Method and system for testing lower limb hip and knee training equipment based on joint movement collaboration

Abstract

The invention relates to the technical field of medical instruments, in particular to a lower limb hip and knee training equipment testing method and system based on joint movement collaboration. Constructing an activation state recognition transition diagram, and performing index recognition on the actual muscle group activation situation through the activation state recognition transition diagram to obtain a current motion mode during equipment training; transmitting and adjusting motion poses on a standard joint execution chain of the hip and knee parts of the lower limbs of the human body according to the current motion mode, generating a standard motion coordination track, and judging whether the motion coordination of the simulated motion coordination track of the equipment is qualified or not based on the standard motion coordination track to obtain a first test result; and arranging a specified motion scene based on the first test result to carry out zero moment point secondary test on the lower limb hip and knee training equipment and discriminating gait torque instantaneous control to obtain a second test result. The method can accurately test and discriminate the movement cooperation qualification performance of the lower limb hip and knee training equipment, and effectively optimizes the equipment adaptation and assists the recovery effect of lower limb hip and knee joints of different patients.

Description

Technical Field

[0001] The present invention relates to the technical field of medical devices, and in particular to a testing method and system for lower limb hip and knee training equipment based on joint motion coordination. Background Art

[0002] With the aging population and the increasing number of patients suffering from sports injuries and neurological injuries (such as stroke and spinal cord injury), rehabilitation training devices are becoming increasingly widely used in the field of medical rehabilitation. Lower limb hip and knee training devices are primarily used to improve hip and knee motor function, enhance joint range of motion, strengthen muscle strength, and promote neuromuscular coordination. However, most existing lower limb hip and knee training devices focus solely on training the hip or knee alone, failing to test the biomechanical properties of the hip and knee coordinated motion during simulated gait. Furthermore, it is difficult to accurately test and analyze the coordination, rhythmicity, and instantaneous control of gait torque between the hip and knee joints of patients with varying degrees of injury. This makes it difficult to accurately determine whether the device has passed or failed testing, impacting the effectiveness of actual training. Some lower limb hip and knee training devices only support single-function injury analysis, making it difficult to tailor training testing strategies to the specific injury status of the patient's lower limb hip and knee joints. This results in significant discrepancies in test results for different patients, hindering subsequent precise control optimization and improvement of the device. Summary of the Invention

[0003] The present invention overcomes the deficiencies of the prior art and provides a method and system for testing lower limb hip and knee training equipment based on joint motion coordination.

[0004] In order to achieve the above object, the technical solution adopted by the present invention is: A first aspect of the present invention provides a method for testing a lower limb hip and knee training device based on joint motion coordination, comprising the following steps: S102: Calculating the tensor distribution of the patient's multi-dimensional injury data that constrains normal movement of the lower limb hip and knee joints based on the probability of correct movement mechanisms in human anthropology, so as to configure a training strategy specifically tailored to the patient. S104: performing collaborative injury training simulation on the patient subject using a three-dimensional simulation motion model of the lower limb hip and knee device, obtaining muscle group activation simulation signals, analyzing and analyzing the trend evolution of the muscle group activation simulation signals, and obtaining the actual muscle group activation status of the patient subject; S106: Constructing an activation state identification transfer map by combining different preset muscle group activation states and corresponding activation transfer indices. Using the activation state identification transfer map, the actual muscle group activation status is indexed and identified to obtain the current motion mode during device training. S108: adjusting the motion posture on the standard joint execution chain of the human lower limb hip and knee according to the current motion mode to generate a standard motion coordination trajectory, and determining whether the motion coordination of the simulated motion coordination trajectory of the device is qualified based on the standard motion coordination trajectory to obtain a first test result; S110: Arranging a designated sports scene based on the first test result to perform a secondary test on the zero torque point of the lower limb hip and knee training equipment and determining the instantaneous control of gait torque to obtain a second test result.

[0005] More specifically, the step S102 includes the following steps: Obtain case report information of the patient subject, extract multi-dimensional injury data of the patient's lower limb hip and knee joints through the case report information, and simultaneously obtain the correct movement mechanism of the lower limb hip and knee joints defined by anthropology based on a big data network; Based on the multidimensional injury data, an injury tensor matrix of different motion dimensions is constructed, the covariance matrix of the injury tensor matrix is calculated, and the constrained eigenvalues and constrained eigenvectors of the multidimensional injury data along different motion dimensions are obtained through the covariance matrix; The kernel function and bandwidth of the constraint feature vector are preset according to the constraint feature value, and the probability density estimation of the injury constraint on the normal movement of the lower limb hip and knee joints caused by the multi-dimensional injury data in different movement dimensions is calculated through the kernel function and bandwidth; The singular value decomposition algorithm is introduced. Based on the correct movement mechanism, the constraining eigenvectors of the injury tensor matrix are decomposed in the singular value decomposition algorithm to obtain the core tensors of the injury degree in different movement dimensions and the factor matrices of the core tensors in different movement dimensions that constrain the normal movement of the patient's lower limb hip and knee joints. Obtaining a dedicated training task for the patient, presetting a minimum task loss function based on the dedicated training task, updating the core tensor and factor matrix based on a decomposition rank alternating constraint of an injury constraint probability density estimate until the minimum task loss function is achieved, and generating a tensor distribution of the injury impact on normal movement of the patient's lower limb hip and knee joints in different movement dimensions when the injury level is determined to generate multidimensional injury data; The motion structure of the lower limb hip and knee training equipment is obtained, and the patient's lower limb hip and knee joints are divided into N sub-joint process blocks based on the motion structure. Training decisions are allocated to each sub-joint process block based on the injury impact tensor distribution, and a dedicated training strategy for the lower limb hip and knee training equipment is generated for the patient.

[0006] More specifically, the step S104 includes the following steps: Obtain assembly design drawings of the lower limb hip and knee training equipment and the joint injury motion process of the patient subject after the patient presents with multi-dimensional injury data. Build a three-dimensional simulation motion model of the lower limb hip and knee equipment in SolidWorks model software based on the assembly design drawings. Build a joint coordinated motion model of the lower limb hip and knee joint injury based on the joint injury motion process. The exclusive training strategy is executed by controlling the three-dimensional simulation running model to simulate the joint coordinated motion model of the patient subject after the hip and knee joint injuries of the lower limbs. During the simulation test, the muscle activation status is recorded in time series using electromyography technology to obtain multiple muscle group activation simulation signals of the patient subject; Extracting a sinusoidal waveform spectrum of each muscle group activation simulation signal, presetting a Hanning window function that balances the time-frequency resolution of muscle group activation based on the sinusoidal waveform spectrum, calculating the instantaneous autocorrelation function of the signal transition through the complex conjugate of the muscle group activation simulation signal, transforming the time delay parameter of the instantaneous autocorrelation function based on the Hanning window function, and obtaining a time-frequency simulation distribution representation of the patient's lower limb hip and knee joints outputting multiple muscle group activation simulation signals; Detect and obtain the local maximum peak point and local minimum peak point of each muscle group activation simulation signal, use the local maximum peak point and local minimum peak point spline interpolation to construct the upper envelope and lower envelope of the muscle group activation simulation signal, and then calculate the equilibrium value between the upper envelope and the lower envelope; A regeneration signal is output by removing the equilibrium value from multiple muscle group activation simulation signals. If the upper envelope of the regeneration signal is completely symmetrical with respect to the lower envelope, the eigenmodes are continuously extracted from the signal according to the time-frequency simulation distribution representation to form a time-frequency distribution eigenmode chain. The actual muscle group activation status of the patient subject during lower limb hip and knee training equipment training is determined based on the time-frequency distribution eigenmode chain.

[0007] More specifically, the step S106 includes the following steps: Based on the big data network, we obtained the ergonomic knowledge graph and muscle movement cases of the lower limb hip and knee joints. We extracted several movement patterns of the lower limb hip and knee joints when different preset muscle group activation states occurred through the ergonomic knowledge graph. Through muscle group movement cases, the historical movement trend span of each preset muscle group activation state that causes the lower limb hip and knee joint movement to produce a coordinated law is extracted, and the activation transfer index of different preset muscle group activation states is preset based on the historical movement trend span; Define each preset muscle group activation state as a state node, use the activation transfer index as the index boundary between each state node and the corresponding movement pattern, and construct an activation state identification transfer diagram by fitting the state node and the index boundary; Constructing a trend change detection model, and performing cumulative calculation of trend transfer rules on the actual muscle group activation status of the patient subject during training with the lower limb hip and knee training device using the trend change detection model to obtain a current activation status cumulative sum; If it is detected that the current activation state cumulative sum is greater than the preset cumulative threshold, then the trend change length of the current activation state cumulative sum is obtained, and the trend change length is weightedly assigned with smooth characters based on the current activation state cumulative sum to obtain the activation state string of the activation state transition at different trend change nodes; Based on the activation transfer index, the next state of each character of the activation state string is traversed and identified in the activation trend recognition transfer diagram, and the acceptance coefficient of the activation trend recognition transfer diagram for each character is output. If the acceptance coefficient is greater than the preset acceptance coefficient, the current movement mode of the patient subject when using the lower limb hip and knee training equipment for training is determined according to the index boundary under the current character state.

[0008] More specifically, the step S108 includes the following steps: Based on the big data network, the standard joint structure diagram and joint movement mechanism of the human lower limb hip and knee are obtained. The joint movement mechanism is used as the execution constraint, and the standard joint execution chain of the human lower limb hip and knee is constructed based on the movement of the standard joint structure diagram under the execution constraint. Obtaining injury characteristics of the patient's lower limb hip and knee joints based on the multi-dimensional injury data, importing the injury characteristics and the current movement mode into the ergonomic knowledge graph for identification, and outputting the patient's maximum stretch landing point in the current movement mode and the free range of motion between adjacent joint connection structures in the standard joint structure diagram; The first and last joints closest to the extreme stretch landing point on the standard joint execution chain are stripped off, and the root node of the first joint and the end effector of the end joint are constructed. Based on the preset transfer length threshold of the free range of motion, the end effector is moved from the fixed root node to the extreme stretch landing point. If the current transfer length between adjacent joint connection structures exceeds the limited transfer length threshold, the motion posture between the adjacent joint connection structures is adjusted until the current transfer length between each adjacent joint connection structure does not exceed the limited transfer length threshold; Repeat the above steps to generate a standard motion coordination trajectory of the patient subject in the current motion mode when the patient's lower limb hip and knee joints are injured. Based on the standard motion coordination trajectory, the motion rhythm and coordination of the lower limb hip and knee training equipment are judged on the simulated motion coordination trajectory to obtain the first test result.

[0009] More specifically, repeating the above steps to generate a standard motion coordination trajectory of the patient subject in the current motion mode with a lower limb hip and knee joint injury, and determining the motion rhythm and coordination of the lower limb hip and knee training device on the simulated motion coordination trajectory based on the standard motion coordination trajectory to obtain a first test result, specifically includes the following steps: Preset the arrival error tolerance of the extreme stretch landing point, repeat the above steps of moving the end effector to the extreme stretch landing point and adjusting the motion posture between adjacent joint connection structures, and obtain the current arrival distance of the end effector relative to the extreme stretch landing point; If the current arrival distance is less than the arrival error tolerance, the motion posture adjustment operation is stopped, a standard motion coordination trajectory of the patient subject in the current motion mode under the condition of lower limb hip and knee joint injury is generated, and a simulated motion coordination trajectory of the lower limb hip and knee training device during the simulated patient training is obtained; The key coordination nodes of the lower limb knee joint following the joint movement mechanism are extracted through the ergonomic knowledge graph. The entropy weight algorithm is introduced to calculate the approximate entropy of each key coordination node on the simulated motion coordination trajectory compared with the standard motion coordination trajectory, and multiple sparse approximate entropies and multiple dense approximate entropies are obtained. Calculating the number ratio between the key collaborative nodes of the sparse approximate entropy and the key collaborative nodes of the dense approximate entropy, and determining whether the number ratio is greater than a preset number ratio; If the quantity ratio is less than the preset quantity ratio, the lower limb hip and knee training device is calibrated as a qualified device; if the quantity ratio is greater than the preset quantity ratio, the lower limb hip and knee training device is calibrated as an unqualified device, and the first test result is obtained.

[0010] More specifically, the step S110 includes the following steps: If the first test result shows that the lower limb hip and knee training device is qualified, a specified motion scene is arranged in the simulation process to test the lower limb hip and knee training device, and multiple sets of joint force sensing test parameters of the lower limb hip and knee training device are obtained; Newton's laws of dynamics were introduced to construct a dynamic topological model. Multiple sets of joint force sensor test parameters were used to perform topological inference on the reaction force between the lower limb knee gait and the specified motion scene within the dynamic topological model. The simulated zero-torque point trajectory of the patient's gait during the simulation was obtained. Obtaining the expected test requirements and drive control base station of the lower limb hip and knee training device, and planning the expected zero-torque point trajectory of the lower limb hip and knee training device applied to the patient subject under the premise of a specified motion scenario based on the expected test requirements; Based on the preset gait torque sites of the drive control base station, the deviation between the simulated zero-torque point trajectory and the expected zero-torque point trajectory at each gait torque site is calculated to obtain multiple misalignment deviation values. Only the gait torque sites corresponding to the misalignment deviation values greater than the preset misalignment deviation threshold are extracted and defined as suspicious gait torque sites; Construct an instantaneous spike fluctuation field, fit the suspected gait torque site in the instantaneous spike fluctuation field, and output the actual instantaneous spike fluctuation fault triggered by the suspected gait torque during the simulation of the lower limb hip and knee training equipment; If the actual instantaneous peak fluctuation fault is at least one level higher than the preset instantaneous peak fluctuation fault, it means that the instantaneous torque control performance of the lower limb hip and knee training device is poor, resulting in gait coordination errors, and a second test result is obtained.

[0011] A second aspect of the present invention provides a lower limb hip and knee training equipment testing system based on joint movement coordination, the lower limb hip and knee training equipment testing system includes a memory and a processor, the memory stores a lower limb hip and knee training equipment testing method program based on joint movement coordination, when the lower limb hip and knee training equipment testing method program is executed by the processor, any one of the steps of the lower limb hip and knee training equipment testing method is implemented.

[0012] The present invention solves the technical defects existing in the background technology, and the beneficial technical effects of the present invention are: The tensor distribution of the normal movement of the lower limb hip and knee joints is constrained by the patient's multi-dimensional injury data according to the probability of the correct movement mechanism of anthropology, so as to configure the device's exclusive training strategy for the patient; the patient is simulated for collaborative injury training through a three-dimensional simulation motion model of the lower limb hip and knee device, muscle group activation simulation signals are obtained, and the trend evolution of the muscle group activation simulation signals is decomposed and analyzed to obtain the actual muscle group activation status of the patient; an activation state identification transfer diagram is constructed by combining different preset muscle group activation states with corresponding activation transfer indices, and the actual muscle group activation status is indexed and identified through the activation state identification transfer diagram to obtain the current movement mode during device training; according to the current movement mode, the movement posture is transferred and adjusted on the standard joint execution chain of the lower limb hip and knee of the human body to generate a standard movement coordination trajectory, and the movement coordination of the simulated movement coordination trajectory of the device is judged based on the standard movement coordination trajectory to obtain a first test result; based on the first test result, a specified movement scene is arranged to perform a secondary test on the zero torque point of the lower limb hip and knee training device and judge the instantaneous control of gait torque to obtain a second test result. The present invention can accurately test and determine whether the lower limb hip and knee training equipment is qualified for the injured patient's movement coordination, rhythm and gait instantaneous control, thereby providing a reliable basis for the subsequent optimization of the lower limb hip and knee training equipment, and effectively improving the equipment adaptation and assisting the recovery effect of the lower limb hip and knee joints of different patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, without paying any creative work, they can also obtain drawings of other embodiments based on these drawings.

[0014] Figure 1 A first method flow chart of a lower limb hip and knee training device testing method based on joint motion coordination is shown; Figure 2 A second method flow chart of a lower limb hip and knee training device testing method based on joint motion coordination is shown; Figure 3 The system framework diagram of the lower limb hip and knee training equipment testing system based on joint movement coordination is shown. DETAILED DESCRIPTION

[0015] In order to more clearly understand the above-mentioned objects, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that, in the absence of conflict, the embodiments of the present application and the features therein can be combined with each other.

[0016] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the scope of protection of the present invention is not limited to the specific embodiments disclosed below.

[0017] The first aspect of the present invention provides a method for testing lower limb hip and knee training equipment based on joint motion coordination, such as Figure 1 As shown, the following steps are included: S102: Calculating the tensor distribution of the patient's multi-dimensional injury data that constrains normal movement of the lower limb hip and knee joints based on the probability of correct movement mechanisms in human anthropology, so as to configure a training strategy specifically tailored to the patient. S104: performing collaborative injury training simulation on the patient subject using a three-dimensional simulation motion model of the lower limb hip and knee device, obtaining muscle group activation simulation signals, analyzing and analyzing the trend evolution of the muscle group activation simulation signals, and obtaining the actual muscle group activation status of the patient subject; S106: Constructing an activation state identification transfer map by combining different preset muscle group activation states and corresponding activation transfer indices. Using the activation state identification transfer map, the actual muscle group activation status is indexed and identified to obtain the current motion mode during device training. S108: adjusting the motion posture on the standard joint execution chain of the human lower limb hip and knee according to the current motion mode to generate a standard motion coordination trajectory, and determining whether the motion coordination of the simulated motion coordination trajectory of the device is qualified based on the standard motion coordination trajectory to obtain a first test result; S110: Arranging a designated sports scene based on the first test result to perform a secondary test on the zero torque point of the lower limb hip and knee training equipment and determining the instantaneous control of gait torque to obtain a second test result.

[0018] More specifically, the step S102 includes the following steps: Obtain case report information of the patient subject, extract multi-dimensional injury data of the patient's lower limb hip and knee joints through the case report information, and simultaneously obtain the correct movement mechanism of the lower limb hip and knee joints defined by anthropology based on a big data network; Based on the multidimensional injury data, an injury tensor matrix of different motion dimensions is constructed, the covariance matrix of the injury tensor matrix is calculated, and the constrained eigenvalues and constrained eigenvectors of the multidimensional injury data along different motion dimensions are obtained through the covariance matrix; The kernel function and bandwidth of the constraint feature vector are preset according to the constraint feature value, and the probability density estimation of the injury constraint on the normal movement of the lower limb hip and knee joints caused by the multi-dimensional injury data in different movement dimensions is calculated through the kernel function and bandwidth; The singular value decomposition algorithm is introduced. Based on the correct movement mechanism, the constraining eigenvectors of the injury tensor matrix are decomposed in the singular value decomposition algorithm to obtain the core tensors of the injury degree in different movement dimensions and the factor matrices of the core tensors in different movement dimensions that constrain the normal movement of the patient's lower limb hip and knee joints. Obtaining a dedicated training task for the patient, presetting a minimum task loss function based on the dedicated training task, updating the core tensor and factor matrix based on a decomposition rank alternating constraint of an injury constraint probability density estimate until the minimum task loss function is achieved, and generating a tensor distribution of the injury impact on normal movement of the patient's lower limb hip and knee joints in different movement dimensions when the injury level is determined to generate multidimensional injury data; The motion structure of the lower limb hip and knee training equipment is obtained, and the patient's lower limb hip and knee joints are divided into N sub-joint process blocks based on the motion structure. Training decisions are allocated to each sub-joint process block based on the injury impact tensor distribution, and a dedicated training strategy for the lower limb hip and knee training equipment is generated for the patient.

[0019] It should be noted that multidimensional injury data refers to the injury severity data affecting the lower limb hip and knee joints in time and space. The severity of lower limb hip and knee injuries varies among patients, but traditional lower limb hip and knee training equipment typically has a relatively simple control mode, making it difficult to develop highly adaptive training strategies for patients with different injury severity levels. Consequently, patients with varying injury severity are all trained with consistent parameters such as joint flexion and extension angles, flexion and extension rates, or flexion and extension forces. This can cause training pain or discomfort for different patients. Therefore, tailored, highly adaptive training strategies are required for each patient based on their injury severity. To this end, this method first obtains multidimensional injury data on the patient's lower limb hip and knee joints. Because training movements of the injured lower limb hip and knee joints may experience localized pain or motion constraints with a certain probability distribution in time and space, the multidimensional injury data is used to construct injury tensor matrices for different motion dimensions. The covariance matrix of the injury tensor matrix is then calculated. This covariance matrix represents the global distribution structure of the multidimensional injury data constraining lower limb hip and knee joint motion along different motion dimensions. The constraint eigenvalues and constraint eigenvectors recorded in the matrix indicate the direction in which the injury severity during lower limb hip and knee joint motion produces a certain probability of localized pain or discomfort restricting joint motion in the temporal and spatial dimensions. This provides a reliable basis for inferring the pattern of random injury constraints that may affect normal lower limb hip and knee joint motion in subsequent injury data across different motion dimensions. Therefore, the kernel function and bandwidth of the constraint eigenvectors can be pre-set based on the constraint eigenvalues to calculate the probability density estimate of the injury constraints that may affect normal lower limb hip and knee joint motion in different motion dimensions, thereby improving the device's ability to rationally determine the training control model for random joint motion constraints that may be introduced by different patient injuries.

[0020] It should be noted that as the pain and discomfort of the hip and knee joints move, they can be locally transferred to bones or muscle groups. For example, if the patient's injury is relatively mild, the flexion and extension of the joints while running while wearing a lower limb hip and knee training device may cause slight soreness in a certain local bone. Therefore, it is necessary to calculate the detailed distribution of the injury impact based on the injury severity to provide high-reliability support for the adaptive training control of the device. Therefore, based on the correct movement mechanism, this method decomposes the constraint eigenvectors of the injury tensor matrix in the singular value decomposition algorithm to efficiently obtain a core tensor and factor matrix about the degree of injury that restricts the normal movement of the hip and knee joints in different movement dimensions. Among them, the core tensor represents the constraint volume of the injury severity under the multidimensional injury data structure, while the factor matrix is composed of the local features of the injury manifestation that restrict the normal movement of the lower limb hip and knee joints under the constraint volume of the injury severity. It is a dimensionality reduction basis vector that can better improve the definition of injury data in different movement dimensions. The two form an expression system for the local joint movement restriction caused by different injury severity. Then, by minimizing the task loss function preset for the exclusive training task to alternately constrain the update of the core tensor and the factor matrix, the injury degree revealed by the multidimensional injury data can be more accurately expressed in the randomly distributed and constrained lower limb hip and knee joints during exercise. The resulting injury impact tensor distribution is the local constraint effect on the normal movement of the patient's lower limb hip and knee joints in different movement dimensions when the injury degree of the multidimensional injury data is generated, corresponding to the slight soreness that occurs in a certain local bone mentioned above. Finally, the training control decision of the lower limb hip and knee training equipment can be further allocated according to the injury impact tensor distribution. This method can tailor comfortable and highly matched training strategies for patients with different injury degrees, so that the test results when the equipment is applied to different patients can be more accurate, providing sufficient test reliability for subsequent equipment training control optimization for different patients.

[0021] More specifically, the step S104 includes the following steps: Obtain assembly design drawings of the lower limb hip and knee training equipment and the joint injury motion process of the patient subject after the patient presents with multi-dimensional injury data. Build a three-dimensional simulation motion model of the lower limb hip and knee equipment in SolidWorks model software based on the assembly design drawings. Build a joint coordinated motion model of the lower limb hip and knee joint injury based on the joint injury motion process. The exclusive training strategy is executed by controlling the three-dimensional simulation running model to simulate the joint coordinated motion model of the patient subject after the hip and knee joint injuries of the lower limbs. During the simulation test, the muscle activation status is recorded in time series using electromyography technology to obtain multiple muscle group activation simulation signals of the patient subject; Extracting a sinusoidal waveform spectrum of each muscle group activation simulation signal, presetting a Hanning window function that balances the time-frequency resolution of muscle group activation based on the sinusoidal waveform spectrum, calculating the instantaneous autocorrelation function of the signal transition through the complex conjugate of the muscle group activation simulation signal, transforming the time delay parameter of the instantaneous autocorrelation function based on the Hanning window function, and obtaining a time-frequency simulation distribution representation of the patient's lower limb hip and knee joints outputting multiple muscle group activation simulation signals; Detect and obtain the local maximum peak point and local minimum peak point of each muscle group activation simulation signal, use the local maximum peak point and local minimum peak point spline interpolation to construct the upper envelope and lower envelope of the muscle group activation simulation signal, and then calculate the equilibrium value between the upper envelope and the lower envelope; A regeneration signal is output by removing the equilibrium value from multiple muscle group activation simulation signals. If the upper envelope of the regeneration signal is completely symmetrical with respect to the lower envelope, the eigenmodes are continuously extracted from the signal according to the time-frequency simulation distribution representation to form a time-frequency distribution eigenmode chain. The actual muscle group activation status of the patient subject during lower limb hip and knee training equipment training is determined based on the time-frequency distribution eigenmode chain.

[0022] It should be noted that there is a close correlation between joint motion and muscle activation. The hip and knee ligament muscles contract to generate force that drives the lower limb hip and knee joints to flex, extend, or rotate. Therefore, analyzing muscle activation can indirectly reflect the training quality of lower limb hip and knee training devices for patients, further clarifying their test performance. This method uses a three-dimensional simulation to test joint coordination training with injured patients. This method replaces the traditional multi-step field sampling test process, reducing significant manpower and labor costs. It also reduces the intervention errors associated with manual testing, effectively improving the efficiency and flexibility of test data acquisition, and ensuring accurate and reliable device test results. The time-frequency distribution characteristics of the dispersed force generated by muscle activation are then extracted from the muscle activation signals of the lower limb hip and knee ligaments recorded during the simulation. Spline interpolation is performed simultaneously based on the local maximum and minimum peak points of each muscle activation simulation signal to construct the upper and lower envelopes of the muscle activation simulation signal, clarifying the local characteristics of the signal and thus determining the signal's oscillation range. The balance between the two measures the signal's local transmission trend, a key prerequisite for highlighting muscle activation trends. By subtracting this balance value from multiple muscle activation simulation signals, a narrowband oscillation pattern with the physical significance of muscle activation guidance can be isolated, making the frequency component of this pattern more uniform and more able to collectively reflect the development of joint movement driven by muscle activation during the test. Analyzing the local balance of the signal through the symmetry of the envelope helps separate the time-frequency distribution components of the signal at different scales, thereby converging into a complete time-frequency distribution eigenmode chain of muscle activation signal trends, significantly improving the accuracy of inferring actual muscle activation trends from signal data.

[0023] It should be noted that while traditional signal time-frequency distribution feature extraction has good time-frequency resolution, it is prone to generating cross-terms. This method suppresses cross-terms by introducing a Hanning window function that trades off the time-frequency resolution of muscle group activation. This maintains relatively clear time-frequency resolution and reduces unnecessary cross-term interference. The instantaneous autocorrelation function represents the autocorrelation characteristics of a signal at a certain point in time, revealing the joint similarity of the signal under different time delays. The accuracy of this instantaneous correlation function is crucial and directly affects the accuracy of the time-frequency distribution. In summary, this method can simulate the lower limb hip and knee training device to drive the patient's injured lower limb hip and knee joint training test and infer the state evolution of the output muscle group activation signal. Based on the muscle activation state, it can characterize the coordinated movement of the joint during the test, thereby providing analytical clues for the training control qualification of the lower limb hip and knee training device and significantly improving the testing accuracy of the lower limb hip and knee training device.

[0024] More specifically, the step S106 includes the following steps: Based on the big data network, we obtained the ergonomic knowledge graph and muscle movement cases of the lower limb hip and knee joints. We extracted several movement patterns of the lower limb hip and knee joints when different preset muscle group activation states occurred through the ergonomic knowledge graph. Through muscle group movement cases, the historical movement trend span of each preset muscle group activation state that causes the lower limb hip and knee joint movement to produce a coordinated law is extracted, and the activation transfer index of different preset muscle group activation states is preset based on the historical movement trend span; Define each preset muscle group activation state as a state node, use the activation transfer index as the index boundary between each state node and the corresponding movement pattern, and construct an activation state identification transfer diagram by fitting the state node and the index boundary; Constructing a trend change detection model, and performing cumulative calculation of trend transfer rules on the actual muscle group activation status of the patient subject during training with the lower limb hip and knee training device using the trend change detection model to obtain a current activation status cumulative sum; If it is detected that the current activation state cumulative sum is greater than the preset cumulative threshold, then the trend change length of the current activation state cumulative sum is obtained, and the trend change length is weightedly assigned with smooth characters based on the current activation state cumulative sum to obtain the activation state string of the activation state transition at different trend change nodes; Based on the activation transfer index, the next state of each character of the activation state string is traversed and identified in the activation trend recognition transfer diagram, and the acceptance coefficient of the activation trend recognition transfer diagram for each character is output. If the acceptance coefficient is greater than the preset acceptance coefficient, the current movement mode of the patient subject when using the lower limb hip and knee training equipment for training is determined according to the index boundary under the current character state.

[0025] It should be noted that different muscles work together in joint movement to achieve smooth and stable joint movement. However, if joint movement is restricted, muscle activation may become unbalanced, leading to compensatory movements and even increasing the risk of injury. Therefore, different movement patterns will activate different muscle groups. Different movement patterns have different muscle group activation characteristics. For example, leg extension mainly activates the quadriceps. Therefore, for joint training and recovery, it is crucial to clarify the movement pattern that the lower limb hip and knee training equipment drives them to respond. To this end, this method performs pattern recognition on the deduced actual muscle group activation situation by constructing an activation state recognition transfer diagram. Because different movement patterns produce different preset muscle group activation states, a well-established inter-linked index relationship exists between them. Therefore, we extracted the historical movement trend span of each preset muscle group activation state that results in synergistic lower limb hip and knee joint movement based on existing case studies. This historical movement trend span represents the degree of deviation from the synergistic and dissynergistic lower limb hip and knee joint movement patterns when transitioning from one muscle group activation state to another. This clearly reflects the activation transition amplitude of muscle group activation states under different movement pattern definitions. Therefore, we can pre-set activation transition indices for different preset muscle group activation states based on the historical movement trend span, providing joint transition labels for muscle group activation transition movement pattern recognition. Specifically, the activation transition index is used as the index boundary between each state node and the corresponding movement pattern. The activation state recognition transition diagram intuitively displays the index relationship between muscle group activation transition state changes and movement patterns. By digitizing and virtually storing these index relationships, we can accurately identify the corresponding movement pattern indexes under different muscle group activation trends, optimize the efficiency of the character indexing of muscle group activation states, and improve the accuracy of affiliation matching of movement patterns associated with muscle group activation states.

[0026] It should be noted that since the activation state recognition transfer diagram is executed in the form of character recognition, the recognition of the actual muscle group activation state should be carried out in the form of characters, so the actual muscle group activation state needs to be characterized. To this end, this method constructs a trend change detection model to accumulate and calculate the trend transfer rules of the actual muscle group activation state to obtain the current activation state cumulative sum. If the current activation state cumulative sum is greater than the preset cumulative threshold, it means that there is a significant change in the state transfer of the current cumulative calculated muscle group activation state, which requires a specific character length to be defined. Therefore, the trend change length is weighted by smoothing the character assignment to generate an activation state string about the state transfer of the activation state at different trend change nodes. Characterization can adapt to the activation state recognition transfer diagram for the recognition of the actual muscle group activation state, and at the same time can improve the recognition efficiency. The character string is an exclusive label for different state transitions, realizing the recognition targeting of the muscle group activation state corresponding to the movement pattern. Finally, the activation state recognition transition diagram is used to identify the next state of each character in the weighted activation state string. If the acceptance coefficient is greater than the preset acceptance coefficient, it indicates that the index boundary has a high acceptance rate for this state and is in an accepting state. Therefore, the movement pattern corresponding to this index boundary is a recognition result that is highly consistent with the actual muscle group activation status. This method can identify the corresponding movement pattern for the muscle group activation trend during the test, thereby facilitating the analysis of the movement coordination of the lower joint driven by the lower limb hip and knee training equipment, and improving the accuracy of the equipment training test.

[0027] More specifically, the step S108 is as follows: Figure 2 As shown, the specific steps include: S202: obtaining a standard joint structure diagram and joint movement mechanism of the human lower limb hip and knee based on a big data network, using the joint movement mechanism as an execution constraint, and constructing a standard joint execution chain of the human lower limb hip and knee based on the movement of the standard joint structure diagram under the execution constraint; S204: Obtaining injury characteristics of the patient's lower limb hip and knee joints based on the multi-dimensional injury data, importing the injury characteristics and the current movement mode into the ergonomic knowledge graph for identification, and outputting the patient's maximum stretch landing point in the current movement mode and the free range of motion between adjacent joint connection structures in the standard joint structure diagram; S206: stripping the head joint and the end joint closest to the extreme stretch landing point on the standard joint execution chain, constructing the root node of the head joint and the end effector of the end joint, and moving the end effector to the extreme stretch landing point starting from the fixed root node based on the preset limited transfer length threshold of the motion freedom width; S208: If the current transfer length between adjacent joint connection structures exceeds the limited transfer length threshold, adjusting the motion posture between the adjacent joint connection structures until the current transfer length between each adjacent joint connection structure does not exceed the limited transfer length threshold; S210: Repeat the above steps to generate a standard motion coordination trajectory of the patient subject in the current motion mode when the patient's lower limb hip and knee joints are injured. Based on the standard motion coordination trajectory, the motion rhythm and coordination of the lower limb hip and knee training equipment are determined for the simulated motion coordination trajectory to obtain a first test result.

[0028] It should be noted that by identifying the movement pattern of the patient during simulation training, the movement law premise of the lower limb hip and knee joints can be clarified. Under this movement law premise, the movement of the lower limb hip and knee joints is maintained at a maximally reasonable movement trajectory. When the movement trajectory of the simulation test is more misaligned than the reasonable movement trajectory, it means that the coordination and rhythm of the joint coordinated movement driven by the lower limb hip and knee training equipment have serious control error problems, and it is considered an unqualified device. Therefore, this method first constructs a standard joint execution chain for the human lower limb hip and knee. This standard joint execution chain complies with the regular movement execution of the standard joint structure of the human lower limb hip and knee under the provisions of the joint movement mechanism. It is a joint movement chain that is highly consistent with the human body joint, and provides a standardized definition basis for the calculation of subsequent standard movement coordinated trajectories. Next, based on the patient's injury characteristics and current movement pattern, the system determines the maximum stretch point for maximum activity in the current movement mode, as well as the free range of motion between adjacent joint connections in the standard joint structure diagram. The maximum stretch point represents the maximum target position for maximum joint stretching, given the severity of the injury; the free range of motion represents the range of lengths of movement between joints. Both serve as patient-generated training trajectory reference and convergence standards, avoiding infinite loops and establishing a dedicated test reference comparison group for patients with varying injury severity, significantly increasing the diversity of test comparisons for lower limb hip and knee training equipment.

[0029] It should be noted that the root node is fixed and the end effector is first moved to the extreme stretch landing point. If the current transfer length between adjacent joint connection structures exceeds the specified transfer length threshold, it means that the joint posture of the current standard joint execution chain does not conform to the coordinated movement of the skeletal flexion and extension length of the patient's injury state. Therefore, each joint needs to be adjusted in sequence, either incrementally or incrementally, to maintain a fixed bone length constraint and gradually move closer to the root. This can bring the end effector closer to the target while maintaining the distance constraint between the joints, ensuring that the root node of the bone does not drift, greatly improving the planning accuracy and coordination of the standard motion collaborative trajectory. This method can construct a standard joint execution chain for the human lower limb hip and knee and reallocate the joint positions according to the injury characteristics and movement patterns of different patients, so that they meet the length constraint while bringing the end effector of the bone closer to the maximum position of extreme stretch, thereby making the test comparison reference of the lower limb hip and knee training equipment more accurate and reliable, and significantly improving the test stability and accuracy of the coordination and rhythm of the lower limb hip and knee training equipment.

[0030] More specifically, repeating the above steps to generate a standard motion coordination trajectory of the patient subject in the current motion mode with a lower limb hip and knee joint injury, and determining the motion rhythm and coordination of the lower limb hip and knee training device on the simulated motion coordination trajectory based on the standard motion coordination trajectory to obtain a first test result, specifically includes the following steps: Preset the arrival error tolerance of the extreme stretch landing point, repeat the above steps of moving the end effector to the extreme stretch landing point and adjusting the motion posture between adjacent joint connection structures, and obtain the current arrival distance of the end effector relative to the extreme stretch landing point; If the current arrival distance is less than the arrival error tolerance, the motion posture adjustment operation is stopped, a standard motion coordination trajectory of the patient subject in the current motion mode under the condition of lower limb hip and knee joint injury is generated, and a simulated motion coordination trajectory of the lower limb hip and knee training device during the simulated patient training is obtained; The key coordination nodes of the lower limb knee joint following the joint movement mechanism are extracted through the ergonomic knowledge graph. The entropy weight algorithm is introduced to calculate the approximate entropy of each key coordination node on the simulated motion coordination trajectory compared with the standard motion coordination trajectory, and multiple sparse approximate entropies and multiple dense approximate entropies are obtained. Calculating the number ratio between the key collaborative nodes of the sparse approximate entropy and the key collaborative nodes of the dense approximate entropy, and determining whether the number ratio is greater than a preset number ratio; If the quantity ratio is less than the preset quantity ratio, the lower limb hip and knee training device is calibrated as a qualified device; if the quantity ratio is greater than the preset quantity ratio, the lower limb hip and knee training device is calibrated as an unqualified device, and the first test result is obtained.

[0031] It should be noted that for the generation of the standard motion collaborative trajectory, this method presets an arrival error tolerance for the extreme stretch landing point. This arrival error tolerance determines the convergence standard for the adjustment of each executing joint in the standard joint execution chain, avoids infinite cycles of adjustment, and reduces the degree of deviation of the standard motion collaborative trajectory. If the current arrival distance is less than the arrival error tolerance, it means that the end joint of the standard joint execution chain after joint adjustment has gradually approached the maximum target position of the extreme stretch, which means that the adjusted joint execution chain conforms to the standardized motion trajectory of the joint in the current motion mode collaborative motion under the actual injury state of the patient, so there is no need to continue adjustment. As for the test deviation judgment of the simulated motion collaborative trajectory compared to the standard motion collaborative trajectory, this method calculates the approximate entropy of each key collaborative node on the simulated motion collaborative trajectory compared to the standard motion collaborative trajectory. Among them, the key collaborative node means the node when the lower limb hip and knee joints have highly coordinated motion. The node can be a muscle connection node or a joint splicing point on the joint. In short, the key collaborative node reflects the key layout of the lower limb hip and knee joint motion coordination. The calculated sparse approximate entropy and dense approximate entropy reflect the degree of deviation of the simulated motion coordination trajectory from the standard motion coordination trajectory. Sparse approximate entropy indicates that the simulated motion coordination trajectory is sparser in terms of the deviation of coordination points compared to the standard motion coordination trajectory, while dense approximate entropy indicates that the deviation of coordination points is denser. If the ratio is less than the preset ratio, it indicates that the patient's joint movements under the lower limb hip and knee training device are highly coordinated and have a stable rhythm, and therefore the device is qualified. Conversely, it indicates that the patient's joint coordination and rhythm during running or slow walking under the lower limb hip and knee training device are poor, resulting in extremely unnatural movements, making it difficult to achieve the training goals, and easily worsening the patient's injury, and therefore the device is unqualified. This method can compare and analyze the simulated trajectory during testing with the standard motion coordination trajectory under the patient's injury state, thereby efficiently and quickly determining whether the coordination and rhythm of the lower limb hip and knee training device-driven patient training are qualified, improving the accuracy and reliability of the quality screening of lower limb hip and knee training device testing.

[0032] More specifically, the step S110 includes the following steps: If the first test result shows that the lower limb hip and knee training device is qualified, a specified motion scene is arranged in the simulation process to test the lower limb hip and knee training device, and multiple sets of joint force sensing test parameters of the lower limb hip and knee training device are obtained; Newton's laws of dynamics were introduced to construct a dynamic topological model. Multiple sets of joint force sensor test parameters were used to perform topological inference on the reaction force between the lower limb knee gait and the specified motion scene within the dynamic topological model. The simulated zero-torque point trajectory of the patient's gait during the simulation was obtained. Obtaining the expected test requirements and drive control base station of the lower limb hip and knee training device, and planning the expected zero-torque point trajectory of the lower limb hip and knee training device applied to the patient subject under the premise of a specified motion scenario based on the expected test requirements; Based on the preset gait torque sites of the drive control base station, the deviation between the simulated zero-torque point trajectory and the expected zero-torque point trajectory at each gait torque site is calculated to obtain multiple misalignment deviation values. Only the gait torque sites corresponding to the misalignment deviation values greater than the preset misalignment deviation threshold are extracted and defined as suspicious gait torque sites; Construct an instantaneous spike fluctuation field, fit the suspected gait torque site in the instantaneous spike fluctuation field, and output the actual instantaneous spike fluctuation fault triggered by the suspected gait torque during the simulation of the lower limb hip and knee training equipment; If the actual instantaneous peak fluctuation fault is at least one level higher than the preset instantaneous peak fluctuation fault, it means that the instantaneous torque control performance of the lower limb hip and knee training device is poor, resulting in gait coordination errors, and a second test result is obtained.

[0033] It should be noted that joint force sensing test parameters include joint angle, velocity, acceleration, or plantar force. If the lower limb hip and knee training device passes preliminary testing, it indicates that the movement coordination and rhythm changes it trains exhibit a certain degree of stability. Therefore, to further explore the accuracy of its control, it is necessary to test and analyze its instantaneous control while maintaining the patient's training gait. To this end, this method tests the zero-torque point of the lower limb hip and knee training device's hip and knee joint motion by applying a specific motion scenario. The zero-torque point is a specific point within the support surface where the torque generated by the ground reaction force about the horizontal coordinate axis is zero. Simply put, when an object (such as a robot or a human body) stands or walks on the ground, the ground generates a reaction force on the object. This reaction force can be decomposed into vertical and horizontal forces. There is a point within the support surface where the horizontal rotational effect (i.e., torque) of the ground reaction force is zero. When a lower limb hip and knee training device drives a patient, it generates a corresponding zero-torque point. Changes in this zero-torque point are closely correlated with changes in gait motion. If the zero-torque point during a simulation deviates from the expected zero-torque point trajectory by a certain amount, it indicates that the lower limb hip and knee training device has transient torque control anomalies, resulting in extremely unstable gait or incorrect parameters such as angles. Regarding the analysis of misalignment, this method uses pre-set gait torque stations on the drive control base station. The drive control base station is the drive motor, transmission device, and other components that implement torque control on the lower limb hip and knee training device. This serves as the control benchmark for determining the rationality of the device-driven gait. Because torque has certain transient control characteristics, this method constructs a transient spike fluctuation domain to fit the zero-torque point control expression of the suspected gait torque station. The output of the actual transient spike fluctuation fault reflects the spike fluctuation hierarchy generated by the gait torque during the simulation, which can fully and meticulously reflect the actual transient torque control performance of the lower limb hip and knee training device. This method can be used to test and identify the gait torque control performance of lower limb hip and knee training equipment, thereby achieving instantaneous control qualification screening of lower limb hip and knee training equipment and ensuring the control quality evaluation and optimization of the equipment.

[0034] The second aspect of the present invention provides a lower limb hip and knee training equipment testing system based on joint motion coordination, such as Figure 3 As shown, the lower limb hip and knee training equipment testing system includes a memory 31 and a processor 32. The memory 31 stores a lower limb hip and knee training equipment testing method program based on joint movement coordination. When the lower limb hip and knee training equipment testing method program is executed by the processor 32, any one of the steps of the lower limb hip and knee training equipment testing method is implemented.

[0035] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A testing method for lower limb hip and knee training equipment based on joint motion coordination, characterized in that: The following steps are involved: S102: Calculate the tensor distribution of the patient's multi-dimensional injury data that constrains normal movement of the lower limb hip and knee joints based on the probability of correct movement mechanisms in human anthropology, so as to configure a device-specific training strategy for the patient; S104: performing collaborative injury training simulation on the patient subject using a three-dimensional simulation motion model of the lower limb hip and knee device, obtaining muscle group activation simulation signals, analyzing and analyzing the trend evolution of the muscle group activation simulation signals, and obtaining the actual muscle group activation status of the patient subject; S106: Constructing an activation state identification transfer map by combining different preset muscle group activation states and corresponding activation transfer indices. Using the activation state identification transfer map, the actual muscle group activation status is indexed and identified to obtain the current motion mode during device training. S108: adjusting the motion posture on the standard joint execution chain of the human lower limb hip and knee according to the current motion mode to generate a standard motion coordination trajectory, and determining whether the motion coordination of the simulated motion coordination trajectory of the device is qualified based on the standard motion coordination trajectory to obtain a first test result; S110: Arranging a designated sports scene based on the first test result to perform a secondary test on the zero torque point of the lower limb hip and knee training equipment and determining the instantaneous control of gait torque to obtain a second test result.

2. The method for testing lower limb hip and knee training equipment based on joint motion coordination according to claim 1, characterized in that: The step S102 specifically includes the following steps: Obtain case report information of the patient subject, extract multi-dimensional injury data of the patient's lower limb hip and knee joints through the case report information, and simultaneously obtain the correct movement mechanism of the lower limb hip and knee joints defined by anthropology based on a big data network; Based on the multidimensional injury data, an injury tensor matrix of different motion dimensions is constructed, the covariance matrix of the injury tensor matrix is calculated, and the constrained eigenvalues and constrained eigenvectors of the multidimensional injury data along different motion dimensions are obtained through the covariance matrix; The kernel function and bandwidth of the constraint feature vector are preset according to the constraint feature value, and the probability density estimation of the injury constraint on the normal movement of the lower limb hip and knee joints caused by the multi-dimensional injury data in different movement dimensions is calculated through the kernel function and bandwidth; The singular value decomposition algorithm is introduced. Based on the correct movement mechanism, the constraining eigenvectors of the injury tensor matrix are decomposed in the singular value decomposition algorithm to obtain the core tensors of the injury degree in different movement dimensions and the factor matrices of the core tensors in different movement dimensions that constrain the normal movement of the patient's lower limb hip and knee joints. Obtaining a dedicated training task for the patient, presetting a minimum task loss function based on the dedicated training task, updating the core tensor and factor matrix based on a decomposition rank alternating constraint of an injury constraint probability density estimate until the minimum task loss function is achieved, and generating a tensor distribution of the injury impact on normal movement of the patient's lower limb hip and knee joints in different movement dimensions when the injury level is determined to generate multidimensional injury data; The motion structure of the lower limb hip and knee training equipment is obtained, and the patient's lower limb hip and knee joints are divided into N sub-joint process blocks based on the motion structure. Training decisions are allocated to each sub-joint process block based on the injury impact tensor distribution, and a dedicated training strategy for the lower limb hip and knee training equipment is generated for the patient.

3. The method for testing lower limb hip and knee training equipment based on joint motion coordination according to claim 1, characterized in that: The step S104 specifically includes the following steps: Obtain assembly design drawings of the lower limb hip and knee training equipment and the joint injury motion process of the patient subject after the patient presents with multi-dimensional injury data. Build a three-dimensional simulation motion model of the lower limb hip and knee equipment in SolidWorks model software based on the assembly design drawings. Build a joint coordinated motion model of the lower limb hip and knee joint injury based on the joint injury motion process. The exclusive training strategy is executed by controlling the three-dimensional simulation running model to simulate the joint coordinated motion model of the patient subject after the hip and knee joint injuries of the lower limbs. During the simulation test, the muscle activation status is recorded in time series using electromyography technology to obtain multiple muscle group activation simulation signals of the patient subject; Extracting a sinusoidal waveform spectrum of each muscle group activation simulation signal, presetting a Hanning window function that balances the time-frequency resolution of muscle group activation based on the sinusoidal waveform spectrum, calculating the instantaneous autocorrelation function of the signal transition through the complex conjugate of the muscle group activation simulation signal, transforming the time delay parameter of the instantaneous autocorrelation function based on the Hanning window function, and obtaining a time-frequency simulation distribution representation of the patient's lower limb hip and knee joints outputting multiple muscle group activation simulation signals; Detect and obtain the local maximum peak point and local minimum peak point of each muscle group activation simulation signal, use the local maximum peak point and local minimum peak point spline interpolation to construct the upper envelope and lower envelope of the muscle group activation simulation signal, and then calculate the equilibrium value between the upper envelope and the lower envelope; A regeneration signal is output by removing the equilibrium value from multiple muscle group activation simulation signals. If the upper envelope of the regeneration signal is completely symmetrical with respect to the lower envelope, the eigenmodes are continuously extracted from the signal according to the time-frequency simulation distribution representation to form a time-frequency distribution eigenmode chain. The actual muscle group activation status of the patient subject during lower limb hip and knee training equipment training is determined based on the time-frequency distribution eigenmode chain.

4. The method for testing lower limb hip and knee training equipment based on joint motion coordination according to claim 1, characterized in that: The step S106 specifically includes the following steps: Based on the big data network, we obtained the ergonomic knowledge graph and muscle movement cases of the lower limb hip and knee joints. We extracted several movement patterns of the lower limb hip and knee joints when different preset muscle group activation states occurred through the ergonomic knowledge graph. Through muscle group movement cases, the historical movement trend span of each preset muscle group activation state that causes the lower limb hip and knee joint movement to produce a coordinated law is extracted, and the activation transfer index of different preset muscle group activation states is preset based on the historical movement trend span; Define each preset muscle group activation state as a state node, use the activation transfer index as the index boundary between each state node and the corresponding movement pattern, and construct an activation state identification transfer diagram by fitting the state node and the index boundary; Constructing a trend change detection model, and performing cumulative calculation of trend transfer rules on the actual muscle group activation status of the patient subject during training with the lower limb hip and knee training device using the trend change detection model to obtain a current activation status cumulative sum; If it is detected that the current activation state cumulative sum is greater than the preset cumulative threshold, then the trend change length of the current activation state cumulative sum is obtained, and the trend change length is weightedly assigned with smooth characters based on the current activation state cumulative sum to obtain the activation state string of the activation state transition at different trend change nodes; Based on the activation transfer index, the next state of each character of the activation state string is traversed and identified in the activation trend recognition transfer diagram, and the acceptance coefficient of the activation trend recognition transfer diagram for each character is output. If the acceptance coefficient is greater than the preset acceptance coefficient, the current movement mode of the patient subject when using the lower limb hip and knee training equipment for training is determined according to the index boundary under the current character state.

5. The method for testing lower limb hip and knee training equipment based on joint motion coordination according to claim 1, characterized in that: The step S108 specifically includes the following steps: Based on the big data network, the standard joint structure diagram and joint movement mechanism of the human lower limb hip and knee are obtained. The joint movement mechanism is used as the execution constraint, and the standard joint execution chain of the human lower limb hip and knee is constructed based on the movement of the standard joint structure diagram under the execution constraint. Obtaining injury characteristics of the patient's lower limb hip and knee joints based on the multi-dimensional injury data, importing the injury characteristics and the current movement mode into the ergonomic knowledge graph for identification, and outputting the patient's maximum stretch landing point in the current movement mode and the free range of motion between adjacent joint connection structures in the standard joint structure diagram; The first and last joints closest to the extreme stretch landing point on the standard joint execution chain are stripped off, and the root node of the first joint and the end effector of the end joint are constructed. Based on the preset transfer length threshold of the free range of motion, the end effector is moved from the fixed root node to the extreme stretch landing point. If the current transfer length between adjacent joint connection structures exceeds the limited transfer length threshold, the motion posture between the adjacent joint connection structures is adjusted until the current transfer length between each adjacent joint connection structure does not exceed the limited transfer length threshold; Repeat the above steps to generate a standard motion coordination trajectory of the patient subject in the current motion mode when the patient's lower limb hip and knee joints are injured. Based on the standard motion coordination trajectory, the motion rhythm and coordination of the lower limb hip and knee training equipment are judged on the simulated motion coordination trajectory to obtain the first test result.

6. The method for testing lower limb hip and knee training equipment based on joint motion coordination according to claim 5, characterized in that: Repeating the above steps to generate a standard motion coordination trajectory of the patient subject in the current motion mode with a lower limb hip and knee joint injury, and determining the motion rhythm and coordination of the lower limb hip and knee training device on the simulated motion coordination trajectory based on the standard motion coordination trajectory to obtain a first test result specifically includes the following steps: Preset the arrival error tolerance of the extreme stretch landing point, repeat the above steps of moving the end effector to the extreme stretch landing point and adjusting the motion posture between adjacent joint connection structures, and obtain the current arrival distance of the end effector relative to the extreme stretch landing point; If the current arrival distance is less than the arrival error tolerance, the motion posture adjustment operation is stopped, a standard motion coordination trajectory of the patient subject in the current motion mode under the condition of lower limb hip and knee joint injury is generated, and a simulated motion coordination trajectory of the lower limb hip and knee training device during the simulated patient training is obtained; The key coordination nodes of the lower limb knee joint following the joint movement mechanism are extracted through the ergonomic knowledge graph. The entropy weight algorithm is introduced to calculate the approximate entropy of each key coordination node on the simulated motion coordination trajectory compared with the standard motion coordination trajectory, and multiple sparse approximate entropies and multiple dense approximate entropies are obtained. Calculating the number ratio between the key collaborative nodes of the sparse approximate entropy and the key collaborative nodes of the dense approximate entropy, and determining whether the number ratio is greater than a preset number ratio; If the quantity ratio is less than the preset quantity ratio, the lower limb hip and knee training device is calibrated as a qualified device; if the quantity ratio is greater than the preset quantity ratio, the lower limb hip and knee training device is calibrated as an unqualified device, and the first test result is obtained.

7. The method for testing lower limb hip and knee training equipment based on joint motion coordination according to claim 1, characterized in that: The step S110 specifically includes the following steps: If the first test result shows that the lower limb hip and knee training device is qualified, a specified motion scene is arranged in the simulation process to test the lower limb hip and knee training device, and multiple sets of joint force sensing test parameters of the lower limb hip and knee training device are obtained; Newton's laws of dynamics were introduced to construct a dynamic topological model. Multiple sets of joint force sensor test parameters were used to perform topological inference on the reaction force between the lower limb knee gait and the specified motion scene within the dynamic topological model. The simulated zero-torque point trajectory of the patient's gait during the simulation was obtained. Obtaining the expected test requirements and drive control base station of the lower limb hip and knee training device, and planning the expected zero-torque point trajectory of the lower limb hip and knee training device applied to the patient subject under the premise of a specified motion scenario based on the expected test requirements; Based on the preset gait torque sites of the drive control base station, the deviation between the simulated zero-torque point trajectory and the expected zero-torque point trajectory at each gait torque site is calculated to obtain multiple misalignment deviation values. Only the gait torque sites corresponding to the misalignment deviation values greater than the preset misalignment deviation threshold are extracted and defined as suspicious gait torque sites; Construct an instantaneous spike fluctuation field, fit the suspected gait torque site in the instantaneous spike fluctuation field, and output the actual instantaneous spike fluctuation fault triggered by the suspected gait torque during the simulation of the lower limb hip and knee training equipment; If the actual instantaneous peak fluctuation fault is at least one level higher than the preset instantaneous peak fluctuation fault, it means that the instantaneous torque control performance of the lower limb hip and knee training device is poor, resulting in gait coordination errors, and a second test result is obtained.

8. A lower limb hip and knee training equipment testing system based on joint motion coordination, characterized in that: The lower limb hip and knee training equipment testing system includes a memory and a processor. The memory stores a lower limb hip and knee training equipment testing method program based on joint movement coordination. When the lower limb hip and knee training equipment testing method program is executed by the processor, the lower limb hip and knee training equipment testing method steps as described in any one of claims 1-7 are implemented.

Images