Exercise training simulation method, system and equipment based on metabolic capability and storage medium
By collecting and analyzing the metabolic characteristics and exercise physiological data of training subjects, and combining time series and load parameters, individualized metabolic response sequences are generated. This solves the problem that existing technologies cannot accurately reflect individual metabolic differences and the correlation between training load and the actual situation, and enables dynamic optimization and scientific guidance of training plans.
Patent Information
- Application Number
- CN202511797373.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-02
- Publication Date
- 2026-03-10
AI Technical Summary
Existing exercise training simulation methods based on metabolic models cannot accurately reflect individual metabolic differences, have insufficient correlation between metabolic characteristic parameters and training load parameters, lack a time-series feedback mechanism for energy consumption prediction, and the simulation output results cannot guide adaptive adjustment of training load.
By collecting the basal metabolic parameters and exercise physiological data of the training subjects, a metabolic feature vector is generated. The metabolic response rate is calculated and energy consumption is predicted by combining the training load parameters and exercise time series. Correlation analysis between the time domain and intensity domain is performed, the training load parameters are adjusted and the simulation calculation is repeated to generate a training simulation scheme.
It enables individualized metabolic modeling, improves the physiological matching degree of simulation input, enhances the dynamic response capability of metabolic prediction, supports accurate assessment of individualized training load and adaptive matching of training plans, and improves the scientificity and safety of exercise training.
Smart Images
Figure CN121641471A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of exercise physiological modeling and computer simulation technology, specifically to an exercise training simulation method, system, device, and storage medium based on metabolic capacity. Background Technology
[0002] In recent years, with the development of exercise physiological monitoring technology and biosensors, the combination of computer simulation technology and physiological modeling algorithms has provided new research paths for predicting exercise metabolic response and optimizing training strategies. However, most existing methods only establish empirical models for specific exercise scenarios (such as running and cycling power training), failing to form a universal metabolic capacity simulation framework that can span intensity and time dimensions. Furthermore, traditional metabolic analysis models often use static feature inputs, treating individual metabolic levels as fixed constants, making it difficult to reflect the real-time changes in metabolic parameters during dynamic training. With the rise of deep learning and temporal modeling technologies, some studies have attempted to fit and predict the training process using time-series networks, but these models tend to be black-box statistical learning, lacking deep coupling with exercise physiological mechanisms and failing to explain the physical logic between metabolic response and energy consumption. There is an urgent need for a multi-dimensional simulation model that can integrate individual metabolic characteristics, exercise physiological data, training load, and time-series features to achieve a dynamic mapping between training plans and energy metabolic states, providing a scientific basis for precision training.
[0003] Existing metabolic modeling methods often rely on uniform parameter models based on average physiological indicators, failing to reflect individual differences in metabolic rate, oxygen utilization efficiency, and lactate accumulation, resulting in simulation outputs lacking individual adaptability. The correlation between training load parameters and energy consumption typically depends on univariate analysis, such as estimating metabolic levels using heart rate or power intervals, without considering the dynamic response of multidimensional metabolic characteristics, thus limiting the model's prediction accuracy under multi-stage training conditions. Traditional simulation systems generally lack temporal feedback mechanisms in energy prediction, meaning the energy consumption results output by the model cannot be used to adaptively correct training parameters, leading to training plans still relying on manual adjustments and hindering closed-loop optimization. Existing systems often focus on numerical estimation of energy consumption, neglecting the distribution patterns of metabolic responses in the time and intensity domains. For example, metabolic fluctuation trends under different intensities, durations, or intervals are not modeled by the system, making it difficult to achieve full-cycle matching between training intensity and metabolic response. Summary of the Invention
[0004] In view of the above-mentioned problems, the present invention is proposed.
[0005] Therefore, the technical problem solved by this invention is that existing exercise training simulation methods based on metabolic models have the following problems: they cannot accurately reflect individual metabolic differences, the correlation between metabolic characteristic parameters and training load parameters is insufficient, the energy consumption prediction lacks a time-series feedback mechanism, and the simulation output results cannot guide the adaptive adjustment of training load.
[0006] To address the aforementioned technical problems, this invention provides the following technical solution: a metabolic capacity-based exercise training simulation method, comprising: collecting basal metabolic parameters and exercise physiological data of the training subjects, and generating a metabolic feature vector; calculating the metabolic response rate based on the metabolic feature vector and combining training load parameters and exercise time series, predicting energy consumption, and obtaining metabolic response sequences under different training load conditions; performing time-domain and intensity-domain correlation analysis on the metabolic response sequences, comparing the metabolic requirements of the target training plan with the metabolic response output of the simulation; adjusting the training load parameters according to the difference results and repeating the simulation calculation to generate a training simulation plan.
[0007] As a preferred embodiment of the exercise training simulation method based on metabolic capacity described in this invention, the collection of basal metabolic parameters and exercise physiological data of the training subjects includes collecting the resting metabolic rate, maximum oxygen uptake, lactate threshold, heart rate variability, body surface temperature, respiratory rate, and energy metabolism ratio of the training subjects; performing time synchronization and feature extraction on the parameters to generate a metabolic feature vector, represented as follows:
[0008]
[0009] in, This is a metabolic feature vector. The first in the metabolic feature vector One parameter.
[0010] As a preferred embodiment of the exercise training simulation method based on metabolic capacity described in this invention, the calculation of metabolic response rate includes constructing an exercise time series as follows:
[0011]
[0012] in, For motion time series, For the first A specific point in time.
[0013] At any time The metabolic reaction rate is expressed as:
[0014]
[0015] in, This refers to the metabolic reaction rate. Based on basal metabolic constant, This represents the total number of metabolic characteristics. These are the weighting coefficients for metabolic features. For training load weighting coefficients, for The training load intensity function at time t, The weighting coefficient for the rate of change of training load. The weighting coefficient is the factor for the effect of time lag. In order to be in Historical training load values at any given time This is the attenuation coefficient.
[0016] As a preferred embodiment of the exercise training simulation method based on metabolic capacity described in this invention, the predicted energy consumption includes: calculating the energy consumption rate, discretizing the energy consumption rate, predicting energy consumption, and the calculated energy consumption rate is expressed as:
[0017]
[0018] in, The rate of energy consumption. Let be the energy mapping constant. These are the metabolic response mapping coefficients. For training load mapping coefficients, These are the energy mapping weight coefficients corresponding to the metabolic characteristic parameters.
[0019] The energy consumption rate can be discretized as follows:
[0020]
[0021] in, For the first in a discrete time series The cumulative energy consumption at each time point is used as the energy consumption prediction result. This represents the time interval between two adjacent sampling time points.
[0022] As a preferred embodiment of the exercise training simulation method based on metabolic capacity described in this invention, the step of obtaining the metabolic response sequence under different training load conditions includes mapping the energy consumption prediction result to the corresponding metabolic response rate at each training load level, resulting in a weighted metabolic response expressed as follows:
[0023]
[0024] in, To be at the training load level Next, time point The weighted metabolic response. This is the metabolic rate weighting coefficient. To be at the training load level The metabolic reaction rate under the condition, Energy consumption weighting coefficient, This refers to the training load level.
[0025] The weighted metabolic responses are arranged in a time series to form metabolic response sequences under different training load conditions, as follows:
[0026]
[0027] in, To be at the training load level The metabolic response sequence is as follows.
[0028] As a preferred embodiment of the exercise training simulation method based on metabolic capacity described in this invention, the step of performing time-domain and intensity-domain correlation analysis on the metabolic response sequence includes: aligning the metabolic demand curve of the target training plan with the metabolic response sequence under different training load levels in time; comparing the deviation between the metabolic rate change trend at each moment and the target metabolic demand; analyzing the change law of metabolic response over time and the distribution characteristics under different training load intensities to determine the degree of matching between energy consumption and metabolic response in the training plan; and comprehensively considering the time-domain deviation and intensity-domain difference to obtain the metabolic response difference result.
[0029] As a preferred embodiment of the exercise training simulation method based on metabolic capacity described in this invention, the generation of the training simulation scheme includes: comparing the metabolic rate change trends under different training load levels based on the metabolic response difference results, identifying the intervals in the target training plan where the metabolic demand and simulation response do not match, correcting the load intensity, duration, and interval period in the training load parameters based on the degree of metabolic deviation in the difference intervals, recalculating the metabolic response rate and energy consumption under the training load, generating a new metabolic response sequence, and iteratively optimizing the training load configuration by aligning the updated metabolic response sequence with the metabolic demand curve of the target training plan in the time domain and comparing it in the intensity domain until the difference between the metabolic response and the target demand is within a preset difference threshold range, and outputting the training simulation scheme.
[0030] Another objective of this invention is to provide a metabolic-capacity-based exercise training simulation system that can generate a metabolic feature vector by collecting the basal metabolic parameters and exercise physiological data of the training subjects, and calculate the metabolic response rate and predict energy consumption based on the metabolic feature vector combined with training load parameters and exercise time series, thereby realizing dynamic simulation of metabolic response during training and solving the problems of ineffective modeling of individual metabolic differences and insufficient accuracy of energy consumption prediction in the prior art.
[0031] As a preferred embodiment of the metabolic capacity-based exercise training simulation system of the present invention, it includes: a metabolic feature acquisition module, a metabolic response calculation module, a metabolic response correlation analysis module, and a training simulation optimization module; the metabolic feature acquisition module is used to collect the basal metabolic parameters and exercise physiological data of the training subjects, generate metabolic feature vectors, and provide basic data for metabolic modeling; the metabolic response calculation module calculates the metabolic response rate based on the metabolic feature vectors, training load parameters, and exercise time series, predicts energy consumption, and generates a metabolic response sequence; the metabolic response correlation analysis module is used to perform time domain and intensity domain analysis on the metabolic response sequence, and compare the metabolic demand of the target training plan with the metabolic response output of the simulation; the training simulation optimization module is used to adjust the training load parameters according to the difference results and repeat the simulation calculation to generate an optimized training simulation plan.
[0032] Another object of the present invention is to provide a metabolic capacity-based exercise training simulation device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement a metabolic capacity-based exercise training simulation method.
[0033] Another object of the present invention is to provide a metabolic capacity-based exercise training simulation storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of a metabolic capacity-based exercise training simulation method.
[0034] The beneficial effects of this invention are as follows: The exercise training simulation method based on metabolic capacity provided by this invention generates individualized metabolic feature vectors by collecting the basal metabolic parameters and exercise physiological data of the training subjects, thereby achieving accurate modeling of the metabolic capacity of the training subjects and improving the physiological matching degree of the simulation input. By calculating the metabolic response rate and predicting energy consumption based on the metabolic feature vector combined with training load parameters and exercise time series, metabolic response sequences can be accurately generated under different training load conditions, thereby improving the dynamic response capability of metabolic prediction. By performing correlation analysis of the metabolic response sequences in the time domain and intensity domain, the difference between the metabolic demand of the target training plan and the simulation output can be identified, supporting the accurate assessment of individualized training load. By adjusting the training load parameters according to the difference results and repeating the simulation calculation, a dynamically optimized training simulation scheme can be formed, thereby achieving adaptive matching between the training plan and the actual metabolic capacity, improving the scientificity and safety of exercise training. Attached Figure Description
[0035] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0036] Figure 1 The above is an overall flowchart of a sports training simulation method based on metabolic capacity provided in Embodiment 1 of the present invention. Detailed Implementation
[0037] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.
[0038] Example 1, referring to Figure 1 As one embodiment of the present invention, a method for simulating exercise training based on metabolic capacity is provided, comprising:
[0039] S1: Collect the basal metabolic parameters and exercise physiological data of the training subjects and generate metabolic feature vectors.
[0040] Furthermore, the basal metabolic parameters and exercise physiological data of the training subjects are collected, including resting metabolic rate, maximum oxygen uptake, lactate threshold, heart rate variability, body surface temperature, respiratory rate, and energy metabolism ratio. These parameters are then synchronized over time and their features are extracted to generate a metabolic feature vector, represented as follows:
[0041]
[0042] in, This is a metabolic feature vector. The first in the metabolic feature vector One parameter.
[0043] It should be noted that the basal metabolic parameters of the training subjects, including resting metabolic rate, maximum oxygen uptake, lactate threshold, heart rate variability, body surface temperature, respiratory rate, and energy metabolism ratio, are obtained to characterize the individual's metabolic capacity. These data can be collected using physiological monitoring equipment under both resting and exercise conditions, and recorded synchronously at uniform time sampling intervals. After data preprocessing, outliers are filtered out, the time series is smoothed, and key metabolic feature values are extracted to form a metabolic feature vector.
[0044] It should also be noted that by fusing and modeling multi-source data such as resting metabolic rate, maximum oxygen uptake, lactate threshold, heart rate variability, body surface temperature, respiratory rate, and energy metabolism ratio, a comprehensive quantitative expression of metabolic characteristics is achieved. This allows for the maintenance of synchronicity among parameters in the time domain, thereby accurately reflecting the changing trend of the training subjects' metabolic capacity under dynamic load.
[0045] S2: Based on metabolic feature vectors and combined with training load parameters and exercise time series, calculate metabolic response rate, predict energy consumption, and obtain metabolic response sequences under different training load conditions.
[0046] Furthermore, calculating the metabolic response rate involves constructing an exercise time series representation as follows:
[0047]
[0048] in, For motion time series, For the first A specific point in time.
[0049] At any time The metabolic reaction rate is expressed as:
[0050]
[0051] in, This refers to the metabolic reaction rate. Based on basal metabolic constant, This represents the total number of metabolic characteristics. These are the weighting coefficients for metabolic features. For training load weighting coefficients, for The training load intensity function at time t, The weighting coefficient for the rate of change of training load. The weighting coefficient is the factor for the effect of time lag. In order to be in Historical training load values at any given time This is the attenuation coefficient.
[0052] It should be noted that the training process is divided into multiple time points, forming a sports time series. Each time point corresponds to a training state. By correlating metabolic characteristic parameters with sports load data, the changing trend of metabolic response can be continuously tracked in the time domain. The metabolic characteristic parameters of the training subjects are used as the basic input, and combined with the training load intensity function and its rate of change, a calculation model for the metabolic response rate is established. The model considers the direct impact of the current training load on the metabolic rate, the dynamic regulatory effect of the load change rate on the metabolic response, and the time lag effect of historical training loads, thereby achieving dynamic prediction of the metabolic response. Weighting coefficients quantify the effects of metabolic characteristics, training load, load change rate, and lag effects, ensuring that the metabolic response rate reflects individual differences in metabolic capacity. By adjusting the weighting coefficients and decay parameters, adaptive corrections can be made for different individuals or different training types to improve the accuracy and generalization ability of the calculation results.
[0053] It should also be noted that by simultaneously introducing the time lag effect of training load intensity, load change rate, and historical load, the direct impact, dynamic changes, and cumulative effects on metabolic rate were systematically quantified. Through the joint setting of the lag weighting coefficient and the decay parameter, the delayed and inertial characteristics of metabolic response during exercise can be captured, thereby reflecting the dynamic metabolic characteristics of an individual under different training rhythms.
[0054] Furthermore, predicting energy consumption includes calculating the energy consumption rate, discretizing the energy consumption rate, predicting energy consumption, and expressing the calculated energy consumption rate as:
[0055]
[0056] in, The rate of energy consumption. Let be the energy mapping constant. These are the metabolic response mapping coefficients. For training load mapping coefficients, These are the energy mapping weight coefficients corresponding to the metabolic feature parameters;
[0057] The energy consumption rate can be discretized as follows:
[0058]
[0059] in, For the first in a discrete time series The cumulative energy consumption at each time point is used as the energy consumption prediction result. This represents the time interval between two adjacent sampling time points.
[0060] It should be noted that, based on the changing patterns of metabolic response rate and training load intensity, and combined with metabolic characteristic parameters, the energy consumption rate at any given time is calculated. The energy mapping constant is used to describe the constant contribution of basal metabolic level to energy consumption; the metabolic response mapping coefficient is used to reflect the impact of changes in metabolic response rate on energy consumption; the training load mapping coefficient is used to characterize the linear response of the current training load intensity to the energy consumption rate; and the energy mapping weight coefficients corresponding to the metabolic characteristic parameters are used to quantify the impact of individual metabolic characteristics on energy conversion efficiency. Through the combined calculation of the above coefficients, the energy consumption rate that dynamically changes with training load can be obtained in the time domain. The obtained energy consumption rate is then discretized according to the time series. By dividing the time axis into several sampling time points, and using the time interval between two adjacent sampling points as the step size, the energy consumption rate is integrated and accumulated to obtain the cumulative energy consumption at each time point in the discrete time series. This discretization process can achieve an approximate calculation of continuous energy consumption within a finite sampling period, making the prediction results more consistent with the energy conversion rhythm in the actual training process.
[0061] It should also be noted that by discretizing the energy consumption rate according to the time series to form the discrete-time cumulative energy consumption result, not only is the resolution and real-time performance of the calculation process improved, but the instability of the continuous integral model in high-frequency training scenarios is also avoided. The discretization mechanism enables the energy consumption calculation to achieve a continuous approximation within a finite sampling period, thus better reflecting the actual changes in human energy metabolism.
[0062] Furthermore, obtaining the metabolic response sequences under different training load conditions includes, at each training load level, the predicted energy expenditure results. Mapping to the corresponding metabolic response rate, the weighted metabolic response is expressed as follows:
[0063]
[0064] in, To be at the training load level Next, time point The weighted metabolic response. This is the metabolic rate weighting coefficient. To be at the training load level The metabolic reaction rate under the condition, Energy consumption weighting coefficient, This refers to the training load level.
[0065] The weighted metabolic responses are arranged in a time series to form metabolic response sequences under different training load conditions, as follows:
[0066]
[0067] in, To be at the training load level The metabolic response sequence is as follows.
[0068] It should be noted that at each training load level Next, calculate the corresponding time. metabolic reaction rate , is represented as:
[0069]
[0070] in, To be at the training load level The metabolic reaction rate under the condition, To be at the training load level Below The training load intensity function at any given time.
[0071] And obtain the energy consumption prediction results at the same time point. By introducing weighting coefficients for metabolic rate and energy expenditure, two types of indicators are weighted and fused to obtain a weighted metabolic response. The metabolic rate weighting coefficient reflects the dominance of metabolic response rate in the overall metabolic response; the energy expenditure weighting coefficient is used to balance the influence of energy expenditure under different load levels, enabling the model to respond differently to metabolic loads under different training intensities. Energy expenditure is normalized to its maximum value, ensuring that the weighted metabolic response at each moment is within the same scale range, thereby eliminating biases caused by individual differences or different training durations. After weighted calculation, the weighted metabolic response at all moments is continuously arranged on the time axis to form a complete weighted metabolic response sequence.
[0072] It should also be noted that by weighting and fusing the predicted energy consumption results with the metabolic response rate, and by normalizing the data, the scale bias caused by individual differences in physical fitness, training duration, or uneven sampling is eliminated, so that the metabolic response at each time point is in the same measurement range. This significantly improves the comparability and modeling stability across individuals and across cycles. The normalization fusion mechanism enables the trend of metabolic response to truly reflect the changes in training load, rather than being affected by differences in physiological baseline.
[0073] S3: Perform time-domain and intensity-domain correlation analysis on the metabolic response sequence to compare the differences between the metabolic requirements of the target training plan and the metabolic response output of the simulation.
[0074] Furthermore, the correlation analysis of the metabolic response sequence in the time domain and intensity domain includes aligning the metabolic demand curve of the target training plan with the metabolic response sequence under different training load levels in time, comparing the deviation of the metabolic rate change trend at each moment from the target metabolic demand, and judging the matching degree between energy consumption and metabolic response in the training plan by analyzing the change law of metabolic response over time and the distribution characteristics under different training load intensities. Finally, the metabolic response difference results are obtained by combining the time domain deviation and the intensity domain difference.
[0075] It should be noted that the metabolic demand curve of the target training plan is time-aligned with the metabolic response sequences under different training load levels. This time alignment ensures that the sampling time within each training cycle matches the corresponding time of the target metabolic demand, allowing for comparison of metabolic response analysis on the same time baseline. The deviation between the metabolic rate change trend at each moment and the target metabolic demand is calculated and compared. Under each training load level, the metabolic rate change values at each sampling time in the metabolic response sequence are extracted, and a metabolic response-time curve is plotted. This curve is then fitted with the target metabolic demand curve to obtain a time-domain deviation index. This index quantifies the time lag and dynamic synchronization of the metabolic response, reflecting the accuracy of the matching between training load scheduling and metabolic response. Based on intensity domain analysis, the distribution characteristics of metabolic responses under different training load levels are statistically compared to identify the correspondence between energy consumption and metabolic response in each training phase. By calculating the mean, variance, and fluctuation range of the metabolic response distribution under each intensity level, the nonlinear correlation characteristics between training intensity and metabolic level are obtained. By further combining the results of time domain deviation and intensity domain difference, a comprehensive evaluation is conducted on the matching degree between energy consumption and metabolic response in the target training plan to determine whether there is insufficient or excessive metabolic response.
[0076] It should also be noted that by fusing the time and intensity domains, a global assessment of the matching degree between energy consumption and metabolic response in the training plan is achieved. This can effectively distinguish the sources of metabolic differences in different training stages, determine whether there is overload or insufficient response, and ensure both real-time performance and adaptability while maintaining analytical accuracy. This significantly improves the accuracy and scientific nature of metabolic response modeling, providing a highly universal and interpretable computational framework for sports training, rehabilitation regulation, and energy management.
[0077] S4: Adjust the training load parameters based on the difference results and repeat the simulation calculation to generate a training simulation scheme.
[0078] Furthermore, the training simulation scheme is generated by comparing the metabolic rate change trends under different training load levels based on the metabolic response difference results, identifying the intervals in the target training plan where the metabolic demand and simulation response do not match, correcting the load intensity, duration, and interval period in the training load parameters based on the degree of metabolic deviation in the difference intervals, recalculating the metabolic response rate and energy consumption under the training load, generating a new metabolic response sequence, and iteratively optimizing the training load configuration by aligning the updated metabolic response sequence with the metabolic demand curve of the target training plan in the time domain and comparing it in the intensity domain until the difference between the metabolic response and the target demand is within a preset difference threshold range, and then outputting the training simulation scheme.
[0079] It should be noted that, based on the results of metabolic response differences, a comparative analysis of the metabolic rate change trends under different training load levels was conducted. By comparing the changing patterns of the metabolic response curves at each load level with the metabolic demand curves in the target training plan, mismatched intervals in the time or intensity domains were identified, determining the periods of metabolic response lag or lead. For the identified metabolic deviation areas, indicators of the degree of metabolic deviation within the difference intervals were extracted, and combined with the load intensity, duration, and interval period in the training load parameters, the metabolic response model in the training plan was corrected. The correction process included: adjusting the training load intensity coefficient and interval time ratio based on the correspondence between metabolic response rate and energy consumption; recalculating the corrected metabolic response rate and energy consumption; generating a new metabolic response sequence; and re-aligning the updated metabolic response sequence with the metabolic demand curve of the target training plan in the time domain and comparing them in the intensity domain. By comparing the deviation trends between metabolic response and metabolic demand, it was determined whether the adjusted simulation results met the target metabolic balance requirements. When the deviation between the metabolic response and the target demand is less than a preset difference threshold, the metabolic response model is considered to have reached convergence. The optimized training simulation scheme is then output, which can provide dynamic feedback for the training plan after the metabolic response and energy demand reach the matching condition. This achieves closed-loop consistency between the metabolic response curve and the target training demand curve, thereby generating a high-precision simulation scheme suitable for individualized training optimization.
[0080] A preferred approach for setting the difference threshold is between ±10% and ±15% of the standard deviation of the target metabolic demand. This threshold is determined based on the statistical results of the average deviation distribution between the metabolic response curve and the target metabolic demand curve in the training samples. The system first calculates the metabolic response deviation over multiple training cycles during the initial simulation phase, forming a metabolic deviation sequence. Then, it calculates the stable range of metabolic response fluctuations using the mean squared error, and extracts the standard deviation value based on this. When the absolute value of the metabolic response deviation over several consecutive cycles is less than 1.1... When the deviation exceeds 1.5, it is considered that the metabolic response is basically consistent with the target requirement; when the deviation exceeds 1.5... If this occurs, it indicates a significant metabolic mismatch, requiring adjustment of training load or periodic correction.
[0081] It should also be noted that by comparing metabolic response differences, the intervals where metabolic demand and actual response do not match in the time domain or intensity domain are identified, forming a set of difference intervals; and based on the three-dimensional characteristics of metabolic deviation, load intensity and energy consumption, the metabolic change patterns of different training stages are dynamically fitted to generate a feedback-enabled metabolic correction parameter matrix, which supports cross-cycle cumulative correction and can comprehensively consider the superposition effect of training duration and interval time, avoiding metabolic oscillations caused by a single correction.
[0082] Example 2, an embodiment of the present invention, provides a sports training simulation system based on metabolic capacity, including a metabolic feature acquisition module, a metabolic response calculation module, a metabolic response correlation analysis module, and a training simulation optimization module.
[0083] Among them, the metabolic feature acquisition module is used to collect the basic metabolic parameters and exercise physiological data of the training subjects, generate metabolic feature vectors, and provide basic data for metabolic modeling.
[0084] The metabolic response calculation module calculates the metabolic response rate, predicts energy consumption, and generates a metabolic response sequence based on metabolic feature vectors, training load parameters, and exercise time series.
[0085] The metabolic response correlation analysis module is used to perform time-domain and intensity-domain analysis on metabolic response sequences, and compare the differences between the metabolic requirements of the target training plan and the metabolic response output by the simulation.
[0086] The training simulation optimization module is used to adjust the training load parameters based on the difference results and repeat the simulation calculation to generate an optimized training simulation scheme.
[0087] This embodiment also provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements a personnel positioning safety management visualization analysis system as proposed in the above embodiment.
[0088] This embodiment also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements a personnel positioning safety management visualization analysis system as proposed in the above embodiment.
[0089] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0090] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.
[0091] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.
[0092] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.
[0093] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.
Claims
1. A method for metabolic capacity-based exercise training simulation, characterized by, The method comprises the following steps: Collecting basic metabolic parameters and exercise physiological data of the training object, and generating a metabolic feature vector; Based on the metabolic feature vector and combined with the training load parameter and the exercise time sequence, the metabolic response rate is calculated, the energy consumption is predicted, and the metabolic response sequence under different training load conditions is obtained; The metabolic response sequence is analyzed in the time domain and the intensity domain, and the difference between the metabolic demand of the target training plan and the metabolic response of the simulation output is compared; According to the difference result, the training load parameter is adjusted and the simulation operation is repeated to generate a training simulation scheme.
2. The metabolic capacity-based exercise training simulation method of claim 1, wherein: The collection of basic metabolic parameters and exercise physiological data of the training object includes collecting resting metabolic rate, maximum oxygen uptake, lactate threshold, heart rate variability, body surface temperature, respiratory rate and energy metabolism ratio of the training object, time synchronization and feature extraction of the parameters, generation of metabolic feature vector, and representation as: wherein, is a metabolic feature vector, is the i-th parameter in the metabolic feature vector, is the i-th parameter in the metabolic feature vector, 3. The metabolic capacity-based exercise training simulation method according to claim 1 or 2, characterized by: The calculation of metabolic response rate includes constructing exercise time sequence represented as: wherein is a motion time series, is the th time point; At any time The rate of the metabolic reaction is expressed as: in, This refers to the metabolic reaction rate. Based on basal metabolic constant, This represents the total number of metabolic characteristics. These are the weighting coefficients for metabolic features. For training load weighting coefficients, for The training load intensity function at time t, The weighting coefficient for the rate of change of training load. The weighting coefficient is the factor for the effect of time lag. In order to be in Historical training load values at any given time This is the attenuation coefficient.
4. The metabolic capacity-based exercise training simulation method of claim 3, wherein: The prediction of energy consumption includes calculating energy consumption rate, discretizing energy consumption rate, predicting energy consumption, and calculating energy consumption rate represented as: wherein, is an energy consumption rate, is an energy mapping constant, is a metabolic reaction mapping coefficient, is a training load mapping coefficient, is an energy mapping weight coefficient corresponding to the metabolic characteristic parameter; Discretizing energy consumption rate is represented as: wherein is the cumulative energy expenditure at the time point in the discrete time series as the energy expenditure prediction result, is the time interval between two adjacent sampling time points.
5. The metabolic capacity based exercise training simulation method according to any one of claims 1, 2, 4, characterized in that: The metabolic response sequence under different training load conditions includes mapping the energy consumption prediction result to the corresponding metabolic response rate under each training load level to obtain the weighted metabolic response represented as: in, To be at the training load level Next, time point The weighted metabolic response. This is the metabolic rate weighting coefficient. To be at the training load level The metabolic reaction rate under the condition, Energy consumption weighting coefficient, Training load level; The weighted metabolic response quantity is arranged in time sequence to form the metabolic response sequence under different training load conditions represented as: wherein, is the metabolic response sequence under training load levels .
6. The metabolic capacity based exercise training simulation method as claimed in claim 5, wherein: The correlation analysis of the metabolic response sequence in the time domain and the intensity domain includes time alignment of the metabolic demand curve of the target training plan and the metabolic response sequence under different training load levels, comparison of the metabolic rate change trend at each time and the deviation degree of the target metabolic demand, judgment of the matching degree of energy consumption and metabolic response in the training plan through analysis of the change law of metabolic response with time and the distribution characteristics under different training load intensities, and comprehensive analysis of the time domain deviation and the intensity domain difference to obtain the metabolic response difference result.
7. The metabolic capacity based exercise training simulation method according to any one of claims 1, 2, 4, 6, wherein: The generation of the training simulation scheme includes comparing the metabolic rate change trend under different training load levels according to the metabolic response difference result, identifying the interval where the metabolic demand and the simulation response in the target training plan do not match, correcting the load intensity, duration and interval period in the training load parameter based on the metabolic deviation degree of the difference interval, recalculating the metabolic response rate and energy consumption under the training load, generating a new metabolic response sequence, and time domain alignment and intensity domain comparison of the updated metabolic response sequence with the metabolic demand curve of the target training plan, iterative optimization of the training load configuration, until the difference between the metabolic response and the target demand is within the preset difference threshold, and outputting the training simulation scheme.
8. A metabolic capacity based athletic training simulation system employing the metabolic capacity based athletic training simulation method of any one of claims 1 to 7. The method comprises a metabolic feature acquisition module, a metabolic response calculation module, a metabolic response correlation analysis module, and a training simulation optimization module. The metabolic feature acquisition module is used to collect basic metabolic parameters and exercise physiological data of the training object, generate a metabolic feature vector, and provide basic data for metabolic modeling. The metabolic response calculation module calculates metabolic response rates, predicts energy consumption, and generates a metabolic response sequence based on the metabolic feature vector, the training load parameter, and the exercise time sequence; The metabolic response correlation analysis module is configured to analyze the metabolic response sequence in the time domain and the intensity domain, and compare the metabolic demand of the target training plan with the metabolic response difference of the simulation output; The training simulation optimization module is configured to adjust the training load parameter according to the difference result and repeat the simulation operation to generate an optimized training simulation scheme. 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-8 when the computer program is executed by the processor. The processor executes the computer program to implement the steps of the method for simulating exercise training based on metabolic capacity according to any one of claims 1 to 7.
10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method for simulating exercise training based on metabolic capacity according to any one of claims 1 to 7.