Fat-reducing training standard degree identification method under limb training course

Abstract

The invention discloses a fat-reducing training standard degree identification method under a limb training course, and relates to the technical field of fitness training, and the method comprises the following steps: an action template establishment step: aiming at fat-reducing training actions, constructing a multi-level standard action template system; according to the method, the standard action template containing multi-aspect characteristic parameters is established, real-time acquisition and characteristic extraction are performed on the user actions, and multi-dimensional comparative analysis is performed on the user action characteristics and the standard template, so that the comprehensive score of the action standard degree can be accurately calculated, and the accurate judgment on the user action standard degree is realized; the problem of inaccurate identification in the prior art is solved; and an individual difference adaptation step is set, and a standard action template is dynamically adjusted according to the basic body information of the user and the action standard degree condition in the training historical data, so that standard degree identification better fits the body conditions of different users, the applicability and accuracy of the identification method are improved, and identification deviation caused by a unified standard is avoided.

Description

Technical Field

[0001] This invention relates to the field of fitness training technology, and in particular to a method for identifying the standard of fat loss training in a body training course. Background Technology

[0002] In today's society, with the increasing awareness of health, weight loss training has become an important part of many people's lives. As a crucial method of weight loss training, the accuracy of the correct movements in physical training courses directly affects the effectiveness and safety of weight loss.

[0003] Currently, during fat loss training in bodyweight exercises, users often struggle to accurately judge whether their movements are performed correctly. Traditional methods rely primarily on in-person coaching, but this approach is limited by time, space, and cost, failing to meet the needs of a large user base. While some existing fitness apps provide demonstrations, they lack accurate recognition and judgment of users' real-time movements, potentially leading to users failing to achieve their desired fat loss results due to incorrect form, and even causing sports injuries.

[0004] Furthermore, different users have different physical conditions and exercise levels, so the required standard of the same limb training movements should also vary. Most existing identification methods use a uniform standard, failing to consider individual differences, which affects the accuracy and applicability of the identification results. At the same time, after identifying non-standard movements, there is a lack of effective feedback and corrective suggestions, making it difficult for users to make targeted improvements, thus affecting the quality of their fat loss training.

[0005] Therefore, there is an urgent need for a method that can accurately identify the standard of movement in fat loss training courses in real time, take into account individual differences, and provide effective feedback to improve the effectiveness and safety of fat loss training and meet the personalized needs of users. Summary of the Invention

[0006] The purpose of this invention is to address the problem that existing fitness applications, while providing movement demonstrations, lack accurate recognition and standardization judgment of users' real-time movements, and to propose a standardization recognition method for fat loss training in limb training courses.

[0007] To achieve the above objectives, the present invention employs the following technology: a method for identifying the standard of fat loss training in a body training course, comprising the following steps:

[0008] Steps for establishing exercise templates: For fat loss training exercises, a multi-level standard exercise template system is constructed. This system introduces an exercise breathing coordination model and a biomechanical energy efficiency model to create corresponding templates for users with different exercise levels. The templates are also updated regularly with reference to the exercise energy efficiency evaluation reports of exercise biomechanics experts.

[0009] User motion data collection steps: When users are training, multiple devices are used to collect motion data in collaboration, including capturing the user's attention EEG signals during movement through an EEG sensor, collecting joint movement trajectories through a depth camera using dynamic region focusing technology, and allocating data weights by combining attention scores during data preprocessing.

[0010] Action feature extraction steps: Multi-dimensional feature extraction is performed on the preprocessed data, including action inertia moment features and metabolic response features, and key feature parameters are selected with the help of the ReliefF algorithm;

[0011] Standardized comparison analysis steps: Construct a dynamic bias propagation network to compare feature parameters, introduce muscle fatigue tolerance comparison when analyzing muscle activity patterns, and generate comprehensive scores and visual comparison charts;

[0012] Standardization judgment and feedback steps: Set three-level standardization judgment criteria, provide feedback in combination with user training goals, generate a correction plan including alternative action recommendations when the score is unqualified, and the feedback interface has an entry point for action feeling feedback.

[0013] Individualized adaptation steps: Determine safe movement range for users who have had leg injuries, and break down movements to strengthen muscle memory for users with weak muscle strength;

[0014] Real-time adaptive adjustment steps: When a user performs multiple non-standard actions in a row, the system combines sensor data to determine the type of problem and pushes corresponding training. As the user improves, the system adjusts the standards to match their ability.

[0015] Furthermore, in the action template establishment step, the basic layer combines the relationship between breathing rhythm and energy consumption of the action to clarify the optimal force point of the action under different breathing depths, and the advanced layer incorporates the energy loss coefficient of the body's center of gravity during the action and the optimal energy efficiency range when users of different body types complete the action.

[0016] Furthermore, in the user action acquisition step, when the user is distracted, the system automatically marks the action data of that period as data to be verified; the depth camera focuses on capturing the joint movement trajectory that has a great impact on the accuracy of the action, and reduces the acquisition accuracy of areas that have little impact on the accuracy of the action; the smartwatch terminal assigns higher weight to data during periods of high concentration.

[0017] Furthermore, in the motion feature extraction step, the motion inertia moment feature reflects the relationship between the magnitude of inertia and motion coordination when various parts of the body rotate, and the metabolic response feature determines whether the motion intensity is within the optimal fat-burning metabolic range by analyzing the user's real-time blood oxygen saturation changes. The ReliefF algorithm takes into account the synergistic relationship between the metabolic response feature and the motion inertia moment feature.

[0018] Furthermore, in the standard degree comparison analysis step, each step of the action is regarded as a network node. The probability of deviation transmission is calculated by analyzing the correlation between nodes, and the visualization comparison chart is displayed in the form of a deviation heatmap to show the deviation distribution and influence intensity.

[0019] Furthermore, in the step of establishing the action template, for the burpee action, the difficulty coefficient is divided into movement cognitive style adaptation, the action beat delay prompt is added for impulsive users, and the rhythm acceleration guidance is added for contemplative users. The system recommends template upgrades based on the matching degree between cognitive style and action data.

[0020] Furthermore, in the user action acquisition step, the edge computing of the smart bracelet adds correlation analysis between action and environmental sound effects, and collects environmental sound effects through the built-in microphone. When noise causes data deviation, the error correction algorithm is automatically activated to correct abnormal data.

[0021] Furthermore, in the standard degree comparison analysis step, for the deadlift action, the deviation transmission analysis introduces the action chain elastic potential energy analysis, and the deviation weight is increased when the user's action elastic potential energy utilization efficiency is low.

[0022] Furthermore, the standardization judgment and feedback steps incorporate a gamified incentive mechanism that is linked to user health data. Users receive virtual badges when their action standardization is high, and badge levels can be increased when health data meets standards. Accumulated badges can be redeemed for relevant discount coupons.

[0023] Furthermore, in the individual difference adaptation step, the standard optimization introduces exercise gene marker analysis, and adjusts the movement standards in combination with the user's exercise gene detection data. If the proportion of fast-twitch muscle fibers is high, the movement speed requirement is increased, and if the proportion of slow-twitch muscle fibers is high, the movement endurance requirement is increased.

[0024] In summary, due to the adoption of the above-mentioned technology in the method for recognizing the standard of fat loss training in a limb training course, the beneficial effects of this invention are:

[0025] 1. By establishing a standard action template containing multiple feature parameters and collecting and extracting user actions in real time, the user action features are compared and analyzed with the standard template in multiple dimensions. This enables accurate calculation of the comprehensive score of action standard, achieving accurate judgment of the standardity of user actions and solving the problem of inaccurate recognition in existing technologies.

[0026] 2. Set up individual difference adaptation steps. Based on the user's basic physical information and the standardization of movements in the training history data, the standard movement template is dynamically adjusted to make the standardization recognition more suitable for the physical conditions of different users, improve the applicability and accuracy of the recognition method, and avoid recognition deviation caused by uniform standards.

[0027] 3. When the user determines that the movement is not standard, the system can generate specific correction suggestions and provide timely feedback to the user. This allows the user to understand the problems with their movements and make targeted adjustments, which helps improve the standard of the user's movements, thereby enhancing the fat loss training effect and reducing the risk of sports injuries.

[0028] 4. When establishing standard movement templates, the principles of fat burning and energy supply in fat loss training and energy consumption data of movements under standard conditions are combined, so that the identified standard movements are not only in good form, but also ensure the best fat burning efficiency, further improving the scientificity and effectiveness of fat loss training.

[0029] 5. By analyzing the trend of movement accuracy, users can understand the changes in their movement accuracy and its correlation with fat loss, providing more comprehensive training improvement suggestions, promoting continuous optimization of training movements, and improving overall training quality. Attached Figure Description

[0030] Figure 1 A flowchart of the method of the present invention is shown. Detailed Implementation

[0031] The following will describe, with reference to the accompanying drawings of the embodiments of the present invention, a method for identifying the standard of fat loss training under a limb training course. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0032] To more clearly and intuitively demonstrate the practical application effects and advantages of the present invention in recognizing the standard of fat loss training under a physical training course, and to verify its feasibility and effectiveness, the present invention will be further described below with reference to embodiments. Through specific scenario simulations and data calculations, the method is explained in detail how it plays a role in recognizing the standard of fat loss training under a real physical training course, helping readers to better understand the technical details and practical value of the invention. The present invention will be further described below with reference to embodiments;

[0033] See Figure 1 The present invention provides a method for identifying the standard of fat loss training in a body training course; it includes the following steps:

[0034] Action Template Creation Steps

[0035] For high knees, a fat-burning exercise, a multi-level standard movement template system was constructed, incorporating a movement-breath coordination model and a biomechanical energy efficiency model. The basic level, building upon existing techniques, combines the relationship between breathing rhythm and energy expenditure to identify the optimal point of force application at different breathing depths. For example, when inhaling to maximum chest expansion, the lungs are full of air, the body's center of gravity is relatively stable, and the initial point of force application when lifting the leg is at the groin, facilitating a smoother transfer of power from the waist to the legs and reducing energy loss. The advanced level incorporates the energy loss coefficient of the body's center of gravity during the movement. In standard movements, a smaller vertical fluctuation in the center of gravity results in less energy expenditure. The optimal energy efficiency range also differs for different body types; heavier users achieve better efficiency with a slightly lower center of gravity, while lighter users achieve better efficiency with a moderately positioned center of gravity. Different templates are created for fitness beginners and experienced enthusiasts. The beginner template focuses on the basic energy efficiency of movements, requiring only basic correct form to avoid unnecessary energy waste. The experienced enthusiast template emphasizes advanced energy efficiency improvements, further reducing energy loss through more precise force control. When updating templates, evaluation reports on movement energy efficiency from sports biomechanics experts are collected. If an expert points out that a certain force application method can improve energy utilization, the relevant parameters of that force application method are updated into the template.

[0036] By introducing a motion-breath coordination model and a biomechanical energy efficiency model, a multi-level standard motion template has been constructed that can accurately adapt to users of different groups and fitness levels. The design, which links breathing rhythm with energy expenditure, makes motion exertion more scientific and reduces energy loss. The differentiated templates for different body types and fitness levels ensure proper form for beginners while meeting the advanced needs of experienced users. Furthermore, continuous optimization through expert evaluation ensures the templates remain professional and practical, providing a reliable reference for subsequent standardization identification.

[0037] User movements are collected. During jumping jack training, in addition to multi-device collaborative data acquisition, bioelectrical signals are correlated with movement. A newly added EEG sensor, worn on the user's head, captures EEG signals indicating the user's focus during movement. When the user is distracted by external interference, the signal fluctuates significantly, and the system automatically marks the movement data for that period as data to be verified. Simultaneously, the depth camera uses dynamic region focusing technology, focusing on clearly capturing the movement trajectories of the knee and hip joints during jumping jacks. For areas with less impact on movement accuracy, such as subtle arm swings, the acquisition precision is appropriately reduced to minimize data redundancy in non-critical areas. During data preprocessing, the smartwatch terminal combines the focus score of the EEG signals. When the user's focus is high, such as fully concentrating on following instructions, the data weight for that period is increased; when the focus is low, the weight of data from distracted states is reduced, ensuring more reliable subsequent analysis.

[0038] Multi-device collaborative data acquisition, combined with bioelectrical signal and motion correlation acquisition technology, significantly improves data reliability. EEG sensors capture attention signals and label data to be verified, dynamic region focusing technology reduces non-critical data redundancy, and smartwatches assign data weights based on attention levels, effectively filtering out interference information. This ensures that the preprocessed dataset more closely reflects the actual training state, laying a high-quality data foundation for feature extraction and standardization analysis.

[0039] User motion feature extraction: When extracting features from preprocessed data of mountain climbing running motion, new features of motion inertia moment and metabolic response feature are added. Moment of inertia moment reflects the relationship between the magnitude of inertia during body rotation and motion coordination. For example, if the moment of inertia changes steadily during leg swing, it indicates coordinated leg rotation and smooth movement; if the moment of inertia fluctuates greatly, it indicates irregular leg swing and poor motion coordination. Metabolic response feature analyzes the user's real-time blood oxygen saturation changes during the movement using a pulse oximeter worn on the finger. When blood oxygen saturation fluctuates slightly within a reasonable range, it indicates that the exercise intensity is within the optimal fat-burning metabolic range; if blood oxygen saturation drops excessively, it indicates that the exercise intensity is too high and exceeds the optimal fat-burning range. When the ReliefF algorithm selects features, the synergistic relationship between metabolic response feature and motion inertia moment feature is taken into consideration. For example, when the motion inertia moment is stable and blood oxygen saturation is within the optimal range, the synergistic effect of these two features has a significant impact on fat-burning effect and movement accuracy, and will be selected as a core feature.

[0040] The system adds motion inertia moment features and metabolic response features, enabling multi-dimensional and in-depth analysis of movements. Motion inertia features directly reflect movement coordination, while metabolic response features determine whether the movement intensity is within the optimal fat-burning range. The combined analysis of these two features with the ReliefF algorithm filters core features and eliminates irrelevant information, making subsequent standardization identification more focused on key factors and improving identification accuracy.

[0041] A comparative analysis of movement standardization was conducted. Taking the push-up exercise as an example, a dynamic deviation propagation network was constructed. Movement elements such as hand placement, shoulder angle, and body straightness were considered as network nodes. By analyzing the correlation between nodes, the probability of deviation propagation was calculated. For example, a deviation in shoulder position could lead to a chain reaction of deviations at multiple nodes, such as improper chest muscle activation and arm angle deviation. Therefore, the shoulder position node has the highest weight in the network. When analyzing muscle activity patterns, a comparison of muscle fatigue tolerance was introduced. In the standard template, the chest muscle fatigue tolerance time was 15 consecutive standard push-ups. If the user's chest muscle activity significantly decreased during the 10th push-up, it indicated that the movement did not complete the standard trajectory before muscle fatigue. The visualization comparison chart used a deviation heatmap, with different colors representing the degree of deviation: red for large deviation and blue for small deviation, visually demonstrating the distribution and intensity of deviation at each stage of the movement.

[0042] The combination of dynamic deviation propagation network and muscle fatigue tolerance analysis enables a more comprehensive standardization assessment. Through network node correlation analysis, key deviation points with a wide impact can be accurately located. Muscle fatigue tolerance comparison can determine whether the movement was completed under effective conditions. Combined with the visualization of deviation heatmaps, both users and the system can clearly understand the problems in the movement, providing a clear basis for subsequent feedback.

[0043] When setting the three-level standard for judgment, feedback related to training goals is added. If the user's goal is rapid fat loss and they reach the excellent level, the feedback will say, "Your movement rhythm is very good. Maintaining this state will further improve fat-burning efficiency." If the user's goal is body shaping and they reach the qualified level, the feedback will emphasize, "Pay attention to the details of chest muscle engagement; this will make the chest muscle lines more defined." The correction plan for the unqualified level includes "alternative exercise recommendations." For example, if a user cannot complete a standard push-up, kneeling push-ups are recommended as a transition. A plan will be created, starting with 10 kneeling push-ups daily for a week, gradually increasing the difficulty to transition to standard push-ups. The feedback interface has a "movement feeling feedback entry." After completing the exercise, the user can enter "lower back pain" in this entry. The system will then focus on the key points of the lower back-related movements and provide adjustment suggestions in the next feedback.

[0044] By incorporating personalized feedback mechanisms based on training goals, the guidance becomes more targeted. Differentiated feedback for fat loss or body shaping goals guides users to work towards their desired training results; alternative exercises and step-by-step plans for unsatisfactory results lower the training threshold for users; and user feedback on movement sensations makes the system suggestions more realistic, improving user acceptance of movement adjustments and execution effectiveness.

[0045] The system adapts to individual user differences. For example, User C, who had a leg injury, was fitted with 3D biomechanical simulation during lunge training. First, a 3D biomechanical model of the user's leg was constructed by scanning, simulating the force distribution at different joint angles. When a certain joint angle was found to minimize stress on the injured area while still ensuring training effectiveness, this angle range was defined as the safe movement range, with the start and end angles clearly defined in the template. For User D, who had weaker muscles, the template incorporated muscle memory enhancement features, breaking down the lunge into muscle memory units such as leg extension, squatting, and returning to the starting position. Each unit had its own standard. After the user accurately completed the leg extension movement three times consecutively, the squatting movement training was unlocked, gradually building muscle memory for the complete movement.

[0046] The application of 3D biomechanical simulation, muscle memory enhancement, and sports gene analysis enables highly personalized standard adaptation. Safe movement ranges are determined for injured users, ensuring training effectiveness while preventing secondary injuries; movements are broken down for users with weak strength, gradually building muscle memory and reducing learning difficulty; and movement requirements are adjusted based on genetic characteristics, making the standard more closely match the user's physiological traits, significantly improving training adaptability and safety.

[0047] The system provides real-time adaptive adjustments to the user. When a user repeatedly performs pull-ups with incorrect shoulder posture, the system initiates neural and muscle linkage training to adjust the posture. Combining data from electromyography (EMG) and electroencephalography (EEG) sensors, if the EMG signal indicates that the muscles are capable of performing the standard movement, but the EEG signal indicates that the neural command transmission is not timely, it is determined to be a neural command transmission problem. A mind-motor synchronization training mini-game is then pushed, allowing the user to first visualize the correct pull-up shoulder posture in their mind, and then follow the prompts to perform the movement, strengthening the neural and muscle connection. If the EMG signal indicates insufficient muscle strength, it is determined to be a muscle control problem, and targeted muscle control training is pushed, such as shoulder external rotation exercises using light dumbbells. As the user's movement improves and their shoulder posture meets the requirements multiple times, the system not only restores the standard posture but also adjusts the pace of the movement according to the user's neural and muscle reaction speed. For example, if the user reacts quickly, the pace of the movement is appropriately increased to match the user's neural response ability.

[0048] The neural and muscular linkage training adjustment mechanism dynamically adapts to the user's training status. It pushes targeted training for neural or muscular problems, accurately addressing the root cause of non-standard movements; it gradually adjusts the standards according to the user's progress, giving the user room to adapt while continuously promoting the improvement of movement quality, achieving a steady increase in training effect, and at the same time enhancing the user's motivation and persistence in training.

[0049] In this embodiment: During the action template creation step, the difficulty level of the burpee action is categorized with a motor cognitive style. For impulsive cognitive style users, who tend to perform actions quickly but are prone to errors, the basic template includes a tempo delay prompt, such as a slightly slower metronome rhythm, to guide the user to follow the slower beat and slow down their movement speed. For contemplative cognitive style users, whose movements are slow but precise, the basic template includes a tempo acceleration guide, using a gradually increasing music tempo to improve their movement fluency. When the system recommends an upgrade, it analyzes the matching degree between the user's cognitive style test results and action data. If impulsive users experience a lower error rate and can consistently complete the action under the slow-tempo template, an upgrade suggestion for an intermediate template is pushed.

[0050] In this embodiment: During the user motion acquisition step, the edge computing of the smart bracelet adds a correlation analysis between motion and environmental sound effects. The smart bracelet's built-in microphone collects the sound effects of the training environment. When there are loud noises of equipment colliding in the gym or howling wind outdoors, the correlation between these sound effects (decibels) and motion data errors is analyzed. When the noise exceeds a certain level, causing deviations in the collected motion data, a data error correction algorithm is automatically activated to correct abnormal motion data caused by noise interference, reducing the interference of environmental noise on the acquisition device.

[0051] In this embodiment, the deviation transmission analysis model for the deadlift movement incorporates kinetic chain elastic potential energy analysis in the standard deviation comparison analysis step. During the deadlift, muscles and tendons store and release elastic potential energy like springs. This storage and release of elastic potential energy follows a certain pattern in the standard template. By comparing the user's utilization of elastic potential energy with the standard template, if the user's elastic potential energy utilization efficiency is low, such as due to incorrect timing of force application leading to energy waste, the deviation weight of this movement is increased. This guides the user to adjust the timing of force application, utilize elastic potential energy to improve movement efficiency, and reduce energy waste.

[0052] In this embodiment, the standardization judgment and feedback steps combine gamified incentive mechanisms with health data-linked rewards. Users receive virtual badges when their actions are highly standardized. Furthermore, if users reach their daily step goals and get sufficient sleep, their badge level increases. Accumulating a certain number of badges allows users to redeem health checkup discount coupons, which can be used at designated medical institutions to enjoy discounts, or to redeem sports equipment coupons to deduct costs when purchasing sportswear and equipment, thus enhancing users' health management awareness.

[0053] In this embodiment, during the individual difference adaptation step, the standard optimization incorporates exercise gene marker analysis. After the user provides exercise gene testing data, if the data shows a high proportion of fast-twitch muscle fibers, it indicates that the user has good explosive power, and the speed requirement in the template should be appropriately increased, such as slightly faster leg raises. If the data shows a high proportion of slow-twitch muscle fibers, it indicates that the user has good endurance, and the endurance requirement in the template should be appropriately increased, such as slightly longer continuous high knee raises, so that the personalized standard better matches the user's genetic characteristics.

[0054] Working principle and usage process of this invention:

[0055] This method first constructs a multi-level template integrating a movement-breath coordination model and a biomechanical energy efficiency model for movements such as high knees. This template is then optimized through expert evaluation to provide standard references for different groups. During user training, data is collected collaboratively by multiple devices, including EEG sensors and depth cameras. The cameras dynamically focus on key joints, and a smartwatch assigns data weights based on attention scores. After preprocessing, a standardized dataset is formed. Next, features such as moment of inertia and metabolic response are extracted from movement data, such as mountain climbing. The ReliefF algorithm is used to filter core features. Taking push-ups as an example, a dynamic bias propagation network compares the user's movements with the template, combined with muscle fatigue tolerance analysis, to generate scores and bias heatmaps. Based on the scores and training goal feedback, alternative movements are recommended when performance is unsatisfactory. Users can provide feedback on their experiences for system optimization suggestions. Simultaneously, 3D biomechanical simulation is used to determine safe movement ranges for injured users, and movements are broken down to strengthen muscle memory for users with weak strength. Standards are adjusted based on exercise gene analysis. The system can also monitor movements such as pull-ups in real time, pushing training based on neurological or muscular problems, dynamically adjusting standards to match user progress, achieving accurate identification, personalized guidance, and intelligent adjustment.

[0056] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the present invention's method for identifying the standard of fat reduction training in a limb training course and its inventive concept, should be covered within the scope of protection of the present invention.

Claims

1. A method for identifying the standard of fat loss training under a physical training course, characterized in that, Includes the following steps: Steps for establishing exercise templates: For fat loss training exercises, a multi-level standard exercise template system is constructed. This system introduces an exercise breathing coordination model and a biomechanical energy efficiency model to create corresponding templates for users with different exercise levels. The templates are also updated regularly with reference to the exercise energy efficiency evaluation reports of exercise biomechanics experts. User motion data collection steps: When users are training, multiple devices are used to collect motion data in collaboration, including capturing the user's attention EEG signals during movement through an EEG sensor, collecting joint movement trajectories through a depth camera using dynamic region focusing technology, and allocating data weights by combining attention scores during data preprocessing. Action feature extraction steps: Multi-dimensional feature extraction is performed on the preprocessed data, including action inertia moment features and metabolic response features, and key feature parameters are selected with the help of the ReliefF algorithm; Standardized comparison analysis steps: Construct a dynamic bias propagation network to compare feature parameters, introduce muscle fatigue tolerance comparison when analyzing muscle activity patterns, and generate comprehensive scores and visual comparison charts; Standardization judgment and feedback steps: Set three-level standardization judgment criteria, provide feedback in combination with user training goals, generate a correction plan including alternative action recommendations when the score is unqualified, and the feedback interface has an entry point for action feeling feedback. Individualized adaptation steps: Determine the safe range of motion for users who have had leg injuries, and break down the movements to strengthen muscle memory for users with weak muscle strength; Real-time adaptive adjustment steps: When a user performs multiple non-standard actions in a row, the system combines sensor data to determine the type of problem and pushes corresponding training. As the user improves, the system adjusts the standards to match their ability.

2. The method for identifying the standard of fat loss training under a body training course according to claim 1, characterized in that, In the action template creation step, the basic layer combines the relationship between breathing rhythm and energy consumption of the action to clarify the optimal force point of the action under different breathing depths, and the advanced layer incorporates the energy loss coefficient of the body's center of gravity during the action and the optimal energy efficiency range when users of different body types complete the action.

3. The method for identifying the standard of fat loss training under a body training course according to claim 1, characterized in that, In the user action acquisition step, when the user is distracted, the system automatically marks the action data of that period as data to be verified; the depth camera focuses on capturing the joint movement trajectory that has a great impact on the accuracy of the action, and reduces the acquisition accuracy of areas that have little impact on the accuracy of the action. Smartwatches assign higher weight to data collected during periods of high user engagement.

4. The method for identifying the standard of fat loss training under a body training course according to claim 1, characterized in that, In the motion feature extraction step, the motion inertia moment feature reflects the relationship between the magnitude of inertia and motion coordination when various parts of the body rotate. The metabolic response feature determines whether the motion intensity is within the optimal fat-burning metabolic range by analyzing the user's real-time blood oxygen saturation changes. The ReliefF algorithm takes into account the synergistic relationship between the metabolic response feature and the motion inertia moment feature.

5. The method for identifying the standard of fat loss training under a body training course according to claim 1, characterized in that, In the standard degree comparison analysis step, each step of the action is regarded as a network node. The probability of deviation transmission is calculated by analyzing the correlation between nodes. The visualization comparison chart uses a deviation heatmap to show the deviation distribution and influence intensity.

6. The method for identifying the standard of fat loss training under a body training course according to claim 1, characterized in that, In the step of establishing the action template, for the burpee, the difficulty coefficient is divided into movement cognitive style adaptation, the action beat delay prompt is added for impulsive users, and the rhythm acceleration guidance is added for thoughtful users. The system recommends template upgrades based on the matching degree between cognitive style and action data.

7. The method for identifying the standard of fat loss training under a body training course according to claim 1, characterized in that, In the user action acquisition step, the edge computing of the smart bracelet adds correlation analysis between action and environmental sound effects. It collects environmental sound effects through the built-in microphone, and automatically starts the error correction algorithm to correct abnormal data when noise causes data deviation.

8. The method for identifying the standard of fat loss training under a body training course according to claim 1, characterized in that, In the standard degree comparison analysis step, for the deadlift action, the deviation transmission analysis introduces the action chain elastic potential energy analysis, and the deviation weight is increased when the user's action elastic potential energy utilization efficiency is low.

9. The method for identifying the standard of fat loss training under a body training course according to claim 1, characterized in that, The standardization judgment and feedback steps incorporate a gamified incentive mechanism that is linked to user health data. Users receive virtual badges when their action standardization is high, and badge levels can be increased as health data meets standards. Accumulated badges can be redeemed for relevant discount coupons.

10. The method for identifying the standard of fat loss training under a body training course according to claim 1, characterized in that, In the individual difference adaptation step, the standard optimization introduces exercise gene marker analysis and adjusts the movement standards in combination with the user's exercise gene detection data. If the proportion of fast-twitch muscle fibers is high, the movement speed requirement is increased, and if the proportion of slow-twitch muscle fibers is high, the movement endurance requirement is increased.

Images