Method and System for Generating Personalized Training Plans in the Metaverse Smart Sports

Abstract

The present invention provides a method and system for generating personalized training plans in metaverse intelligent sports, which relates to the technical field of intelligent sports. It includes obtaining the user's metaverse scene movement data, calculating the actual exercise load based on the human biomechanics model, using neural networks for time series analysis to predict the physiological limit threshold, constructing a training knowledge graph, and generating a phased training plan adapted to the user through a graph neural network, and finally presenting it in the form of a metaverse virtual scene. The present invention can provide personalized, safe and scientific training guidance, improving the training effect and user experience.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent sports, and particularly to a method and system for generating personalized training plans in metaverse intelligent sports. Background Art

[0002] With the booming development of metaverse technology, combining intelligent sports training with metaverse virtual scenarios has become an important research direction. Traditional sports training methods mainly rely on coaches' experience for guidance, making it difficult to achieve precise personalized training planning. The intelligent sports training system in the metaverse environment can collect users' real-time sports data through sensing devices, analyze users' sports performance by combining artificial intelligence algorithms, and provide users with immersive virtual training experiences. Currently, related research mainly focuses on aspects such as sports data collection, action recognition and analysis, and virtual scene construction.

[0003] However, the existing metaverse intelligent sports training systems still have deficiencies. They lack an accurate evaluation mechanism for users' exercise loads, are unable to accurately grasp users' physiological limits, and are prone to overtraining or undertraining; the formulation of training plans is too simplistic, failing to fully consider users' historical training data and personalized needs, resulting in unsatisfactory training effects; the knowledge representation method is single, making it difficult to effectively explore the correlation relationships between training items and unable to achieve scientific progression of training plans; there is a lack of analysis of users' long-term training patterns, making it difficult to accurately predict users' training effects. Summary of the Invention

[0004] Embodiments of the present invention provide a method and system for generating personalized training plans in metaverse intelligent sports, which can solve the problems in the prior art.

[0005] In the first aspect of the embodiments of the present invention, a method for generating a personalized training plan in metaverse intelligent sports is provided, including:

[0006] Obtain the sports data of the user in the metaverse virtual scene;

[0007] Based on the bone joint point position data in the sports data, call a preset human biomechanics model to calculate the corresponding exercise load parameters of the user in the real environment;

[0008] Perform time series analysis on the exercise load parameters through a neural network model, use an attention mechanism to extract the long-term and short-term features of the user's exercise pattern, and based on the extracted long-term and short-term features, predict the physiological limit thresholds of the user under different exercise intensities;

[0009] Construct training knowledge triples according to the user's historical training data, and construct a personalized training knowledge graph through multi-level knowledge extraction and dynamic graph optimization based on the training knowledge triples;

[0010] Construct a graph neural network model, input the personalized training knowledge graph into the graph neural network model, and generate a phased training plan for the user based on the node feature vectors output by the graph neural network model. Among them, the training items in the phased training plan are sorted according to a progressive relationship, and the exercise intensity of each training item is within the range of the physiological limit threshold;

[0011] Convert the phased training plan into training instructions for the metaverse virtual scene, and display a training guidance interface in the metaverse virtual scene.

[0012] In an alternative embodiment,

[0013] Based on the bone joint point position data in the motion data, call a preset human biomechanical model to calculate the corresponding motion load parameters of the user in the real environment, including:

[0014] According to the bone joint point position data in the motion data, use a kinematic inversion model to calculate the user's joint angle data; based on the joint angle data at adjacent moments, calculate the user's joint motion speed data and joint motion acceleration data;

[0015] Establish a human bone link model, map the bone joint point position data to the corresponding bone nodes in the human bone link model, and calculate the pressure values and torque values of each joint according to the connection relationship between the bone nodes in the human bone link model;

[0016] Input the joint angle data and joint force data into the static force analysis channel of a preset human biomechanical model for processing to obtain static force characteristics, which characterize the muscle force distribution required for the user to maintain the current posture;

[0017] Input the joint motion speed data and the joint motion acceleration data into the dynamic force analysis channel of the human biomechanical model for processing to obtain dynamic force characteristics, which characterize the joint impact force and inertial force during the user's movement;

[0018] Perform fusion processing on the static force characteristics and the dynamic force characteristics through the feature fusion layer of the human biomechanical model to obtain the output result of the feature fusion layer;

[0019] Calculate the corresponding motion load parameters of the user in the real environment according to the output result of the feature fusion layer.

[0020] In an alternative embodiment, time series analysis is performed on the exercise load parameters through a neural network model. The attention mechanism is used to extract the long-term and short-term features of the user's exercise pattern. Based on the extracted long-term and short-term features, the physiological limit thresholds of the user under different exercise intensities are predicted, including:

[0021] An adaptive time window is constructed according to the user's historical exercise load parameters, and the window length is dynamically adjusted based on the exercise volatility to generate variable-length time series data segments;

[0022] The variable-length time series data segments are input into a recurrent convolutional neural network, and local exercise feature sequences are extracted through a multi-layer recurrent convolutional structure;

[0023] The local exercise feature sequences are input into a graph attention network, the local exercise feature sequences are constructed into a time series feature map, and the time series dependence relationship between feature nodes is extracted through graph convolution operations to obtain global correlation features;

[0024] The local exercise feature sequences and the global correlation features are input into a time series attention module. The time series attention module constructs a multi-scale feature pyramid and calculates adaptive weight coefficients for the local exercise feature sequences at different time scales;

[0025] The adaptive weight coefficients and the global correlation features are subjected to time series cross-attention calculation to generate enhanced features at multiple time scales, and the enhanced features at the multiple time scales are fused through a cross-scale feature aggregation network to obtain the long-term and short-term features of the user's exercise pattern;

[0026] A Bayesian neural network is used to model the long-term and short-term features, the probability distribution function of the physiological limit threshold is calculated, and the mean value of the probability distribution function is used as the prediction result of the physiological limit threshold of the user under different exercise intensities.

[0027] In an alternative embodiment, a Bayesian neural network is used to model the long-term and short-term features, the probability distribution function of the physiological limit threshold is calculated, and the mean value of the probability distribution function is used as the prediction result of the physiological limit threshold of the user under different exercise intensities, including:

[0028] The long-term and short-term features are input into a feature encoding network to generate a sequence of feature vectors;

[0029] A Bayesian neural network is constructed, latent variables are set in each layer of the Bayesian neural network, and the sequence of feature vectors is input into the Bayesian neural network;

[0030] Based on the sequence of feature vectors, training sample pairs are constructed, and a variational autoencoder is used to model the latent variables in the Bayesian neural network to obtain the prior distribution of the latent variables;

[0031] Input the prior distribution of the latent variable into a probabilistic neural network to generate a weight distribution, which is used to characterize the uncertainty of each layer of network parameters in the Bayesian neural network;

[0032] Optimize the weight distribution through the stochastic variational inference method, generate multiple sets of network parameters according to the weight distribution, construct a deep ensemble model based on the multiple sets of network parameters, input new long-term and short-term features into the deep ensemble model, and output multiple prediction results based on the deep ensemble model;

[0033] Perform probability density estimation on the multiple prediction results to obtain the probability distribution function of the physiological limit threshold, calculate the mean of the probability distribution function, and use the mean as the prediction result of the user's physiological limit threshold under different exercise intensities.

[0034] In an alternative embodiment, construct training knowledge triples based on the user's historical training data, and construct a personalized training knowledge graph through multi-level knowledge extraction and dynamic graph optimization, including:

[0035] Perform temporal segmentation on the user's historical training data to obtain training data sequences for multiple training cycles;

[0036] Extract training entities and training relationships from the training data sequences, construct training knowledge triples, input the training knowledge triples into a knowledge reasoning model, and perform semantic expansion on the training knowledge triples based on the knowledge reasoning model;

[0037] Perform multi-granularity partitioning on the training knowledge triples, construct knowledge subgraphs at each granularity level, where the knowledge subgraphs contain training entity nodes and training relationship edges at that granularity level;

[0038] Perform representation learning on the knowledge subgraphs, iteratively update the feature representations of the training entity nodes through a message passing mechanism, calculate the similarity matrix between nodes based on the updated feature representations, and construct a node importance scoring model in combination with the weight distribution of the training relationship edges;

[0039] Calculate the importance scores of the training entity nodes according to the node importance scoring model, set an adaptive pruning threshold based on the importance scores, perform dynamic pruning on the knowledge subgraphs, and aggregate the features of the pruned multiple knowledge subgraphs to construct a hierarchical training knowledge graph;

[0040] Map new training data to the hierarchical training knowledge graph, and update the training entity nodes and training relationship edges in the hierarchical training knowledge graph;

[0041] Generate a personalized training knowledge graph based on the hierarchical training knowledge graph.

[0042] In an alternative embodiment, construct a graph neural network model, input the personalized training knowledge graph into the graph neural network model, and generate a phased training plan for the user based on the node feature vectors output by the graph neural network model, including:

[0043] Construct a graph neural network model, perform spatial dimension encoding on the topological structure features of training entity nodes, and use a temporal-aware graph convolutional network to model the dynamic evolution features of training entity nodes in the temporal dimension to obtain spatial dimension features and temporal dimension features;

[0044] Input the personalized training knowledge graph into the graph neural network model, and adaptively fuse the spatial dimension features and the temporal dimension features through a multi-layer cross-attention mechanism to generate multi-dimensional feature vectors of training entity nodes;

[0045] Use self-attention-guided graph pooling operations to sparsely reduce the dimensionality of the multi-dimensional feature vectors to obtain compressed feature representations of training entity nodes;

[0046] Construct a hierarchical reinforcement learning model for multi-objective joint optimization based on the compressed feature representations, model the progression relationship constraint and the exercise intensity constraint as hierarchical optimization objectives, and separately learn the global sorting strategy and local intensity parameters of training items through a two-layer policy network;

[0047] Input the global sorting strategy and the local intensity parameters into the training plan generation module, determine the progression order of training items according to the global sorting strategy, and adjust the exercise intensity of training items according to the local intensity parameters to generate a phased training plan that meets the progression relationship and exercise intensity requirements.

[0048] In an alternative embodiment, construct a hierarchical reinforcement learning model for multi-objective joint optimization based on the compressed feature representations, model the progression relationship constraint and the exercise intensity constraint as hierarchical optimization objectives, and separately learn the global sorting strategy and local intensity parameters of training items through a two-layer policy network, including:

[0049] Model the progression relationship constraint of training items as a high-level optimization objective, model the exercise intensity constraint of training items as a low-level optimization objective, and calculate the high-level reward value and low-level reward value of the state-action pair using a fuzzy evaluation matrix;

[0050] Construct a two - layer policy network. The high - level policy network of the two - layer policy network uses a multi - scale sliding time window to segment and encode the training item sequence, calculates the progressive correlation score between items within each time window, and dynamically adjusts the progressive correlation threshold in combination with the high - level reward value to generate a global sorting reference policy for training items;

[0051] The low - level policy network of the two - layer policy network constructs a multi - dimensional physiological load model based on the heart rate variability index and exercise metabolism level of training items, and dynamically adjusts the intensity parameters through a soft - constraint optimization method introducing a buffer interval in combination with the low - level reward value to generate a local intensity adjustment policy for training items;

[0052] Establish a two - way information channel between the high - level policy network and the low - level policy network using a recurrent neural network. Input the global sorting reference policy and the local intensity adjustment policy into the two - way information channel, and iteratively optimize the global sorting reference policy and the local intensity adjustment policy based on a cross - layer constraint function to obtain the global sorting policy and local intensity parameters of training items.

[0053] In the second aspect of the embodiments of the present invention, a personalized training plan generation system in a meta - universe intelligent exercise is provided, including:

[0054] A first unit for obtaining the exercise data of a user in a meta - universe virtual scene;

[0055] A second unit for calling a preset human biomechanics model to calculate the corresponding exercise load parameters of the user in the real environment based on the bone joint point position data in the exercise data;

[0056] A third unit for performing time - series analysis on the exercise load parameters through a neural network model, extracting long - term and short - term features of the user's exercise pattern using an attention mechanism, and predicting the physiological limit threshold of the user under different exercise intensities based on the extracted long - term and short - term features;

[0057] A fourth unit for constructing training knowledge triples based on the user's historical training data, and constructing a personalized training knowledge graph through multi - level knowledge extraction and dynamic graph optimization based on the training knowledge triples;

[0058] A fifth unit for constructing a graph neural network model, inputting the personalized training knowledge graph into the graph neural network model, and generating a phased training plan for the user based on the node feature vectors output by the graph neural network model. Among them, the training items in the phased training plan are sorted according to a progressive relationship, and the exercise intensity of each training item is within the range of the physiological limit threshold;

[0059] The sixth unit is used to convert the phased training plan into training instructions for the metaverse virtual scene, and display a training guidance interface in the metaverse virtual scene.

[0060] In a third aspect of the embodiments of the present invention, an electronic device is provided, including:

[0061] A processor;

[0062] A memory for storing instructions executable by the processor;

[0063] Wherein, the processor is configured to call the instructions stored in the memory to execute the method described above.

[0064] In a fourth aspect of the embodiments of the present invention, a computer-readable storage medium is provided, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the method described above is implemented.

[0065] In the embodiments of the present invention, by obtaining the motion data of the user in the metaverse virtual scene, combining the human biomechanics model and the neural network model, the real motion load of the user can be accurately calculated and the physiological limit threshold can be predicted, thus ensuring the scientificity and safety of the training plan and effectively avoiding the risks of overtraining or undertraining; constructing a personalized training knowledge graph and applying a graph neural network to generate a training plan, fully considering the user's historical data and the progressive relationship between training items, realizing the personalized customization and dynamic optimization of the training plan, improving the training effect and user experience; seamlessly converting the generated training plan into training instructions for the metaverse virtual scene and presenting them to the user through a visual training guidance interface, breaking the limitations of the real environment and providing the user with an immersive and interactive intelligent training experience, promoting the effective integration of virtual and real. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 It is a schematic flowchart of the method for generating a personalized training plan in the metaverse intelligent exercise of the embodiments of the present invention;

[0067] Figure 2 It is a comparison chart of the number of parameters and calculation efficiency of each uncertainty modeling method;

[0068] Figure 3 It is a visualization diagram of the training item progressive relationship network and the multi-scale sliding time window. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0069] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are only a part rather than all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0070] The technical solutions of the present invention will be described in detail below with specific embodiments. These specific embodiments may be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments.

[0071] Figure 1 It is a schematic flowchart of a method for generating a personalized training plan in the metaverse intelligent exercise of the embodiments of the present invention. As Figure 1 shown, the method includes:

[0072] Obtain the exercise data of the user in the metaverse virtual scene;

[0073] Based on the bone joint point position data in the exercise data, call a preset human biomechanics model to calculate the corresponding exercise load parameters of the user in the real environment;

[0074] Perform time series analysis on the exercise load parameters through a neural network model, use the attention mechanism to extract the long-term and short-term features of the user's exercise pattern, and based on the extracted long-term and short-term features, predict the physiological limit threshold of the user under different exercise intensities;

[0075] Construct training knowledge triples according to the historical training data of the user, and construct a personalized training knowledge graph based on the training knowledge triples through the method of multi-level knowledge extraction and dynamic graph optimization;

[0076] Construct a graph neural network model, input the personalized training knowledge graph into the graph neural network model, and generate a phased training plan for the user based on the node feature vectors output by the graph neural network model. Among them, the training items in the phased training plan are sorted according to the progressive relationship, and the exercise intensity of each training item is within the range of the physiological limit threshold;

[0077] Convert the phased training plan into a training instruction in the metaverse virtual scene, and display a training guidance interface in the metaverse virtual scene.

[0078] In an alternative embodiment, based on the bone joint point position data in the exercise data, calling a preset human biomechanics model to calculate the corresponding exercise load parameters of the user in the real environment includes:

[0079] Based on the bone joint point position data in the said motion data, use a kinematic inversion model to calculate the user's joint angle data; based on the joint angle data at adjacent moments, calculate the user's joint motion speed data and joint motion acceleration data;

[0080] Establish a human bone linkage model, map the bone joint point position data to the corresponding bone nodes in the human bone linkage model, and calculate the pressure values and torque values of each joint according to the connection relationship between the bone nodes in the human bone linkage model;

[0081] Input the joint angle data and joint force data into the static force analysis channel of a preset human biomechanical model for processing to obtain static force characteristics, and the static force characteristics characterize the muscle force distribution required for the user to maintain the current posture;

[0082] Input the joint motion speed data and the joint motion acceleration data into the dynamic force analysis channel of the human biomechanical model for processing to obtain dynamic force characteristics, and the dynamic force characteristics characterize the joint impact force and inertial force during the user's movement;

[0083] Perform fusion processing on the static force characteristics and the dynamic force characteristics through the feature fusion layer of the human biomechanical model to obtain the output result of the feature fusion layer;

[0084] Calculate the corresponding motion load parameters of the user in the real environment according to the output result of the feature fusion layer.

[0085] In a specific implementation manner, the bone joint point position data is obtained through devices such as an optical motion capture system, an inertial sensor, or a depth camera. This data includes at least 15 key points: head, neck, left and right shoulders, left and right elbows, left and right wrists, waist, left and right hips, left and right knees, and left and right ankles, and each joint point is represented by three-dimensional coordinates (x, y, z). Use a kinematic inversion model to calculate the joint angle data. Taking the elbow joint as an example, calculate the elbow joint angle through the included angle between the upper arm and forearm bone vectors. Specifically, if the upper arm vector is v1=(x1, y1, z1) and the forearm vector is v2=(x2, y2, z2), the elbow joint angle θ can be calculated through the vector dot product and the modulus length. For example, at a certain moment, the upper arm vector is (0.25, 0.15, 0.05) and the forearm vector is (0.10, 0.20, 0.15), and the calculated elbow joint angle is 37.5 degrees. Repeat similar calculations for the main joints of the whole body to obtain a complete joint angle data set.

[0086] Based on the joint angle data at adjacent moments, calculate the joint movement speed and acceleration. Assume the sampling frequency is 30Hz, and the time interval between adjacent frames is 33.3 milliseconds. For any joint, such as the elbow joint, if the angle at time t is θt = 85 degrees and the angle at time t+1 is θt+1 = 88 degrees, then the joint movement speed vt = (θt+1 - θt) / Δt = 90 degrees / second. Similarly, if the speed at time t+1 is vt+1 = 105 degrees / second, then the acceleration at = (vt+1 - vt) / Δt = 450 degrees / second 2 Perform similar calculations for all joints to form a complete dataset of joint movement speed and acceleration. In practical applications, to reduce the influence of noise, the sliding window averaging method is used to smooth the data, and the window size is taken as 5 frames. For example, when a user is walking fast, the knee joint angle change rate remains at about 120 degrees / second, and the acceleration peak appears in the landing and pushing-off phases of the gait cycle, with a value of about 800 degrees / second 2 .

[0087] Construct a human bone linkage model that includes bone nodes and connection relationships. This model contains 17 bone nodes and 16 linkages, forming a tree structure with the pelvis as the root node. Each bone segment has preset mass, length, and moment of inertia parameters. In the standard adult male model, the mass of the upper arm is about 2.0kg, the mass of the forearm is about 1.2kg, the mass of the thigh is about 7.5kg, and the mass of the calf is about 3.5kg. Map the bone joint point position data to the corresponding nodes of the human bone linkage model, and calculate the joint pressure and torque according to the connection relationship between the nodes. Taking the knee joint as an example, assume the user's weight is 70kg. In the semi-squat posture, through static analysis, considering the mass of the thigh, calf, and gravity, the calculated knee joint pressure is about 1.5 times the body weight, that is, about 1030N, and the knee joint torque is about 31.5 Nm. Perform similar calculations for the main joints of the whole body to form a joint force dataset.

[0088] Input the joint angle data and joint force data into the static force analysis channel of the preset human biomechanical model. This channel contains a multi-layer neural network structure. The input layer receives the joint angle and force data, and the hidden layer contains 64 nodes, using the ReLU activation function. Through the processing of this channel, static force features are obtained. These features contain 32-dimensional vectors, representing the muscle force distribution required for the user to maintain the current posture. Taking the squat posture as an example, the component value in the feature that reflects the load of the hip joint muscle group is 0.75, and the component value of the knee joint muscle group load is 0.82, indicating that the static load on the knee joint in this posture is slightly higher than that on the hip joint.

[0089] Input the joint movement speed data and joint movement acceleration data into the dynamic force analysis channel of the human biomechanics model. This channel adopts a temporal convolutional network structure, including a one-dimensional convolutional layer with a time window size of 8 to extract temporal features. Through the processing of this channel, dynamic force features are obtained. This feature is a 24-dimensional vector, representing the joint impact force and inertial force during the movement. Taking the running motion as an example, the dynamic impact force feature component of the ankle joint during the landing phase reaches 0.86, and that of the knee joint is 0.72, indicating that running has a greater dynamic impact on the ankle joint.

[0090] Fuse the static force features and dynamic force features through the feature fusion layer of the human biomechanics model. The feature fusion layer adopts an attention mechanism to dynamically adjust the weights of the static features and dynamic features according to the movement type. For static postures such as yoga movements, the weight of the static features is relatively high, about 0.75; for high-speed movements such as jumping, the weight of the dynamic features is relatively high, about 0.85. After fusion, a 48-dimensional comprehensive feature vector is obtained. According to the output result of the feature fusion layer, the corresponding movement load parameters of the user in the real environment are calculated through a fully connected layer, including three indicators: muscle fatigue index, joint pressure index, and exercise intensity index, all of which are normalized to the range of 0-1. Taking a group of continuous squat movements as an example, after completing 10 standard squats, the quadriceps muscle fatigue index is 0.65, the knee joint pressure index is 0.58, and the overall exercise intensity index is 0.45, indicating that this exercise has a greater load on the quadriceps, but the joint pressure and overall intensity are moderate.

[0091] During application, the model is personalized adjusted according to the body parameters (height, weight, bone proportion, etc.) of different users. Adjust the joint force calculation parameters through the body mass index (BMI). For every 5-unit increase in the BMI value, the joint pressure index increases by about 12%. This method supports real-time calculation. At a data acquisition frequency of 60Hz, the update delay of the movement load parameters is less than 50 milliseconds, meeting the real-time interaction requirements. Through the monitoring of the movement load parameters, potential overtraining risks can be identified in a timely manner. When the joint pressure index of a certain joint continuously exceeds 0.8 for 60 seconds, an overload warning is generated, and it is recommended that the user adjust the movement mode or intensity.

[0092] The calculation of the exercise load parameters also takes into account the influence of environmental factors. For example, when exercising on a slope, for every 5-degree increase in the slope, the pressure indices of the knee joint and the ankle joint increase by approximately 8% and 12% respectively. Specific parameter adjustment strategies are set for different exercise types. For high-impact exercises (such as jumping and sprinting), the weight of the dynamic force characteristics is increased to 0.9, while for low-intensity continuous exercises (such as jogging and cycling), the weights of the static and dynamic characteristics are more balanced, being 0.45 and 0.55 respectively. The exercise load assessment results can be used to adjust the personalized training plan. When the load index of a certain part continuously exceeds the safety threshold, alternative training suggestions are automatically generated to ensure the training effect while reducing the risk of sports injuries.

[0093] In this embodiment, the joint angles, velocities, and accelerations calculated through kinematic inversion can accurately capture the geometric and dynamic characteristics of the user's movement, providing a reliable basis for subsequent analysis; the joint pressures and torques calculated based on the bone link model comprehensively reflect the two force characteristics of static (muscle strength required to maintain posture) and dynamic (impact force, inertial force), helping to deeply understand the true load borne by each joint during exercise; by continuously updating the force characteristics with data at adjacent times, real-time monitoring of the load changes during the exercise process can be achieved, providing timely basis for exercise guidance and risk warning; the load parameters calculated by fusing the static and dynamic force characteristics can be customized to evaluate the training intensity and recovery needs according to the body types and exercise methods of different users; the quantitative joint force and torque data help to detect abnormal stress concentrations in a timely manner, guiding posture adjustment and training plan optimization, thereby reducing the injury risk and improving the exercise performance.

[0094] In an alternative embodiment, a neural network model is used to perform time series analysis on the exercise load parameters. The attention mechanism is adopted to extract the long-term and short-term characteristics of the user's exercise pattern, and based on the extracted long-term and short-term characteristics, the physiological limit thresholds of the user at different exercise intensities are predicted, including:

[0095] An adaptive time window is constructed according to the user's historical exercise load parameters, and the window length is dynamically adjusted based on the exercise volatility to generate variable-length time series data segments;

[0096] The variable-length time series data segments are input into a recurrent convolutional neural network, and the local exercise feature sequences are extracted through a multi-layer recurrent convolutional structure;

[0097] The local exercise feature sequences are input into a graph attention network, the local exercise feature sequences are constructed into a time series feature graph, and the time series dependence relationship between the feature nodes is extracted through graph convolution operations to obtain global correlation features;

[0098] Input the local motion feature sequence and the global correlation feature into the temporal attention module. The temporal attention module constructs a multi-scale feature pyramid and calculates adaptive weight coefficients for the local motion feature sequence at different time scales.

[0099] Perform temporal cross-attention calculation on the adaptive weight coefficients and the global correlation feature to generate enhanced features at multiple time scales, and fuse the enhanced features at multiple time scales through a cross-scale feature aggregation network to obtain the long-term and short-term features of the user's motion pattern.

[0100] Use a Bayesian neural network to model the long-term and short-term features, calculate the probability distribution function of the physiological limit threshold, and use the mean value of the probability distribution function as the prediction result of the user's physiological limit threshold under different exercise intensities.

[0101] In a specific embodiment, an adaptive time window is constructed according to the user's historical exercise load parameters. Collect the user's historical exercise load data for at least 30 days, including muscle fatigue index, joint pressure index, and exercise intensity index. Calculate the volatility of the exercise load parameters, which is defined as the ratio of the change amplitude within the adjacent 7 days to the mean value. Divide the volatility into three intervals: low volatility (<0.15), medium volatility (0.15 - 0.35), and high volatility (>0.35). For the low volatility interval, set the fixed window length to 14 days; for the medium volatility interval, set the window length to 10 days; for the high volatility interval, set the window length to 7 days. For example, if a user's recent exercise intensity index volatility is 0.28, which belongs to the medium volatility interval, set the window length to 10 days. Slide and segment the data within each window, with an overlapping rate of 50% for adjacent segments, to generate variable-length temporal data segments. For example, the variable-length temporal data segments generated by a user contain the exercise load parameters at 10 time points, and each time point contains 3 index values.

[0102] Input the variable-length temporal data segments into a recurrent convolutional neural network, which contains 3 layers of recurrent convolutional structures. Each layer contains 16, 32, and 64 convolutional kernels, with a kernel size of 3 and a stride of 1. The first layer of convolution processes the input variable-length temporal data to extract primary temporal features; the second layer performs recurrent convolution on the output of the first layer to capture medium-term change patterns; the third layer performs recurrent convolution on the output of the second layer to extract high-order temporal features. The recurrent depth of the recurrent convolution is set to 5, that is, each layer of convolution is applied 5 times with parameter sharing. Through the recurrent convolutional structure, a local motion feature sequence is extracted. For example, for an input data segment of 10×3 dimensions (10 time points, 3 indicators per point), after being processed by the recurrent convolutional network, a local motion feature sequence of 10×64 dimensions is obtained, which characterizes the local time dependence of the user's motion pattern.

[0103] Input the local motion feature sequence into the graph attention network. Each time point of the feature sequence is regarded as a node in the graph, and the adjacency matrix is constructed according to the correlation between time points. The edge weights between nodes are calculated based on the similarity of feature vectors, and connections are established between nodes with a similarity exceeding 0.6. The constructed temporal feature graph contains 10 nodes (corresponding to 10 time points). The graph attention network contains 2 layers of graph convolutional layers, with 32 and 16 attention heads respectively in each layer, and the attention dimension is 8. The first layer of graph convolution aggregates the information of its neighbor nodes for each node, and the second layer further expands the receptive field to capture the correlations between nodes in a wider range. Through the graph convolution operation, the temporal dependence relationship between feature nodes is extracted to obtain the global correlation features. The dimension of the global correlation features is 10×128, which contains rich long-range dependence information between time points. For example, analysis finds that there is a significant correlation between the exercise intensity and the muscle fatigue index 2 - 3 days later, and the correlation coefficient is 0.72.

[0104] Input the local motion feature sequence and the global correlation features into the temporal attention module. This module constructs a 3-level feature pyramid, corresponding to time scales of 3 days, 5 days, and 10 days respectively. For each scale, calculate the adaptive weight coefficients of the local motion feature sequence. The weight calculation uses the self-attention mechanism, which maps the feature sequence into query, key, and value parts, calculates the attention scores through the matching degree between the query and the key, and obtains the weight coefficients of each time point. The shorter scale (3 days) focuses on recent fluctuations, and the longer scale (10 days) captures long-term trends. For example, for the 5-day scale, the weight coefficients of a user's joint pressure index in the last two days are 0.25 and 0.30, indicating that the data of these two days have a greater impact on the current prediction.

[0105] Perform temporal cross-attention calculation between the adaptive weight coefficients and the global correlation features. The cross-attention takes the global correlation features as the query, the weighted local features as the key and value, and generates enhanced features. Calculate the enhanced features for the three time scales of 3 days, 5 days, and 10 days respectively to obtain three feature matrices with a dimension of 10×128. The enhanced features of the three time scales are fused through a cross-scale feature aggregation network. The aggregation network uses the channel attention mechanism to assign different weights to features of different scales. For example, for a more volatile exercise pattern, the feature weights of the 3-day and 5-day scales are 0.45 and 0.35 respectively, and the 10-day scale is 0.2; for a stable exercise pattern, the weights of the three scales are 0.2, 0.3, and 0.5 respectively. After aggregation, the long-term and short-term features of the user's exercise pattern are obtained, with a dimension of 10×256.

[0106] A Bayesian neural network is used to model long-term and short-term features. The Bayesian neural network consists of 3 fully connected layers, with the number of nodes being 128, 64, and 32 respectively, and the activation function being Leaky ReLU. Instead of using fixed values, the network weights follow a prior distribution, which is initially set to a Gaussian distribution with a mean of 0 and a variance of 0.1. The network weights are sampled using the variational inference method, and 50 samples are taken each time for prediction. The network outputs are calculated for multiple sets of sampled weights, and the mean and variance of the outputs are statistically analyzed to obtain the probability distribution function of the physiological limit threshold. For each exercise intensity level (low, medium, high), an independent probability distribution function is calculated. The mean of the probability distribution function is used as the prediction result of the physiological limit threshold for the user at different exercise intensities. For example, for a certain user during medium-intensity exercise, the predicted value of the physiological limit threshold of the muscle fatigue index is 0.72 ± 0.08, indicating that there is a risk of overtraining when the user's muscle fatigue index exceeds 0.72.

[0107] The method of this embodiment is adjusted personalized according to user characteristics. For the age factor, for every 10-year increase, the predicted physiological limit threshold is reduced by 5 - 8%; for gender differences, the joint pressure index threshold for female users is on average 10% lower than that for male users. Regarding the exercise level, users are divided into beginner (<6 months of training experience), intermediate (6 - 24 months), and advanced (>24 months), and the baseline correction coefficients for predicting the threshold are set to 0.85, 1.0, and 1.15 respectively. The method of this embodiment supports incremental learning. After every 7 days of new data collection, the new data is combined with the historical data to update the weight distribution of the Bayesian neural network, realizing the continuous optimization of the model. The experimental results show that this method has a higher accuracy in predicting the physiological limit threshold of users' exercise compared with the traditional fixed-threshold method and also compared with non-Bayesian deep learning methods.

[0108] In this embodiment, the adaptive variable-length time window can intelligently capture the key turning points and abnormal fluctuations during exercise, significantly reducing the information loss and noise interference caused by a fixed window; the multi-layer recursive convolution and graph attention network cooperate to extract local details and global temporal dependencies, realizing a deep and multi-dimensional representation of the exercise pattern; the multi-scale attention pyramid dynamically weights short-term bursts and long-term trend features, enhancing the sensitivity to exercise information at different time scales; cross-scale feature aggregation fuses enhanced features at each scale through temporal cross-attention, taking into account both immediate responses and long-term trends, further improving the accuracy and robustness of pattern recognition and prediction; the Bayesian neural network performs probabilistic modeling on long-term and short-term features, not only outputting a reliable confidence assessment of the physiological limit threshold, but also providing personalized, safe, and efficient training suggestions for different individuals at each exercise intensity.

[0109] In an alternative embodiment, a Bayesian neural network is used to model the long - short - term features, calculate the probability distribution function of the physiological limit threshold, and take the mean of the probability distribution function as the prediction result of the user's physiological limit threshold under different exercise intensities, including:

[0110] Input the long - short - term features into a feature encoding network to generate a sequence of feature vectors;

[0111] Construct a Bayesian neural network, set latent variables in each layer of the Bayesian neural network, and input the sequence of feature vectors into the Bayesian neural network;

[0112] Construct training sample pairs based on the sequence of feature vectors, use a variational auto - encoder to model the latent variables in the Bayesian neural network, and obtain the prior distribution of the latent variables;

[0113] Input the prior distribution of the latent variables into a probability neural network to generate a weight distribution, and the weight distribution is used to characterize the uncertainty of each layer of network parameters in the Bayesian neural network;

[0114] Optimize the weight distribution through the stochastic variational inference method, generate multiple sets of network parameters according to the weight distribution, construct a deep ensemble model based on the multiple sets of network parameters, input new long - short - term features into the deep ensemble model, and output multiple prediction results based on the deep ensemble model;

[0115] Perform probability density estimation on the multiple prediction results to obtain the probability distribution function of the physiological limit threshold, calculate the mean of the probability distribution function, and take the mean as the prediction result of the user's physiological limit threshold under different exercise intensities.

[0116] In a specific embodiment, the long - short - term features are input into a feature encoding network to generate a sequence of feature vectors. The feature encoding network adopts a bidirectional long - short - term memory network structure, including two layers of bidirectional LSTM layers, with 128 hidden units in each layer. The input long - short - term feature dimension is 10×256, corresponding to 256 - dimensional feature vectors at 10 time points. The time - series data is processed by forward and backward LSTM units respectively to capture bidirectional time - dependent relationships. The dimension of the sequence of feature vectors output by the encoding network is 10×256, retaining the original dimension but enhancing the feature expression ability. For users with different exercise patterns, such as strength training users and endurance training users, different parameter initialization strategies are adopted. The forget - gate bias of strength training users is initialized to 1.5, and the forget - gate bias of endurance training users is initialized to 1.0 to adapt to the time - series characteristics of different exercise patterns. In an example, the numerical distribution of the feature vector sequence of a certain strength training user in the dimension related to muscle fatigue is between 0.65 - 0.85, while the numerical distribution in the dimension related to cardiopulmonary function is between 0.40 - 0.55.

[0117] Construct a Bayesian neural network, set latent variables in each layer of the Bayesian neural network, and input the feature vector sequence into the Bayesian neural network. The Bayesian neural network contains 3 fully connected layers with 128, 64, and 32 nodes respectively, and uses the Swish activation function. In each layer of the network, set the latent variable z to control the distribution of weights and biases. The dimension of the latent variable z matches the number of weight parameters in the corresponding layer. For example, the connection from the input layer to the first hidden layer requires 256×128 = 32768 weight parameters, and the dimension of the corresponding latent variable z is set to 256. The dimensions of the latent variables in the first, second, and third layers are 256, 128, and 64 respectively. The network input is a 10×256 feature vector sequence, which is converted into a 256-dimensional feature vector through average pooling operation in the time dimension, and then processed by each fully connected layer in turn.

[0118] Construct training sample pairs based on the feature vector sequence, and use a variational autoencoder to model the latent variables in the Bayesian neural network to obtain the prior distribution of the latent variables. The training sample pair refers to consecutive adjacent feature vectors, such as the feature vectors at time t and t+1, which are used to capture the time series change characteristics. The variational autoencoder consists of an encoder and a decoder. The encoder is composed of two fully connected layers with 128 and 64 nodes respectively, which maps the input feature vector to the latent variable space; the decoder is also composed of two fully connected layers with 64 and 128 nodes respectively, which reconstructs the latent variable into a feature vector. The encoder outputs the mean and variance parameters of the latent variable z, and samples to obtain the latent variable z. Through the training of the variational autoencoder, the prior distribution of the latent variable z is obtained, which is represented as a multi-dimensional Gaussian distribution, and the sizes of the mean vector and covariance matrix are consistent with the dimension of the latent variable. For example, the mean vector of the prior distribution of the first-layer latent variable is between -0.05 and 0.05, and the elements of the diagonal covariance matrix are between 0.01 and 0.1.

[0119] Input the prior distribution of the latent variable into a probabilistic neural network to generate a weight distribution, which is used to characterize the uncertainty of the network parameters in each layer of the Bayesian neural network. The probabilistic neural network contains a single-layer fully connected network, with the input being the latent variable z and the output being the distribution parameters of the weight matrix W and the bias vector b. The weight distribution is represented by a low-rank Gaussian distribution, and the covariance structure is defined by the combination of a mean matrix and several rank-one matrices, reducing the number of parameters. For the first-layer connection, the dimension of the weight mean matrix is 256×128, and the actual number of stored parameters is reduced by 90%. The mean of the weight distribution is usually initialized as a small random number in the interval [-0.05, 0.05], and the standard deviation is initialized as 0.01. For different types of features, different weight initialization strategies are set: He initialization is used for exercise intensity-related features, and the standard initialization method based on the input and output dimensions is used for recovery ability-related features.

[0120] The weight distribution is optimized by the stochastic variational inference method. Multiple sets of network parameters are generated according to the weight distribution, and a deep ensemble model is constructed based on multiple sets of network parameters. The stochastic variational inference is implemented using the Bayes by Backprop algorithm. Specifically, for the weight W of each layer of the network, its posterior distribution is defined as a Gaussian distribution, parameterized by the mean vector μ and the standard deviation vector σ. During the forward propagation process, instead of directly using the deterministic weights, weights are sampled from the posterior distribution. The sampling process uses the reparameterization trick: first, noise ε is sampled from the standard normal distribution, and then the weight sample is obtained through the transformation W = μ + σ * ε. This trick ensures that the gradient can be backpropagated through the random nodes. The loss function consists of two parts: the prediction loss and the complexity loss. The prediction loss uses the mean squared error to measure the gap between the model prediction and the actual target; the complexity loss uses the KL divergence to measure the difference between the posterior distribution and the prior distribution to prevent overfitting. For the prior distribution, a mixture of Gaussian distributions is adopted, including a narrow Gaussian (mean 0, standard deviation 0.05) and a wide Gaussian (mean 0, standard deviation 2.0), with a mixing ratio of 0.5:0.5. This mixed prior can encourage both parameter sparsity and expressiveness simultaneously. During the backpropagation process, the parameters μ and σ are updated by gradient descent. The initial learning rate is set to 0.001, the Adam optimizer is used, and a learning rate decay strategy is applied, multiplying the learning rate by 0.9 every 2000 iterations. To improve the training stability, the gradient clipping technique is applied to limit the gradient norm not to exceed 5.0. In a typical training, after 10,000 iterations, the model loss drops from the initial value of 4.82 to 0.67, and the average standard deviation of the weight distribution converges to a specific pattern. For example, the standard deviation of the weights related to muscle fatigue prediction is in the range of 0.03 - 0.08, while the standard deviation of the weights related to joint pressure prediction is in the range of 0.02 - 0.05, reflecting the differences in uncertainty for different prediction tasks.

[0121] After the optimization is completed, 50 different sets of weight parameters are sampled from the weight distribution to form 50 sub-networks, thus forming a deep ensemble model. Each set of weight parameters maintains the same network structure but has different parameter values, reflecting the characteristics of the posterior distribution of Bayesian inference. The long-term and short-term features of new users are input into each sub-network, and 50 independent prediction results are obtained. For example, for a certain user under high-intensity training conditions, the threshold range of the muscle fatigue index predicted by the 50 sub-networks is between 0.68 and 0.83, and the threshold range of the joint pressure index is between 0.65 and 0.78. The degree of dispersion of the prediction results reflects the uncertainty level of the model's prediction for this user. For users with sufficient training data, the prediction results are more concentrated, and the standard deviation is usually less than 0.05; while for users with sparse data or inconsistent training patterns, the prediction results are more dispersed, and the standard deviation can reach 0.12.

[0122] Perform probability density estimation on multiple prediction results to obtain the probability distribution function of the physiological limit threshold, calculate the mean of the probability distribution function, and use the mean as the prediction result of the user's physiological limit threshold under different exercise intensities. The kernel density estimation method is used to perform probability density estimation on 50 prediction results. The kernel function is selected as the Gaussian kernel, and the bandwidth parameter is adaptively determined. The probability density function is represented by 100 uniformly sampled points to form the probability distribution of the physiological limit threshold. Calculate the mean of the probability distribution function as the final prediction result of the physiological limit threshold. At the same time, extract the standard deviation of the distribution to quantify the uncertainty of the prediction. For example, for a certain user under medium-intensity training conditions, the predicted result of the physiological limit threshold of the muscle fatigue index is 0.75 ± 0.06, indicating that within the 95% confidence interval, the muscle fatigue index threshold of this user is between 0.63 and 0.87. According to the prediction result, when the system real-time monitors that the user's muscle fatigue index exceeds 0.75, an overtraining risk warning is issued.

[0123] In the prior art, the prediction of the physiological limit threshold usually adopts the fixed threshold method or a single neural network model, which cannot effectively handle individual differences and prediction uncertainties. The fixed threshold method relies on expert experience to set a unified standard, ignoring individual differences, and the accuracy rate is less than 60%; although a single neural network can learn individual characteristics, it lacks the ability to quantify uncertainties and cannot evaluate the reliability of prediction results. The prediction accuracy is unstable in the case of large data fluctuations. The improvement starting point of the present invention is to introduce a Bayesian framework to handle prediction uncertainties, and combine a variational autoencoder to model the prior distribution of latent variables to achieve more accurate personalized prediction. By setting hierarchical latent variables and using a low-rank Gaussian distribution to represent weights, the number of parameters is significantly reduced, and the calculation efficiency is improved. The random variational inference is used to optimize the weight distribution, which is faster than the traditional Markov chain Monte Carlo method. Through uncertainty quantification, the system can automatically adjust the warning threshold according to the prediction reliability, significantly reduce the false alarm rate, and improve the user experience and training safety.

[0124] In this embodiment, through the feature encoding network and Bayesian latent variable modeling, it is possible to quantify the distribution of long-term and short-term motion characteristics and the uncertainty of network parameters, thereby greatly improving the reliability of threshold prediction; by using a variational autoencoder to learn the prior distribution of latent variables, the model still has strong generalization ability when the sample size is limited; applying random variational inference to generate multiple groups of network parameters and construct a deep integration effectively enhances the robustness of the model to noise and abnormal data and reduces the risk of overfitting; by performing probability density estimation on multiple prediction results, not only can a point estimate of the physiological limit threshold be given, but also a confidence interval can be provided, providing decision-making support for personalized exercise recommendations and risk assessment; this end-to-end Bayesian deep learning framework takes into account both performance and interpretability, facilitating subsequent flexible deployment under different exercise intensities and scenarios and realizing the optimization of individualized training programs.

[0125] As Figure 2 shown, the traditional Bayesian network and the MCMC Bayesian network have the largest number of parameters, reaching 2587K and 2482K respectively, and the longest inference time (267ms and 294ms); the Dropout Bayesian and LSTM networks have relatively moderate numbers of parameters, 1692K and 1426K respectively, and the inference times are 211ms and 138ms; the integrated neural network performs poorly in terms of the number of parameters (2093K), but performs well in terms of the inference time (187ms); while the solution of this embodiment significantly reduces the number of parameters to 958K by using hierarchical latent variables and low-rank Gaussian distributions to represent weights, a reduction of 62.97% compared to the traditional Bayesian network. At the same time, the inference time is only 93ms, a reduction of 68.37% compared to the MCMC Bayesian network. This result shows that the solution of this embodiment not only outperforms the existing methods in terms of prediction performance, but also achieves a significant improvement in computational efficiency. In particular, by replacing the traditional Markov chain Monte Carlo method with the stochastic variational inference method, the inference speed is greatly improved, enabling the system to run in real time on resource-constrained portable devices, providing the possibility for practical applications. The low number of parameters and high computational efficiency enable this system to be deployed on portable devices such as smart watches to achieve real-time monitoring and early warning of the user's physiological limits.

[0126] In an alternative embodiment, a training knowledge triple is constructed based on the historical training data of the user, and a personalized training knowledge graph is constructed by means of multi-level knowledge extraction and dynamic graph optimization, including:

[0127] Performing temporal segmentation on the historical training data of the user to obtain training data sequences for multiple training cycles;

[0128] Extracting training entities and training relationships from the training data sequences to construct training knowledge triples, inputting the training knowledge triples into a knowledge reasoning model, and semantically expanding the training knowledge triples based on the knowledge reasoning model;

[0129] Performing multi-granularity partitioning on the training knowledge triples, and constructing knowledge subgraphs at each granularity level, where the knowledge subgraphs contain training entity nodes and training relationship edges at that granularity level;

[0130] Performing representation learning on the knowledge subgraphs, iteratively updating the feature representations of the training entity nodes through a message passing mechanism, calculating a similarity matrix between nodes based on the updated feature representations, and constructing a node importance scoring model in combination with the weight distribution of the training relationship edges;

[0131] Calculate the importance scores of the training entity nodes according to the node importance scoring model, set an adaptive pruning threshold based on the importance scores, perform dynamic pruning on the knowledge subgraphs, aggregate the features of the pruned multiple knowledge subgraphs, and construct a hierarchical training knowledge graph;

[0132] Map the new training data to the hierarchical training knowledge graph, and update the training entity nodes and training relationship edges in the hierarchical training knowledge graph;

[0133] Generate a personalized training knowledge graph based on the hierarchical training knowledge graph.

[0134] In a specific implementation manner, perform temporal segmentation on the historical training data of the user to obtain training data sequences for multiple training cycles. Specifically, the system collects all the fitness records of the user in the past 6 months, including information such as training type, training duration, training intensity, and calories burned, and divides them by week as a training cycle to obtain 24 training cycle data sequences. For example, the data of user Xiao Wang in the first week is: Monday (running, 30 minutes, medium intensity, 250 calories), Wednesday (strength training, 45 minutes, high intensity, 320 calories), Friday (yoga, 60 minutes, low intensity, 180 calories).

[0135] Extract training entities and training relationships from the training data sequences to construct training knowledge triples. Training entities include user identifiers, training items, training parts, training equipment, etc.; training relationships include "participate in", "use", "exercise", etc. For example, from the data of user Xiao Wang in the first week, the following triples can be extracted: (Xiao Wang, participate in, running), (running, exercise, cardiopulmonary function), (Xiao Wang, use, dumbbell), (strength training, exercise, arm muscles), etc. Input these triples into a pre-trained knowledge reasoning model for semantic expansion. Based on rules and statistical analysis, the model infers new relationships, such as (running, contribute to, fat loss), (strength training, enhance, metabolic rate), etc., enriching the original knowledge.

[0136] Perform multi-granularity partitioning on the training knowledge triples, and construct knowledge subgraphs at each granularity level. According to different attributes of training activities, it is divided into three granularities: training type granularity (such as aerobic training, anaerobic training), training goal granularity (such as fat loss, muscle gain), and training detail granularity (such as specific actions, equipment use). At the training type granularity level, construct a knowledge subgraph containing nodes such as "running", "strength training", "yoga", etc., and the edges represent the association relationships between training types; at the training goal granularity level, construct a knowledge subgraph containing nodes such as "fat loss", "muscle gain", "improve cardiopulmonary function", etc.; at the training detail granularity level, construct a knowledge subgraph containing specific actions and equipment.

[0137] Perform representation learning on the knowledge subgraph, and iteratively update the feature representations of training entity nodes through a message passing mechanism. In actual implementation, each node is initialized as a 128-dimensional vector, and through 3 rounds of message passing iteration, it collects information from adjacent nodes and updates its own features. For example, the "Running" node updates its own feature representation by aggregating information from nodes such as "Fat Loss" and "Cardiopulmonary Function" connected to it. Based on the updated feature representations, calculate the cosine similarity between nodes to obtain a similarity matrix. Combine the weight distribution of training relationship edges (set according to user training frequency and preferences) to construct a node importance scoring model. This model comprehensively considers the connectivity, centrality of nodes, and the degree of match with user training preferences.

[0138] Calculate the importance scores of training entity nodes according to the node importance scoring model. For example, for user Xiaowang, the "Strength Training" node has a score of 0.85, the "Running" node has a score of 0.76, and the "Yoga" node has a score of 0.63. Based on these scores, set an adaptive pruning threshold, and take 80% of the average score of nodes at each granularity level as the threshold. Dynamically prune the knowledge subgraph, removing nodes with scores lower than the threshold and their associated edges. For example, the "Swimming" node with a score of only 0.42 is pruned. Combine the pruned multiple knowledge subgraphs through a feature aggregation method, retain the information of nodes at different granularity levels, and construct a hierarchical training knowledge graph.

[0139] When new training data is generated, map it to the hierarchical training knowledge graph. For example, in the 25th week, the user added "High-Intensity Interval Training" data. The system extracts relevant triples and maps them to the existing graph. If the new entity "High-Intensity Interval Training" has a high similarity with the existing node "Aerobic Training", an association is established between them; at the same time, update the features and relationship weights of the affected nodes. If the user performs the same training for three consecutive weeks, the weight of the corresponding relationship edge will increase by 20% to reflect the user's stable preference.

[0140] Generate a personalized training knowledge graph based on the updated hierarchical training knowledge graph. The system analyzes the user's recent training focus and long-term training pattern, highlights nodes and relationships with high importance scores, and hides content that the user has not paid attention to recently. For example, for user Xiaowang who is recently focused on strength training, in his personalized training knowledge graph, the "Strength Training" and related nodes will be emphasized, and their close connection with the training goal of "Muscle Gain" will be shown, while weakening the display of "Yoga" related content.

[0141] In this embodiment, based on the knowledge triples constructed from training entities and relationships and semantically augmented by the inference model, implicit training elements and associations can be mined, providing a more comprehensive knowledge basis for subsequent analysis; the multi-granularity partitioning and subgraph construction take into account both the macroscopic framework and microscopic details of training knowledge, enabling the model to not only understand the overall training profile but also capture key action nodes; through the representation learning of message passing and the calculation of the similarity matrix, the importance score constructed by combining the relationship edge weight distribution is used to achieve the precise identification of key training entities, greatly enhancing the focus of the knowledge graph; the adaptive pruning based on node importance not only compresses redundant information, reduces computational overhead, but also enhances the model's robustness to noisy data; the real-time mapping and updating of new training data to the hierarchical knowledge graph make the finally generated personalized training knowledge graph both structured and dynamically evolvable, providing reliable support for formulating more targeted training plans and continuous optimization.

[0142] In an alternative embodiment, a graph neural network model is constructed, and the personalized training knowledge graph is input into the graph neural network model. Based on the node feature vectors output by the graph neural network model, a phased training plan for the user is generated, including:

[0143] Construct a graph neural network model, encode the topological structure features of training entity nodes in the spatial dimension, and model the dynamic evolution features of training entity nodes in the temporal dimension using a temporal-aware graph convolutional network to obtain spatial dimension features and temporal dimension features;

[0144] Input the personalized training knowledge graph into the graph neural network model, and adaptively fuse the spatial dimension features and the temporal dimension features through a multi-layer cross-attention mechanism to generate multi-dimensional feature vectors of training entity nodes;

[0145] Use self-attention-guided graph pooling operation to sparsely reduce the dimension of the multi-dimensional feature vectors to obtain the compressed feature representation of training entity nodes;

[0146] Based on the compressed feature representation, construct a hierarchical reinforcement learning model with multi-objective joint optimization, model the progressive relationship constraint and the exercise intensity constraint as hierarchical optimization objectives, and respectively learn the global sorting strategy and local intensity parameters of training items through a two-layer policy network;

[0147] Input the global sorting strategy and the local intensity parameters into the training plan generation module, determine the progressive order of training items according to the global sorting strategy, and adjust the exercise intensity of training items according to the local intensity parameters to generate a phased training plan that meets the requirements of progressive relationship and exercise intensity.

[0148] In a specific implementation, a graph neural network model is constructed, which can extract two-dimensional features of training entity nodes. In the spatial dimension, a dedicated topological structure encoder is used to process the association features between nodes. Specifically, for the node vi in the training knowledge graph, its first-order neighbor node set N(vi) is obtained, and the neighbor information is aggregated through a message passing mechanism. For each neighbor node vj ∈ N(vi), the attention weight of it to the central node vi is calculated, and this weight reflects the importance of the neighbor node to the central node. For example, for the "squat" training node, the directly related "thigh muscle group" node will obtain a higher weight, while the indirectly related "balance ability" node will obtain a lower weight.

[0149] In the temporal dimension, a time-aware graph convolutional network is used to capture the time evolution pattern of node features. First, the user's historical training data is divided into multiple time windows in chronological order, for example, one week for each window. For the feature vector xit of the node vi at the time window t, through the sliding window method, the temporal dependence relationship is modeled by combining the feature sequences of the previous k time windows {xi(t - k),..., xi(t - 1), xit}. For example, the change trajectory of the user's load on the "bench press" training item from the initial 30 kg to 50 kg can be used to predict the appropriate future training intensity.

[0150] The personalized training knowledge graph is input into the above graph neural network model, and the spatial dimension features and temporal dimension features are fused through a multi-layer cross-attention mechanism. In the implementation, a three-layer cross-attention structure is adopted, and each layer contains two parallel attention sub-modules, which process spatial features and temporal features respectively. For the node vi, its spatial feature vector is vis, and its temporal feature vector is vit. First, the cross-attention coefficient between the two is calculated, and then based on the attention coefficient, feature fusion is performed to generate a comprehensive feature representation. For example, for the "beginner" user node, the system may assign a higher weight to the temporal features to capture its ability improvement curve; while for the "professional trainer" user node, it may assign a higher weight to the spatial features and focus on the synergy relationship between training items.

[0151] The self-attention-guided graph pooling operation is used to sparsely reduce the dimension of the multi-dimensional feature vector. Specifically, first, the importance score of each node in the graph is calculated. For example, the "strength training" node has a higher importance score for strength-based users. According to the importance score, the top K key nodes are selected (in practice, K is usually set to 30% of the original number of nodes), and the information of these nodes and their features is retained. At the same time, the information of other non-key nodes is merged to form a compressed graph structure. The finally obtained compressed feature representation not only retains the detailed information of the key training entities but also reduces the computational complexity of subsequent processing.

[0152] Based on the compressed feature representation, a hierarchical reinforcement learning model for multi-objective joint optimization is constructed. This model consists of two layers of policy networks: the high-level policy network is responsible for learning the global sorting policy of training items, and the low-level policy network is responsible for optimizing the local intensity parameters. During training, a composite reward function is designed to guide the model's learning, which takes into account both the progressive relationship constraint and the exercise intensity constraint. For example, for a novice fitness user, the model will first arrange basic exercises such as "standard squats", and then recommend advanced exercises such as "weighted squats", and dynamically adjust the training intensity according to the user's feedback.

[0153] Specifically, the high-level policy network adopts a three-layer fully connected neural network structure, with the compressed feature representation as the input and the priority score of the training item as the output. For example, on a leg training day, "warm-up stretch" gets the highest priority (0.95), "squat" comes second (0.87), and "leg press" is third (0.65). The low-level policy network adopts a two-layer neural network, and for each training item, it outputs its detailed parameters, such as the number of sets (3 - 5 sets), the number of repetitions per set (8 - 12 times), and the load percentage (60% - 80% of the maximum load).

[0154] The global sorting policy and the local intensity parameters are input into the training plan generation module to generate the final phased training plan. This module first determines the progressive order of training items according to the global sorting policy. For example, a weekly training plan may be sorted as "chest training → back training → leg training → shoulder training → recovery day". Then, it adjusts the specific implementation details of each training item according to the local intensity parameters. For example, for "chest training day", the system may arrange: "warm-up (5 minutes of running, heart rate reaches 120 - 130 bpm)" → "bench press (4 sets, 10 repetitions per set, 65% of the maximum load)" → "incline bench press (3 sets, 12 repetitions per set, 60% of the maximum load)" → "push-ups (3 sets, until exhaustion)" → "stretching and relaxation (10 minutes)".

[0155] In this embodiment, by jointly encoding the training entity features in both the spatial and temporal dimensions through a graph neural network, the structural evolution and dynamic changes during the training process can be comprehensively captured; the multi-layer cross-attention mechanism realizes the adaptive fusion of spatial and temporal features, enhancing the multi-dimensional expression ability and fine-grained difference perception of the training feature representation; self-attention-guided graph pooling is used for feature sparsification and dimensionality reduction, which not only retains the key information but also effectively compresses the model scale, improving the computational efficiency and generalization performance; the hierarchical reinforcement learning model based on the compressed features separately models the training item sorting and the exercise intensity regulation, taking into account the rationality of the global training progress and the personalized optimization of the local training load; a phased training plan that is progressive and adapted to the exercise intensity is generated through a two-layer policy network, ensuring that the training plan is scientific and progressive and conforms to the physiological load law, thereby improving the training effect and reducing the risk of injury.

[0156] In an alternative embodiment, a hierarchical reinforcement learning model for multi-objective joint optimization is constructed based on the compressed feature representation. The progressive relationship constraint and the exercise intensity constraint are modeled as hierarchical optimization objectives. The global sorting strategy and the local intensity parameters of the training items are learned through a two-layer policy network, including:

[0157] Model the progressive relationship constraint of the training items as a high-level optimization objective, model the exercise intensity constraint of the training items as a low-level optimization objective, and calculate the high-level reward value and the low-level reward value of the state-action pair using a fuzzy evaluation matrix;

[0158] Construct a two-layer policy network. The high-level policy network of the two-layer policy network uses a multi-scale sliding time window to segment and encode the training item sequence, calculates the progressive correlation score between items within each time window, and dynamically adjusts the progressive correlation threshold in combination with the high-level reward value to generate a global sorting reference strategy for the training items;

[0159] The low-level policy network of the two-layer policy network constructs a multi-dimensional physiological load model based on the heart rate variability index and the exercise metabolism level of the training items, and dynamically adjusts the intensity parameters through a soft constraint optimization method introducing a buffer interval in combination with the low-level reward value to generate a local intensity adjustment strategy for the training items;

[0160] Use a recurrent neural network to establish a bidirectional information channel between the high-level policy network and the low-level policy network. Input the global sorting reference strategy and the local intensity adjustment strategy into the bidirectional information channel, and iteratively optimize the global sorting reference strategy and the local intensity adjustment strategy based on a cross-layer constraint function to obtain the global sorting strategy and the local intensity parameters of the training items.

[0161] In a specific implementation, the progressive relationship constraint of training items is modeled as a high-level optimization objective, and the exercise intensity constraint of training items is modeled as a low-level optimization objective. A fuzzy evaluation matrix is used to calculate the high-level reward value and low-level reward value of the state-action pair. The progressive relationship constraint of training items refers to the sequential relationship between different training items in terms of technical difficulty, physiological load, and training objectives. For example, "basic strength training" should precede "specific explosive power training", and "low-intensity aerobic training" should precede "high-intensity interval training". The progressive relationship constraint is divided into five levels: strong leading relationship (the subsequent item cannot be carried out until the previous item is completed), weak leading relationship (it is recommended to complete the previous item first), no relationship, weak subsequent relationship, and strong subsequent relationship. The exercise intensity constraint of training items refers to the physiological load limit during the execution of the item, including parameters such as heart rate range, percentage of strength load, and perceived fatigue degree. The exercise intensity constraint is divided into three levels: low-intensity interval (heart rate is 60%-70% of the maximum heart rate), medium-intensity interval (heart rate is 70%-85% of the maximum heart rate), and high-intensity interval (heart rate is 85%-95% of the maximum heart rate). The dimension of the fuzzy evaluation matrix is the number of states × the number of actions, where the state represents the current physiological and training state of the trainee, and the action represents the optional training items. Each element in the matrix is calculated by a fuzzy membership function, and the value range is 0-1. The larger the value, the higher the suitability of the state-action pair. The high-level reward value mainly considers the progressive rationality, technical connection, and cycle matching degree of training items; the low-level reward value mainly considers the intensity suitability, fatigue recovery degree, and physiological tolerance. For example, for a certain strength trainee, the high-level reward value of choosing "high-intensity squats" in the "moderate fatigue state" is 0.3 (low, because it violates the progressive relationship), and the low-level reward value is 0.2 (low, because the intensity does not match the current recovery state).

[0162] Construct a two - layer policy network. The high - level policy network of the two - layer policy network uses a multi - scale sliding time window to segment and encode the training item sequence. Calculate the progressive correlation score between items within each time window, and dynamically adjust the progressive correlation threshold in combination with the high - level reward value to generate a global sorting reference policy for training items. The high - level policy network adopts a three - layer fully - connected neural network structure. The input layer dimension is the dimension of the state vector (usually 16 - 32 dimensions), the number of hidden layer nodes is 64, and the output layer dimension is the dimension of the action space (i.e., the number of optional training items). The multi - scale sliding time window includes a short - term window (3 - 5 days), a medium - term window (7 - 14 days), and a long - term window (21 - 28 days), which capture training rules at different time scales respectively. Within each time window, calculate the progressive correlation score between training items. The score calculation is based on the cosine similarity of item feature vectors and an expert - defined progressive rule library. The progressive correlation score ranges from - 1 to 1. A positive value indicates a positive progressive relationship between items, and a negative value indicates a conflict. The progressive correlation threshold is initially set to 0.6 and then dynamically adjusted according to the high - level reward value: a high reward value (>0.8) causes the threshold to be reduced by 5% - 10%, increasing the sorting flexibility; a low reward value (<0.3) causes the threshold to be increased by 5% - 10%, strengthening the sorting constraint. The global sorting reference policy is generated by performing a topological sort on the training items, considering the progressive relationship constraints and the priority of training objectives. For example, in a 12 - week strength training plan, the global sorting reference policy ranks basic strength training items (such as squats and bench presses) in the first 4 weeks, compound strength training items in the middle 4 weeks, and specific strength and explosive power training items in the last 4 weeks.

[0163] The low-level policy network of the double-layer policy network constructs a multi-dimensional physiological load model based on the heart rate variability index and exercise metabolism level of the training item. By introducing a soft constraint optimization method with a buffer interval and combining with the low-level reward value, the intensity parameter is dynamically adjusted to generate a local intensity adjustment strategy for the training item. The low-level policy network adopts a dual-channel convolutional neural network structure. One channel processes heart rate variability data, and the other channel processes metabolic index data. Finally, the intensity parameter adjustment value is merged and output through a fully connected layer. The heart rate variability index includes RMSSD (root mean square of the differences between adjacent RR intervals), SDNN (standard deviation of all RR intervals), LF / HF ratio (ratio of low-frequency power to high-frequency power), etc., which are used to evaluate the state of the autonomic nervous system and the degree of fatigue recovery. The exercise metabolism level is evaluated by indicators such as blood lactate concentration, excess post-exercise oxygen consumption (EPOC), and respiratory quotient (RER). The multi-dimensional physiological load model integrates these indicators into an 8-dimensional vector, representing the current physiological load state of the trainer. The soft constraint optimization method with a buffer interval sets an ideal target value and an acceptable range for each intensity parameter. For example, the ideal relative intensity of a certain strength training item is 80% 1RM (80% of one-repetition maximum), and the acceptable range is 75% - 85% 1RM. The dynamic adjustment of the intensity parameter is based on the low-level reward value and the current physiological state: when the low-level reward value is high and the physiological state is good, the intensity parameter can be adjusted upward by 1% - 3%; when the low-level reward value is low or the physiological state is poor, the intensity parameter is adjusted downward by 3% - 5%. For example, for an athlete with a poor recovery state (RMSSD is 20% lower than the baseline), the original squat training intensity of 85% 1RM will be adjusted to 80% 1RM.

[0164] A bidirectional information channel is established between the high-level policy network and the low-level policy network using a recurrent neural network. The global sorting reference policy and the local intensity adjustment policy are input into the bidirectional information channel, and the global sorting reference policy and the local intensity adjustment policy are iteratively optimized based on a cross-layer constraint function to obtain the global sorting policy and the local intensity parameters of the training items. The bidirectional information channel adopts a long short-term memory network (LSTM) structure with a hidden state dimension of 128 and a time step of the number of days in the training plan. The LSTM network can capture long-term dependencies in the training plan, memorize important training patterns and transition points. The bidirectional information channel transmits sorting constraint information from the high level to the low level to guide the reasonable range of intensity parameters; it transmits physiological load information from the low level to the high level to affect the adjustment direction of item sorting. The cross-layer constraint function comprehensively considers three aspects: the satisfaction of the progressive relationship, the rationality of the intensity parameters, and the physiological recovery window, and takes the weighted sum of the three as the optimization objective, with a weight ratio of 4:3:3. The iterative optimization process adopts an alternating update strategy: the global sorting policy is updated in odd rounds, and the local intensity parameters are updated in even rounds, with 20 iterations. In each iteration, according to the current state and the expected goal, the sorting policy or the intensity parameters are fine-tuned to gradually approach the optimal solution. For example, in a certain iteration, it is found that three consecutive days of high-intensity training result in insufficient physiological recovery, and the system will adjust the global sorting to insert low-intensity recovery training or rest days between high-intensity training days. After optimization, the obtained global sorting policy is represented as a sequence of training items, specifying the training items to be executed and their order within each training cycle; the local intensity parameters are represented as the specific execution parameters of each training item, such as weight, number of sets, number of repetitions, intensity range, etc.

[0165] In the prior art, the sorting and intensity adjustment of training items usually adopt rule-based methods or single-level optimization algorithms. Rule-based methods rely on preset training templates and expert experience, lack the ability of personalized adaptation, and are difficult to cope with the dynamic changes of the trainer's state; single-level optimization algorithms either focus on the global training structure and ignore local intensity adjustment, or focus on local training parameters and lack global coordination, and cannot take into account the systematicness and adaptability of training. The improvement starting point of the present invention is to introduce a two-layer optimization architecture, regard the sorting and intensity adjustment of training items as two interrelated but different-level optimization problems, and achieve cross-layer collaboration through a two-way information channel. The high-level policy network ensures that the sorting of training items conforms to the progressive relationship and cycle characteristics, and provides global guidance; the low-level policy network adjusts the training intensity according to the real-time physiological state to ensure the suitability of training stimuli. The fuzzy evaluation matrix and multi-scale sliding time window technology can handle the uncertainty and time dependence in training decisions and improve the robustness of the optimization results. Compared with traditional methods, the method of this embodiment has significant advantages in training effects, with an increased training objective achievement rate, improved training adaptability (the ability of the training plan to adjust according to state changes), and a reduced risk of overtraining. In terms of personalization, the method of this embodiment can generate differentiated training plans for users with different training levels and goals. The plan for beginners pays more attention to the cultivation of basic abilities and technical learning, the plan for intermediate trainers emphasizes systematicness and cycle changes, and the plan for advanced trainers highlights special abilities and fine adjustment. In terms of application scenarios, this method is applicable to various training types, including strength training, endurance training, ball game training, etc., and realizes the adaptation to different training domains by adjusting the corresponding progressive relationship constraints and intensity parameter definitions.

[0166] Such as Figure 3As shown, a complete training sequence is presented, which includes 7 key training item nodes and the progressive relationships between them. Meanwhile, the training sequence is analyzed and optimized through the multi-scale sliding time window technique. Each node in the figure represents a training item, and the size of the node reflects the importance of the training item. It can be seen that the circle of node 5 (high-intensity interval) is the largest, indicating its core position in the entire training sequence; while nodes 1 (warm-up activity) and 7 (relaxation and recovery) are smaller. Although they are essential, they belong to auxiliary training links. The connecting lines between the nodes represent the progressive relationships between the training items, and the thickness of the lines represents the intensity of the progressive correlation. It should be noted that the connecting line from node 6 (special skill training) to node 7 (relaxation and recovery) is the thickest (correlation value 0.95), indicating that the progressive relationship of immediately performing relaxation and recovery after special training is the closest; while the connecting line from node 5 (high-intensity interval) to node 7 (relaxation and recovery) is thinner (correlation value 0.6), indicating that the direct progressive relationship between the two is relatively weak, and it is more suitable to use special skill training as a transition. The three dashed boxes in the figure represent multi-scale sliding time windows, which are respectively marked as "Time Window 1: Correlation Threshold = 0.65", "Time Window 2: Correlation Threshold = 0.75" and "Time Window 3: Correlation Threshold = 0.85". These windows cover different ranges of training items and set increasing correlation thresholds, reflecting the innovative method of the solution in this embodiment for analyzing the progressive relationships between training items at different time scales. Through the combined analysis of this network structure and multi-scale windows, the solution in this embodiment can simultaneously consider the close relationships between local training items and the structural characteristics of the overall training sequence, thereby generating a training item sorting strategy that not only meets the progressive requirements but also has global optimal characteristics.

[0167] The personalized training plan generation system in the metaverse intelligent sports according to the embodiment of the present invention includes:

[0168] The first unit is used to obtain the motion data of the user in the metaverse virtual scene;

[0169] The second unit is used to call a preset human biomechanics model to calculate the corresponding motion load parameters of the user in the real environment based on the bone joint point position data in the motion data;

[0170] The third unit is used to perform time series analysis on the motion load parameters through a neural network model, extract the long-term and short-term characteristics of the user's motion pattern by using the attention mechanism, and predict the physiological limit threshold of the user under different exercise intensities based on the extracted long-term and short-term characteristics;

[0171] The fourth unit is used to construct a training knowledge triple based on the historical training data of the user, and construct a personalized training knowledge graph through the method of multi-level knowledge extraction and dynamic graph optimization based on the training knowledge triple;

[0172] A fifth unit for constructing a graph neural network model, inputting the personalized training knowledge graph into the graph neural network model, and generating a phased training plan for the user based on the node feature vectors output by the graph neural network model. Among them, the training items in the phased training plan are sorted according to a progressive relationship, and the exercise intensity of each training item is within the range of the physiological limit threshold;

[0173] A sixth unit for converting the phased training plan into training instructions for a metaverse virtual scene and displaying a training guidance interface in the metaverse virtual scene.

[0174] A third aspect of the embodiments of the present invention provides an electronic device, including:

[0175] A processor;

[0176] A memory for storing instructions executable by the processor;

[0177] Among them, the processor is configured to call the instructions stored in the memory to execute the method described above.

[0178] A fourth aspect of the embodiments of the present invention provides a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the method described above is implemented.

[0179] The present invention can be a method, apparatus, system, and / or computer program product. The computer program product can include a computer-readable storage medium, on which computer-readable program instructions for executing various aspects of the present invention are uploaded.

[0180] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for generating a personalized training plan in the metaverse intelligent exercise, characterized in that, Including: Obtain the motion data of the user in the metaverse virtual scene; Based on the bone joint point position data in the motion data, call a preset human biomechanics model to calculate the corresponding motion load parameters of the user in the real environment; Perform time series analysis on the motion load parameters through a neural network model, adopt an attention mechanism to extract the long-term and short-term features of the user's motion pattern, and based on the extracted long-term and short-term features, predict the physiological limit threshold of the user under different exercise intensities, including: Construct an adaptive time window according to the user's historical motion load parameters, dynamically adjust the window length based on the motion volatility, and generate variable-length time series data segments; input the variable-length time series data segments into a recurrent convolutional neural network, and extract the local motion feature sequence through a multi-layer recurrent convolutional structure; Input the local motion feature sequence into a graph attention network, construct the local motion feature sequence into a time series feature map, extract the time series dependence relationship between feature nodes through graph convolution operations, and obtain global correlation features; input the local motion feature sequence and the global correlation features into a time series attention module, and the time series attention module constructs a multi-scale feature pyramid to calculate the adaptive weight coefficient of the local motion feature sequence at different time scales; Perform time series cross-attention calculation on the adaptive weight coefficient and the global correlation features to generate enhanced features of multiple time scales, and fuse the enhanced features of the multiple time scales through a cross-scale feature aggregation network to obtain the long-term and short-term features of the user's motion pattern; use a Bayesian neural network to model the long-term and short-term features, calculate the probability distribution function of the physiological limit threshold, and use the mean value of the probability distribution function as the prediction result of the physiological limit threshold of the user under different exercise intensities; Construct training knowledge triples according to the user's historical training data, and construct a personalized training knowledge graph based on the training knowledge triples through multi-level knowledge extraction and dynamic graph optimization; Construct a graph neural network model, input the personalized training knowledge graph into the graph neural network model, and generate a phased training plan for the user based on the node feature vectors output by the graph neural network model, including: Encode the topological structure features of the training entity nodes in the spatial dimension, and model the dynamic evolution features of the training entity nodes in the time series dimension using a time series-aware graph convolutional network to obtain spatial dimension features and time series dimension features; Input the personalized training knowledge graph into the graph neural network model, adaptively fuse the spatial dimension features and the time series dimension features through a multi-layer cross-attention mechanism to generate a multi-dimensional feature vector of the training entity nodes; use a self-attention-guided graph pooling operation to sparsely reduce the dimension of the multi-dimensional feature vector to obtain a compressed feature representation of the training entity nodes; Construct a hierarchical reinforcement learning model for multi-objective joint optimization, model the progressive relationship constraint and the exercise intensity constraint as hierarchical optimization objectives, and learn the global sorting strategy and local intensity parameters of the training items through a two-layer policy network, including: Model the progressive relationship constraint of training items as a high-level optimization objective, model the exercise intensity constraint of training items as a low-level optimization objective, and use a fuzzy evaluation matrix to calculate the high-level reward value and low-level reward value of the state-action pair; Construct a two-layer policy network. The high-level policy network of the two-layer policy network uses a multi-scale sliding time window to segment and encode the training item sequence, calculates the progressive correlation score between items within each time window, and dynamically adjusts the progressive correlation threshold in combination with the high-level reward value to generate a global sorting reference policy for training items; The low-level policy network of the two-layer policy network constructs a multi-dimensional physiological load model based on the heart rate variability index and exercise metabolism level of training items, and dynamically adjusts the intensity parameters through a soft constraint optimization method introducing a buffer interval in combination with the low-level reward value to generate a local intensity adjustment policy for training items; Use a recurrent neural network to establish a bidirectional information channel between the high-level policy network and the low-level policy network, input the global sorting reference policy and the local intensity adjustment policy into the bidirectional information channel, and iteratively optimize the global sorting reference policy and the local intensity adjustment policy based on a cross-layer constraint function to obtain the global sorting policy and local intensity parameters of training items; Input the global sorting policy and the local intensity parameters into a training plan generation module, determine the progressive order of training items according to the global sorting policy, adjust the exercise intensity of training items according to the local intensity parameters, and generate a phased training plan that meets the progressive relationship and exercise intensity requirements; Convert the phased training plan into training instructions for a metaverse virtual scene, and display a training guidance interface in the metaverse virtual scene.

2. The method according to claim 1, wherein Based on the skeletal joint point position data in the motion data, call a preset human biomechanical model to calculate the corresponding motion load parameters of the user in the real environment, including: According to the skeletal joint point position data in the motion data, use a kinematic inversion model to calculate the user's joint angle data; based on the joint angle data at adjacent times, calculate the user's joint motion speed data and joint motion acceleration data; Establish a human skeletal link model, map the skeletal joint point position data to the corresponding skeletal nodes in the human skeletal link model, and calculate the pressure value and torque value of each joint according to the connection relationship between the skeletal nodes in the human skeletal link model; Input the joint angle data and joint force data into the static force analysis channel of a preset human biomechanical model for processing to obtain static force characteristics, which characterize the muscle force distribution required for the user to maintain the current posture; Input the joint motion speed data and the joint motion acceleration data into the dynamic force analysis channel of the human biomechanical model for processing to obtain dynamic force characteristics, which characterize the joint impact force and inertial force during the user's movement; Perform fusion processing on the static force characteristics and the dynamic force characteristics through the feature fusion layer of the human biomechanical model to obtain the output result of the feature fusion layer; Based on the output result of the feature fusion layer, calculate the corresponding exercise load parameters of the user in the real environment.

3. The method according to claim 1, characterized in that, Use a Bayesian neural network to model the long-term and short-term features, calculate the probability distribution function of the physiological limit threshold, and take the mean value of the probability distribution function as the prediction result of the user's physiological limit threshold under different exercise intensities, including: Input the long-term and short-term features into the feature encoding network to generate a sequence of feature vectors; Construct a Bayesian neural network, set latent variables in each layer of the Bayesian neural network, and input the sequence of feature vectors into the Bayesian neural network; Construct training sample pairs based on the sequence of feature vectors, use a variational autoencoder to model the latent variables in the Bayesian neural network, and obtain the prior distribution of the latent variables; Input the prior distribution of the latent variables into a probability neural network to generate a weight distribution, and the weight distribution is used to characterize the uncertainty of each layer of network parameters in the Bayesian neural network; Optimize the weight distribution through the stochastic variational inference method, generate multiple sets of network parameters according to the weight distribution, construct a deep ensemble model based on the multiple sets of network parameters, input new long-term and short-term features into the deep ensemble model, and output multiple prediction results based on the deep ensemble model; Perform probability density estimation on the multiple prediction results to obtain the probability distribution function of the physiological limit threshold, calculate the mean value of the probability distribution function, and take the mean value as the prediction result of the user's physiological limit threshold under different exercise intensities.

4. The method according to claim 1, wherein Construct training knowledge triples based on the user's historical training data, and construct a personalized training knowledge graph through multi-level knowledge extraction and dynamic graph optimization based on the training knowledge triples, including: Perform temporal segmentation on the user's historical training data to obtain training data sequences for multiple training cycles; Extract training entities and training relationships from the training data sequence, construct training knowledge triples, input the training knowledge triples into a knowledge reasoning model, and perform semantic expansion on the training knowledge triples based on the knowledge reasoning model; Perform multi-granularity partitioning on the training knowledge triples, construct knowledge subgraphs at each granularity level, and the knowledge subgraphs contain training entity nodes and training relationship edges at that granularity level; Perform representation learning on the knowledge subgraphs, iteratively update the feature representations of the training entity nodes through a message passing mechanism, calculate the similarity matrix between nodes based on the updated feature representations, and construct a node importance scoring model in combination with the weight distribution of the training relationship edges; Calculate the importance scores of the training entity nodes according to the node importance scoring model, set an adaptive pruning threshold based on the importance scores, perform dynamic pruning on the knowledge subgraphs, aggregate the features of the pruned multiple knowledge subgraphs, and construct a hierarchical training knowledge graph; Map new training data to the hierarchical training knowledge graph, and update the training entity nodes and training relationship edges in the hierarchical training knowledge graph; Generate a personalized training knowledge graph based on the hierarchical training knowledge graph.

5. A personalized training plan generation system in the metaverse intelligent exercise, which is used to implement the method described in any one of the foregoing claims 1-4, and is characterized in that, Including: The first unit is used to obtain the motion data of the user in the metaverse virtual scene; The second unit is used to calculate the corresponding motion load parameters of the user in the real environment by calling a preset human biomechanics model based on the bone joint point position data in the motion data; The third unit is used to perform time series analysis on the motion load parameters through a neural network model, extract the long-term and short-term features of the user's motion pattern by using an attention mechanism, and predict the physiological limit threshold of the user under different exercise intensities based on the extracted long-term and short-term features; The fourth unit is used to construct training knowledge triples based on the user's historical training data, and construct a personalized training knowledge graph through multi-level knowledge extraction and dynamic graph optimization based on the training knowledge triples; The fifth unit is used to construct a graph neural network model, input the personalized training knowledge graph into the graph neural network model, and generate a phased training plan for the user based on the node feature vectors output by the graph neural network model, wherein the training items in the phased training plan are sorted according to a progressive relationship, and the exercise intensity of each training item is within the range of the physiological limit threshold; The sixth unit is used to convert the phased training plan into training instructions for the metaverse virtual scene and display a training guidance interface in the metaverse virtual scene.

6. An electronic device, characterized in that, Comprising: A processor; A memory for storing instructions executable by the processor; Wherein, the processor is configured to call the instructions stored in the memory to execute the method according to any one of claims 1 to 4.

7. A computer-readable storage medium having computer program instructions stored thereon, characterized in that, When the computer program instructions are executed by the processor, the method according to any one of claims 1 to 4 is implemented.

Images