joint angle prediction precision and applicability are greatly improved.

The invention provides a dexterous hand finger joint angle control method, device and system and a medium, and relates to the technical field of dexterous hands. The joint angles of the fingers of the dexterous hand comprise the first joint angle and the second joint angle, the first joint angle and the second joint angle belong to active degrees of freedom, and the control method for the joint angles of the fingers of the dexterous hand comprises the steps that a control instruction for the fingers of the dexterous hand is obtained; according to the control instruction, the tracking control law of the first joint angle and the tracking control law of the second joint angle, the first joint angle and the second joint angle are controlled, the tracking control law of the first joint angle and the tracking control law of the second joint angle are determined based on a superspiral sliding mode control algorithm and a dynamic model of the finger. Through the tracking control law designed based on the super-spiral sliding mode control algorithm and the dynamic model, the stability and precision of dexterous hand finger joint angle control are improved.

The invention relates to the technical field of knee joint rehabilitation evaluation, in particular to a knee joint rehabilitation evaluation method based on a human skeleton by using a space-time diagram convolutional network, and the method comprises the following steps: obtaining a rehabilitation evaluation gait video set; extracting human body key point skeleton data, and slicing the human body key point skeleton data into gait samples according to the number of time frames; preprocessing the gait sample, and extracting joint, skeleton and joint angle features; a gait-link method is adopted to divide a space gait skeleton diagram, a space-time attention mechanism is added, and an improved CTR-GCN network model is constructed; training the improved CTR-GCN network model by using the gait sample to obtain a gait evaluation model; and processing a gait video to be evaluated, and inputting the processed gait video into the gait evaluation model to obtain a rehabilitation evaluation result of the patient. According to the method, the human body key point skeleton in the walking video of the patient is extracted and input into the space-time diagram convolutional network for training, the rehabilitation evaluation model is obtained, the rehabilitation condition of the patient is evaluated by using the model, and the requirement of rehabilitation evaluation is met.

The invention provides a joint angle inverse solution method, device and equipment of a redundant mechanical arm and a medium, and the method comprises the steps that a target function of the redundant mechanical arm is obtained, the target function is an optimization function with the joint angle of each joint on the redundant mechanical arm closest to a preset movement midpoint of each joint as a target, and the joint angle of each joint is calculated according to the last iteration angle of each joint; the target function is solved by adopting the limiting constraint condition of each joint and the pose constraint condition of the tail end joint of the redundant mechanical arm, the current iteration angle of each joint is obtained, the actual pose of the tail end joint is obtained according to the current iteration angle of each joint, and the target function is obtained according to the actual pose and the expected pose of the tail end joint. And determining whether a preset joint angle iteration stopping condition is met or not, and if the preset joint angle iteration stopping condition is met, determining that the current iteration angle of each joint is the target angle of each joint when the preset joint angle iteration stopping condition is met. And each joint is controlled based on the target angle, so that each joint is closest to the preset movement midpoint.

The invention relates to a personalized exercise rehabilitation risk early warning method and device based on IMU dynamic instability assessment, and the method comprises the steps: collecting multi-dimensional exercise data of a subject, carrying out the posture fusion, and obtaining the limb posture, joint angle change rate and angular momentum of the subject; performing time sequence mode decomposition to extract a single gait cycle and a specific jump landing attitude; calculating a biomechanical feature vector of each motion primitive; inputting the single gait cycle, the specific jump landing attitude and the biomechanical feature vector into a hybrid injury induced motion model, and outputting a multi-dimensional injury risk index vector; and comparing the multi-dimensional injury risk index vector with historical health data and a moving target dynamic adjustment threshold value of the subject, and if the threshold value is exceeded, providing real-time auditory, tactile or visual feedback to the subject. According to the method, the influence of movement speed and rhythm change is overcome, dynamic instability in movement can be more sensitively reflected, and personalized risk assessment in a real sense is realized.

The invention discloses a badminton player action posture analysis system and method based on multi-sensor fusion, and relates to the technical field of athletic training auxiliary systems.The system comprises a wearable sensing subsystem, an environment sensing subsystem and a central processing and feedback subsystem; the wearable sensing subsystem is arranged on an inertia measurement unit and a pressure sensing insole of a body to collect movement inertia and plantar pressure data; the environment perception subsystem collects global videos through multiple cameras. The central processing and feedback subsystem performs synchronous processing on multi-source data, adopts a hierarchical fusion algorithm, restrains inertia integral drift by utilizing a plantar contact state, reconstructs a three-dimensional skeleton posture and a motion trail in combination with visual key points and skeleton restraint, drives a digital twin model, compares with a standard motion model, and performs three-dimensional motion control on the three-dimensional skeleton posture and the motion trail. Quantitative evaluation results such as joint angle deviation, time sequence difference and pressure center track are generated, and visual feedback is performed through a display device and an augmented reality terminal for badminton training evaluation and technical deviation correction.

The invention provides a human body posture abnormity assessment method based on a body measurement all-in-one machine, and the method comprises the steps: obtaining the video data, collected by multiple cameras, of the bending and foot touching actions of a subject, carrying out the preliminary positioning of a spine, a lumbar vertebra and thoracic vertebra transition region, and key points of legs, and extracting the coordinates of the key points; leg joint angle change is calculated according to the leg key point coordinates, if the angle change amplitude is lower than a preset threshold value, it is judged that leg flexibility is insufficient, a key point tracking strategy is adjusted, and the tracking density of a leg area is increased; according to the posture abnormity score, generating a posture abnormity report of the bending and foot touching actions of the subject, and marking specific positions of spine curvature abnormity, stiffness increase of a transition area between the lumbar vertebra and the thoracic vertebra and insufficient leg flexibility; and dynamically updating a key point tracking strategy and an attitude anomaly judgment threshold according to the action normativity score, and optimizing the accuracy and real-time performance of subsequent action evaluation.

The invention relates to the technical field of digital health, in particular to a personalized rehabilitation exercise method for rheumatoid arthritis patients based on a BCW theory, which comprises the following steps: acquiring joint angle change and calculating a pain delay response coefficient, detecting fluctuation of supporting force and stabilizing force to obtain a joint load tolerance value, analyzing respiratory coordination to generate a respiratory coordination index, and performing rehabilitation training on the respiratory coordination index. The method comprises the steps that a joint angle sensor and pain intensity data are analyzed, a BCW capacity factor weight value is generated in a weighted mode, a fuzzy control algorithm is input to conduct hierarchical mapping adjustment on action amplitude frequency and rest intervals, and exercise adaptability feedback data are generated through monitoring completion degree and pain feedback. The exercise intensity is dynamically adjusted in real time through a data model, a personalized rehabilitation scheme is automatically optimized, the problems that subjective feedback is relied on, and physiological changes cannot be responded in time are solved, more accurate exercise amount adjustment is provided, the situation that the joint burden is increased due to improper exercise intensity is avoided, and the rehabilitation process is effectively promoted.

The invention discloses a multi-modal fusion muscular tension dynamic assessment method and system, relates to the technical field of biological dynamic assessment, and is used for solving the problem that muscle activity grade classification errors are increased due to dependence on single surface myoelectricity or joint angle sensor data. Joint angle variation, resistance variation and force feedback intensity are extracted, an evaluation mechanism is constructed in combination with region division and historical threshold values, and muscle activity evaluation levels are calculated; and comparing a preset threshold value to identify a flexibility level, entering a resistance evaluation mechanism when a condition is met, analyzing a muscular tension change trend in resistance data, completing dynamic refined judgment of a flexible state, realizing staged, regionalized and trended fusion evaluation, and improving muscular tension state identification and flexibility level judgment precision.

The invention provides a rehabilitation training feedback system and method. The method comprises the following steps: acquiring a surface electromyogram signal; a plurality of activation trend indexes are determined through the surface electromyogram signals, and then muscle force activation points of different muscle areas are extracted from the surface electromyogram signals according to all the activation trend indexes; performing collaborative analysis on the basis of a function collaborative relationship in combination with all muscle force activation points to obtain time sequence response tensors between all motion joints and corresponding muscle areas when motion responses are inconsistent; according to the joint angle information and the time sequence response tensor, constructing a functional coupling graph, and further performing kinematic chain simulation on a rehabilitation training process through the functional coupling graph to obtain a response consistency index; and performing feedback control on the rehabilitation training process of the patient according to the response consistency index in combination with a preset consistency threshold. By means of the scheme, feedback control can be conducted on rehabilitation training of the patient based on the space-time coupling relation between muscle group microstructure changes and mechanical conduction characteristics.

The invention relates to the technical field of rehabilitation instruments, in particular to a whole-body joint rehabilitation training device and a control method thereof. The method comprises the following steps: acquiring joint angles, IMU data and electromyographic signals when a user executes a plurality of standard actions; according to the joint angle, determining a joint motion range risk level of the target joint; according to the joint angle, the IMU data and the electromyographic signal, determining a compensatory behavior risk level and a cooperative efficiency score of a target joint; determining a training mode according to the risk level of the compensatory behavior, wherein the training mode at least comprises a general mode and a mode for the compensatory behavior; determining training parameters according to the joint motion range risk level, wherein the training parameters comprise resistance; adjusting the training parameters according to the collaborative efficiency score; and outputting the training mode and the adjusted training parameters. According to the method, the rehabilitation efficiency can be improved, and compensatory behaviors during training are reduced.

Embodiments of the present disclosure provide a method and a system for determining a finger joint angle. The method includes obtaining first sensor data relating to at least two target finger joints of a user, the first sensor data is obtained using at least two strain sensors, each of the strain sensors is arranged in a glove body worn by the user and located at one target finger joints, and the at least two target finger joints include at least two adjacent metacarpophalangeal joints of the user; obtaining a first mapping relationship, wherein the first mapping relationship reflects a relationship between sensor data corresponding to the at least two target finger joints and joint angles of the at least two target finger joints; and determining a first joint angle of each of the at least two target finger joints based on the first sensor data and the first mapping relationship.

The invention discloses a lightweight multi-mode lower limb motion intention recognition method and system, and relates to the technical field of biomedicine. The method comprises the steps that multi-channel surface electromyogram signals sEMG of a target lower limb and joint angle signals and joint torque signals of lower limbs on the same side are synchronously collected; performing feature extraction by using a double-branch structure to obtain muscle-related deep time sequence features and joint-related high-level semantic features; performing feature fusion through a bidirectional cross attention mechanism to obtain cross attention fusion features; and performing flattening, nonlinear mapping, regularization and Softmax classification on the cross attention fusion features, and outputting the motion intention of the target lower limb. Through double-branch input, depth feature extraction and a bidirectional cross attention mechanism, on the premise of ensuring recognition precision, a lightweight attention module, a residual structure and a cross-modal interaction mechanism are introduced, and the parameter quantity and calculation overhead are reduced.

The invention provides a posture analysis and risk assessment method and device based on kinematics feature extraction, and relates to the technical field of medical diagnosis assessment, and the technical scheme is characterized in that the method comprises the steps: collecting the angle data of key joints in the movement process of a patient, and forming a joint angle time sequence; calculating the deviation between each joint angle of the patient and a corresponding joint angle in a predefined standard action template; performing weighted summation on the deviations of the corresponding joint angles to obtain a weighted Euclidean distance; a time window is set, the weighted Euclidean distances in the time window are averaged, a dynamic deviation value is obtained, and the dynamic deviation value reflects the deviation degree between the patient actions in the time window and the standard action template; and dividing the dynamic deviation value into different risk levels according to a preset risk threshold. The attitude analysis and risk assessment method and device based on kinematics feature extraction have the advantages of being high in portability, easy and convenient to operate, rapid in assessment and visual in result.

The invention relates to the technical field of sports protection, in particular to an intelligent protection system for lower limb joints in sports. Comprising a mounting bandage, a wearing support plate, a controller, an attitude sensor and a joint angle sensor, a driving device is arranged on the wearable supporting plate; the controller is arranged on the wearable supporting plate and comprises a data calculation module used for calculating and analyzing data of the attitude sensor and the joint angle sensor and recognizing abnormal signs of a wearer; the emergency warning module is used for sending warning information when abnormal signs are recognized; the alarm module is used for carrying out alarm processing when the warning information is sent out and measures cannot be taken within a preset time; the motion recognition module is used for recognizing the motion type of the wearer through the attitude sensor, generating a wearable supporting plate rigidity control signal according to the joint risk of the motion type, and adjusting the rigidity of the wearable supporting plate through the driving device. According to the technical scheme, the injury risk of lower limb joints in movement can be effectively reduced.

The invention relates to the technical field of non-human primate experimental animal upper limb movement ability evaluation and analysis, in particular to a non-human primate experimental animal upper limb movement ability comprehensive evaluation, data acquisition and analysis method. The comprehensive evaluation comprises the steps that upper limb comprehensive exercise ability evaluation is carried out by adopting an upper limb comprehensive exercise ability evaluation scale on the basis of upper limb feeding operation; and the upper limb coarse movement and the finger fine movement can be quantitatively evaluated. The data acquisition and analysis method comprises the following steps: S1, acquiring comprehensive movement time of upper limbs; s2, coordinate values of all key points of the upper limbs on a two-dimensional plane are obtained; s3, acquiring a 3D motion space trajectory; s4, analyzing the movement speed of the upper limb marked key points; s5, the joint angle of the elbow joint and the movement range of the palm, the elbow and the shoulder are obtained; and S6, analyzing to obtain finger key point distance change data. According to the invention, comprehensive objective evaluation and analysis of upper limb coarse movement and finger fine movement of non-human primate experimental animals can be realized.

The invention relates to the technical field of monitoring and alarming, in particular to an intelligent orthopedic rehabilitation training monitoring system based on multi-modal sensing, which comprises a basic data synchronous acquisition module, a dynamic stiffness differential analysis module, a defensive contraction judgment module and a load boundary dynamic reconstruction module. According to the method, a time sequence is constructed by synchronously collecting joint angle and moment data, an instantaneous dynamic stiffness change trend is analyzed by combining a moment and angle difference value, a Savitz-golay filter is used for carrying out second-order differential processing on dynamic stiffness to capture a stiffness second-order derivative mutation point, and the critical moment when defensive contraction pain occurs to the joint of a patient is recognized. The maximum activity angle upper limit is dynamically reconstructed based on the critical angle and the safety buffering difference value, a control instruction is directly fed back to a driving end to execute reverse braking, crossing from single-position monitoring to multi-dimensional mechanical state sensing is achieved, it is ensured that the activity boundary is automatically adjusted according to real-time physiological feedback of a patient, and the safety performance of the patient is improved. And secondary injury caused by forcibly breaking through a pain threshold value is prevented.

The invention discloses a singular avoidance control method and device for a six-axis mechanical arm based on virtual seven degrees of freedom. The tail end of the mechanical arm is provided with a virtual rotating shaft which coincides with the original point of a tail end coordinate system and is perpendicular to a rotating shaft of the tail end coordinate system. The control method comprises the steps that position information and angle information of all joints of the mechanical arm and the actual pose and expected pose of the tail end in the current detection period are obtained; based on the position information and the angle information of all the joints, the weight value of the virtual rotating shaft is correspondingly adjusted by combining the state that the mechanical arm approaches the shoulder singular point and / or the wrist singular point, a quadratic programming problem used for avoiding the singular points is reconstructed, and a to-be-executed joint angle increment vector is solved; and on the basis of the to-be-executed joint angle increment vector, the angle value of each joint of the mechanical arm in the next detection period is calculated, and the mechanical arm is controlled to move on the basis of the angle value of each joint so as to avoid shoulder singular points and / or wrist singular points of the mechanical arm.

Aspects of the present disclosure relate to systems and methods for performing operations including: receiving a plurality of bone scaling factors, each bone scaling factor corresponding to a respective bone of a bone model; receiving a plurality of joint angle factors that jointly define a pose of the bone model; generating a bone model based on the received bone scaling factors and the received joint angle factors; generating a base surface based on the plurality of bone scaling factors; generating an identity surface by deforming the base surface; and generating a 3D body model by mapping the identity surface to the posed bone model.

The invention relates to a joint angle prediction model construction method and system.The method comprises the steps that seven-channel gait time sequence signals in a multi-terrain walking mode are obtained, and the seven-channel gait time sequence signals comprise thigh four-channel sEMG signals, hip joint angle signals and target joint angle signals; sequentially selecting gait time sequence signals of each channel according to a time sequence by using a sliding window, and carrying out feature vector extraction; generating a feature matrix by using the feature vectors extracted by a preset number of continuous windows, and constructing a model training data set; constructing a joint angle prediction model by using an LSTM network; and taking the time domain feature and the hip joint angle feature in the feature matrix as the input of the model, taking the target joint angle feature as the output of the model, and training and verifying the joint angle prediction model by using a model training data set. The thigh surface electromyogram signals and hip joint angle information are fused, fewer sensor channels are used, and the cost and complexity of the system are reduced.

The invention discloses a muscle function rhythm analysis method and system based on unhealthy side cooperation and electronic equipment, and relates to the technical field of data processing. The method comprises the following steps: acquiring an uninjured side electromyographic signal of a patient, and a joint angle signal and a movement track signal of an affected side; based on the electromyographic signal, extracting an uninjured-side cooperative adjustment decline trajectory, and based on the joint angle signal and the motion trajectory signal, extracting an affected-side function take-over response trajectory; identifying a critical point of affected-side function takeover; calculating a first change curvature and a second change curvature, and taking a time point when the first change curvature is greater than the second change curvature for the first time as a motion stability starting point of the affected side; extreme point distribution is extracted, the motion rhythm period of the affected side is determined, and the time length change trend is calculated; and based on the time length change trend, determining a function autonomous maintenance score, and calculating a muscle function rhythm index of the upper limb of the affected side according to the function autonomous maintenance score. By implementing the technical scheme provided by the invention, the accuracy of analyzing the motion data of the limb on the affected side can be improved.

The invention discloses a brain-computer interface-based hand function rehabilitation auxiliary training method, which belongs to the technical field of rehabilitation training, and specifically comprises the following steps of: acquiring an original electroencephalogram signal of hand action of a patient, and synchronously recording an actual movement track of a healthy side hand; separating the original electroencephalogram signal into an action intention signal and an action control signal; activating a mirror image hand model in the virtual training scene based on the action intention signal, and mapping the action control signal into a three-dimensional motion parameter; dynamically correcting the joint movement range of the mirror image hand model according to the actual movement track of the uninjured side hand, and generating virtual hand actions matched with the physiological features of the patient; extracting track key point coordinates of the mirror image action and a joint angle change sequence, and converting the track key point coordinates and the joint angle change sequence into a driving instruction of affected side exoskeleton equipment; the exoskeleton resistance change is fed back to the virtual training scene in real time, and the motion damping of the mirror image hand model is adjusted; according to the invention, personalized precise assistance of hand function rehabilitation training is realized, and the adaptability and effectiveness of training are improved.

The invention discloses a rehabilitation training action difficulty grading analysis and scheme recommendation method and system. The method comprises the following steps: defining a geometric center of a key virtual joint point; calculating a human joint mass center and a moving limb mass center; joint kinematics parameter meters are calculated, wherein the joint kinematics parameter meters comprise angles, angular velocities and angular accelerations; based on the mass center of the moving limb, the body weight ratio and the kinematics parameters, calculating torque in combination with a mechanics principle; based on prime mover muscle analysis of a human body posture, combining a joint angle and an angular velocity direction, and performing work division according to functions of prime mover muscles in human anatomy; evaluating an action difficulty grade; and comparing the actual functional state of the patient with the training standard corresponding to the current difficulty weight. The recognition precision is remarkably improved.

The invention discloses a motion state determination method, system and device based on human upper limb inverse kinematics and a medium, and relates to the field of robot kinematics control, and the method comprises the steps: obtaining an upper limb working space of a human upper limb; according to the upper limb working space, discrete sampling is carried out based on a Monte Carlo sampling method, and an initial discrete point set is determined; performing sampling density adjustment on the sensitive area, the boundary area and the singular area in the initial discrete point set to obtain a final discrete point set; determining a joint angle set corresponding to each discrete point, and constructing a joint angle database; retrieving a joint angle database based on a kd-tree method, and determining an initial joint angle; local optimization is carried out based on a gradient descent method, and a joint angle corresponding to each tail end position is determined; determining the motion state of the upper limbs of the human body; the joint angle corresponding to each tail end pose of the human upper limb can be quickly and accurately determined, and then the current motion state of the human upper limb is determined.

The invention relates to the technical field of human body kinematics parameter measurement, in particular to an adult joint motion range evaluation method and system based on a multi-view video, and the method comprises the steps: obtaining a multi-view video sequence of a testee, and generating an observation data set containing two-dimensional key point observation, a human body segmentation mask and camera parameter information; constructing an individualized joint geometric model containing a bone segment length, a joint center, a joint principal axis and a joint angle coordinate system based on the observation data set, and generating a three-dimensional symbol distance field; constructing a factor graph and performing incremental optimization solution, and outputting a joint angle sequence and an abnormal frame set; and determining an activity range interval and carrying out anti-fact consistency check, and if the validity is not satisfied, calculating an information matrix by a Jacobian matrix to generate a supplementary collection instruction to update a result, thereby improving robustness and verifiability.

The invention provides a man-machine cooperative control method and system, and the method comprises the steps: collecting a plurality of electromyographic signals of limbs, and carrying out the filtering of the electromyographic signals, so as to remove the power frequency interference, and obtaining a denoised signal; adopting a sliding window method to extract time domain features and frequency domain features of the de-noised signal to form a multi-feature vector; inputting the multi-feature vector into an integrated learning model, and outputting a joint angle predicted value; performing real-time calculation by utilizing an estimation formula based on the joint angle predicted value to obtain a man-machine interaction torque; calculating a mode switching factor based on the man-machine interaction torque in the task period; acquiring an expected movement track and an actual movement track of the rehabilitation equipment, and calculating a track error; and on the basis of comparison results of the track error and the mode switching factor with a preset threshold value, the training mode of the rehabilitation equipment is switched, so that the misjudgment risk of a single signal source decision is remarkably reduced.

The invention discloses a rehabilitation evaluation system and method based on data feedback, and the method comprises the steps: obtaining a continuous online rehabilitation video as rehabilitation training video frame data, and constructing a rehabilitation training motion data set; extracting joint angle features and skeleton point distance features from the action data set by adopting a label classification technology, and obtaining distance measurement of each human body joint skeleton point coordinate; matching the time sequence with the action features by adopting a dynamic adjustment algorithm for the action feature combination, and constructing a classification evaluation model of rehabilitation training actions; a data feedback mechanism is introduced into the classification evaluation model of the rehabilitation training actions, the relation between rehabilitation requirements and rehabilitation evaluation is mapped, the whole system achieves detailed analysis and dynamic adaptation of the rehabilitation training actions, accurate rehabilitation suggestions can be provided according to individual differences, the effectiveness of a treatment strategy is ensured through real-time monitoring and adjustment, and the rehabilitation training effect is improved. And the rehabilitation effect and efficiency are greatly improved.