Intelligent scoring method and system for joint movement

Abstract

The invention provides an intelligent scoring method and system for joint movement. The method comprises the following steps: acquiring six-degree-of-freedom inertial motion data and surface electromyogram signals, and establishing a motion sequence topological structure containing a space-time reference based on a dynamic sampling strategy; secondly, decomposing inertial data into rigid body and physiological tremor components, and generating a three-dimensional biomechanical model containing joint rotation center drift, multi-plane coupling errors and trajectory curvature; secondly, constructing a time-varying mapping relation between the surface electromyogram signals and the exercise load, segmenting the signals based on phase mutation points, analyzing phase synchronism of an active muscle group and an antagonistic muscle group, and extracting a muscle cooperation mode; and finally, generating a motion feature tensor in a four-dimensional space-time coordinate system through technologies such as space-time coupling and a dynamic transfer function, analyzing an evolution mode of the motion feature tensor in real time to construct a scoring function cluster, and generating a composite scoring value. According to the technical scheme provided by the invention, the accuracy and reliability of joint movement quality evaluation are remarkably improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent scoring technology, and in particular to a joint motion intelligent scoring method and system. Background Art

[0002] The diagnosis and rehabilitation assessment of joint diseases require accurate measurement of joint motion and related muscle activity. In order to provide personalized treatment plans, doctors and technicians need a method that can accurately quantify the quality of joint motion so that rehabilitation training plans can be adjusted in a timely manner.

[0003] Currently, joint motion analysis mainly relies on optical motion capture systems combined with surface electromyography (sEMG). These methods usually use a fixed sampling frequency to collect data and analyze the motion characteristics of the joints through standard biomechanical models. In addition, most existing scoring systems are based on fixed parameters or simple threshold comparisons, lacking detailed consideration of dynamic changes during joint motion.

[0004] Existing technologies have limitations in processing complex joint movements, especially in the inaccurate identification of subtle movement components such as physiological tremors, making it difficult to reflect the specific changes in each stage of joint movement in real time. At the same time, traditional methods are insufficient in integrating surface electromyographic signals with joint kinematic parameters, and cannot effectively capture the dynamic changes of muscle synergy and phase synchronization, thus affecting the accuracy of joint movement quality assessment. Summary of the invention

[0005] The present application provides a joint motion intelligent scoring method and system to solve the problem in the prior art that it is difficult to reflect the specific changes in each stage of joint motion in real time.

[0006] In a first aspect, the present application provides a joint motion intelligent scoring method, comprising:

[0007] Collect the six-degree-of-freedom inertial motion data and surface electromyography signals of the target joint motion chain, and establish a motion sequence topology structure containing spatiotemporal reference markers based on the joint motion phase-triggered dynamic sampling strategy;

[0008] Decomposing the inertial motion data into a rigid body motion component and a physiological tremor component, and generating a three-dimensional biomechanical model including the instantaneous rotation center drift of the joint, multi-plane coupling errors and motion trajectory curvature through dynamic inverse solution;

[0009] The time-varying mapping relationship between surface electromyographic signals and exercise load was constructed, and the surface electromyographic signals were segmented by asymmetric window length based on the phase mutation points of kinematic parameters. A phase synchronization quantitative model of the active muscle group contraction waveform and the antagonist muscle group inhibition waveform was established within the segmentation interval. The muscle coordination pattern across the exercise cycle was extracted by analyzing the energy gradient field of the surface electromyographic signals.

[0010] The instantaneous rotation center drift of the joint in the three-dimensional biomechanical model is coupled with the electromyographic coordination mode in time and space, and the differential constraint relationship between the joint posture change and the electromyographic activation intensity is established through the kinematic chain dynamics transfer function, and the motion characteristic tensor is generated in the four-dimensional space-time coordinate system;

[0011] The evolution pattern of the motion feature tensor is analyzed in real time, and a scoring function cluster with a time-varying topological structure is independently constructed according to the difference in coupling strength among the acceleration, stabilization and deceleration periods of the motion. Each sub-function is nonlinearly superimposed with the energy transfer efficiency of the motion chain and the neural control stability index to generate a composite scoring value with motion quality diagnosis function.

[0012] Optionally, the instantaneous rotation center drift of the joint in the three-dimensional biomechanical model is coupled with the myoelectric coordination mode in time and space, a differential constraint relationship between the joint posture change and the myoelectric activation intensity is established through the kinematic chain dynamics transfer function, and a motion feature tensor is generated in a four-dimensional space-time coordinate system, including:

[0013] Based on the dynamic transfer function of the kinematic chain, the instantaneous angular velocity covariant derivative of the instantaneous rotation center drift of the joint in the three-dimensional biomechanical model is aligned in time and space with the phase gradient of the electromyographic synergy mode to generate a dynamic coupling equation; wherein, the constraint conditions of the dynamic coupling equation are jointly calibrated by the joint ligament tension distribution model and the time domain attenuation rate of the surface electromyographic signal inhibition waveform to ensure the physical dimension consistency of the kinematic parameters and the electromyographic parameters;

[0014] In a four-dimensional space-time coordinate system, a tensor product operation is performed on the output of the dynamic coupling equation and the propagation path of the multi-plane coupling error of the joint to generate an initial characteristic tensor field; wherein the dimension of the tensor product operation is dynamically adjusted by the curvature change rate of the drift trajectory of the joint rotation center, so that the initial tensor field simultaneously encodes the energy propagation direction of the motion chain and the electromyographic phase synchronization;

[0015] The asymmetric distribution characteristics of the energy gradient of the surface electromyography signal are used to calculate the viscoelastic coefficient matrix of the kinematic chain, and the initial tensor field is adaptively smoothed and filtered based on the viscoelastic coefficient matrix to generate a motion feature tensor containing a physiological hysteresis effect.

[0016] Optionally, the step of calculating the viscoelastic coefficient matrix of the kinematic chain using the asymmetric distribution characteristics of the surface electromyographic signal energy gradient includes:

[0017] An energy gradient covariance tensor is constructed based on the phase gradient distribution of the electromyographic synergy mode, and the covariance tensor is anisotropically weighted by the curvature change rate of the drift trajectory of the joint rotation center in the three-dimensional biomechanical model to generate an initial viscoelastic parameter set with kinematic chain energy propagation direction characteristics;

[0018] The initial viscoelastic parameter set is input into a convolution kernel function constructed based on the time domain attenuation rate of the surface electromyography signal suppression waveform, the frequency domain response characteristics corresponding to the joint ligament tension distribution model are extracted through a multi-scale sliding window, and the parameters are normalized in combination with the constraint conditions of the dynamic coupling equation to form a frequency domain mapping relationship of the viscoelastic coefficient matrix;

[0019] The step of performing adaptive smoothing filtering on the initial tensor field based on the viscoelastic coefficient matrix to generate a motion feature tensor containing a physiological hysteresis effect comprises:

[0020] A bandwidth adjustment factor of a tensor field filter is established according to the frequency domain mapping relationship, and a coupling weight of the energy propagation direction of the motion chain and the electromyographic phase synchronization is dynamically matched by utilizing the asymmetric distribution characteristics of the surface electromyographic signal energy gradient to generate an adaptive filter kernel with a physiological hysteresis compensation effect;

[0021] The initial feature tensor field is subjected to multi-channel parallel convolution operation through the adaptive filter kernel, the propagation path curvature parameters of the multi-plane coupling error of the joint are synchronously integrated, and the energy distribution topological structure of the motion feature tensor is iteratively updated to generate a motion feature tensor containing physiological hysteresis effect.

[0022] Optionally, the real-time analysis of the evolution pattern of the motion feature tensor autonomously constructs a scoring function cluster with a time-varying topological structure according to the difference in coupling strength between the motion acceleration period, the stable period and the deceleration period, wherein each sub-function is nonlinearly superimposed through the motion chain energy transfer efficiency and the neural control stability index to generate a composite scoring value with motion quality diagnosis function, including:

[0023] In the motion feature tensor, according to the phase boundary mark output by the motion stage recognition module, the distribution of manifold curvature extreme points is extracted along the energy propagation path, and the covariance matrix of the manifold curvature change rate and the electromyographic phase synchronization stability in each motion stage is calculated to generate an energy dissipation spatiotemporal map; wherein the detection rule of the manifold curvature extreme points is dynamically defined by the amplitude-frequency characteristics of the multi-plane coupling error of the joint;

[0024] In the neural control time series feature space, the abnormal area in the energy dissipation spatiotemporal map is mapped to the time-frequency overlapping interval of the electromyographic inhibition waveform, and a set of sub-functions with variable dimensional weights is generated based on the hysteresis effect parameters output by the viscoelastic correction model of the kinematic chain. The topological structure of the sub-function is dynamically constructed by the Hausdorff dimension of the drift trajectory of the joint rotation center, and the coupling weights between the sub-functions are calculated by the mutual information entropy of the electromyographic phase delay and the energy transmission efficiency of the kinematic chain.

[0025] The output values ​​of the sub-function set are integrated along the energy propagation path of the motion chain through a topological integral algorithm to generate a composite score value reflecting the coordination of joint movement; at the same time, the composite score value is compared with the physiological consistency threshold of the motion feature tensor, and the iterative step size of the dynamic calibration factor is dynamically adjusted through the back-propagation mechanism to achieve closed-loop optimization.

[0026] Optionally, in the neural control time series feature space, the abnormal area in the energy dissipation spatiotemporal map is mapped to the time-frequency overlapping interval of the electromyographic inhibition waveform, and a sub-function set with variable dimensional weights is generated based on the hysteresis effect parameters output by the viscoelastic correction model of the kinematic chain, including:

[0027] A time-frequency mask matrix is ​​constructed based on the boundary features of the abnormal region of the energy dissipation spatiotemporal map, and the mask matrix is ​​phase-delay compensated by the hysteresis effect parameters of the kinematic chain viscoelastic correction model to generate a time-frequency overlapping feature vector with a kinematic chain energy propagation direction constraint;

[0028] The time-frequency overlapping feature vector is input into a topological mapping network constructed based on the mutual information entropy of electromyographic phase delay and kinematic chain energy transmission efficiency, the Hausdorff dimension of the joint rotation center drift trajectory is used to dynamically adjust the network layer connection weights, and an initial weight set of a sub-function containing variable dimensional parameters is output;

[0029] The generating of a sub-function set with variable dimensional weights comprises:

[0030] A multidimensional weight distribution function is constructed according to the sub-function initial weight set and the time-frequency attenuation characteristics of the electromyographic inhibition waveform, and the distribution function is dynamically truncated and filtered through the physiological consistency threshold of the motion feature tensor to generate a sub-function dimension adjustment factor that satisfies the viscoelastic constraint of the motion chain;

[0031] The output of the topological mapping network is reconstructed by nonlinear interpolation using the dimension adjustment factor, and the covariance matrix characteristics of the manifold curvature change rate of the energy dissipation space-time map are synchronously integrated to iteratively generate a set of sub-functions with a time-varying topological structure.

[0032] Optionally, it also includes:

[0033] The topological invariance index of the energy propagation path in the motion feature tensor is extracted and nonlinearly mapped with the phase synchronization stability of the electromyographic synergy pattern to generate a dynamic calibration factor.

[0034] The dynamic calibration factor is fed back into the constraint condition of the dynamic coupling equation through an iterative optimization algorithm until the energy propagation path of the motion feature tensor and the time-frequency distribution of the electromyographic inhibition waveform reach a preset physiological consistency threshold.

[0035] Optionally, the time-varying mapping relationship between the surface electromyographic signal and the exercise load is constructed, the surface electromyographic signal is segmented with an asymmetric window length based on the phase mutation point of the kinematic parameter, a phase synchronization quantification model of the active muscle group contraction waveform and the antagonist muscle group inhibition waveform is established within the segmentation interval, and the muscle synergy pattern across the exercise cycle is extracted by analyzing the energy gradient field of the surface electromyographic signal, including:

[0036] A dynamic window length adjustment factor is constructed based on the phase mutation point detection result of the kinematic parameters, and the time-frequency energy mutation characteristics of the surface electromyographic signal at the phase mutation point are extracted by a wavelet transform modulus maximum detection algorithm to generate a surface electromyographic signal segmentation index with an asymmetric window length segmentation boundary;

[0037] Dynamically window the original surface electromyographic signal according to the surface electromyographic signal segmentation index, and asymmetrically align the signal segments of the agonist muscle group and the antagonist muscle group in the time domain using the dynamic window length adjustment factor to generate a segmentation interval containing a phase synchronization analysis reference point;

[0038] In the segmented interval, the instantaneous phase difference sequence of the surface electromyographic signals of the agonist muscle group and the antagonist muscle group is extracted by using the Hilbert-Huang transform, and the phase difference mutual information entropy matrix is ​​constructed in combination with the dynamic window length adjustment factor. The entropy matrix is ​​dynamically weighted by the curvature parameter of the energy propagation path of the motion chain to generate a phase synchronization index reflecting the stability of neural control;

[0039] An energy gradient covariance tensor is constructed based on the segmented index of the surface electromyographic signal in the segmented interval, and the phase synchronization index is decomposed into principal components along the energy propagation direction of the motion chain to extract the principal component vector that characterizes the cross-cycle synergy feature. The principal component vector is normalized for the motion chain energy through the amplitude-frequency characteristics of the multi-plane coupling error in the three-dimensional biomechanical model to generate a feature set corresponding to the neuromuscular synergy pattern.

[0040] In a second aspect, the present application provides a joint motion intelligent scoring system, comprising:

[0041] Establish a module for collecting six-degree-of-freedom inertial motion data and surface electromyographic signals of the target joint motion chain, trigger a dynamic sampling strategy based on the joint motion phase, and establish a motion sequence topology structure containing spatiotemporal reference markers;

[0042] A generation module, used for decomposing the inertial motion data into a rigid body motion component and a physiological tremor component, and generating a three-dimensional biomechanical model including the instantaneous rotation center drift of the joint, multi-plane coupling error and motion trajectory curvature through dynamic inverse solution;

[0043] A processing module is used to construct a time-varying mapping relationship between surface electromyographic signals and exercise load, perform asymmetric window length segmentation on the surface electromyographic signals based on the phase mutation points of kinematic parameters, establish a phase synchronization quantitative model of the active muscle group contraction waveform and the antagonist muscle group inhibition waveform within the segmentation interval, and extract the muscle coordination pattern across the exercise cycle through the surface electromyographic signal energy gradient field analysis;

[0044] The generation module is also used to couple the instantaneous rotation center drift of the joint in the three-dimensional biomechanical model with the electromyographic coordination mode in time and space, establish the differential constraint relationship between the joint posture change and the electromyographic activation intensity through the motion chain dynamics transfer function, and generate a motion feature tensor in a four-dimensional space-time coordinate system; analyze the evolution pattern of the motion feature tensor in real time, and independently construct a scoring function cluster with a time-varying topological structure according to the difference in coupling intensity between the acceleration period, the stable period and the deceleration period of the movement, wherein each sub-function is nonlinearly superimposed through the motion chain energy transfer efficiency and the neural control stability index to generate a composite scoring value with motion quality diagnosis function.

[0045] In a third aspect, the present application provides a computing device comprising a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a joint motion intelligent scoring method as described in the first aspect above.

[0046] In a fourth aspect, the present application provides a computer storage medium storing a computer program, which, when executed by a computer, implements a joint motion intelligent scoring method as described in the first aspect.

[0047] In the present application, the six-degree-of-freedom inertial motion data and surface electromyography signals of the target joint motion chain are collected, and a motion sequence topological structure containing spatiotemporal reference markers is established based on a dynamic sampling strategy triggered by the joint motion phase; the inertial motion data is decomposed into a rigid body motion component and a physiological tremor component, and a three-dimensional biomechanical model containing the instantaneous rotation center drift of the joint, multi-plane coupling error and motion trajectory curvature is generated through dynamic inverse solution; a time-varying mapping relationship between the surface electromyography signal and the motion load is constructed, and the surface electromyography signal is segmented with an asymmetric window length based on the phase mutation point of the kinematic parameters, and a phase synchronization quantification model of the active muscle group contraction waveform and the antagonist muscle group inhibition waveform is established within the segmentation interval, and a time-varying mapping relationship between the surface electromyography signal and the motion load is constructed based on the phase mutation point of the kinematic parameters. The muscle coordination pattern across the movement cycle is extracted through surface electromyographic signal energy gradient field analysis; the instantaneous rotation center drift of the joint in the three-dimensional biomechanical model is coupled with the electromyographic coordination pattern in time and space, and the differential constraint relationship between the joint posture change and the electromyographic activation intensity is established through the kinematic chain dynamics transfer function, and a motion feature tensor is generated in a four-dimensional space-time coordinate system; the evolution pattern of the motion feature tensor is analyzed in real time, and a scoring function cluster with a time-varying topological structure is independently constructed according to the difference in coupling strength between the acceleration period, the stable period and the deceleration period of the movement, wherein each sub-function is nonlinearly superimposed through the kinematic chain energy transfer efficiency and the neural control stability index to generate a composite scoring value with motion quality diagnosis function.

[0048] The technical solution of this application has the following beneficial effects:

[0049] By combining the six-degree-of-freedom inertial motion data and surface electromyography signals, not only the mechanical motion characteristics of the joints are taken into account, but also the electrophysiological characteristics of muscle activity are deeply analyzed, achieving detailed quantification of the complex dynamic behaviors during joint movement. Using dynamic inverse solution technology and three-dimensional biomechanical models, subtle changes in joint movement can be accurately captured. In addition, by performing asymmetric window length segmentation and phase synchronization quantification on the surface electromyography signals, muscle synergy can be more realistically reflected, thereby improving scoring accuracy. Ultimately, the composite score values ​​generated based on these advanced analysis methods help to achieve accurate diagnosis of joint movement quality.

[0050] Further, the method of the present invention involves coupling the instantaneous rotation center drift of the joint in the three-dimensional biomechanical model with the electromyographic synergy mode in time and space through the dynamic transfer function of the kinematic chain and generating a dynamic coupling equation, the constraint condition of which is determined by the joint ligament tension distribution and the time domain attenuation rate of the surface electromyographic signal suppression waveform, ensuring parameter consistency; in the four-dimensional space-time coordinate system, the initial characteristic tensor field is generated by combining the dynamic coupling equation output with the joint multi-plane coupling error propagation path through tensor product operation, and its dimension is adjusted according to the curvature change rate of the joint rotation center drift trajectory, and the energy propagation direction and electromyographic phase synchronization are encoded at the same time; further, the viscoelastic coefficient matrix is ​​calculated using the asymmetric distribution characteristics of the surface electromyographic signal energy gradient, and the initial tensor field is adaptively smoothed and filtered based on this matrix, and finally a motion characteristic tensor containing physiological hysteresis effect is generated. This method solves the problem of difficulty in accurately capturing joint subtle movements and muscle synergy in traditional technology through precise space-time coupling and dynamic adjustment mechanism, effectively improves the accuracy and reliability of joint motion quality assessment, especially in the process of processing complex joint motion, it can more truly reflect the energy propagation characteristics and electromyographic phase synchronization of the kinematic chain.

[0051] Furthermore, the method of the present invention utilizes the asymmetric distribution characteristics of the energy gradient of the surface electromyography signal. First, an energy gradient covariance tensor is constructed based on the phase gradient distribution of the electromyography synergy mode, and anisotropically weighted by the curvature change rate of the drift trajectory of the joint rotation center to generate an initial viscoelastic parameter set with the energy propagation direction characteristics of the motion chain; then, this parameter set is input into a convolution kernel function constructed by the time domain attenuation rate of the surface electromyography signal suppression waveform, and the frequency domain response characteristics are extracted through a multi-scale sliding window and the parameters are normalized to form a frequency domain mapping relationship of the viscoelastic coefficient matrix; then, a bandwidth adjustment factor is established according to the frequency domain mapping relationship, and the coupling weights are dynamically matched in combination with the asymmetric distribution characteristics of the energy gradient of the surface electromyography signal to generate an adaptive filter kernel; finally, the filter kernel is used to perform multi-channel parallel convolution operations on the initial feature tensor field, synchronously fuse the propagation path curvature parameters of the multi-plane coupling error of the joint, and iteratively update the energy distribution topological structure of the motion feature tensor to generate a motion feature tensor containing a physiological hysteresis effect. This method effectively compensates for the physiological hysteresis effect that is ignored by traditional analysis methods in dealing with complex joint movements by accurately calculating and applying the viscoelastic coefficient matrix and combining it with adaptive smoothing filtering technology. It significantly improves the accuracy of capturing subtle joint movements and muscle synergy, thereby enhancing the authenticity and reliability of joint movement quality assessment.

[0052] These and other aspects of the present application will become more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions in the present application or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0054] Figure 1 A flow chart of a joint motion intelligent scoring method provided by the present application is shown;

[0055] Figure 2 A schematic diagram of the structure of an intelligent scoring system for joint motion provided by the present application is shown;

[0056] Figure 3 A schematic diagram of the structure of a computing device provided by the present application is shown. DETAILED DESCRIPTION

[0057] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0058] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0059] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0060] Figure 1 A flowchart of a joint motion intelligent scoring method is provided for an embodiment of the present application, such as Figure 1 As shown, the method includes:

[0061] 101. Collect the six-degree-of-freedom inertial motion data and surface electromyographic signals of the target joint motion chain, and establish a motion sequence topology structure containing spatiotemporal reference markers based on the joint motion phase-triggered dynamic sampling strategy;

[0062] In this step, the six-degree-of-freedom inertial motion data and surface electromyographic signals of the target joint kinematic chain are collected. These data include information such as position, velocity, acceleration, etc., which are used to analyze the motion state of the joint and muscle activity, and trigger the dynamic sampling strategy based on the joint motion phase to establish the motion sequence topology structure containing spatiotemporal reference markers.

[0063] In an embodiment of the present application, the six-degree-of-freedom motion data of the target joint and the related surface electromyography signals are captured by sensors, and a dynamic sampling strategy is used to trigger data collection of different frequencies according to different stages of joint movement, thereby constructing a spatiotemporal marking topological structure that accurately reflects the entire process of joint movement.

[0064] Suppose you need to evaluate an athlete's knee rehabilitation. First, you install an inertial measurement unit (IMU) and a surface electromyography (sEMG) sensor around the athlete's knee. When the athlete performs a series of specified movements, relevant data is collected in real time and the key spatiotemporal markers of each movement stage are recorded for subsequent analysis.

[0065] 102. Decomposing the inertial motion data into a rigid body motion component and a physiological tremor component, and generating a three-dimensional biomechanical model including the instantaneous rotation center drift of the joint, multi-plane coupling error and motion trajectory curvature through dynamic inverse solution;

[0066] In this step, the collected inertial motion data is decomposed into rigid body motion components and physiological tremor components. The former describes the basic motion pattern of the joint, and the latter reflects subtle involuntary movements. A three-dimensional biomechanical model including the instantaneous rotation center drift of the joint, multi-plane coupling errors, and motion trajectory curvature is generated through dynamic inverse solution technology.

[0067] In an embodiment of the present application, a dynamic inverse solution method is used to separate the rigid body motion and physiological tremor components from the original data, and then the instantaneous rotation center change of the joint during movement, the error caused by the interaction between planes, and the curvature of the motion trajectory are calculated to form a detailed three-dimensional biomechanical model.

[0068] Continuing with the above example, by processing the collected data, it is possible to separate the normal movement of the athlete's knee during exercise and the tiny vibrations caused by incomplete recovery, and based on this, a biomechanical model can be established to quantify its recovery status.

[0069] 103. Construct the time-varying mapping relationship between surface electromyographic signals and exercise load, perform asymmetric window length segmentation on surface electromyographic signals based on the phase mutation points of kinematic parameters, establish a phase synchronization quantitative model of the active muscle group contraction waveform and the antagonist muscle group inhibition waveform within the segmentation interval, and extract the muscle coordination pattern across the exercise cycle through surface electromyographic signal energy gradient field analysis;

[0070] In this step, the time-varying mapping relationship between surface electromyographic signals and exercise load is constructed to identify muscle activation patterns in different exercise phases. The surface electromyographic signals are segmented by asymmetric window length based on the phase mutation points of kinematic parameters to distinguish the contraction waveform of the active muscle group from the inhibition waveform of the antagonist muscle group, and a phase synchronization quantification model is established to extract the muscle synergy pattern across the exercise cycle.

[0071] In an embodiment of the present application, a specific algorithm is used to identify phase mutation points in surface electromyographic signals, and based on this, the window length is dynamically adjusted to perform signal segmentation, the behavior patterns of the agonist muscle groups and the antagonist muscle groups are analyzed separately, a phase synchronization index between them is constructed, and further research is conducted on how the muscles work in coordination during the entire movement process.

[0072] In the above case, it is possible to determine which muscles are mainly working and which are assisting or inhibiting when the athlete is doing a specific movement. This helps to understand the efficiency of cooperation between their muscles and provide a basis for formulating more effective rehabilitation training.

[0073] 104. Couple the instantaneous rotation center drift of the joint in the three-dimensional biomechanical model with the myoelectric coordination mode in time and space, establish a differential constraint relationship between the joint posture change and the myoelectric activation intensity through the kinematic chain dynamics transfer function, and generate a motion feature tensor in a four-dimensional space-time coordinate system;

[0074] In this step, the instantaneous rotation center drift of the joint in the three-dimensional biomechanical model is combined with the electromyographic coordination pattern, and the differential constraint relationship between the joint posture change and the electromyographic activation intensity is established through the kinematic transfer function of the motion chain. Finally, a motion characteristic tensor that comprehensively describes the joint motion characteristics is generated in the four-dimensional space-time coordinate system.

[0075] In an embodiment of the present application, the existing three-dimensional biomechanical model and electromyographic synergy model are utilized and linked through mathematical modeling to create a dynamic system that can accurately represent the relationship between joint position changes and muscle activity intensity, and express it in the form of a tensor in a four-dimensional space-time coordinate system for subsequent analysis.

[0076] In the example of athletes, the motion characteristics of the knee are combined with the intensity of muscle activity to generate a comprehensive motion feature tensor, which allows the functional recovery of the knee to be observed from multiple dimensions.

[0077] 105. The evolution pattern of the motion characteristic tensor is analyzed in real time, and according to the difference in coupling strength among the acceleration period, the stabilization period and the deceleration period of the motion, a scoring function cluster with a time-varying topological structure is independently constructed, wherein each sub-function is nonlinearly superimposed through the motion chain energy transfer efficiency and the neural control stability index to generate a composite scoring value with motion quality diagnosis function.

[0078] In this step, the evolution pattern of the motion feature tensor is analyzed in real time, and a scoring function cluster is independently constructed according to the different characteristics of the acceleration, stabilization and deceleration periods of movement. Each sub-function achieves nonlinear superposition by considering the energy transfer efficiency of the motion chain and the stability of neural control, and finally generates a composite scoring value with diagnostic function.

[0079] In the embodiment of the present application, the characteristics of different movement stages are identified by continuous monitoring and analysis of the motion feature tensor, and the scoring criteria are automatically adjusted to ensure that each stage can be accurately evaluated. By integrating multiple evaluation indicators, a scoring system that comprehensively reflects the quality of joint movement is formed.

[0080] For athletes, this process helps give specific scores based on their performance in different stages of the sport, guiding their rehabilitation training to be more scientific and effective.

[0081] In summary, steps 101 to 105 cover the complete process from data collection, processing to analysis, aiming to provide a comprehensive and accurate intelligent scoring system for joint motion to meet personalized medical and rehabilitation needs and improve treatment outcomes and quality of life.

[0082] In order to solve the problem that traditional methods are difficult to accurately capture the physiological hysteresis effect in the process of processing joint movement, in some embodiments, the instantaneous rotation center drift of the joint in the three-dimensional biomechanical model is spatiotemporally coupled with the myoelectric coordination mode in step 104, and the differential constraint relationship between the joint posture change and the myoelectric activation intensity is established through the kinematic chain dynamics transfer function, and a motion feature tensor is generated in a four-dimensional spatiotemporal coordinate system, including:

[0083] Based on the dynamic transfer function of the kinematic chain, the instantaneous angular velocity covariant derivative of the instantaneous rotation center drift of the joint in the three-dimensional biomechanical model is aligned in time and space with the phase gradient of the electromyographic synergy mode to generate a dynamic coupling equation; wherein, the constraint conditions of the dynamic coupling equation are jointly calibrated by the joint ligament tension distribution model and the time domain attenuation rate of the surface electromyographic signal suppression waveform to ensure the physical dimension consistency of the kinematic parameters and the electromyographic parameters; in the four-dimensional space-time coordinate system, the output of the dynamic coupling equation is subjected to a tensor product operation with the propagation path of the joint multi-plane coupling error to generate an initial characteristic tensor field; wherein, the dimension of the tensor product operation is dynamically adjusted by the curvature change rate of the joint rotation center drift trajectory, so that the initial tensor field simultaneously encodes the energy propagation direction of the kinematic chain and the electromyographic phase synchronization; the viscoelastic coefficient matrix of the kinematic chain is calculated using the asymmetric distribution characteristics of the surface electromyographic signal energy gradient, and the initial tensor field is adaptively smoothed and filtered based on the viscoelastic coefficient matrix to generate a motion characteristic tensor containing a physiological hysteresis effect.

[0084] In this embodiment, the concept of kinematic chain dynamic transfer function is first introduced, which is used to describe the mechanical behavior of the joint during movement and its relationship with muscle activity; secondly, the dynamic coupling equation is generated by combining the instantaneous rotation center drift of the joint and the electromyographic coordination mode, and this equation can reflect the changes in the joint movement state; thirdly, the tensor product operation is used to combine the result of the dynamic coupling equation with the joint multi-plane coupling error to form an initial characteristic tensor field in a four-dimensional space-time coordinate system that can express the joint movement characteristics; finally, by analyzing the energy gradient of the surface electromyography signal, the viscoelastic coefficient matrix is ​​constructed and applied to the adaptive smoothing filter to compensate for the physiological hysteresis effect.

[0085] In an embodiment of the present application, first, sensors are used to acquire joint motion data and surface electromyographic signals; secondly, the rigid body motion and physiological tremor components are separated through dynamic inverse solution technology, and a three-dimensional biomechanical model is established; thirdly, the sampling strategy is adjusted according to the different stages of joint motion, and the behavior patterns of the active muscle groups and the antagonist muscle groups are identified; then, the joint motion is associated with the muscle activity in combination with the dynamic transfer function of the motion chain to form a dynamic coupling equation; then, this information is integrated through tensor product operations to generate a tensor field that describes the joint motion characteristics; finally, the adaptive filtering technology is used to process the initial tensor field to ensure that it can accurately reflect the physiological hysteresis effect.

[0086] Here is a specific example:

[0087] Suppose that a patient needs to evaluate the recovery of his knee after surgery. First, an inertial measurement unit (IMU) and a surface electromyography (sEMG) sensor are installed around the knee. The collected data are used to distinguish rigid body motion from physiological tremor and establish a three-dimensional biomechanical model. Then, the key kinematic parameter phase mutation points are identified according to the patient's movement pattern, and the signal window length is adjusted for segmentation. Next, the above information is used to generate dynamic coupling equations, and the results are combined with the multi-plane coupling errors of the joints to form the initial feature tensor field in the four-dimensional space-time coordinate system. Finally, the viscoelastic coefficient matrix is ​​calculated by analyzing the energy gradient of the surface electromyography signal, and applied to the adaptive smoothing filter to generate a motion feature tensor containing the physiological hysteresis effect. Through the above steps, not only can the recovery of the patient's knee be understood in detail, but also personalized rehabilitation suggestions can be provided to accelerate the rehabilitation process.

[0088] In order to further improve the accuracy of capturing physiological hysteresis effects in joint motion analysis, in some embodiments, the method of calculating the viscoelastic coefficient matrix of the kinematic chain using the asymmetric distribution characteristics of the energy gradient of the surface electromyography signal includes:

[0089] An energy gradient covariance tensor is constructed based on the phase gradient distribution of the electromyographic synergy mode, and the covariance tensor is anisotropically weighted by the curvature change rate of the drift trajectory of the joint rotation center in the three-dimensional biomechanical model to generate an initial viscoelastic parameter set with the energy propagation direction characteristics of the motion chain; the initial viscoelastic parameter set is input into a convolution kernel function constructed based on the time domain attenuation rate of the surface electromyographic signal suppression waveform, and the frequency domain response characteristics corresponding to the joint ligament tension distribution model are extracted through a multi-scale sliding window, and the parameters are normalized in combination with the constraints of the dynamic coupling equation to form a frequency domain mapping relationship of the viscoelastic coefficient matrix; the initial viscoelastic parameter set is input into a convolution kernel function constructed based on the time domain attenuation rate of the surface electromyographic signal suppression waveform, and the frequency domain response characteristics corresponding to the joint ligament tension distribution model are extracted through a multi-scale sliding window, and the parameters are normalized in combination with the constraints of the dynamic coupling equation to form a frequency domain mapping relationship of the viscoelastic coefficient matrix; The tensor field is adaptively smoothed and filtered to generate a motion feature tensor containing a physiological hysteresis effect, including: establishing a bandwidth adjustment factor of the tensor field filter according to the frequency domain mapping relationship, dynamically matching the coupling weight of the energy propagation direction of the motion chain and the electromyography phase synchronization using the asymmetric distribution characteristics of the surface electromyography signal energy gradient, and generating an adaptive filter kernel with a physiological hysteresis compensation effect; performing multi-channel parallel convolution operations on the initial feature tensor field through the adaptive filter kernel, synchronously fusing the propagation path curvature parameters of the multi-plane coupling error of the joint, and iteratively updating the energy distribution topological structure of the motion feature tensor to generate a motion feature tensor containing a physiological hysteresis effect.

[0090] In this embodiment, the concept of energy gradient covariance tensor is first introduced, which is used to describe the energy changes and spatial distribution in electromyographic activity; secondly, the above tensor is anisotropically weighted by considering the curvature change rate of the drift trajectory of the joint rotation center, so as to obtain an initial viscoelastic parameter set reflecting the energy propagation direction characteristics of the motion chain; thirdly, the convolution kernel function is designed by using the time domain attenuation rate of the suppressed waveform of the surface electromyographic signal, and the corresponding frequency domain features are extracted by the multi-scale sliding window technology; finally, an adaptive filtering method is used to adjust the bandwidth of the tensor field filter based on the above information to achieve accurate compensation for the physiological hysteresis effect.

[0091] In an embodiment of the present application, first, the phase gradient distribution of the electromyographic synergy mode is used to construct an energy gradient covariance tensor; secondly, the tensor is anisotropically weighted based on the curvature change rate of the drift trajectory of the joint rotation center to generate an initial viscoelastic parameter set; again, these parameters are input into a convolution kernel function constructed by the time domain attenuation rate of the surface electromyographic signal suppression waveform, the frequency domain response characteristics are extracted through a multi-scale sliding window, and the parameters are normalized in combination with the constraints of the dynamic coupling equation; then, the bandwidth adjustment factor of the tensor field filter is set according to the obtained frequency domain mapping relationship; then, the filter kernel is adjusted using the asymmetric distribution characteristics of the energy gradient of the surface electromyographic signal so that it can match the coupling weight of the energy propagation direction of the motion chain and the electromyographic phase synchronization; finally, the adaptive filter kernel is applied to perform multi-channel parallel convolution operations on the initial feature tensor field, and the propagation path curvature parameters of the multi-plane coupling error of the joint are synchronously integrated to generate the final motion feature tensor.

[0092] Here is a specific example:

[0093] Assuming that the knee rehabilitation of an athlete needs to be evaluated, an inertial measurement unit (IMU) and surface electromyography (sEMG) sensors are first installed around the knee. After collecting data, an energy gradient covariance tensor is constructed based on the phase gradient distribution of the electromyography synergy pattern. Subsequently, the covariance tensor is anisotropically weighted according to the curvature change rate of the drift trajectory of the joint rotation center to generate an initial viscoelastic parameter set. Next, these parameters are input into a convolution kernel function constructed by the time domain attenuation rate of the surface electromyography signal suppression waveform, and the frequency domain response features are extracted through a multi-scale sliding window, and the parameters are normalized. After that, the bandwidth adjustment factor of the tensor field filter is set according to the obtained frequency domain mapping relationship. The filter kernel is adjusted using the asymmetric distribution characteristics of the energy gradient of the surface electromyography signal so that it can match the coupling weight of the energy propagation direction of the motion chain and the electromyography phase synchronization. Finally, an adaptive filter kernel is applied to perform multi-channel parallel convolution operations on the initial feature tensor field to synchronously integrate the propagation path curvature parameters of the multi-plane coupling error of the joint. By following the above steps, we can not only understand the athlete's knee recovery in detail, but also provide them with personalized rehabilitation suggestions to accelerate their recovery process.

[0094] In order to further improve the accuracy and personalization of joint motion quality assessment, in some embodiments, the real-time analysis of the evolution pattern of the motion feature tensor autonomously constructs a scoring function cluster with a time-varying topological structure according to the difference in coupling strength between the acceleration period, the stable period and the deceleration period of the motion, wherein each sub-function is nonlinearly superimposed through the energy transfer efficiency of the motion chain and the neural control stability index to generate a composite scoring value with motion quality diagnosis function, including:

[0095] In the motion feature tensor, according to the phase boundary mark output by the motion stage recognition module, the distribution of manifold curvature extreme points is extracted along the energy propagation path, and the covariance matrix of the manifold curvature change rate and the electromyographic phase synchronization stability in each motion stage is calculated to generate an energy dissipation spatiotemporal map; wherein, the detection rule of the manifold curvature extreme points is dynamically defined by the amplitude-frequency characteristics of the joint multi-plane coupling error; in the neural control timing feature space, the abnormal area in the energy dissipation spatiotemporal map is mapped to the time-frequency overlapping interval of the electromyographic inhibition waveform, and based on the hysteresis effect parameters output by the viscoelastic correction model of the motion chain, a variable-dimensional spatiotemporal map is generated. A set of sub-functions with different degrees of weight; wherein the topological structure of the sub-functions is dynamically constructed by the Hausdorff dimension of the drift trajectory of the joint rotation center, and the coupling weights between the sub-functions are calculated by the mutual information entropy of the electromyographic phase delay and the energy propagation efficiency of the motion chain; the output values ​​of the sub-function set are integrated along the energy propagation path of the motion chain through a topological integral algorithm to generate a composite score value reflecting the coordination of joint motion; at the same time, the composite score value is compared with the physiological consistency threshold of the motion feature tensor, and the iterative step size of the dynamic calibration factor is dynamically adjusted through the back-propagation mechanism to achieve closed-loop optimization.

[0096] In this embodiment, the concept of energy dissipation spatiotemporal map is first introduced, which is used to describe the changes in energy distribution during joint movement and its relationship with the synchronization of muscle activity; secondly, the amplitude-frequency characteristics of the multi-plane coupling error of the joint are used to dynamically define the detection rules of the extreme points of manifold curvature, ensuring the accurate capture of subtle joint movements; thirdly, by analyzing the relationship between the electromyographic inhibition waveform and the time-frequency overlapping interval, combined with the viscoelastic correction model of the motion chain, effective identification of abnormal motion areas is achieved; finally, the topological integral algorithm is used to process the above information to generate a composite score value that can comprehensively reflect the coordination of joint movement.

[0097] In an embodiment of the present application, first, the phase boundary markers of different motion stages (acceleration, stability, deceleration) are identified from the motion feature tensor; secondly, the distribution of manifold curvature extreme points is extracted along the energy propagation path, and the covariance matrix of its rate of change and the stability of electromyographic phase synchronization is calculated to form an energy dissipation space-time map; thirdly, in the neural control timing feature space, the abnormal areas in the energy dissipation space-time map are mapped to the time-frequency overlapping interval of the electromyographic inhibition waveform, and a set of sub-functions with variable dimensional weights is generated based on the hysteresis effect parameters output by the viscoelastic correction model of the motion chain; then, the coupling weights between the sub-functions are dynamically adjusted according to the Hausdorff dimension of the drift trajectory of the joint rotation center; finally, the outputs of these sub-functions are integrated through a topological integral algorithm to generate a composite score value reflecting the coordination of joint motion, and closed-loop optimization is performed through a back-propagation mechanism.

[0098] Here is a specific example:

[0099] Suppose that the recovery of an athlete after knee surgery needs to be evaluated. First, an inertial measurement unit (IMU) and a surface electromyography (sEMG) sensor are installed around the knee. After collecting data, the phase boundary markers of different movement stages are identified. Then, the distribution of manifold curvature extreme points is extracted along the energy propagation path, and the covariance matrix of the manifold curvature change rate and the electromyography phase synchronization stability in each movement stage is calculated to generate an energy dissipation spatiotemporal map. Subsequently, in the neural control temporal feature space, the abnormal areas in the energy dissipation spatiotemporal map are mapped to the time-frequency overlapping interval of the electromyography inhibition waveform, and a set of sub-functions with variable dimensional weights is generated based on the hysteresis effect parameters output by the viscoelastic correction model of the kinematic chain. Then, the coupling weights between the sub-functions are dynamically adjusted according to the Hausdorff dimension of the drift trajectory of the joint rotation center. Finally, the outputs of these sub-functions are integrated through a topological integral algorithm to generate a composite score reflecting the coordination of joint movement, which is compared with the physiological consistency threshold of the motion feature tensor, and the iterative step size of the dynamic calibration factor is dynamically adjusted through the back-propagation mechanism. By following the above steps, we can not only understand the athlete's knee recovery in detail, but also provide them with personalized rehabilitation suggestions to accelerate their recovery process.

[0100] In order to further improve the accuracy of identifying abnormal areas during joint movement and generate a set of sub-functions that can adapt to different dimensional weights, in some embodiments, in the neural control time series feature space, the abnormal area in the energy dissipation spatiotemporal map is mapped to the time-frequency overlapping interval of the electromyographic inhibition waveform, and based on the hysteresis effect parameters output by the viscoelastic correction model of the kinematic chain, a set of sub-functions with variable dimensional weights is generated, including:

[0101] A time-frequency mask matrix is ​​constructed based on the boundary features of the abnormal area of ​​the energy dissipation spatiotemporal map, and the mask matrix is ​​phase-delayed compensated by the hysteresis effect parameters of the viscoelastic correction model of the kinematic chain to generate a time-frequency overlapping feature vector with a kinematic chain energy propagation direction constraint; the time-frequency overlapping feature vector is input into a topological mapping network constructed based on the mutual information entropy of electromyographic phase delay and kinematic chain energy propagation efficiency, and the network interlayer connection weights are dynamically adjusted by using the Hausdorff dimension of the drift trajectory of the joint rotation center, and a sub-function initial weight set containing variable dimensional parameters is output; the generation of a sub-function set with variable dimensional weights includes: constructing a multidimensional weight distribution function according to the sub-function initial weight set and the time-frequency attenuation characteristics of the electromyographic inhibition waveform, dynamically truncating and filtering the distribution function by the physiological consistency threshold of the motion feature tensor, and generating a sub-function dimension adjustment factor that satisfies the viscoelastic constraint of the kinematic chain; the output of the topological mapping network is nonlinearly interpolated and reconstructed by using the dimensional adjustment factor, and the manifold curvature change rate covariance matrix features of the energy dissipation spatiotemporal map are synchronously integrated to iteratively generate a sub-function set with a time-varying topological structure.

[0102] In this embodiment, the concept of time-frequency mask matrix is ​​first introduced, which is used to mark and process abnormal areas in the energy dissipation spatiotemporal map; secondly, the phase delay of these abnormal areas is adjusted by combining the hysteresis effect parameters of the viscoelastic correction model of the motion chain to ensure that it can accurately reflect the energy propagation direction of the motion chain; thirdly, the topological mapping network is used to dynamically adjust the connection weights between network layers to adapt to different motion modes; finally, a multidimensional weight allocation function and nonlinear interpolation reconstruction technology are used to generate a set of sub-functions with adaptive dimensional weights.

[0103] In an embodiment of the present application, first, a time-frequency mask matrix is ​​constructed according to the boundary features of the abnormal area of ​​the energy dissipation space-time map; secondly, the hysteresis effect parameters of the viscoelastic correction model of the motion chain are used to compensate the phase delay of the mask matrix, and a time-frequency overlapping feature vector with a constraint on the energy propagation direction of the motion chain is generated; again, these feature vectors are input into a topological mapping network constructed based on the mutual information entropy of the electromyographic phase delay and the energy propagation efficiency of the motion chain, and the connection weights between the network layers are dynamically adjusted using the Hausdorff dimension of the drift trajectory of the joint rotation center; then, a multidimensional weight allocation function is constructed based on the initial weight set of the sub-function and the time-frequency attenuation characteristics of the electromyographic inhibition waveform, and it is dynamically truncated and filtered through the physiological consistency threshold of the motion feature tensor; finally, the output of the topological mapping network is nonlinearly interpolated and reconstructed using the generated dimensionality adjustment factor, and the manifold curvature change rate covariance matrix features of the energy dissipation space-time map are synchronously integrated to iteratively generate a set of sub-functions with a time-varying topological structure.

[0104] Here is a specific example:

[0105] Suppose that the recovery of a patient after knee surgery needs to be evaluated. First, an inertial measurement unit (IMU) and a surface electromyography (sEMG) sensor are installed around the knee. After collecting data, a time-frequency mask matrix is ​​constructed based on the boundary features of the abnormal area of ​​the energy dissipation spatiotemporal map. Then, the mask matrix is ​​phase-delayed compensated using the hysteresis effect parameters of the viscoelastic correction model of the kinematic chain to generate time-frequency overlapping feature vectors with constraints on the energy propagation direction of the kinematic chain. Subsequently, these feature vectors are input into a topological mapping network constructed based on the mutual information entropy of the electromyographic phase delay and the energy propagation efficiency of the kinematic chain, and the connection weights between network layers are dynamically adjusted using the Hausdorff dimension of the drift trajectory of the joint rotation center. Then, a multidimensional weight allocation function is constructed based on the initial weight set of the sub-function and the time-frequency attenuation characteristics of the electromyographic inhibition waveform, and it is dynamically truncated and filtered through the physiological consistency threshold of the motion feature tensor. Finally, the output of the topological mapping network is nonlinearly interpolated and reconstructed using the generated dimensionality adjustment factor, and the covariance matrix features of the manifold curvature change rate of the energy dissipation spatiotemporal map are synchronously fused to iteratively generate a set of sub-functions with a time-varying topological structure. Through the above steps, we can not only understand the patient's knee recovery status in detail, but also provide them with personalized rehabilitation training suggestions to accelerate their recovery process.

[0106] In order to further improve the accuracy and physiological consistency of joint motion analysis, some embodiments further include:

[0107] The topological invariance index of the energy propagation path in the motion feature tensor is extracted, and nonlinearly mapped with the phase synchronization stability of the electromyographic synergy pattern to generate a dynamic calibration factor; the dynamic calibration factor is fed back into the constraint conditions of the dynamic coupling equation through an iterative optimization algorithm until the energy propagation path of the motion feature tensor and the time-frequency distribution of the electromyographic inhibition waveform reach a preset physiological consistency threshold.

[0108] In this embodiment, the concept of topological invariance indicators is first introduced, which is used to describe the stability characteristics of energy propagation paths during movement; secondly, these topological invariance indicators are combined with the phase synchronization stability of the electromyographic synergy pattern through a nonlinear mapping method to generate a dynamic calibration factor that can reflect the relationship between the two; finally, the dynamic calibration factor is continuously adjusted using an iterative optimization algorithm and fed back into the dynamic coupling equation to ensure that the final result meets the preset physiological consistency standard.

[0109] In an embodiment of the present application, first, the topological invariance index of the energy propagation path is extracted from the motion feature tensor; secondly, a nonlinear mapping is performed based on these indexes and the phase synchronization stability of the electromyographic synergy pattern to generate a dynamic calibration factor; thirdly, an iterative optimization algorithm is used to feedback the dynamic calibration factor into the constraint conditions of the dynamic coupling equation; then, the parameters are gradually adjusted so that the time-frequency distribution of the energy propagation path of the motion feature tensor and the electromyographic inhibition waveform gradually approaches a preset physiological consistency threshold; finally, when the preset conditions are met, the iteration is stopped to complete the entire calibration process.

[0110] Here is a specific example:

[0111] Suppose that the recovery of an athlete after knee surgery needs to be evaluated. First, an inertial measurement unit (IMU) and a surface electromyography (sEMG) sensor are installed around the knee. After collecting data, the topological invariance index of the energy propagation path is extracted from the motion feature tensor. Then, a nonlinear mapping is performed based on these indexes and the phase synchronization stability of the electromyographic synergy pattern to generate a dynamic calibration factor. Subsequently, the dynamic calibration factor is fed back into the constraints of the dynamic coupling equation using an iterative optimization algorithm. Then, the parameters are gradually adjusted so that the energy propagation path of the motion feature tensor and the time-frequency distribution of the electromyographic inhibition waveform gradually approach the preset physiological consistency threshold. In this process, continuous monitoring and adjustment are performed until the difference between the two is minimized. Finally, when all conditions meet the preset criteria, the iteration is terminated to obtain the final calibration result. Through the above steps, not only can the recovery of the athlete's knee be understood in detail, but also personalized rehabilitation training suggestions can be provided to accelerate the recovery process.

[0112] In order to further improve the understanding of the relationship between surface electromyographic signals and exercise loads, and accurately extract muscle synergy patterns, in some embodiments, the time-varying mapping relationship between surface electromyographic signals and exercise loads is constructed, the surface electromyographic signals are segmented with asymmetric window lengths based on the phase mutation points of kinematic parameters, a phase synchronization quantification model of the active muscle group contraction waveform and the antagonist muscle group inhibition waveform is established within the segmentation interval, and the muscle synergy pattern across the exercise cycle is extracted by analyzing the energy gradient field of the surface electromyographic signals, including:

[0113] A dynamic window length adjustment factor is constructed based on the phase mutation point detection result of the kinematic parameters, and the time-frequency energy mutation characteristics of the surface electromyographic signal at the phase mutation point are extracted by the wavelet transform modulus maximum detection algorithm to generate a surface electromyographic signal segmentation index with an asymmetric window length segmentation boundary; the original surface electromyographic signal is dynamically windowed according to the surface electromyographic signal segmentation index, and the signal segments of the agonist muscle group and the antagonist muscle group are asymmetricly aligned in the time domain using the dynamic window length adjustment factor to generate a segmentation interval containing a phase synchronization analysis benchmark point; the surface muscle segments of the agonist muscle group and the antagonist muscle group are respectively extracted by using the Hilbert-Huang transform in the segmentation interval. The instantaneous phase difference sequence of the electrical signal is combined with the dynamic window length adjustment factor to construct a phase difference mutual information entropy matrix, and the entropy matrix is ​​dynamically weighted by the curvature parameter of the motion chain energy propagation path to generate a phase synchronization index reflecting the stability of neural control; an energy gradient covariance tensor is constructed based on the segmented index of the surface electromyography signal in the segmented interval, and the phase synchronization index is decomposed into principal components along the energy propagation direction of the motion chain to extract the principal component vector that characterizes the cross-cycle synergy feature, and the principal component vector is normalized for the motion chain energy through the amplitude-frequency characteristics of the multi-plane coupling error in the three-dimensional biomechanical model to generate a feature set corresponding to the neuromuscular synergy pattern.

[0114] In this embodiment, the concept of a dynamic window length adjustment factor is first introduced, which is used to adjust the segmentation window length of the surface electromyographic signal according to the phase mutation point of the kinematic parameters; secondly, the key time points in the surface electromyographic signal are identified by the wavelet transform modulus maximum detection algorithm to generate asymmetric window length segmentation boundaries; thirdly, these boundaries are used to segment the original signal and perform asymmetric time domain alignment to ensure that the signal segments of the agonist muscle group and the antagonist muscle group can be correctly matched; finally, the instantaneous phase difference of each muscle group is analyzed by the Hilbert-Huang transform, and the cross-cycle muscle synergy pattern is extracted in combination with the energy gradient covariance tensor.

[0115] In an embodiment of the present application, a dynamic window length adjustment factor is first constructed based on the phase mutation point detection results of the kinematic parameters; secondly, a wavelet transform modulus maximum detection algorithm is used to identify key time points in the surface electromyographic signal, and a surface electromyographic signal segmentation index with an asymmetric window length segmentation boundary is generated; thirdly, the original surface electromyographic signal is dynamically windowed according to these indexes, and the dynamic window length adjustment factor is used to perform asymmetric time domain alignment on the signal segments of the agonist muscle group and the antagonist muscle group; then, the Hilbert-Huang transform is used to extract the surface electromyographic signals of the agonist muscle group and the antagonist muscle group in each segmentation interval. The instantaneous phase difference sequence is combined with the dynamic window length adjustment factor to construct the phase difference mutual information entropy matrix; then, the entropy matrix is ​​dynamically weighted by the curvature parameter of the energy propagation path of the motion chain to generate a phase synchronization index reflecting the stability of neural control; finally, the energy gradient covariance tensor is constructed based on the segmented index of the surface electromyography signal in the segmentation interval, and the principal component decomposition is performed along the energy propagation direction of the motion chain to extract the principal component vector representing the cross-cycle synergy characteristics, and the motion chain energy is normalized by the amplitude-frequency characteristics of the multi-plane coupling error in the three-dimensional biomechanical model to generate a feature set corresponding to the neuromuscular synergy pattern.

[0116] Here is a specific example:

[0117] Suppose that the recovery of an athlete after knee surgery needs to be evaluated. First, an inertial measurement unit (IMU) and a surface electromyography (sEMG) sensor are installed around the knee. After collecting data, a dynamic window length adjustment factor is constructed based on the phase mutation point detection results of kinematic parameters. Then, the wavelet transform modulus maximum detection algorithm is used to identify the key time points in the surface electromyography signal, and a surface electromyography signal segmentation index with asymmetric window length segmentation boundaries is generated. Subsequently, the original surface electromyography signal is dynamically windowed according to these indexes, and the signal segments of the agonist and antagonist muscle groups are asymmetricly aligned in the time domain using the dynamic window length adjustment factor. Then, the Hilbert algorithm is used in each segmentation interval. -Huang transform extracts the instantaneous phase difference sequence of the surface electromyographic signals of the agonist and antagonist muscle groups, and combines the dynamic window length adjustment factor to construct the phase difference mutual information entropy matrix; next, the entropy matrix is ​​dynamically weighted by the curvature parameter of the energy propagation path of the motion chain to generate a phase synchronization index reflecting the stability of neural control; on this basis, the energy gradient covariance tensor is constructed based on the segmented index of the surface electromyographic signal in the segmented interval, and the principal component decomposition is performed along the energy propagation direction of the motion chain to extract the principal component vector representing the cross-cycle synergy feature, and the motion chain energy is normalized by the amplitude-frequency characteristics of the multi-plane coupling error in the three-dimensional biomechanical model to generate the feature set corresponding to the neuromuscular synergy mode. Through the above steps, not only can the recovery status of the athlete's knee be understood in detail, but also personalized rehabilitation training suggestions can be provided to accelerate their rehabilitation process.

[0118] Figure 2 A structural diagram of a joint motion intelligent scoring system is provided for an embodiment of the present application, such as Figure 2 As shown, the device comprises:

[0119] Establishing module 21, for collecting six degrees of freedom inertial motion data and surface electromyographic signals of the target joint motion chain, and establishing a motion sequence topology structure including spatiotemporal reference markers based on a joint motion phase-triggered dynamic sampling strategy;

[0120] A generating module 22, for decomposing the inertial motion data into a rigid body motion component and a physiological tremor component, and generating a three-dimensional biomechanical model including the instantaneous rotation center drift of the joint, multi-plane coupling error and motion trajectory curvature through dynamic inverse solution;

[0121] Processing module 23, used to construct a time-varying mapping relationship between surface electromyographic signals and exercise load, perform asymmetric window length segmentation on the surface electromyographic signals based on the phase mutation points of kinematic parameters, establish a phase synchronization quantification model of the active muscle group contraction waveform and the antagonist muscle group inhibition waveform within the segmentation interval, and extract the muscle coordination pattern across the exercise cycle through surface electromyographic signal energy gradient field analysis;

[0122] The generation module is also used to couple the instantaneous rotation center drift of the joint in the three-dimensional biomechanical model with the electromyographic coordination mode in time and space, establish the differential constraint relationship between the joint posture change and the electromyographic activation intensity through the motion chain dynamics transfer function, and generate a motion feature tensor in a four-dimensional space-time coordinate system; analyze the evolution pattern of the motion feature tensor in real time, and independently construct a scoring function cluster with a time-varying topological structure according to the difference in coupling intensity between the acceleration period, the stable period and the deceleration period of the movement, wherein each sub-function is nonlinearly superimposed through the motion chain energy transfer efficiency and the neural control stability index to generate a composite scoring value with motion quality diagnosis function.

[0123] Figure 2 The joint motion intelligent scoring device can perform Figure 1 The implementation principle and technical effect of the joint motion intelligent scoring method described in the illustrated embodiment will not be described in detail. The specific manner in which each module and unit performs operations in the joint motion intelligent scoring device in the above embodiment has been described in detail in the embodiment of the method, and will not be described in detail here.

[0124] In one possible design, Figure 2 The joint motion intelligent scoring device of the embodiment shown can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0125] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0126] The processing component 32 is used for the above Figure 1 The joint movement intelligent scoring method of the embodiment.

[0127] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0128] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0129] Of course, the computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0130] The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc.

[0131] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0132] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0133] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 The joint motion intelligent scoring method of the illustrated embodiment.

[0134] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0135] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0136] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0137] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A joint motion intelligent scoring method, characterized in that: include: Collect the six-degree-of-freedom inertial motion data and surface electromyography signals of the target joint motion chain, and establish a motion sequence topology structure containing spatiotemporal reference markers based on the joint motion phase-triggered dynamic sampling strategy; Decomposing the inertial motion data into a rigid body motion component and a physiological tremor component, and generating a three-dimensional biomechanical model including the instantaneous rotation center drift of the joint, multi-plane coupling errors and motion trajectory curvature through dynamic inverse solution; The time-varying mapping relationship between surface electromyographic signals and exercise load was constructed, and the surface electromyographic signals were segmented by asymmetric window length based on the phase mutation points of kinematic parameters. A phase synchronization quantitative model of the active muscle group contraction waveform and the antagonist muscle group inhibition waveform was established within the segmentation interval. The muscle coordination pattern across the exercise cycle was extracted by analyzing the energy gradient field of the surface electromyographic signals. The instantaneous rotation center drift of the joint in the three-dimensional biomechanical model is coupled with the electromyographic coordination mode in time and space, and the differential constraint relationship between the joint posture change and the electromyographic activation intensity is established through the kinematic chain dynamics transfer function, and the motion characteristic tensor is generated in the four-dimensional space-time coordinate system; The evolution pattern of the motion feature tensor is analyzed in real time, and a scoring function cluster with a time-varying topological structure is independently constructed according to the difference in coupling strength among the acceleration, stabilization and deceleration periods of the motion. Each sub-function is nonlinearly superimposed with the energy transfer efficiency of the motion chain and the neural control stability index to generate a composite scoring value with motion quality diagnosis function.

2. The joint motion intelligent scoring method according to claim 1, characterized in that: The instantaneous rotation center drift of the joint in the three-dimensional biomechanical model is coupled with the electromyographic coordination mode in time and space, and the differential constraint relationship between the joint posture change and the electromyographic activation intensity is established through the kinematic chain dynamics transfer function, and the motion feature tensor is generated in the four-dimensional space-time coordinate system, including: Based on the dynamic transfer function of the kinematic chain, the instantaneous angular velocity covariant derivative of the instantaneous rotation center drift of the joint in the three-dimensional biomechanical model is aligned in time and space with the phase gradient of the electromyographic synergy mode to generate a dynamic coupling equation; wherein, the constraint conditions of the dynamic coupling equation are jointly calibrated by the joint ligament tension distribution model and the time domain attenuation rate of the surface electromyographic signal inhibition waveform to ensure the physical dimension consistency of the kinematic parameters and the electromyographic parameters; In a four-dimensional space-time coordinate system, a tensor product operation is performed on the output of the dynamic coupling equation and the propagation path of the multi-plane coupling error of the joint to generate an initial characteristic tensor field; wherein the dimension of the tensor product operation is dynamically adjusted by the curvature change rate of the drift trajectory of the joint rotation center, so that the initial tensor field simultaneously encodes the energy propagation direction of the motion chain and the electromyographic phase synchronization; The asymmetric distribution characteristics of the energy gradient of the surface electromyography signal are used to calculate the viscoelastic coefficient matrix of the kinematic chain, and the initial tensor field is adaptively smoothed and filtered based on the viscoelastic coefficient matrix to generate a motion feature tensor containing a physiological hysteresis effect.

3. The method according to claim 2, characterized in that The method of calculating the viscoelastic coefficient matrix of the kinematic chain by utilizing the asymmetric distribution characteristics of the energy gradient of the surface electromyography signal includes: An energy gradient covariance tensor is constructed based on the phase gradient distribution of the electromyographic synergy mode, and the covariance tensor is anisotropically weighted by the curvature change rate of the drift trajectory of the joint rotation center in the three-dimensional biomechanical model to generate an initial viscoelastic parameter set with kinematic chain energy propagation direction characteristics; The initial viscoelastic parameter set is input into a convolution kernel function constructed based on the time domain attenuation rate of the surface electromyography signal suppression waveform, the frequency domain response characteristics corresponding to the joint ligament tension distribution model are extracted through a multi-scale sliding window, and the parameters are normalized in combination with the constraint conditions of the dynamic coupling equation to form a frequency domain mapping relationship of the viscoelastic coefficient matrix; The step of performing adaptive smoothing filtering on the initial tensor field based on the viscoelastic coefficient matrix to generate a motion feature tensor containing a physiological hysteresis effect comprises: A bandwidth adjustment factor of a tensor field filter is established according to the frequency domain mapping relationship, and a coupling weight of the energy propagation direction of the motion chain and the electromyographic phase synchronization is dynamically matched by utilizing the asymmetric distribution characteristics of the surface electromyographic signal energy gradient to generate an adaptive filter kernel with a physiological hysteresis compensation effect; The initial feature tensor field is subjected to multi-channel parallel convolution operation through the adaptive filter kernel, the propagation path curvature parameters of the multi-plane coupling error of the joint are synchronously integrated, and the energy distribution topological structure of the motion feature tensor is iteratively updated to generate a motion feature tensor containing physiological hysteresis effect.

4. The joint motion intelligent scoring method according to claim 1, characterized in that: The real-time analysis of the evolution mode of the motion feature tensor autonomously constructs a scoring function cluster with a time-varying topological structure according to the difference in coupling strength between the motion acceleration period, the stable period and the deceleration period, wherein each sub-function is nonlinearly superimposed through the motion chain energy transfer efficiency and the neural control stability index to generate a composite scoring value with motion quality diagnosis function, including: In the motion feature tensor, according to the phase boundary mark output by the motion stage recognition module, the distribution of manifold curvature extreme points is extracted along the energy propagation path, and the covariance matrix of the manifold curvature change rate and the electromyographic phase synchronization stability in each motion stage is calculated to generate an energy dissipation spatiotemporal map; wherein the detection rule of the manifold curvature extreme points is dynamically defined by the amplitude-frequency characteristics of the multi-plane coupling error of the joint; In the neural control time series feature space, the abnormal area in the energy dissipation spatiotemporal map is mapped to the time-frequency overlapping interval of the electromyographic inhibition waveform, and a set of sub-functions with variable dimensional weights is generated based on the hysteresis effect parameters output by the viscoelastic correction model of the kinematic chain. The topological structure of the sub-function is dynamically constructed by the Hausdorff dimension of the drift trajectory of the joint rotation center, and the coupling weights between the sub-functions are calculated by the mutual information entropy of the electromyographic phase delay and the energy transmission efficiency of the kinematic chain. The output values ​​of the sub-function set are integrated along the energy propagation path of the motion chain through a topological integral algorithm to generate a composite score value reflecting the coordination of joint movement; at the same time, the composite score value is compared with the physiological consistency threshold of the motion feature tensor, and the iterative step size of the dynamic calibration factor is dynamically adjusted through the back-propagation mechanism to achieve closed-loop optimization.

5. The method according to claim 4, characterized in that In the neural control time series feature space, the abnormal area in the energy dissipation spatiotemporal map is mapped to the time-frequency overlapping interval of the electromyographic inhibition waveform, and a sub-function set with variable dimensional weights is generated based on the hysteresis effect parameters output by the viscoelastic correction model of the kinematic chain, including: A time-frequency mask matrix is ​​constructed based on the boundary features of the abnormal region of the energy dissipation spatiotemporal map, and the mask matrix is ​​phase-delay compensated by the hysteresis effect parameters of the kinematic chain viscoelastic correction model to generate a time-frequency overlapping feature vector with a kinematic chain energy propagation direction constraint; The time-frequency overlapping feature vector is input into a topological mapping network constructed based on the mutual information entropy of electromyographic phase delay and kinematic chain energy transmission efficiency, the Hausdorff dimension of the joint rotation center drift trajectory is used to dynamically adjust the network layer connection weights, and an initial weight set of a sub-function containing variable dimensional parameters is output; The generating of a sub-function set with variable dimensional weights comprises: A multidimensional weight distribution function is constructed according to the sub-function initial weight set and the time-frequency attenuation characteristics of the electromyographic inhibition waveform, and the distribution function is dynamically truncated and filtered through the physiological consistency threshold of the motion feature tensor to generate a sub-function dimension adjustment factor that satisfies the viscoelastic constraint of the motion chain; The output of the topological mapping network is reconstructed by nonlinear interpolation using the dimension adjustment factor, and the covariance matrix characteristics of the manifold curvature change rate of the energy dissipation space-time map are synchronously integrated to iteratively generate a set of sub-functions with a time-varying topological structure.

6. The method according to claim 2, characterized in that Also includes: The topological invariance index of the energy propagation path in the motion feature tensor is extracted and nonlinearly mapped with the phase synchronization stability of the electromyographic synergy pattern to generate a dynamic calibration factor. The dynamic calibration factor is fed back into the constraint condition of the dynamic coupling equation through an iterative optimization algorithm until the energy propagation path of the motion feature tensor and the time-frequency distribution of the electromyographic inhibition waveform reach a preset physiological consistency threshold.

7. The method according to claim 1, characterized in that The method constructs a time-varying mapping relationship between surface electromyographic signals and exercise load, performs asymmetric window length segmentation on the surface electromyographic signals based on the phase mutation points of kinematic parameters, establishes a phase synchronization quantification model of the active muscle group contraction waveform and the antagonist muscle group inhibition waveform within the segmentation interval, and extracts the muscle coordination pattern across the exercise cycle through surface electromyographic signal energy gradient field analysis, including: A dynamic window length adjustment factor is constructed based on the phase mutation point detection result of the kinematic parameters, and the time-frequency energy mutation characteristics of the surface electromyographic signal at the phase mutation point are extracted by a wavelet transform modulus maximum detection algorithm to generate a surface electromyographic signal segmentation index with an asymmetric window length segmentation boundary; Dynamically window the original surface electromyographic signal according to the surface electromyographic signal segmentation index, and asymmetrically align the signal segments of the agonist muscle group and the antagonist muscle group in the time domain using the dynamic window length adjustment factor to generate a segmentation interval containing a phase synchronization analysis reference point; In the segmented interval, the instantaneous phase difference sequence of the surface electromyographic signals of the agonist muscle group and the antagonist muscle group is extracted by using the Hilbert-Huang transform, and the phase difference mutual information entropy matrix is ​​constructed in combination with the dynamic window length adjustment factor. The entropy matrix is ​​dynamically weighted by the curvature parameter of the energy propagation path of the motion chain to generate a phase synchronization index reflecting the stability of neural control; An energy gradient covariance tensor is constructed based on the segmented index of the surface electromyographic signal in the segmented interval, and the phase synchronization index is decomposed into principal components along the energy propagation direction of the motion chain to extract the principal component vector that characterizes the cross-cycle synergy feature. The principal component vector is normalized for the motion chain energy through the amplitude-frequency characteristics of the multi-plane coupling error in the three-dimensional biomechanical model to generate a feature set corresponding to the neuromuscular synergy pattern.

8. An intelligent scoring system for joint motion, characterized in that: include: Establish a module for collecting six-degree-of-freedom inertial motion data and surface electromyographic signals of the target joint motion chain, trigger a dynamic sampling strategy based on the joint motion phase, and establish a motion sequence topology structure containing spatiotemporal reference markers; A generation module, used for decomposing the inertial motion data into a rigid body motion component and a physiological tremor component, and generating a three-dimensional biomechanical model including the instantaneous rotation center drift of the joint, multi-plane coupling error and motion trajectory curvature through dynamic inverse solution; A processing module is used to construct a time-varying mapping relationship between surface electromyographic signals and exercise load, perform asymmetric window length segmentation on the surface electromyographic signals based on the phase mutation points of kinematic parameters, establish a phase synchronization quantitative model of the active muscle group contraction waveform and the antagonist muscle group inhibition waveform within the segmentation interval, and extract the muscle coordination pattern across the exercise cycle through the surface electromyographic signal energy gradient field analysis; The generation module is also used to couple the instantaneous rotation center drift of the joint in the three-dimensional biomechanical model with the electromyographic coordination mode in time and space, establish the differential constraint relationship between the joint posture change and the electromyographic activation intensity through the motion chain dynamics transfer function, and generate a motion feature tensor in a four-dimensional space-time coordinate system; analyze the evolution pattern of the motion feature tensor in real time, and independently construct a scoring function cluster with a time-varying topological structure according to the difference in coupling intensity between the acceleration period, the stable period and the deceleration period of the movement, wherein each sub-function is nonlinearly superimposed through the motion chain energy transfer efficiency and the neural control stability index to generate a composite scoring value with motion quality diagnosis function.

9. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement the joint movement intelligent scoring method as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, the joint movement intelligent scoring method as described in any one of claims 1 to 7 is implemented.

Images