Lower limb movement data real-time analysis method and system applied to rehabilitation guidance

Abstract

The invention discloses a lower limb motion data real-time analysis method and system applied to rehabilitation guidance, and the method comprises the steps: calling a personalized model according to user information, converting real-time motion data into historical motion feature vectors, inputting the historical motion feature vectors into a real-time prediction module, and generating multiple frames of future motion feature vectors through coding and decoding; calculating a deviation value between each future motion feature vector and a preset threshold range to obtain a motion deviation value, calculating a motion risk proportion of each future motion feature vector, performing weighted fusion to obtain a motion risk probability, and generating an equipment parameter adjustment value and pose adjustment information through reverse mapping; and finally, according to risk probability assessment training stage promotion, synchronously displaying correction information and adjusting equipment operation parameters. According to the method, the dynamic model is constructed through pre-training, real-time prediction of future motion features is realized in combination with the lightweight LSTM, and the predictability and personalized adaptation ability of rehabilitation guidance are improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a real-time analysis method and system for lower limb motion data applied to rehabilitation guidance. Background Art

[0002] Traditional methods rely on real-time data to detect deviations and are unable to predict potential risks in motion trajectories, resulting in a time lag between equipment parameter adjustment and posture correction, causing risk warning lags, and problems such as a lack of foresight in corrective measures. Summary of the invention

[0003] In view of the above problems, the present invention provides a method and system for real-time analysis of lower limb motion data for rehabilitation guidance, which solves the problem of delayed risk warning in traditional rehabilitation training.

[0004] To achieve the above objectives, in a first aspect, the present application provides a real-time analysis method of lower limb motion data for rehabilitation guidance, comprising:

[0005] Obtain user information, and call the personalized model corresponding to the current user according to the user information. The personalized model is configured as a group-individual adversarial pre-training model, and the personalized model includes a real-time prediction module;

[0006] The real-time motion data of the current user is obtained at a preset frequency and input into the personalized model to obtain the user's motion risk probability and correction information. The correction information includes the device parameter adjustment value and posture adjustment information, including:

[0007] The real-time motion data is converted into a multi-frame historical motion feature vector arranged in time order, and input into a real-time prediction module, which is configured to be built based on a lightweight LSTM network model;

[0008] The real-time prediction module performs encoding and decoding operations on the historical motion feature vectors of multiple frames to obtain the future motion feature vectors of multiple frames arranged in chronological order;

[0009] Obtaining a preset threshold range, calculating the deviation value between each future motion feature vector and the preset threshold range, and obtaining motion deviation values ​​arranged in chronological order;

[0010] The motion risk ratio of each future motion feature vector is calculated according to the motion deviation value, and multiple motion risk ratios are weightedly fused to obtain the motion risk probability;

[0011] and, reversely mapping the motion deviation value to a device parameter matrix to obtain a plurality of device parameter adjustment values, and reversely mapping the motion deviation value to a user posture matrix to obtain posture adjustment information of the current user;

[0012] Whether to execute the next stage of stage training steps is determined based on the sports risk probability assessment, and the correction information is displayed and the corresponding equipment operating parameters are adjusted.

[0013] Furthermore, the motion risk ratio of each future motion feature vector is calculated according to the motion deviation value, and multiple motion risk ratios are weightedly fused to obtain the motion risk probability including:

[0014] Obtaining a preset joint weight distribution table, which stores weight coefficients of each lower limb joint at different rehabilitation stages, and the weight coefficients are positively correlated with the importance of the lower limb joints in rehabilitation training;

[0015] According to the user's current rehabilitation stage, a corresponding set of weight coefficients is extracted from the joint weight distribution table;

[0016] For each future motion feature vector, perform matrix multiplication on the motion deviation components of each lower limb joint contained in it and the corresponding weight coefficient to obtain the joint weighted deviation value after dimension compression;

[0017] The joint weighted deviation value is input into the rehabilitation risk quantification model for nonlinear normalization processing, and the motion risk ratio of each future motion feature vector is output. The rehabilitation risk quantification model is obtained through the following steps:

[0018] Obtain a preset age-parameter mapping table and call a basic parameter group of the S-type function that matches the user's age;

[0019] According to the current rehabilitation stage, query the stage-slope comparison table to obtain the corresponding slope adjustment coefficient;

[0020] The basic parameter group and the slope adjustment coefficient are fused through a one-dimensional convolutional layer to generate a user-adaptive normalization function, i.e., a rehabilitation risk quantification model.

[0021] The sliding time window method is used to perform temporal fusion of the motion risk proportions of multiple frames to obtain the motion risk probability.

[0022] Furthermore, the motion deviation value is reversely mapped to the device parameter matrix to obtain multiple device parameter adjustment values ​​including:

[0023] Build a device parameter mapping library, including:

[0024] Obtain the preset rehabilitation stage-power response curve, and establish a nonlinear mapping relationship between the motion deviation value and the device power adjustment amount in different rehabilitation stages;

[0025] Configure the motion mode-speed comparison matrix to define the reference speed and allowable adjustment range corresponding to each phase of the gait cycle;

[0026] Loading a safety constraint parameter table to store a damping adjustment threshold boundary based on the user's physiological characteristics;

[0027] Decompose the motion deviation value according to the device parameter mapping relationship library, including:

[0028] According to the current rehabilitation stage index to the rehabilitation stage-power response curve, the time domain integral of the motion deviation value is input into the power conversion module, and the power adjustment amount adapted to the output stage is output;

[0029] Analyze the frequency domain characteristic components of the motion deviation value, match the motion mode-speed comparison matrix to obtain the reference speed correction coefficient;

[0030] The spatial distribution characteristics of the motion deviation value and the user's physiological parameters are input into the damping regulator, and the compliant damping adjustment amount is generated in combination with the safety constraint parameter table;

[0031] Output device parameter adjustment values, which include power adjustment amount, reference speed correction factor and compliance damping adjustment amount.

[0032] Furthermore, the motion deviation value is reversely mapped to the user posture matrix, and the posture adjustment information of the current user is obtained, including:

[0033] Construct the user pose matrix, including:

[0034] Obtain a preset joint-posture mapping table and establish a corresponding relationship between the motion deviation components of each lower limb joint and the ideal posture parameters;

[0035] Configure the rehabilitation stage-correction intensity comparison table to define the maximum posture adjustment range allowed in different rehabilitation stages;

[0036] Load the user's physiological-posture constraint table and store the personalized posture safety range based on the user's height and weight;

[0037] The motion deviation value is decomposed according to the user posture matrix, including:

[0038] Decompose the motion deviation value into each joint motion plane, and obtain the initial posture correction value through the joint-posture mapping table;

[0039] According to the current rehabilitation stage, the rehabilitation stage-correction intensity comparison table is queried, and the initial posture correction amount is subjected to intensity standardization to obtain the correction intensity coefficient;

[0040] The correction intensity coefficient, the initial posture correction amount and the user's physiological parameters are input into the posture optimizer, and the safe posture adjustment instruction and the final posture correction amount are generated in combination with the user's physiological-posture constraint table;

[0041] Output posture adjustment information, which includes correction strength coefficient, initial posture correction amount, final posture correction amount and safe posture adjustment instruction.

[0042] Furthermore, the preset threshold range is configured to be initialized by the following steps during the user's first training:

[0043] Acquire user information, and match a first preset number of group samples in a database according to the user information, wherein the matching constraints include injury type similarity, physiological characteristic similarity, and movement abnormality similarity;

[0044] Obtain a basic adversarial model and iteratively train the basic adversarial model using group samples, including:

[0045] The projected gradient descent method is used to generate disturbance samples that meet the preset disturbance range;

[0046] Repair the disturbed sample according to the preset constraint conditions, where the preset constraint conditions are biomechanical constraint conditions;

[0047] The group samples and the perturbation samples are mixed and input into the basic adversarial model and iteratively trained until a first preset training accuracy threshold is met, indicating that the basic adversarial model training is completed;

[0048] Input the group samples into the trained basic adversarial model and output the sample threshold range of each group sample;

[0049] Arrange multiple sample threshold ranges in order of the degree of matching between the group sample and the user information, and select the sample threshold range with the highest matching degree as the preset threshold range.

[0050] Furthermore, the personalized model also includes a threshold adjustment module, and the method also includes:

[0051] When the user is not training for the first time, the preset threshold range is configured to be updated through the threshold adjustment module, including:

[0052] After the user finishes exercising, the real-time exercise data of the current batch of the user is obtained and recorded as the latest exercise data, and the historical exercise data of each batch within a preset historical period is obtained;

[0053] Generate personal adversarial samples based on the latest and historical motion data;

[0054] Acquire the latest user information of the user, and match the latest group samples of a second preset number in the database according to the latest user information, where the matching constraints include injury type similarity, physiological feature similarity, and movement abnormality similarity;

[0055] The latest group sample and the individual adversarial sample are mixed and input into the threshold adjustment module for iterative training until the second preset training accuracy threshold is met, indicating that the threshold adjustment module has been updated;

[0056] The latest motion data is input into the updated threshold adjustment module to obtain the updated preset threshold range.

[0057] Furthermore, based on the latest motion data and historical motion data within a preset historical period, generating personal adversarial samples includes:

[0058] Extracting significant feature information from the latest motion data, the significant feature information including the first motion frame with the highest motion completion, the second motion frame with the largest motion deviation, and the third motion frame with clinical typicality;

[0059] In the dormant state, semantic feature reconstruction is performed on the salient feature information, including:

[0060] The pre-set diffusion model is used to decouple the significant feature information to obtain the kinematic parameters, which include joint angles, joint torque distribution, motion speed curves, and muscle force patterns.

[0061] Construct physical constraint information and personal constraint information based on kinematic parameters;

[0062] Generate variant samples similar to the salient feature information based on historical movement data, physical constraint information, and personal constraint information;

[0063] The mutated samples are inserted into the historical motion data according to the execution sequence of the first action frame, the second action frame, and the third action frame in the latest action data to obtain personal adversarial samples.

[0064] Furthermore, based on the latest motion data and historical motion data within a preset historical period, generating personal adversarial samples includes:

[0065] Extracting first abnormal feature information from the latest motion data, the first abnormal feature information including joint motion trajectory deviation features, muscle activation abnormal features, and motion timing disorder features;

[0066] Mapping the first abnormal feature information to the federated shared latent space for similarity matching includes:

[0067] Calculate the latent space projection similarity with the second abnormal feature information of other users in the database;

[0068] Filter matching cases whose latent space projection similarity exceeds a preset similarity threshold, and obtain the desensitization correction strategy associated with the matching cases;

[0069] The first abnormal feature information is fused and reconstructed according to the desensitization correction strategy to generate a resonant adversarial sample after the first abnormal feature information is corrected;

[0070] The generated resonance adversarial sample is mixed with the historical motion data and the latest motion data to obtain the personal adversarial sample.

[0071] Furthermore, based on the latest motion data and historical motion data within a preset historical period, generating personal adversarial samples includes:

[0072] Extracting first motion feature information from the latest motion data, the first motion feature information including the user's habitual motion pattern features, typical incorrect motion features, and biomechanical reasonable motion features;

[0073] generating second motion characteristic information based on the biomechanical constraint condition, wherein the second motion characteristic information is configured to meet clinical standards but have a preset difference from the first motion characteristic information;

[0074] Add an explainability label to each second action feature information, where the explainability label contains specific quantitative indicators required for action improvement;

[0075] Inputting the first action feature information and the second action feature information into the personalized model respectively, obtaining a first risk assessment result corresponding to the first action feature information and a second risk assessment result corresponding to the second action feature information;

[0076] generating an acceptance index based on the second risk assessment result, and generating a stubbornness index based on the first risk assessment result;

[0077] The second action feature information is filtered according to the acceptance index and the stubbornness index, and recorded as a valid adversarial sample, and mixed with the historical motion data and the latest motion data to obtain a personal adversarial sample.

[0078] In a second aspect, the present invention further provides a real-time analysis system for lower limb motion data used for rehabilitation guidance, which is applicable to the real-time analysis method of the first aspect, and the system includes a data acquisition module and a logic processing module;

[0079] The data collection module is used to obtain user information. The data collection module is also used to obtain the real-time motion data of the current user according to a preset frequency;

[0080] The logic processing module is used to call the personalized model corresponding to the current user according to the user information. The personalized model is configured as a group adversarial pre-training model. The personalized model includes a real-time prediction module.

[0081] The logic processing module is also used to input the real-time motion data into the personalized model to obtain the user's motion risk probability and correction information. The correction information includes the device parameter adjustment value and posture adjustment information, including:

[0082] The real-time motion data is converted into a multi-frame historical motion feature vector arranged in time order, and input into a real-time prediction module, which is configured to be built based on a lightweight LSTM network model;

[0083] The real-time prediction module performs encoding and decoding operations on the historical motion feature vectors of multiple frames to obtain the future motion feature vectors of multiple frames arranged in chronological order;

[0084] Obtaining a preset threshold range, calculating the deviation value between each future motion feature vector and the preset threshold range, and obtaining motion deviation values ​​arranged in chronological order;

[0085] The motion risk ratio of each future motion feature vector is calculated according to the motion deviation value, and multiple motion risk ratios are weightedly fused to obtain the motion risk probability;

[0086] and, reversely mapping the motion deviation value to a device parameter matrix to obtain a plurality of device parameter adjustment values, and reversely mapping the motion deviation value to a user posture matrix to obtain posture adjustment information of the current user;

[0087] Whether to execute the next stage of stage training steps is determined based on the sports risk probability assessment, and the correction information is displayed and the corresponding equipment operating parameters are adjusted.

[0088] Different from the existing technology, the above technical scheme provides a real-time analysis method and system for lower limb motion data applied to rehabilitation guidance. The method calls the personalized model according to user information, converts the real-time motion data into historical motion feature vectors and inputs them into the real-time prediction module, and generates multiple frames of future motion feature vectors through encoding and decoding; calculates the deviation value of each future motion feature vector from the preset threshold range to obtain the motion deviation value, and calculates the motion risk ratio of each future motion feature vector, obtains the motion risk probability through weighted fusion, and generates the device parameter adjustment value and posture adjustment information through reverse mapping; finally, the training stage is advanced according to the risk probability assessment, and the correction information is displayed synchronously and the device operation parameters are adjusted. This technical scheme constructs a dynamic model through pre-training, and combines lightweight LSTM to realize real-time prediction of future motion characteristics, which improves the predictability and personalized adaptation capabilities of rehabilitation guidance.

[0089] The above-mentioned records related to the invention content are only an overview of the technical solution of the present application. In order to enable ordinary technicians in the field to more clearly understand the technical solution of the present application, and then implement it according to the text of the specification and the contents recorded in the drawings, and to make the above-mentioned purpose and other purposes, features and advantages of the present application easier to understand, the following is an explanation in combination with the specific implementation mode and drawings of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0090] The drawings are only used to illustrate the principles, implementation methods, applications, characteristics and effects of the specific embodiments of the present invention and other related contents, and shall not be considered as limiting the present application.

[0091] In the drawings of the specification:

[0092] Figure 1 A method step diagram of steps S101 to S107 of the real-time analysis method described in the specific implementation method;

[0093] Figure 2 A method step diagram of steps S201 to S205 of the real-time analysis method described in the specific implementation method;

[0094] Figure 3 A method step diagram of step S301 to step S303 of the real-time analysis method described in the specific implementation method;

[0095] Figure 4 A method step diagram of step S401 to step S403 of the real-time analysis method described in the specific implementation method;

[0096] Figure 5 It is a structural schematic diagram of the real-time analysis system described in the specific implementation method.

[0097] The reference numerals in the above drawings are described as follows:

[0098] 1. Real-time analysis system;

[0099] 11. Data acquisition module;

[0100] 12. Logic processing module. DETAILED DESCRIPTION

[0101] In order to explain in detail the possible application scenarios, technical principles, specific schemes that can be implemented, and the purposes and effects that can be achieved, the following is a detailed description of the specific embodiments listed in conjunction with the accompanying drawings. The embodiments described herein are only used to more clearly illustrate the technical solutions of the present application, and are therefore only used as examples, and cannot be used to limit the scope of protection of the present application.

[0102] Reference to "embodiment" herein means that the specific features, structures or characteristics described in conjunction with the embodiment may be included in at least one embodiment of the present application. The term "embodiment" appearing in various places in the specification does not necessarily refer to the same embodiment, nor does it particularly limit its independence or association with other embodiments. In principle, in the present application, as long as there is no technical contradiction or conflict, the various technical features mentioned in the embodiments can be combined in any way to form a corresponding implementable technical solution.

[0103] Unless otherwise defined, the technical terms used in this document have the same meanings as those generally understood by those skilled in the art to which this application belongs; the use of relevant terms in this document is only for describing specific embodiments and is not intended to limit this application.

[0104] In the description of this application, the term "and / or" is an expression used to describe the logical relationship between objects, indicating that three relationships may exist, for example, A and / or B, which means: A exists, B exists, and A and B exist at the same time. In addition, the character " / " in this article generally indicates that the objects before and after are in an "or" logical relationship.

[0105] In the present application, terms such as “first” and “second” are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship of quantity, priority or sequence between these entities or operations.

[0106] Without further limitations, in this application, the words "include", "comprises", "has" or other similar open-ended expressions used in sentences are intended to cover non-exclusive inclusion. These expressions do not exclude the presence of additional elements in the process, method or product including the elements, so that the process, method or product including a series of elements may include not only those limited elements, but also other elements not explicitly listed, or also include elements inherent to such process, method or product.

[0107] Similar to the understanding in the Examination Guidelines, in this application, expressions such as "greater than", "less than", "exceed" and the like are understood to exclude the number itself; expressions such as "above", "below", "within" and the like are understood to include the number itself. In addition, in the description of the embodiments of this application, "multiple" means more than two (including two), and similar expressions related to "multiple" are also understood in this way, such as "multiple groups", "multiple times", etc., unless otherwise clearly and specifically limited.

[0108] In the description of the embodiments of the present application, space-related expressions used, such as "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "vertical", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., indicate the orientation or position relationship based on the orientation or position relationship shown in the specific embodiments or drawings, and are only for the convenience of describing the specific embodiments of the present application or facilitating the reader's understanding, and do not indicate or imply that the referred device or component must have a specific position, a specific orientation, or be constructed or operated in a specific orientation, and therefore cannot be understood as a limitation on the embodiments of the present application.

[0109] The processor described in the embodiments of the present application can be implemented by hardware, firmware, software or a combination thereof, and can use a circuit, a single or multiple application-specific integrated circuits (Application Specific Integrated Circuit, ASIC), a digital signal processor (Digital Signal Processor, DSP), a digital signal processing device (Digital Signal Processing Device, DSPD), a programmable logic device (Programmable Logic Device, PLD), a field programmable gate array (Field Programmable Gate Array, FPGA), a central processing unit (Central Processing Unit, CPU), a controller, a microcontroller, at least one of a microprocessor, and also includes other physical, biological or chemical structures that can achieve similar or equivalent functions to the processors listed above, such as biological neurons, quantum computing units, DNA computing units, etc., so that the processor can execute some or all of the steps in the computer program or method involved in the various embodiments of the present application, or any combination of the steps mentioned therein.

[0110] The computer program involved in the embodiment can be stored in a computer device readable storage medium, which includes but is not limited to a disk, a tape, a magnetic card, a floppy disk, a flash memory, an optical disk, an optical card, a read-only memory (ROM), a random access memory (RAM), an erasable programmable ROM (EPROM) and an electrically erasable programmable ROM (EEPROM), etc., and also includes other biological, physical or chemical structures that can achieve the same or equivalent functions as the storage media listed above, such as DNA, RNA, protein and other units with information storage capabilities. In a specific embodiment, the storage medium involved can be one of the above-mentioned media types, or a combination of the above-mentioned media types. In different embodiments, the computer program involved in the embodiment can be stored in a single medium in a centralized manner, or it can be stored in multiple media in a distributed manner. The memory containing the computer device readable storage medium can be a non-volatile memory or a random access memory. These computer device readable storage media can be built into the device, or they can be connected to the device involved in the embodiment as an external device or a part of an external device. In some embodiments, a memory with a computer device readable storage medium is deployed locally; in other embodiments, a solution of deploying the memory away from the processor may also be adopted, such as a network attached memory accessed via an RF circuit or an external port and a communication network, wherein the communication network may be the Internet, one or more intranets, a local area network (LAN), a wide area network (WLAN), a storage area network (SAN), etc., or a suitable combination thereof, as long as the computer device can access the memory. In addition, the computer program involved in the embodiment may be stored in plaintext / ciphertext form, or may be designed as training data, which may be integrated and reorganized through model training and implicitly stored in the parameter state of a deep neural network or other machine learning model.

[0111] See also Figure 1 In a first aspect, this embodiment provides a method for real-time analysis of lower limb motion data for rehabilitation guidance, comprising:

[0112] S101, obtaining user information, and calling a personalized model corresponding to the current user according to the user information, wherein the personalized model is configured as a group-individual adversarial pre-training model, and the personalized model includes a real-time prediction module;

[0113] S102, obtaining the real-time motion data of the current user at a preset frequency, and inputting it into the personalized model to obtain the user's motion risk probability and correction information, the correction information including the device parameter adjustment value and posture adjustment information, including:

[0114] S103, converting the real-time motion data into a multi-frame historical motion feature vector arranged in chronological order, and inputting the historical motion feature vector into a real-time prediction module, wherein the real-time prediction module is configured to be constructed based on a lightweight LSTM network model;

[0115] S104, the real-time prediction module performs encoding and decoding operations on the historical motion feature vectors of the multiple frames to obtain future motion feature vectors of the multiple frames arranged in chronological order;

[0116] S105, obtaining a preset threshold range, calculating the deviation value between each future motion feature vector and the preset threshold range, and obtaining motion deviation values ​​arranged in chronological order;

[0117] S106, calculating the motion risk ratio of each future motion feature vector according to the motion deviation value, performing weighted fusion on multiple motion risk ratios, and obtaining a motion risk probability;

[0118] and, reversely mapping the motion deviation value to a device parameter matrix to obtain a plurality of device parameter adjustment values, and reversely mapping the motion deviation value to a user posture matrix to obtain posture adjustment information of the current user;

[0119] S107, assessing whether to execute the next stage of stage training steps based on the sports risk probability, and displaying the correction information and adjusting the corresponding equipment operating parameters.

[0120] In step S101, user information refers to multidimensional information including user physiological characteristics, injury type and historical rehabilitation data, which is used to generate an initial personalized model through database matching. The group-individual adversarial pre-training model refers to an adversarial training framework based on group samples and individual data. By introducing perturbation samples and biomechanical constraints in the pre-training stage, the model has the dual characteristics of group experience and individual adaptation. The real-time prediction module is used to achieve efficient processing of time series features.

[0121] In step S102, the preset frequency is dynamically determined by the sampling capacity of the device sensor and the current rehabilitation stage of the user. Real-time motion data includes lower limb joint angles, motion trajectory speed and acceleration indicators. Preferably, the device parameter adjustment value includes a power adjustment amount, a speed correction coefficient and a damping adjustment amount, which are used to dynamically adjust the power output of the rehabilitation device; the posture adjustment information includes joint correction amount and strength parameters, which are generated based on the user's physiological constraints to guide the adjustment of the lower limb posture to avoid sports injuries. The device parameter adjustment value and posture adjustment information are generated by reverse mapping the motion deviation value to achieve synchronous optimization of device adaptation and user action.

[0122] In step S103, the lightweight LSTM network optimizes computational efficiency by reducing the number of hidden layer nodes and parameter pruning while retaining the ability to capture temporal features.

[0123] In step S104, the encoder extracts the spatiotemporal correlation of the historical motion feature vectors, and the decoder generates multiple frames of future motion feature vectors based on the attention mechanism.

[0124] In step S105, preferably, the preset threshold range is initialized by matching similar group samples to generate an adversarial model during the first training, and is updated by the threshold adjustment module of the personalized model in combination with personal historical data during non-first training. The specific content is described below. When calculating the motion deviation value, the Euclidean distance can be used to quantify the degree of deviation between the future motion feature vector and the boundary of the preset threshold range.

[0125] In step S106, the motion risk ratio of each future motion feature vector is calculated based on the motion deviation value. This can be understood in conjunction with the following example: for each future motion feature vector, the deviation components of the hip, knee and other joints contained therein are multiplied by the weight coefficient of the corresponding rehabilitation stage (e.g., the hip joint has a higher weight in the early stage), and nonlinear compression is performed through an age-adaptive S-type function to output a motion risk ratio in the range of 0-1. Multiple motion risk ratios are weighted and fused, and the weight coefficients of the frames in the sliding time window are used (e.g., the weight of the proximal frame is increased by 20%), and a comprehensive motion risk probability is generated through a temporal attention mechanism.

[0126] The process of obtaining the device parameter adjustment value can be understood as: decomposing the motion deviation value into power, speed and damping components. For example, the gait phase deviation triggers the speed control matrix correction, and the power response curve converts the time domain deviation integral into the motor power increase. At the same time, the user's bone density constraint is combined to limit the damping adjustment range.

[0127] The process of obtaining posture adjustment information can be understood as: mapping the motion deviation value to the joint posture plane. For example, the sagittal plane deviation of the knee joint generates a 5° flexion correction through a mapping table, and the adjustment range is limited to 3° based on the user's height and weight constraints. Finally, the posture instruction containing the safety boundary is output.

[0128] In step S107, when the probability of motion risk is lower than the preset stage migration threshold, the next stage of training is triggered, otherwise the current stage is maintained and parameter adjustment is performed. Furthermore, the preset stage migration threshold can be determined by integrating the group rehabilitation benchmark and the individual dynamic characteristics: the initial threshold is established based on the historical training data of patients with similar injuries (such as the peak value of the gait risk probability distribution of the fracture group of 0.25), and the user's real-time electromyographic signal attenuation rate, bone density growth curve and other physiological indicators are superimposed for offset correction (±0.1 interval), and the risk fluctuation standard deviation of the last 7 training sessions is used to dynamically tighten the boundary. For example, after knee surgery, the user's initial threshold is set to 0.3. When the muscle strength increases by 20% and the risk probability is stable at 0.25 for 3 consecutive times, the threshold is lowered to 0.22 to trigger advancement, so as to avoid hindering the rehabilitation process due to a single abnormal fluctuation.

[0129] Optionally, the correction information is displayed visually through an interactive interface, and the equipment operating parameters are adjusted in real time by the control system.

[0130] The real-time analysis method of lower limb motion data provided in this embodiment realizes accurate rehabilitation guidance by constructing a group-individual confrontation pre-training model. The method first calls a personalized model based on user information, uses a lightweight LSTM network to encode historical motion feature vectors in real time and decodes and predicts future multi-frame motion trends (i.e., future motion feature vectors of multiple frames), calculates motion deviation values ​​in combination with a preset threshold range, and simultaneously generates device parameter adjustment values ​​and posture correction information. While ensuring computational efficiency, this method realizes individualized adaptation of the rehabilitation training process through the coordinated adjustment of device power output and user motion posture: on the one hand, the confrontation training framework is used to balance group universality and individual differences, and improve the robustness of motion risk prediction; on the other hand, the motion deviation is converted into a two-dimensional regulation of device parameters and posture through a reverse mapping mechanism, which accelerates functional recovery while reducing the risk of secondary injury. The dynamic threshold mechanism combines historical risk fluctuations with the evolution of physiological indicators to ensure the rationality and safety of rehabilitation stage migration, effectively avoid misjudgment problems caused by local data anomalies, and form a closed-loop optimized intelligent rehabilitation decision-making system.

[0131] See also Figure 2 In some embodiments, the motion risk ratio of each future motion feature vector is calculated according to the motion deviation value, and multiple motion risk ratios are weightedly fused to obtain the motion risk probability, including:

[0132] S201, obtaining a preset joint weight distribution table, wherein the joint weight distribution table stores weight coefficients of various lower limb joints at different rehabilitation stages, and the weight coefficients are positively correlated with the importance of the lower limb joints in rehabilitation training;

[0133] S202, extracting a corresponding weight coefficient set from a joint weight distribution table according to the user's current rehabilitation stage;

[0134] S203, for each future motion feature vector, performing matrix multiplication operation on the motion deviation components of each lower limb joint contained therein and the corresponding weight coefficient to obtain a joint weighted deviation value after dimension compression;

[0135] S204, inputting the joint weighted deviation value into the rehabilitation risk quantification model for nonlinear normalization processing, and outputting the motion risk proportion of each future motion feature vector. The rehabilitation risk quantification model is obtained by the following steps:

[0136] Obtain a preset age-parameter mapping table and call a basic parameter group of the S-type function that matches the user's age;

[0137] According to the current rehabilitation stage, query the stage-slope comparison table to obtain the corresponding slope adjustment coefficient;

[0138] The basic parameter group and the slope adjustment coefficient are fused through a one-dimensional convolutional layer to generate a user-adaptive normalization function, i.e., a rehabilitation risk quantification model.

[0139] S205 , performing time series fusion on motion risk proportions of multiple frames by using a sliding time window method to obtain a motion risk probability.

[0140] In step S201, the formation of the joint weight allocation table is based on a comprehensive analysis of clinical rehabilitation medicine experience and historical training data. The difference in the importance of each lower limb joint at different rehabilitation stages is reflected in the gradient change of the weight coefficient: for example, in the early stage after fracture surgery, the hip joint is assigned a higher weight because it bears the main supporting function. As the rehabilitation process progresses, the weight of knee flexion and extension activities gradually increases. The joint weight allocation table is formed by statistically analyzing the degree of influence of joint movement deviation on the rehabilitation effect of patients with similar injuries at a specific stage, combined with expert experience calibration, to ensure that the weight coefficient matches the priority of joint function recovery.

[0141] In step S202, the user's current rehabilitation stage is determined by the system through a dynamic comparison of the real-time motion risk probability and the preset stage migration threshold. When the motion risk probability is stably lower than the current stage threshold during multiple consecutive training sessions, the system determines to enter the next stage. This step queries the joint weight allocation table to extract the weight coefficient set that matches the current stage, realizes the dynamic adaptation of the joint importance assessment, and provides a staged parameter benchmark for subsequent weighted calculations.

[0142] In step S203, each future motion feature vector contains independent motion deviation components of each lower limb joint, such as the hip, knee, and ankle. By multiplying with the corresponding elements of the weight coefficient set, the multidimensional deviation vector is compressed into a scalar joint weighted deviation value, which is essentially a linear combination of each joint deviation weighted by importance, so that the joint deviation that has a greater impact on the rehabilitation effect occupies a higher proportion in subsequent calculations.

[0143] In step S204, the process of obtaining the motion risk ratio of each future motion feature vector can be understood as follows: the construction of the rehabilitation risk quantification model depends on the dual parameter adaptation of age and rehabilitation stage. Specifically, the age-parameter mapping table pre-stores the basic parameter group of the S-type function according to the physiological differences in the motor function recovery ability of users of different age groups, which is used to adjust the steepness of the normalized curve; the stage-slope comparison table adjusts the slope of the curve according to the rehabilitation process. For example, a flat curve is used in the early stage to avoid excessive sensitivity, and the slope is increased in the later stage to improve the risk response accuracy; the basic parameter group and the slope adjustment coefficient are fused through a one-dimensional convolution layer to generate a user-adaptive S-type function, and the joint weighted deviation value is nonlinearly mapped to the motion risk ratio in the range of 0-1, so that the risk quantification result reflects both the individual physiological characteristics and the characteristics of the rehabilitation stage.

[0144] In step S205, the time window length is matched with the device sampling frequency, and the weight coefficient of each frame in the window is adjusted with the time attenuation factor, and the near-end frame is given a higher weight to strengthen the influence of the recent motion trend. The temporal attention mechanism is introduced in the fusion process to automatically identify abnormal fluctuation frames and reduce their contribution, and finally output the smoothed motion risk probability through weighted summation. This step suppresses instantaneous noise interference, enhances the temporal coherence and decision reliability of the risk assessment results, and provides a stable basis for stage migration judgment.

[0145] This embodiment realizes dynamic calibration of joint importance adaptively in the rehabilitation stage through the joint weight allocation table, and completes the weighted fusion of multi-dimensional motion deviation components in combination with matrix multiplication operations, effectively strengthening the rehabilitation impact weights of key joints. The rehabilitation risk quantification model is based on the two-dimensional parameter fusion of the age-parameter mapping table and the stage-slope comparison table, constructs a user-adaptive S-type function, and nonlinearly maps the joint weighted deviation value to the motion risk proportion. The sliding time window mechanism is used in conjunction with the temporal attention algorithm to capture the motion risk trend while suppressing instantaneous noise, and realize the smooth output of risk probability. This method improves the physiological fit of risk assessment through the synergy of staged weight adaptation and personalized normalization processing; optimizes decision stability with the help of temporal fusion, ensures the scientificity and safety of rehabilitation stage migration judgment, and forms an accurate and reliable dynamic risk quantification system.

[0146] See also Figure 3 In some embodiments, the motion deviation value is reversely mapped to the device parameter matrix to obtain multiple device parameter adjustment values ​​including:

[0147] S301, constructing a device parameter mapping relationship library, including:

[0148] Obtain the preset rehabilitation stage-power response curve, and establish a nonlinear mapping relationship between the motion deviation value and the device power adjustment amount in different rehabilitation stages;

[0149] Configure the motion mode-speed comparison matrix to define the reference speed and allowable adjustment range corresponding to each phase of the gait cycle;

[0150] Loading a safety constraint parameter table to store a damping adjustment threshold boundary based on the user's physiological characteristics;

[0151] S302, decomposing the motion deviation value according to the device parameter mapping relationship library, including:

[0152] According to the current rehabilitation stage index to the rehabilitation stage-power response curve, the time domain integral of the motion deviation value is input into the power conversion module, and the power adjustment amount adapted to the output stage is output;

[0153] Analyze the frequency domain characteristic components of the motion deviation value, match the motion mode-speed comparison matrix to obtain the reference speed correction coefficient;

[0154] The spatial distribution characteristics of the motion deviation value and the user's physiological parameters are input into the damping regulator, and the compliant damping adjustment amount is generated in combination with the safety constraint parameter table;

[0155] S303, outputting device parameter adjustment values, where the device parameter adjustment values ​​include a power adjustment amount, a reference speed correction coefficient, and a compliance damping adjustment amount.

[0156] In step S301, the establishment of the rehabilitation stage-power response curve is based on the coupling analysis of historical rehabilitation data and clinical expert experience. By statistically analyzing the correspondence between the user's motion deviation value and the device power adjustment amount in different rehabilitation stages, combined with the sensitivity requirements of the injury type to the power response, a nonlinear mapping curve with stage characteristics is fitted. For example, a low-slope curve is used in the early rehabilitation stage to achieve mild power compensation, and a high-slope curve is used in the later stage to enhance the response strength.

[0157] The definition of the reference speed of the motion mode-speed comparison matrix comes from the standard gait cycle analysis. The gait cycle can be understood as the complete movement process of the user's unilateral limb from heel touchdown to the same side heel touchdown again, including the support phase, swing phase, etc. The reference speed is set according to the statistical value of the gait phase duration of healthy people, and the allowable adjustment range is dynamically expanded according to the user's joint range of motion test results to ensure adjustment within the physiological tolerance limit.

[0158] The safety constraint parameter table integrates the user's age, bone density, and muscle strength level physiological indicators, and combines biomechanical simulation to calculate the safety threshold of the damping force of each joint to form the dynamic boundary conditions of the damping adjustment amount, which is the threshold boundary of the damping adjustment amount.

[0159] In step S302, the power conversion module converts the nonlinear mapping relationship between the rehabilitation stage and the power response curve into a quantitative output of the power regulation amount through the time accumulation effect of the motion deviation value accumulated by the time domain integral amount. For example, for a persistent foot drop deviation, an increase in the integral amount triggers a higher power compensation.

[0160] Preferably, the frequency domain feature component extracts the periodic fluctuation characteristics of the motion deviation through fast Fourier transform, matches the preset gait phase-speed relationship in the motion pattern-speed comparison matrix, identifies abnormal frequency components and generates a reference speed correction coefficient. For example, when an abnormal shortening of the swing phase period is detected, the reference speed is reduced according to the reference speed correction coefficient.

[0161] The spatial distribution characteristics reflect the vector distribution of motion deviation values ​​in the hip, knee and ankle joints. Combined with the muscle strength balance and joint stability indicators in the user's physiological parameters, the damping force difference required for each joint is calculated through the damping regulator, and then limited according to the safety constraint parameter table to generate a compliant damping adjustment amount that meets the user's current physiological state.

[0162] In step S303, the power adjustment amount compensates for the time-domain cumulative effect of motion deviation by outputting torque of the driving device; the reference speed correction coefficient dynamically adapts to the actual gait rhythm of the user; and the compliance damping adjustment amount balances the force distribution of the joints in the spatial dimension. The three act together on the device actuator to form a precise parameter adjustment of time-frequency-space multi-domain linkage, ensuring that rehabilitation training achieves optimal motion trajectory tracking within the physiological safety boundary.

[0163] This embodiment constructs a device parameter mapping relationship library including a rehabilitation stage-power response curve, a motion mode-speed comparison matrix and a safety constraint parameter table to achieve multi-dimensional decoupling analysis of the time domain integral, frequency domain characteristic components and spatial distribution characteristics of the motion deviation value. Combined with the phase compensation mechanism of the power conversion module, the reference speed dynamic correction algorithm and the biomechanical constraint strategy of the damping regulator, the coordinated output of the power adjustment amount, the reference speed correction coefficient and the compliant damping adjustment amount is generated, which effectively balances the device response sensitivity and physiological tolerance, improves the motion trajectory tracking accuracy while ensuring the safety boundary of the joint movement, and forms an adaptive parameter control system that conforms to the characteristics of the rehabilitation stage and the individual differences of users.

[0164] See also Figure 4 In some embodiments, the motion deviation value is reversely mapped to the user posture matrix to obtain the posture adjustment information of the current user, including:

[0165] S401, constructing a user pose matrix, including:

[0166] Obtain a preset joint-posture mapping table and establish a corresponding relationship between the motion deviation components of each lower limb joint and the ideal posture parameters;

[0167] Configure the rehabilitation stage-correction intensity comparison table to define the maximum posture adjustment range allowed in different rehabilitation stages;

[0168] Load the user's physiological-posture constraint table and store the personalized posture safety range based on the user's height and weight;

[0169] S402, decomposing the motion deviation value according to the user posture matrix, including:

[0170] Decompose the motion deviation value into each joint motion plane, and obtain the initial posture correction value through the joint-posture mapping table;

[0171] According to the current rehabilitation stage, the rehabilitation stage-correction intensity comparison table is queried, and the initial posture correction amount is subjected to intensity standardization to obtain the correction intensity coefficient;

[0172] The correction intensity coefficient, the initial posture correction amount and the user's physiological parameters are input into the posture optimizer, and the safe posture adjustment instruction and the final posture correction amount are generated in combination with the user's physiological-posture constraint table;

[0173] S403, outputting posture adjustment information, where the posture adjustment information includes a correction strength coefficient, an initial posture correction amount, a final posture correction amount, and a safe posture adjustment instruction.

[0174] In step S401, the construction of the joint-posture mapping table is based on the coupling analysis of the lower limb kinematic model and clinical gait data. By collecting the motion angle parameters of the hip, knee, and ankle joints in the sagittal and coronal planes during the gait cycle of healthy people and combining the joint coordination law of the ideal gait trajectory, a quantitative mapping relationship between the joint motion deviation component (such as the knee flexion angle deviation) and the ideal posture parameter (such as the ideal flexion angle) is established.

[0175] Preferably, the definition of the maximum posture adjustment range follows the staging principle of rehabilitation medicine: low amplitude limits are used in the early rehabilitation stage to avoid excessive stretching of damaged tissues, and the adjustment range is gradually increased in the later stages to enhance the training intensity. The specific threshold is calibrated comprehensively through expert experience and biomechanical tolerance testing.

[0176] The user's physiological-posture constraint table calculates the personalized posture safety range by establishing a statistical regression model of height, weight and lower limb joint mobility. For example, it dynamically adjusts the mechanical limit threshold of the hip joint abduction angle according to the length of the user's lower limbs to ensure that the posture adjustment conforms to the anatomical characteristics of the human body.

[0177] In step S402, the motion deviation value decomposition is achieved through multi-plane motion analysis, and the overall motion deviation vector is projected to the sagittal plane, coronal plane and other motion planes of each joint. For example, the foot inversion deviation is decomposed into the ankle joint coronal plane inversion angle deviation component, and then the initial posture correction amount (such as ankle abduction 5°) is obtained based on the joint-posture mapping table matching.

[0178] The intensity normalization process generates a correction intensity coefficient in the range of 0-1 by proportionally converting the initial posture correction amount with the maximum allowable amplitude of the corresponding stage in the rehabilitation stage-correction intensity comparison table. For example, when the initial correction amount is 8° and the maximum amplitude of the stage is 10°, the coefficient is 0.8. The posture optimizer can use a constrained gradient descent algorithm, use the correction intensity coefficient as a weight factor, scale the initial posture correction amount, and perform limited iterative calculations in combination with the safety range boundary in the user's physiological-posture constraint table (such as knee flexion does not exceed 120°), and output the final posture correction amount that meets the physiological limitations and the corresponding safety adjustment instructions (such as "adjust the knee flexion correction from 10° to 8°").

[0179] In step S403, the correction intensity coefficient quantifies the adjustment force adapted during the rehabilitation stage, the initial posture correction value reflects the original correction requirement of the motion deviation value, the final posture correction value represents the actual execution value after safety constraint optimization, and the safe posture adjustment instruction transmits the action execution strategy to the device in text or coded form. The four work together to ensure that the posture adjustment progressively approaches the ideal motion trajectory within the personalized physiological safety range.

[0180] This embodiment constructs a user posture matrix including a joint-posture mapping table, a rehabilitation stage-correction intensity comparison table and a user physiological-posture constraint table, realizes the joint-level decomposition of motion deviation values ​​and the matching of initial posture correction values ​​based on multi-plane motion analysis, generates the final posture correction value and safety adjustment instructions through a posture optimizer combined with the user physiological-posture constraint table, and realizes anatomically precise correction of motion deviation and progressive posture adjustment while ensuring the safe range of personalized joint movement, effectively balances the intensity of rehabilitation training and physiological tolerance, ensures the dynamic adaptability and execution safety of posture adjustment instructions, and promotes the user's motion trajectory to reliably approach ideal parameters.

[0181] In some embodiments, the preset threshold range is configured to be initialized by the following steps when the user trains for the first time:

[0182] Acquire user information, and match a first preset number of group samples in a database according to the user information, wherein the matching constraints include injury type similarity, physiological characteristic similarity, and movement abnormality similarity;

[0183] Obtain a basic adversarial model and iteratively train the basic adversarial model using group samples, including:

[0184] The projected gradient descent method is used to generate disturbance samples that meet the preset disturbance range;

[0185] Repair the disturbed sample according to the preset constraint conditions, where the preset constraint conditions are biomechanical constraint conditions;

[0186] The group samples and the perturbation samples are mixed and input into the basic adversarial model and iteratively trained until a first preset training accuracy threshold is met, indicating that the basic adversarial model training is completed;

[0187] Input the group samples into the trained basic adversarial model and output the sample threshold range of each group sample;

[0188] Arrange multiple sample threshold ranges in order of the degree of matching between the group sample and the user information, and select the sample threshold range with the highest matching degree as the preset threshold range.

[0189] In this embodiment, the determination of the first preset number needs to balance the coverage of the database and the computational efficiency, and is dynamically adjusted by counting the size of the injury type group to which the user belongs and combining it with the training resource limit, for example, selecting the typical sample size based on the clustering result of the injury type similarity. In the step of matching the group samples according to the user information, preferably, the injury type similarity is compared by ICF classification coding, the physiological characteristic similarity is calculated by the Euclidean distance after normalization of parameters such as height, weight, and bone density, and the movement abnormality similarity is evaluated by the cosine similarity of the joint angle deviation vector within the gait cycle, and the weighted scores of the three are combined to select the nearest sample in the database.

[0190] For the iterative training of the basic adversarial model, the setting of the preset perturbation range depends on the clinical research data of the variability of biomechanical parameters, such as the natural fluctuation range of the hip flexion angle, and the upper and lower bounds are determined by counting the standard deviation multiples of the gait parameters of healthy people. When the projected gradient descent method is used to generate perturbation samples, a small perturbation is first applied along the gradient direction in the motion parameter space of the original population sample, and then the perturbed parameter vector is projected into the credible domain formed by the preset perturbation range to ensure that the perturbation sample meets the anatomical kinematic constraints.

[0191] The repair of disturbance samples based on preset constraints is achieved through a biomechanical rule engine. For example, when the disturbance causes the knee flexion angle to exceed the physiological limit, the quadratic programming algorithm is used to adjust the adjacent joint angles to maintain the closure of the lower limb kinematic chain, or the feasible posture is recalculated based on inverse kinematics.

[0192] After the population samples and the repaired perturbation samples are mixed and input into the basic adversarial model, the model learns the discriminative features of the real samples and the perturbation samples through the adversarial training mechanism. During the iterative training process, the misjudgment rate of the classifier drives the optimization of the perturbation strategy until the model reaches a stable discrimination capability for the mixed sample set. Preferably, the first preset training accuracy threshold is set according to the clinical verification results, and the classification accuracy of the model for normal gait and abnormal perturbation on an independent test set is usually required to exceed the preset clinical decision confidence level.

[0193] The trained basic adversarial model extracts the hidden feature distribution of group samples through forward propagation, and combines the kernel density estimation method to output the dynamic threshold range of motion parameters corresponding to each sample, which is the sample threshold range.

[0194] When finally selecting the sample threshold range with the highest matching degree, a weighted fusion strategy is used to multiply the injury type weight, physiological feature weight and movement abnormality weight, and the threshold interval corresponding to the first place in the comprehensive matching degree ranking is selected as the initialization result, which is the preset threshold range.

[0195] This embodiment matches highly correlated group samples based on injury type, physiological characteristics and movement abnormality similarity, combines projected gradient descent to generate perturbation samples under biomechanical constraints, uses adversarial training to optimize the model's ability to distinguish between real and perturbation samples, outputs a dynamic threshold range, and then screens the optimal matching result through weighted fusion, thereby achieving personalized initialization of the preset threshold range during the user's first training, effectively improving the adaptation accuracy of the threshold range with injury characteristics and movement abnormalities, ensuring biomechanical compliance, and enhancing the basic adversarial model's robust recognition ability for abnormal fluctuations in motion parameters.

[0196] In some embodiments, the personalized model further includes a threshold adjustment module, and the method further includes:

[0197] When the user is not training for the first time, the preset threshold range is configured to be updated through the threshold adjustment module, including:

[0198] After the user finishes exercising, the real-time exercise data of the current batch of the user is obtained and recorded as the latest exercise data, and the historical exercise data of each batch within a preset historical period is obtained;

[0199] Generate personal adversarial samples based on the latest and historical motion data;

[0200] Acquire the latest user information of the user, and match the latest group samples of a second preset number in the database according to the latest user information, where the matching constraints include injury type similarity, physiological feature similarity, and movement abnormality similarity;

[0201] The latest group sample and the individual adversarial sample are mixed and input into the threshold adjustment module for iterative training until the second preset training accuracy threshold is met, indicating that the threshold adjustment module has been updated;

[0202] The latest motion data is input into the updated threshold adjustment module to obtain the updated preset threshold range.

[0203] In this embodiment, the determination of the preset historical period needs to comprehensively consider the progress speed of the rehabilitation stage and the stability requirements of the motion data. For example, for users in the early stage of recovery, a shorter period is used to capture rapidly changing characteristics, while for users in the later stage, the period is extended to ensure data continuity.

[0204] Preferably, generating personal adversarial samples based on the latest motion data and historical motion data can be understood as: extracting clinically significant feature frames (such as frames with the highest degree of action completion, frames with the largest deviation, and typical error frames) from the latest motion data, combining diffusion model decoupling to obtain mechanical parameters such as joint angles and muscle activation patterns, and then generating variant samples based on the physical constraints and personal motion pattern characteristics in the historical motion data, and finally inserting the variant samples into the historical data in the original time sequence to form adversarial samples; or reconstructing and generating resonant adversarial samples that meet personal biomechanical characteristics through a desensitization correction strategy that matches similar abnormal cases in a federated shared latent space; or generating standard motion features with interpretable labels based on biomechanical constraints, combining risk assessment indicators to screen effective adversarial samples, and realizing the diverse construction of personalized adversarial samples. The specific content is described below.

[0205] Preferably, the determination of the second preset number follows the same coverage-efficiency balance principle as the first preset number, but the impact of the user's latest physiological state changes on sample matching needs to be additionally considered, such as dynamically adjusting the matching sample size according to the transition of the rehabilitation stage. When matching the latest group sample based on the latest user information, the injury type similarity uses the dynamically updated ICF coding comparison, the physiological feature similarity recalculates the normalized distance based on the latest physical measurement parameters, and the movement abnormality similarity optimizes the deviation vector weight through the latest gait analysis results, forming a multi-dimensional similarity evaluation system to screen the most relevant samples in the database.

[0206] After the latest group samples and personal adversarial samples are mixed and input into the threshold adjustment module, the model learns the discrimination boundary between the real group data and the personalized adversarial perturbation through the adversarial training mechanism. Its classifier continuously adjusts the threshold decision boundary in the process of distinguishing normal movement patterns from adversarial samples until the model achieves stable discrimination performance for the mixed data set. Preferably, the determination of the second preset training accuracy threshold needs to refer to the historical training convergence curve and the clinical expert evaluation results, and usually requires the model to achieve a clinically acceptable level of recognition accuracy for threshold over-limit events on the validation set.

[0207] The updated threshold adjustment module dynamically adjusts the upper and lower limits of the thresholds of each motion parameter by analyzing the distribution offset of the latest motion data in the hidden feature space, combining the correlation between the group sample threshold range and the adversarial sample perturbation intensity, and finally outputs an updated preset threshold range that conforms to the group rules and adapts to the individual's rehabilitation progress.

[0208] This embodiment sets a preset historical period through dynamic adaptation of the rehabilitation stage, generates personal adversarial samples based on the latest motion data and historical motion data, combines the latest group samples of multi-dimensional similarity matching, and uses adversarial training to optimize the threshold decision boundary, so as to achieve a dynamic balance between the threshold range of group rules and individual rehabilitation progress, and improve the personalized adaptability of movement abnormality recognition.

[0209] In some embodiments, generating a personal adversarial sample according to the latest motion data and historical motion data within a preset historical period includes:

[0210] Extracting significant feature information from the latest motion data, the significant feature information including the first motion frame with the highest motion completion, the second motion frame with the largest motion deviation, and the third motion frame with clinical typicality;

[0211] In the dormant state, semantic feature reconstruction is performed on the salient feature information, including:

[0212] The pre-set diffusion model is used to decouple the significant feature information to obtain the kinematic parameters, which include joint angles, joint torque distribution, motion speed curves, and muscle force patterns.

[0213] Construct physical constraint information and personal constraint information based on kinematic parameters;

[0214] Generate variant samples similar to the salient feature information based on historical movement data, physical constraint information, and personal constraint information;

[0215] The mutated samples are inserted into the historical motion data according to the execution sequence of the first action frame, the second action frame, and the third action frame in the latest action data to obtain personal adversarial samples.

[0216] In this embodiment, the generation of personal adversarial samples is achieved by analyzing the significant feature information in the user's latest motion data and fusing historical motion data for mutation reconstruction.

[0217] The first action frame in the significant feature information reflects the user's current optimal motion performance and is used to capture the biomechanical characteristics under the correct motion mode; the second action frame reveals the abnormal mechanical state corresponding to the maximum motion deviation, which is used to locate the weak links in rehabilitation training; the third action frame is associated with clinically typical movement disorder patterns (such as foot drop and knee hyperextension), which is used to match common abnormal features to enhance the medical relevance of the sample.

[0218] Semantic feature reconstruction is performed in the dormant state, that is, background processing tasks are started during the non-real-time operation period of the system. The multimodal motion data is feature decoupled through a preset diffusion model, which is a generative model pre-trained based on the variational autoencoder architecture. Noise disturbances are gradually injected through the forward diffusion process, and then the kinematic parameters such as joint angles and joint torque distribution are separated through the reverse denoising network, realizing the conversion from raw sensor data to interpretable biomechanical indicators.

[0219] Constructing physical constraint information based on kinematic parameters can be understood as extracting human kinematic limit values ​​(such as maximum joint range of motion) from decoupled joint angles and torque distributions to form rigid boundary constraints; personal constraint information is based on the user's unique speed curve pattern in historical motion data, muscle force timing and other parameters to generate soft adaptation rules (such as gait phase deviation tolerance). The two constrain the generation logic of variant samples from the dimensions of biomechanical universality and individual motion characteristics, respectively, to ensure that they conform to anatomical laws and continue the user's personalized motion pattern.

[0220] When generating variant samples, the physical constraint information is used as hard boundary conditions and the personal constraint information is used as a soft optimization target. The generative adversarial network is used to search for feasible solutions that are similar to the information mechanics of the significant feature but with parameter perturbations in the latent space of the historical motion data, forming new samples that retain the user's personalized characteristics and introduce controllable variations.

[0221] Preferably, the process of inserting variant samples into historical data in the original time sequence is implemented through a motion phase alignment algorithm. For example, the first motion frame variant sample is inserted at the beginning of the gait support phase to strengthen the memory of the correct pattern, and the second motion frame variant sample is inserted at the end of the swing phase to simulate extreme deviation scenarios, thereby constructing an adversarial sample set covering multiple scenarios.

[0222] This embodiment extracts motion mechanics parameters that are deeply coupled with clinical characteristics through analysis of key action frames (i.e., significant feature information), and generates safe and compliant variant samples in combination with the physical-individual dual constraint mechanism, thereby providing adversarial training data with both individual adaptability and biomechanical rationality for the threshold adjustment module, thereby enhancing the model's generalization ability for complex motion patterns.

[0223] In some embodiments, generating a personal adversarial sample according to the latest motion data and historical motion data within a preset historical period includes:

[0224] Extracting first abnormal feature information from the latest motion data, the first abnormal feature information including joint motion trajectory deviation features, muscle activation abnormal features, and motion timing disorder features;

[0225] Mapping the first abnormal feature information to the federated shared latent space for similarity matching includes:

[0226] Calculate the latent space projection similarity with the second abnormal feature information of other users in the database;

[0227] Filter matching cases whose latent space projection similarity exceeds a preset similarity threshold, and obtain the desensitization correction strategy associated with the matching cases;

[0228] The first abnormal feature information is fused and reconstructed according to the desensitization correction strategy to generate a resonant adversarial sample after the first abnormal feature information is corrected;

[0229] The generated resonance adversarial sample is mixed with the historical motion data and the latest motion data to obtain the personal adversarial sample.

[0230] In this embodiment, the first abnormal feature information is used to accurately characterize the user's current motor dysfunction mode. The first abnormal feature is mapped to the federated shared latent space for similarity matching, which can optimize the local adversarial sample generation effect by using the correction experience of similar abnormal cases in the group knowledge base under the premise of data desensitization, where the federated shared latent space refers to the cross-institutional feature encoding space obtained through pre-training of the federated learning framework, which can realize feature-level information interaction without sharing the original data.

[0231] Preferably, when calculating the latent space projection similarity, the cosine similarity measurement method of the feature vector is adopted to evaluate the directional alignment of the latent vector after encoding the first abnormal feature and the second abnormal feature latent vector of other users in the database, so as to screen out matching cases with highly similar motion abnormality patterns.

[0232] The preset similarity threshold is determined based on the cluster analysis results of historical rehabilitation cases. By statistically analyzing the distribution density of abnormal features of users with similar injuries in the latent space and combining expert experience to set a minimum similarity threshold (such as 0.75), it ensures that the matching cases have clinical reference value.

[0233] The desensitization correction strategy refers to the anonymization of sensitive parameters involving personal identity information in matching cases (such as age and height), while retaining its abnormal correction logic (such as the adjustment coefficient of the knee hyperextension correction angle).

[0234] The first abnormal feature is weightedly fused with the correction parameters of the matching case through the feature interpolation algorithm to reconstruct a resonant adversarial sample that retains the individual abnormal characteristics of the user and incorporates the group correction experience. For example, for the user's foot inversion trajectory deviation, the matching case provides a strategy for enhancing the valgus torque, which is desensitized and fused according to the similarity weight to generate a correction sample that adapts to the current user's muscle strength level.

[0235] Finally, the resonant adversarial samples are mixed with historical and latest motion data to form a dataset covering individual and group dual-dimensional abnormal patterns, providing the threshold adjustment module with adversarial training samples that are both biomechanically reasonable and privacy-compliant, thereby enhancing the model's generalized recognition capabilities for complex movement disorders.

[0236] This embodiment achieves privacy-preserving matching and adversarial sample generation of cross-user abnormal features through a federated shared latent space. After extracting joint trajectory deviation, muscle activation abnormality, and timing disorder features, the first abnormal feature is mapped to the shared latent space constructed by federated learning for cosine similarity matching, and desensitization correction strategies for highly similar cases are screened. Resonant adversarial samples are generated through feature interpolation fusion, and finally historical and latest motion data are mixed to form a training set. Under the premise of protecting user privacy, this method generates adversarial samples that are both biomechanically reasonable and personalized by dynamically integrating group correction experience and individual abnormal features, effectively improving the generalization recognition accuracy of the threshold adjustment module for complex movement disorder patterns and the reliability of rehabilitation decisions.

[0237] In some embodiments, generating a personal adversarial sample according to the latest motion data and historical motion data within a preset historical period includes:

[0238] Extracting first motion feature information from the latest motion data, the first motion feature information including the user's habitual motion pattern features, typical incorrect motion features, and biomechanical reasonable motion features;

[0239] generating second motion characteristic information based on the biomechanical constraint condition, wherein the second motion characteristic information is configured to meet clinical standards but have a preset difference from the first motion characteristic information;

[0240] Add an explainability label to each second action feature information, where the explainability label contains specific quantitative indicators required for action improvement;

[0241] Inputting the first action feature information and the second action feature information into the personalized model respectively, obtaining a first risk assessment result corresponding to the first action feature information and a second risk assessment result corresponding to the second action feature information;

[0242] generating an acceptance index based on the second risk assessment result, and generating a stubbornness index based on the first risk assessment result;

[0243] The second action feature information is filtered according to the acceptance index and the stubbornness index, and recorded as a valid adversarial sample, and mixed with the historical motion data and the latest motion data to obtain a personal adversarial sample.

[0244] In this embodiment, the first motion feature information extracted from the latest motion data includes the user's habitual motion pattern characteristics (such as a small knee flexion angle in the gait cycle), typical incorrect motion characteristics (such as excessive ankle inversion when the heel touches the ground) and biomechanically reasonable motion characteristics (such as a hip joint extension angle that meets standard gait parameters).

[0245] The process of generating the second motion feature information based on biomechanical constraints can be understood as constructing ideal motion parameters according to clinical kinematic specifications (such as the safe range of joint mobility), introducing controllable variations through preset differences (such as joint angle ±5° offset, timing phase ±10% delay), and forming a standard motion feature set that has adjustable deviations from the user's current motion pattern.

[0246] The explainable labels added to each second action feature information contain specific quantitative indicators of action improvement requirements (such as "hip abduction angle needs to be increased by 3°" or "plantar pressure center moves forward 2cm"), which are used to clarify the optimization direction and execution standards of adversarial samples.

[0247] After the first motion feature information and the second motion feature information are input into the personalized model, the first risk assessment result obtained reflects the movement risk probability in the user's current motion mode (such as habitual insufficient flexion leading to a risk value of 0.4 for knee arthritis), and the second risk assessment result evaluates the potential risk after the standard motion is adjusted (such as a risk value of 0.2 after increasing the hip abduction angle).

[0248] The acceptance index is generated by comparing the second risk assessment result with the user's physiological tolerance threshold, characterizing the feasibility of the standard action adjustment plan (for example, if the risk reduction reaches 30%, the acceptance is high); the stubbornness index is calculated based on the degree of deviation of the first risk assessment result relative to the historical training data, reflecting the potential harm of the user maintaining the current action pattern (for example, if the risk value continues to be 20% higher than the average of similar users, the stubbornness is high).

[0249] When screening effective adversarial samples, priority is given to the second action feature information whose acceptance index is higher than the preset acceptance threshold and whose stubbornness index reaches the alarm level (such as acceptance>0.7 and stubbornness>0.6), to ensure that the adversarial samples can both guide users to transition to reasonable biomechanical actions and break through the training inertia of their inherent error patterns. Preferably, the preset acceptance threshold is set by statistically analyzing the median distribution of the risk reduction rate of standard actions adjusted in historical training of users with similar injuries, such as taking the lowest acceptance percentile of successful cases; the alarm level is determined based on the statistical fluctuation range of the user's historical risk assessment results, and is triggered when the stubbornness index exceeds two standard deviations of the personal historical mean. The specific threshold is calibrated by clinical experts based on the injury type and rehabilitation stage to ensure that the screening criteria have both group universality and individual adaptability.

[0250] Finally, historical motion data, the latest motion data and the screened effective adversarial samples are mixed to form a multi-dimensional training set covering habitual patterns, standard movements and gradual adjustment instructions. By repeatedly exposing users to optimized motion scenarios, the model's ability to guide behavioral pattern migration is enhanced, achieving targeted correction of incorrect movements in rehabilitation training and gradual reshaping of exercise habits.

[0251] It should be noted that the above three embodiments all generate personal adversarial samples based on the latest motion data and historical motion data within a preset historical period. The difference is that: the first embodiment of the above three embodiments focuses on semantic reconstruction based on the user's own motion characteristics, generates variant samples that conform to individual biomechanical characteristics through physical constraints and historical data, and mainly enhances the model's ability to recognize specific motion pattern deviations; the second embodiment of the above three embodiments uses the correction strategy of matching external similar cases in the federated shared latent space, and expands the generalization of the model to rare abnormal patterns through resonant adversarial samples; the third embodiment of the above three embodiments integrates clinical standards to generate comparative samples with interpretable labels, combines risk assessment to screen effective adversarial samples, and guides the model to identify reasonable improvement directions. The three generate adversarial samples from three dimensions: individual feature enhancement, group knowledge transfer, and clinical rule guidance, forming a complementary relationship: the first embodiment of the above three embodiments ensures personalized adaptation, the second embodiment of the above three embodiments supplements data diversity, and the third embodiment of the above three embodiments injects clinical prior knowledge, and jointly improves the dynamic adaptability of the threshold adjustment module to complex motion abnormalities.

[0252] See also Figure 5 In the second aspect, the present embodiment further provides a lower limb motion data real-time analysis system 1 for rehabilitation guidance, which is applicable to the real-time analysis method of the first aspect, and the system includes a data acquisition module 11 and a logic processing module 12;

[0253] The data collection module 11 is used to obtain user information. The data collection module 11 is also used to obtain the real-time motion data of the current user according to a preset frequency;

[0254] The logic processing module 12 is used to call the personalized model corresponding to the current user according to the user information, the personalized model is configured as a group confrontation pre-training model, and the personalized model includes a real-time prediction module;

[0255] The logic processing module 12 is also used to input the real-time motion data into the personalized model to obtain the user's motion risk probability and correction information, the correction information including the device parameter adjustment value and posture adjustment information, including:

[0256] The real-time motion data is converted into a multi-frame historical motion feature vector arranged in time order, and input into a real-time prediction module, which is configured to be built based on a lightweight LSTM network model;

[0257] The real-time prediction module performs encoding and decoding operations on the historical motion feature vectors of multiple frames to obtain the future motion feature vectors of multiple frames arranged in chronological order;

[0258] Obtaining a preset threshold range, calculating the deviation value between each future motion feature vector and the preset threshold range, and obtaining motion deviation values ​​arranged in chronological order;

[0259] The motion risk ratio of each future motion feature vector is calculated according to the motion deviation value, and multiple motion risk ratios are weightedly fused to obtain the motion risk probability;

[0260] and, reversely mapping the motion deviation value to a device parameter matrix to obtain a plurality of device parameter adjustment values, and reversely mapping the motion deviation value to a user posture matrix to obtain posture adjustment information of the current user;

[0261] Whether to execute the next stage of stage training steps is determined based on the sports risk probability assessment, and the correction information is displayed and the corresponding equipment operating parameters are adjusted.

[0262] In this embodiment, preferably, the data acquisition module 11 includes a wearable inertial measurement unit, a joint angle sensor and a physiological parameter acquisition device, which is used to obtain real-time physiological data such as lower limb movement trajectory, joint angle changes, user heart rate, electromyography signals, etc., and integrates a user information entry interface to receive clinical information such as injury type and rehabilitation stage.

[0263] The real-time analysis system of this embodiment executes the real-time analysis method described in the first aspect. The specific content refers to the aforementioned technical solution and will not be described in detail here.

[0264] By adopting the above technical solution, the present invention is different from the prior art and has the following beneficial effects:

[0265] The present invention realizes accurate rehabilitation decision-making by constructing a group-individual adversarial pre-training model, calling a personalized model based on user information, using a lightweight LSTM network to encode historical motion feature vectors in real time and decode to predict future motion trends, combining a dynamic threshold mechanism to calculate motion deviation values, and synchronously generating device parameter adjustment values ​​and posture correction information. The adversarial training framework balances group universality and individual differences, uses the reverse mapping of the device parameter matrix to achieve multi-dimensional adjustment of power, speed and damping, and generates safe correction instructions in combination with the anatomical constraints of the user posture matrix. The dynamic threshold initialization and update mechanism integrates group sample matching, biomechanical constraint repair and federal shared latent space matching strategies, and introduces group correction experience to generate personalized adversarial samples under the premise of privacy protection. Effective adversarial samples are screened based on biomechanical reasonable motion characteristics and risk assessment indicators, and motion migration guidance is optimized in combination with acceptance and stubbornness indicators. The system forms a closed-loop optimized rehabilitation training process control through real-time motion risk probability assessment and device-posture collaborative adjustment, improves the motion trajectory tracking accuracy while ensuring the physiological safety boundary, and realizes the accuracy, real-time and safety of personalized rehabilitation guidance.

[0266] Finally, it should be noted that although the above embodiments have been described in the specification and drawings of this application, this does not limit the scope of patent protection of this application. All technical solutions generated by replacing or modifying equivalent structures or equivalent processes based on the essential concept of this application using the contents recorded in the specification and drawings of this application, as well as directly or indirectly implementing the technical solutions of the above embodiments in other related technical fields, are included in the scope of patent protection of this application.

Claims

1. A real-time analysis method for lower limb motion data for rehabilitation guidance, characterized in that: include: Acquire user information, and call a personalized model corresponding to the current user according to the user information, wherein the personalized model is configured as a group-individual adversarial pre-training model, and the personalized model includes a real-time prediction module; The real-time motion data of the current user is obtained at a preset frequency, and is input into the personalized model to obtain the user's motion risk probability and correction information, wherein the correction information includes device parameter adjustment values ​​and posture adjustment information, including: Convert the real-time motion data into a plurality of historical motion feature vectors arranged in chronological order, and input the historical motion feature vectors into a real-time prediction module, wherein the real-time prediction module is configured to be constructed based on a lightweight LSTM network model; The real-time prediction module performs encoding and decoding operations on the historical motion feature vectors of multiple frames to obtain future motion feature vectors of multiple frames arranged in chronological order; Obtaining a preset threshold range, calculating a deviation value between each of the future motion feature vectors and the preset threshold range, and obtaining motion deviation values ​​arranged in chronological order; Calculate the motion risk ratio of each future motion feature vector according to the motion deviation value, and perform weighted fusion on multiple motion risk ratios to obtain the motion risk probability; and, reversely mapping the motion deviation value to a device parameter matrix to obtain a plurality of device parameter adjustment values, and reversely mapping the motion deviation value to a user posture matrix to obtain posture adjustment information of the current user; Whether to execute the next stage training step is determined based on the motion risk probability assessment, and the correction information is displayed and the corresponding equipment operating parameters are adjusted.

2. The real-time analysis method for lower limb motion data for rehabilitation guidance according to claim 1, characterized in that: Calculating the motion risk ratio of each future motion feature vector according to the motion deviation value, and weighted fusion of multiple motion risk ratios to obtain the motion risk probability includes: Obtaining a preset joint weight distribution table, wherein the joint weight distribution table stores weight coefficients of each lower limb joint at different rehabilitation stages, and the weight coefficients are positively correlated with the importance of the lower limb joints in rehabilitation training; According to the user's current rehabilitation stage, extracting a corresponding set of weight coefficients from the joint weight allocation table; For each of the future motion feature vectors, performing matrix multiplication operation on the motion deviation components of each lower limb joint contained therein and the corresponding weight coefficient to obtain a joint weighted deviation value after dimension compression; The joint weighted deviation value is input into the rehabilitation risk quantification model for nonlinear normalization processing, and the motion risk proportion of each future motion feature vector is output. The rehabilitation risk quantification model is obtained by the following steps: Obtain a preset age-parameter mapping table and call a basic parameter group of the S-type function that matches the user's age; According to the current rehabilitation stage, query the stage-slope comparison table to obtain the corresponding slope adjustment coefficient; The basic parameter group and the slope adjustment coefficient are subjected to feature fusion through a one-dimensional convolution layer to generate a user-adaptive normalization function, i.e., the rehabilitation risk quantification model; The motion risk proportions of multiple frames are time-series fused using a sliding time window method to obtain the motion risk probability.

3. The real-time analysis method for lower limb motion data for rehabilitation guidance according to claim 1, characterized in that: The motion deviation value is reversely mapped to the device parameter matrix to obtain multiple device parameter adjustment values ​​including: Build a device parameter mapping library, including: Obtain the preset rehabilitation stage-power response curve, and establish a nonlinear mapping relationship between the motion deviation value and the device power adjustment amount in different rehabilitation stages; Configure the motion mode-speed comparison matrix to define the reference speed and allowable adjustment range corresponding to each phase of the gait cycle; Loading a safety constraint parameter table to store a damping adjustment threshold boundary based on the user's physiological characteristics; Decomposing the motion deviation value according to the device parameter mapping relationship library includes: According to the current rehabilitation stage index to the rehabilitation stage-power response curve, the time domain integral of the motion deviation value is input into the power conversion module, and the power adjustment amount adapted for the output stage is output; Analyze the frequency domain characteristic components of the motion deviation value, and match the motion mode-speed comparison matrix to obtain a reference speed correction coefficient; Inputting the spatial distribution characteristics of the motion deviation value and the user's physiological parameters into the damping regulator, and combining the safety constraint parameter table to generate a compliant damping adjustment amount; Output device parameter adjustment values, wherein the device parameter adjustment values ​​include a power adjustment amount, a reference speed correction coefficient, and a compliance damping adjustment amount.

4. The real-time analysis method for lower limb motion data for rehabilitation guidance according to claim 1, characterized in that: The motion deviation value is reversely mapped to the user posture matrix to obtain the posture adjustment information of the current user, including: Construct the user pose matrix, including: Obtain a preset joint-posture mapping table and establish a corresponding relationship between the motion deviation components of each lower limb joint and the ideal posture parameters; Configure the rehabilitation stage-correction intensity comparison table to define the maximum posture adjustment range allowed in different rehabilitation stages; Load the user's physiological-posture constraint table and store the personalized posture safety range based on the user's height and weight; Decomposing the motion deviation value according to the user posture matrix includes: Decomposing the motion deviation value into each joint motion plane, and obtaining the initial posture correction value through the joint-posture mapping table; According to the current rehabilitation stage, the rehabilitation stage-correction intensity comparison table is queried, and the initial posture correction amount is subjected to intensity standardization processing to obtain a correction intensity coefficient; Inputting the correction intensity coefficient, the initial posture correction amount and the user's physiological parameters into the posture optimizer, and generating a safe posture adjustment instruction and a final posture correction amount in combination with the user's physiological-posture constraint table; Output posture adjustment information, wherein the posture adjustment information includes a correction strength coefficient, an initial posture correction amount, a final posture correction amount, and a safe posture adjustment instruction.

5. The real-time analysis method of lower limb motion data for rehabilitation guidance according to claim 1, characterized in that: The preset threshold range is configured to be initialized by the following steps when the user is training for the first time: Acquire user information, and match a first preset number of group samples in a database according to the user information, wherein the matching constraints include injury type similarity, physiological feature similarity, and movement abnormality similarity; A basic adversarial model is obtained, and group samples are used to iteratively train the basic adversarial model, including: The projected gradient descent method is used to generate disturbance samples that meet the preset disturbance range; Repairing the disturbance sample according to preset constraint conditions, wherein the preset constraint conditions are biomechanical constraint conditions; Mixing the population sample and the disturbance sample and inputting them into the basic adversarial model for iterative training until a first preset training accuracy threshold is met, indicating that the basic adversarial model training is completed; Input the group samples into the trained basic adversarial model, and output the sample threshold range of each group sample; The plurality of sample threshold ranges are arranged in order of the degree of matching between the group sample and the user information, and the sample threshold range with the highest degree of matching is selected as the preset threshold range.

6. The real-time analysis method of lower limb motion data for rehabilitation guidance according to claim 1, characterized in that: The personalized model further includes a threshold adjustment module, and the method further includes: When the user is not training for the first time, the preset threshold range is configured to be updated by the threshold adjustment module, including: After the user finishes exercising, the real-time exercise data of the current batch of the user is obtained and recorded as the latest exercise data, and the historical exercise data of each batch within a preset historical period is obtained; Generate a personal adversarial sample based on the latest motion data and the historical motion data; Acquire the latest user information of the user, and match the latest group samples of a second preset number in the database according to the latest user information, where the matching constraints include injury type similarity, physiological feature similarity, and movement abnormality similarity; The latest group sample and the individual adversarial sample are mixed and input into the threshold adjustment module for iterative training until a second preset training accuracy threshold is met, indicating that the threshold adjustment module has been updated; The latest motion data is input into the updated threshold adjustment module to obtain an updated preset threshold range.

7. The real-time analysis method for lower limb motion data for rehabilitation guidance according to claim 6, characterized in that: Generating a personal adversarial sample according to the latest motion data and the historical motion data within a preset historical period includes: Extracting significant feature information from the latest motion data, the significant feature information including a first motion frame with the highest motion completion, a second motion frame with the largest motion deviation, and a third motion frame with clinical typicality; In the dormant state, the semantic feature reconstruction of the salient feature information includes: Decoupling the significant feature information through a preset diffusion model to obtain kinematic parameters, which include joint angles, joint torque distribution, motion speed curves, and muscle force patterns; constructing physical constraint information and personal constraint information according to the kinematic parameters; Generating a variation sample similar to the significant feature information based on the historical motion data, the physical constraint information, and the personal constraint information; The variant sample is inserted into the historical motion data according to the execution sequence of the first action frame, the second action frame, and the third action frame in the latest action data to obtain the personal adversarial sample.

8. The real-time analysis method for lower limb motion data for rehabilitation guidance according to claim 6, characterized in that: Generating a personal adversarial sample according to the latest motion data and the historical motion data within a preset historical period includes: Extracting first abnormal feature information from the latest motion data, wherein the first abnormal feature information includes joint motion trajectory deviation features, muscle activation abnormality features, and motion timing disorder features; Mapping the first abnormal feature information to the federated shared latent space for similarity matching includes: Calculate the latent space projection similarity with the second abnormal feature information of other users in the database; Filter matching cases whose latent space projection similarity exceeds a preset similarity threshold, and obtain the desensitization correction strategy associated with the matching cases; According to the desensitization correction strategy, the first abnormal feature information is fused and reconstructed to generate a resonance adversarial sample after the first abnormal feature information is corrected; The generated resonance adversarial sample is mixed with the historical motion data and the latest motion data to obtain the personal adversarial sample.

9. The real-time analysis method for lower limb motion data for rehabilitation guidance according to claim 6, characterized in that: Generating a personal adversarial sample according to the latest motion data and the historical motion data within a preset historical period includes: Extracting first motion feature information from the latest motion data, wherein the first motion feature information includes a user's habitual motion pattern features, typical incorrect motion features, and biomechanical reasonable motion features; generating second motion characteristic information based on the biomechanical constraint condition, wherein the second motion characteristic information is configured to meet clinical standards but has a preset difference from the first motion characteristic information; Adding an explainability label to each second action feature information, wherein the explainability label includes specific quantitative indicators required for action improvement; Inputting the first action feature information and the second action feature information into a personalized model respectively, obtaining a first risk assessment result corresponding to the first action feature information and a second risk assessment result corresponding to the second action feature information; generating an acceptance index according to the second risk assessment result, and generating a stubbornness index according to the first risk assessment result; The second action feature information is filtered according to the acceptance index and the stubbornness index, and recorded as a valid adversarial sample, and mixed with the historical motion data and the latest motion data to obtain the personal adversarial sample.

10. A real-time analysis system for lower limb motion data used for rehabilitation guidance, characterized in that: The real-time analysis method according to any one of claims 1 to 9, wherein the system comprises a data acquisition module and a logic processing module; The data acquisition module is used to obtain user information, and the data acquisition module is also used to obtain the real-time motion data of the current user according to a preset frequency; The logic processing module is used to call the personalized model corresponding to the current user according to the user information, the personalized model is configured as a group adversarial pre-training model, and the personalized model includes a real-time prediction module; The logic processing module is also used to input the real-time motion data into the personalized model to obtain the user's motion risk probability and correction information, wherein the correction information includes device parameter adjustment values ​​and posture adjustment information, including: Convert the real-time motion data into a plurality of historical motion feature vectors arranged in chronological order, and input the historical motion feature vectors into a real-time prediction module, wherein the real-time prediction module is configured to be constructed based on a lightweight LSTM network model; The real-time prediction module performs encoding and decoding operations on the historical motion feature vectors of multiple frames to obtain future motion feature vectors of multiple frames arranged in chronological order; Obtaining a preset threshold range, calculating a deviation value between each of the future motion feature vectors and the preset threshold range, and obtaining motion deviation values ​​arranged in chronological order; Calculate the motion risk ratio of each future motion feature vector according to the motion deviation value, and perform weighted fusion on multiple motion risk ratios to obtain the motion risk probability; and, reversely mapping the motion deviation value to a device parameter matrix to obtain a plurality of device parameter adjustment values, and reversely mapping the motion deviation value to a user posture matrix to obtain posture adjustment information of the current user; Whether to execute the next stage training step is determined based on the motion risk probability assessment, and the correction information is displayed and the corresponding equipment operating parameters are adjusted.

Images