Exercise prescription generation device, method, equipment and medium

Abstract

This application discloses an exercise prescription generation device, method, equipment, and medium, relating to the field of sports health management technology and applied to computer devices. It includes: a feature extraction module that simultaneously collects body composition and muscle strength data from obese subjects, and obtains body composition and muscle strength features through preprocessing and feature extraction; a preliminary generation module that performs hierarchical judgment on the two types of features to determine the obesity type and muscle strength level, and generates a preliminary exercise prescription based on the combination results; a prescription generation module that uses the body-muscle combination index to determine aerobic exercise parameters and determines resistance training parameters based on the muscle strength level, generating a target exercise prescription for the current execution cycle; an exercise review module that obtains the review results after the subject executes the prescription; and a prescription adjustment module that adjusts the prescription based on the review results to obtain the target exercise prescription for the next execution cycle. This effectively solves the problems of single-dimensional exercise prescription assessment, insufficient personalization, inaccurate intensity matching, and lack of quantitative decision-making and dynamic adjustment.

Description

Technical Field

[0001] This invention relates to the field of sports health management technology, and in particular to a device, method, equipment and medium for generating exercise prescriptions. Background Technology

[0002] Obesity has become a major public health problem, and exercise intervention is the core means of health management for obese populations. Existing exercise prescription technologies mostly rely on single or partial indicators such as BMI (Body Mass Index), weight, and heart rate for assessment. These technologies suffer from several drawbacks, including fragmented and singular assessment dimensions, low personalization, heavy reliance on human experience in prescription formulation, lack of quantitative decision-making models driven by body composition and muscle strength data, disconnect between the assessment and prescription formulation stages, and static exercise programs lacking automatic adjustment mechanisms based on dynamic changes in body condition. Consequently, these technologies cannot accurately identify specific phenotypes in obese individuals, and it is difficult to precisely match exercise type, intensity, and load according to individual differences in body composition and muscle strength. This often leads to problems such as mismatch between exercise programs and actual exercise capabilities, insufficient exercise safety, poor intervention effects, low standardization and repeatability, and limitations in clinical translation and large-scale application.

[0003] In summary, addressing the challenges of a single-dimensional assessment method, insufficient personalization, inaccurate intensity matching, and lack of quantitative decision-making and dynamic adjustment in exercise prescriptions for obese individuals remains an important issue in this field. Summary of the Invention

[0004] In view of this, the purpose of this invention is to provide an exercise prescription generation device, method, equipment, and medium to address the problems of single-dimensional assessment, insufficient personalization, inaccurate intensity matching, and lack of quantitative decision-making and dynamic adjustment in exercise prescriptions for obese individuals. The specific solution is as follows: In a first aspect, this application discloses an exercise prescription generation device, comprising: applied to a computer device, including: The feature extraction module is used to simultaneously collect body composition data and muscle strength data of obese subjects, and to preprocess and extract features from the body composition data and muscle strength data to obtain body composition features and muscle strength features. A preliminary generation module is used to hierarchically determine the body composition characteristics and muscle strength characteristics to identify the obesity type and muscle strength level of the obese subject, and generate a preliminary exercise prescription based on the combination of the obesity type and muscle strength level; wherein, the preliminary exercise prescription includes exercise type and exercise ratio; The prescription generation module is used to determine the aerobic exercise type parameter in the preliminary exercise prescription by using the body muscle joint index obtained by weighted fusion of the body composition features and the muscle strength features, and to determine the resistance training type parameter in the preliminary exercise prescription according to the muscle strength level, so as to generate the target exercise prescription for the current execution cycle based on the aerobic exercise type parameter and the resistance training type parameter. The exercise reassessment module is used to obtain the reassessment results generated when the obese subject performs the target exercise prescription; The prescription adjustment module is used to adjust the target exercise prescription based on the review results to obtain the target exercise prescription for the next execution cycle.

[0005] Optionally, the feature extraction module includes: The first receiving unit is used to receive raw body composition data of obese subjects collected by a bioelectrical impedance analyzer; wherein, the raw body composition data includes body fat percentage, total muscle mass, limb muscle mass, visceral fat area and waist-to-hip ratio. The second receiving unit is used to synchronously receive the raw muscle strength data of obese subjects collected by the hand grip strength meter / isokinetic muscle strength testing system; wherein, the raw muscle strength data includes upper limb muscle strength, lower limb muscle strength and core muscle strength; The preprocessing unit is used to preprocess the original body composition data and the original muscle strength data to obtain target body composition data and target muscle strength data; wherein, the preprocessing includes integrity check, logical verification, outlier removal and standardization processing; The feature extraction unit is used to extract features from the target body composition data and the target muscle strength data to obtain body composition features and muscle strength features; wherein, the body composition features include body fat percentage level, muscle mass index, visceral fat level, body muscle ratio and sarcopenia index, and the muscle strength features include grip strength index, lower limb muscle strength index, core stability index and muscle balance index.

[0006] Optionally, the exercise prescription generation device further includes: The weighting determination unit is used to determine the negative weight of the body fat percentage level in the body composition feature, the positive weight of the muscle mass index in the body composition feature, and the positive weight of the grip strength index in the muscle strength feature. The weighted fusion unit is used to weight and fuse the body fat percentage level, the muscle mass index, and the grip strength index to obtain the body-muscle combined index.

[0007] Optionally, the preliminary generation module includes: The first judgment unit is used to determine whether the muscle mass index is less than a first preset muscle mass threshold if the body fat percentage level is greater than a preset level. The first obesity determination unit is used to determine the obesity type of the obese subject as a preset simple obesity type if the muscle mass index is not less than the first preset muscle mass threshold. The second judgment unit is used to determine whether the grip strength index is less than the preset grip strength threshold if the muscle mass index is less than the first preset muscle mass threshold. The second obesity determination unit is used to determine the obesity type of the obese subject as a preset sarcopenic obesity type if the grip strength index is less than a preset grip strength threshold. The third obesity determination unit is used to determine that the obesity type of the obese subject is a preset hidden obesity type if the grip strength index is not less than a preset grip strength threshold.

[0008] Optionally, the preliminary generation module includes: The first muscle strength determination unit is used to determine the muscle strength level of the obese subject as a preset good muscle strength type if the muscle mass index is not less than the first preset muscle mass threshold. The second muscle strength determination unit is used to determine the muscle strength level of the obese subject as a preset normal muscle strength type if the muscle mass index is less than the first preset muscle mass threshold and not less than the second preset muscle mass threshold. The third muscle strength determination unit is used to determine the muscle strength level of the obese subject as a preset low muscle strength type if the muscle mass index is less than the second preset muscle mass threshold.

[0009] Optionally, the exercise type includes aerobic exercise and resistance training; the prescription generation module includes: An assessment unit is used to obtain a multi-dimensional exercise risk assessment of the obese subject to obtain assessment results; The aerobic exercise parameter determination unit is used to determine the upper and lower limits of target heart rate in the aerobic exercise type parameters based on the evaluation results, and to determine the intensity percentage in the aerobic exercise type parameters using the body-muscle joint index obtained by weighted fusion of the body composition characteristics and the muscle strength characteristics. The resistance training parameter determination unit is used to determine the resistance training type parameters in the preliminary exercise prescription based on the evaluation results and the muscle strength level.

[0010] Optionally, the exercise prescription generation device further includes: The visualization unit is used to visualize the target exercise prescription to generate one or more visualization results, such as body composition radar chart, muscle strength comparison chart, exercise intensity curve, and advanced route chart. The video generation unit is used to generate a guidance video corresponding to the target exercise prescription; wherein the guidance video includes a warm-up exercise video, a main training exercise video, and a cool-down exercise video.

[0011] Secondly, this application discloses a method for generating exercise prescriptions, applied to a computer device, comprising: Body composition data and muscle strength data of obese subjects were collected simultaneously. The body composition data and muscle strength data were preprocessed and feature extracted to obtain body composition features and muscle strength features. The body composition characteristics and muscle strength characteristics are hierarchically determined to identify the obesity type and muscle strength level of the obese subject, and a preliminary exercise prescription is generated based on the combination of the obesity type and the muscle strength level; wherein, the preliminary exercise prescription includes exercise type and exercise ratio; The aerobic exercise type parameter in the preliminary exercise prescription is determined by using the weighted fusion of the body composition features and the muscle strength features to obtain the body-muscle joint index, and the resistance training type parameter in the preliminary exercise prescription is determined according to the muscle strength level, so as to generate the target exercise prescription for the current execution cycle based on the aerobic exercise type parameter and the resistance training type parameter; Obtain the reassessment results generated when the obese subject performs the target exercise prescription; The target exercise prescription is adjusted based on the review results to obtain the target exercise prescription for the next execution cycle.

[0012] Thirdly, this application discloses an electronic device, including: Memory, used to store computer programs; A processor is configured to execute the computer program to implement the steps of the aforementioned disclosed exercise prescription generation method.

[0013] Fourthly, this application discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the steps of the aforementioned disclosed exercise prescription generation method.

[0014] The beneficial effects of this application are as follows: This application is applied to a computer device, comprising: a feature extraction module, used to simultaneously collect body composition data and muscle strength data of obese subjects, preprocess and extract features from the body composition data and muscle strength data to obtain body composition features and muscle strength features; a preliminary generation module, used to perform hierarchical determination of the body composition features and muscle strength features to determine the obesity type and muscle strength level of the obese subject, and generate a preliminary exercise prescription based on the combination result of the obesity type and the muscle strength level; wherein, the preliminary exercise prescription includes exercise type and exercise ratio; and a prescription generation module, used for... The aerobic exercise type parameter in the preliminary exercise prescription is determined by using the weighted fusion of the body composition characteristics and the muscle strength characteristics to obtain the body muscle joint index, and the resistance training type parameter in the preliminary exercise prescription is determined according to the muscle strength level, so as to generate the target exercise prescription for the current execution cycle based on the aerobic exercise type parameter and the resistance training type parameter; the exercise review module is used to obtain the review results generated by the obese subject executing the target exercise prescription; the prescription adjustment module is used to adjust the target exercise prescription according to the review results to obtain the target exercise prescription for the next execution cycle. Therefore, this application, through the feature extraction module, simultaneously collects and preprocesses body composition and muscle strength features, ensuring data accuracy and feature effectiveness. This provides a reliable data foundation for subsequent prescription generation. The preliminary generation module performs hierarchical judgment based on body composition and muscle strength features and combines obesity type and muscle strength level to generate a preliminary exercise prescription, which can significantly improve the targeting and personalization of the exercise program. The prescription generation module determines the parameters of aerobic exercise and resistance training based on the body-muscle combination index and muscle strength level, which can achieve precise quantitative matching of exercise intensity and training load, effectively reducing the subjectivity and experience dependence of prescription formulation, and improving the scientificity and safety of exercise prescriptions. The exercise review module and the prescription adjustment module work together to obtain review results and dynamically adjust the exercise prescription, forming a complete closed loop of assessment, decision-making, execution, feedback and optimization, continuously ensuring the effectiveness and suitability of exercise intervention, and improving the intelligence and standardization level of exercise prescription management for obese people. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0016] Figure 1 This is a schematic diagram of the structure of a sports prescription device disclosed in this application; Figure 2This is a schematic diagram of a specific exercise prescription device disclosed in this application; Figure 3 This is a schematic diagram of a specific fractal decision tree disclosed in this application; Figure 4 This is a flowchart of a method for generating an exercise prescription disclosed in this application; Figure 5 This is a structural diagram of an electronic device disclosed in this application. Detailed Implementation

[0017] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0018] Obesity has become a major public health challenge, with more than half of adults being overweight or obese. Exercise, as an important component of lifestyle intervention, is a core means of health management for overweight and obese populations. However, traditional exercise prescription methods have the following problems: ① Limited assessment dimensions: Existing technologies mostly rely on simple indicators such as BMI and weight, lacking a comprehensive assessment of body composition and functional indicators such as body fat percentage, muscle mass, and muscle strength; ② Insufficient personalization: Existing methods mostly use general templates, failing to fully consider the differences in individual muscle strength levels and body composition characteristics; ③ Lack of precise matching of exercise programs: failing to accurately match exercise intensity and type according to individual muscle strength levels and body composition characteristics.

[0019] Existing methods: 1) primarily rely on general body composition analysis data and machine learning algorithms to generate prescriptions, without addressing the combined application of body composition analysis and muscle strength assessment, nor designing personalized exercise parameters for the specific physiological characteristics of obese individuals. 2) Prescriptions are generated based on quantitative exercise prescription templates for obesity, mainly focusing on the quantitative monitoring of heart rate and energy expenditure, lacking a systematic assessment of body composition and muscle strength levels, and failing to establish a correlation model between body composition, muscle strength, and exercise prescription. 3) The FITT-VP principle (frequency, intensity, time, method, total amount, progression) is proposed to guide exercise prescription development, providing a macro framework, but no specific technical path for combining body composition analysis and muscle strength assessment is provided, and a quantitative decision-making model based on body composition and muscle strength data is lacking. 4) It is suggested that exercise prescriptions should include exercise frequency, intensity, time, method, total amount, progression, and precautions, emphasizing that overweight and obese individuals should pay attention to exercise warm-up and stretching recovery; and that exercise plans should be personalized according to health status and drug response. However, this also does not address the combined application of body composition and muscle strength assessment techniques, and lacks specific methods for matching muscle strength levels with exercise programs for obese individuals. 5) A regression model study based on body composition to predict muscle strength developed a regression equation for predicting muscle strength using anthropometry and body composition indicators. This study only established the predictive relationship between body composition and muscle strength and did not involve a method for developing exercise prescriptions based on body composition and muscle strength assessment. 6) A study on 36 weeks of personalized resistance training to improve sarcopenic obesity used the FITT-VP principle to develop personalized exercise prescriptions. Although this method involved both body composition assessment and muscle strength testing, it did not establish a joint analysis model for body composition and muscle strength data, and failed to automatically match the optimal exercise program based on body composition and muscle strength characteristics.

[0020] In summary, existing technologies have the following main shortcomings: ① Fragmented assessment indicators: Existing methods either focus on body composition analysis or muscle strength assessment, lacking a comprehensive assessment system that organically combines the two; ② Experience-based prescription formulation: Exercise prescriptions rely heavily on the experience of professionals, lacking quantitative decision support based on body composition and muscle strength data; ③ Limited personalization: They fail to accurately match exercise type, intensity, and frequency according to the body composition characteristics (such as high body fat percentage and low muscle mass) and muscle strength level of obese individuals; ④ Lack of dynamic adjustment mechanisms: Existing methods are mostly static prescriptions, failing to adjust prescriptions based on dynamic changes in body composition and muscle strength.

[0021] To address this, this application provides an exercise prescription generation solution that resolves the issues of single-dimensional assessment, insufficient personalization, inaccurate intensity matching, and lack of quantitative decision-making and dynamic adjustment in exercise prescriptions for obese individuals.

[0022] See Figure 1 As shown in the figure, this application discloses an exercise prescription generation device, applied to a computer device, comprising: The feature extraction module 11 is used to simultaneously collect body composition data and muscle strength data of obese subjects, and to preprocess and extract features from the body composition data and muscle strength data to obtain body composition features and muscle strength features.

[0023] The preliminary generation module 12 is used to perform hierarchical determination of the body composition characteristics and the muscle strength characteristics to determine the obesity type and muscle strength level of the obese subject, and generate a preliminary exercise prescription based on the combination result of the obesity type and the muscle strength level; wherein, the preliminary exercise prescription includes exercise type and exercise ratio.

[0024] The prescription generation module 13 is used to determine the aerobic exercise type parameter in the preliminary exercise prescription by using the body muscle joint index obtained by weighted fusion of the body composition features and the muscle strength features, and to determine the resistance training type parameter in the preliminary exercise prescription according to the muscle strength level, so as to generate the target exercise prescription for the current execution cycle based on the aerobic exercise type parameter and the resistance training type parameter.

[0025] The exercise reassessment module 14 is used to obtain the reassessment results generated when the obese subject performs the target exercise prescription.

[0026] The prescription adjustment module 15 is used to adjust the target exercise prescription according to the review results to obtain the target exercise prescription for the next execution cycle.

[0027] In this embodiment, the feature extraction module 11 includes: a first receiving unit 111, used to receive raw body composition data of obese subjects collected by a bioelectrical impedance analyzer; wherein the raw body composition data includes body fat percentage, total muscle mass, limb muscle mass, visceral fat area, and waist-to-hip ratio; a second receiving unit 112, used to simultaneously receive raw muscle strength data of obese subjects collected by a grip strength meter / isokinetic muscle strength testing system; wherein the raw muscle strength data includes upper limb muscle strength, lower limb muscle strength, and core muscle strength; and a preprocessing unit 113, used to preprocess the raw body composition data. The target body composition data and target muscle strength data are preprocessed together to obtain target body composition data and target muscle strength data. The preprocessing includes integrity checks, logical verification, outlier removal, and standardization. The feature extraction unit 114 is used to extract features from the target body composition data and target muscle strength data to obtain body composition features and muscle strength features. The body composition features include body fat percentage, muscle mass index, visceral fat level, body muscle ratio, and sarcopenia index. The muscle strength features include grip strength index, lower limb muscle strength index, core stability index, and muscle balance index.

[0028] Feature extraction module 11 includes a first receiving unit 111, which is used to receive raw body composition data of obese subjects collected by a bioelectrical impedance analyzer; specifically, raw body composition data is collected by an eight-electrode bioelectrical impedance analyzer, and the measurement indicators and technical parameters are as follows: 1.1) Body fat percentage (%): Measurement range 5%-60%, accuracy ±1%; 1.2) Total muscle mass (kg): Measurement range 20-80kg, accuracy ±0.5kg; 1.3) Muscle mass of the limbs (kg): Measure the muscle mass of the left / right upper limb and the left / right lower limb respectively; 1.4) Visceral fat area (cm²): Measurement range 0-300cm², accuracy ±5%; 1.5) Waist-to-hip ratio: the ratio of waist circumference to hip circumference, with a calculation accuracy of ±0.01.

[0029] The measurement specifications are as follows: 2.1) Fasting for at least 4 hours before measurement; 2.2) Empty your bladder and bowels before measurement; 2.3) During the measurement, the subject stands barefoot, holds the electrodes with both hands, and lets their arms hang naturally. 2.4) Measurement time is approximately 2 minutes.

[0030] Feature extraction module 11 includes a second receiving unit 112, which is used to synchronously receive the raw muscle strength data of obese subjects collected by a grip strength meter / isokinetic muscle strength testing system. Specifically, the upper limb muscle strength, lower limb muscle strength, and core muscle strength of obese subjects can be collected by an electronic grip strength meter and an isokinetic muscle strength testing system. The test indicators and technical parameters are shown in Table 1. Table 1 Test Indicators and Technical Parameters

[0031] The testing specifications are as follows: 3.1) Grip strength test: Stand with arms hanging naturally, grip with maximum force for 3 seconds, test twice for each hand, and record the maximum value; 3.2) Lower limb muscle strength test: sitting position, knee flexion and extension, 3 times and average value is taken; 3.3) Core muscle strength test: With the lower limbs fixed in a seated position, perform maximum trunk flexion and extension, and take the average of 3 measurements. Furthermore, the exercise prescription generation device also includes a basic information input terminal, as detailed below: ① Hardware configuration: Tablet or desktop computer with touchscreen; ② Enter information: Demographic information: age (years), sex (male / female), height (cm), weight (kg); Medical history: Type 2 diabetes, hypertension, cardiovascular disease, metabolic syndrome, etc.; Exercise history: Regular exercise habits (yes / no), type of exercise, weekly exercise frequency; Medication history: hypoglycemic drugs, antihypertensive drugs, lipid-lowering drugs, GLP-1 receptor agonists, etc.

[0032] Feature extraction module 11 includes a preprocessing unit 113, which performs preprocessing operations on the original body composition data and original muscle strength data in sequence, including integrity checks, logical verification, outlier removal, and standardization, to obtain target body composition data and target muscle strength data, as follows: 4.1) Completeness check: Check if any required fields are missing; missing value handling: If body composition data is missing, prompt for remeasurement; if basic information is missing, prompt for supplementary entry.

[0033] 4.2) Logical verification: Verification rule: Body fat percentage > muscle mass × 0.5 (characteristics of obese people); Verification rule: Grip strength < weight × 0.5 (screening for low muscle strength); If it fails, it is marked as abnormal data and a retest is prompted.

[0034] 4.3) Outlier removal: The 3σ principle is adopted: data exceeding the mean ± 3 times the standard deviation are considered outliers; body composition outlier determination: body fat percentage > 50% or < 10%, muscle mass < 15 kg or > 60 kg; muscle strength outlier determination: grip strength < 5 kg or > 60 kg, lower limb peak torque < 50 Nm or > 300 Nm.

[0035] 4.4) Standardization processing: Body composition index standardization: Z score = (measured value - reference population mean) / reference population standard deviation; Muscle strength index standardization: Muscle strength index = measured muscle strength / reference value for the same sex and age × 100%.

[0036] In other words, the integrity check is used to verify whether there are any missing body composition data, muscle strength data and basic information and to suggest supplementation or retesting. The logical verification is used to verify the rationality of the data based on the correlation rules between body fat percentage and muscle mass, and between muscle strength and weight in obese people and to mark abnormal data and suggest retesting. The outlier removal adopts the 3σ principle to remove abnormal body composition and muscle strength data that exceed the mean ± 3 times the standard deviation. The standardization process is used to convert body composition indicators into Z-scores and muscle strength indicators into muscle strength indices to unify the data dimensions.

[0037] Feature extraction module 11 includes feature extraction unit 114, which is used to extract features from target body composition data and target muscle strength data to obtain body composition features and muscle strength features, as shown in Tables 2 and 3. Table 2 Construction of body component feature sets

[0038] Table 3 Construction of muscle strength feature set

[0039] The exercise prescription generation device further includes: a weight determination unit, used to determine the negative weight of the body fat percentage level in the body composition features, the positive weight of the muscle mass index in the body composition features, and the positive weight of the grip strength index in the muscle strength features; and a weighted fusion unit, used to perform weighted fusion of the body fat percentage level, the muscle mass index, and the grip strength index to obtain a combined body-muscle index.

[0040] The exercise prescription generation device also includes: a weight determination unit, used to determine the negative weight of body fat percentage level in body composition characteristics, the positive weight of muscle mass index in body composition characteristics, and the positive weight of grip strength index in muscle strength characteristics. The weight determination unit sets the negative weight of body fat percentage level to -0.4, the positive weight of muscle mass index to 0.3, and the positive weight of grip strength index to 0.3, based on the influence of body composition and muscle strength on exercise prescription formulation in obese individuals. These weight parameters are optimal weighting coefficients determined after validation with a large number of obese population samples, accurately reflecting the negative impact of excessive body fat percentage on the health of obese individuals and the positive contribution of muscle mass and strength levels to exercise ability and intervention effects; and a weighted fusion unit, used to perform weighted fusion calculations on the standardized body fat percentage level, muscle mass index, and grip strength index according to the corresponding weights set by the weight determination unit to obtain the Body Composition-Muscle Index (BCMI). The specific weighted fusion formula is as follows: BCMI = -0.4 × Standardized Body Fat Percentage Grade + 0.3 × Standardized Muscle Mass Index + 0.3 × Standardized Grip Strength Index; The weighted fusion unit uses this formula to quantitatively integrate the core characteristics of body composition and the core characteristics of muscle strength, transforming multidimensional physiological indicators into a single comprehensive evaluation index. Based on the calculation results, the body-muscle combined index is then graded as follows: BCMI < -1.0: Poor muscle condition (high body fat + low muscle strength); -1.0≤BCMI<0: General muscle condition; 0 ≤ BCMI < 1.0: Good muscle condition; BCMI ≥ 1.0: Excellent muscle condition; In other words, the body muscle joint index is divided into four levels: poor body muscle condition, average body muscle condition, good body muscle condition, and excellent body muscle condition. This provides a unified quantitative basis for subsequent obesity classification, muscle strength stratification, exercise type matching, and exercise intensity determination, and achieves the organic integration and accurate assessment of body composition characteristics and muscle strength characteristics.

[0041] The initial generation module 12 first constructs a three-level obesity classification decision tree based on body fat percentage, muscle mass index, and grip strength index in body composition characteristics. It then classifies obese subjects into three types of obesity: simple obesity, sarcopenic obesity, and hidden obesity, based on body fat percentage, muscle mass index, and grip strength index. Next, it performs dual stratification of muscle strength based on grip strength index and lower limb muscle strength index in muscle strength characteristics, classifying obese subjects into three muscle strength levels: low muscle strength, normal muscle strength, and good muscle strength. Subsequently, based on a preset exercise type decision matrix, it combines and matches the three obesity types with the three muscle strength levels to obtain nine combination results. For each combination result, it automatically matches the corresponding exercise type and exercise ratio, generating an initial exercise prescription containing a clear exercise type and corresponding exercise ratio. This provides the core basis for subsequent accurate calculation of exercise parameters and generation of complete standardized exercise prescriptions.

[0042] In this embodiment, the exercise type includes aerobic exercise and resistance training; the prescription generation module 13 includes: an assessment unit for obtaining a multi-dimensional exercise risk assessment of the obese subject to obtain assessment results; an aerobic exercise parameter determination unit for determining the upper and lower target heart rate limits in the aerobic exercise type parameters based on the assessment results, and determining the intensity percentage in the aerobic exercise type parameters using the body-muscle joint index obtained by weighted fusion of the body composition characteristics and the muscle strength characteristics; and a resistance training parameter determination unit for determining the resistance training type parameters in the preliminary exercise prescription based on the assessment results and the muscle strength level.

[0043] The prescription generation module 13 uses the weighted fusion of body composition characteristics and muscle strength characteristics to obtain the body-muscle combination index, which determines the aerobic exercise type parameters in the preliminary exercise prescription, and determines the resistance training type parameters in the preliminary exercise prescription based on the muscle strength level, so as to generate the target exercise prescription for the current execution cycle based on the aerobic exercise type parameters and the resistance training type parameters; the prescription generation module 13 includes an assessment unit (i.e., a risk screening unit), specifically: ① Cardiovascular risk assessment: Measure resting blood pressure: a systolic blood pressure ≥140 mmHg or a diastolic blood pressure ≥90 mmHg indicates high risk; Electrocardiogram screening: ST segment changes and arrhythmias indicate high risk; Exercise test: Modified Bruce protocol, the presence of signs of myocardial ischemia is considered high risk.

[0044] ② Joint injury risk assessment: Knee function assessment: A WOMAC score >20 indicates high risk; Lower limb alignment assessment: Knee varus / valgus >10° is considered high risk; Previous injury history: Knee surgery or severe sprain is a high-risk factor.

[0045] ③ Metabolic abnormality risk assessment: Fasting blood glucose ≥7.0 mmol / L or glycated hemoglobin ≥6.5% is considered high risk; Dyslipidemia: Triglycerides ≥2.3 mmol / L or LDL cholesterol ≥4.1 mmol / L are considered high risk.

[0046] In other words, the assessment unit is used to obtain multidimensional exercise risk assessments of obese subjects to obtain assessment results. The multidimensional exercise risk assessment includes cardiovascular risk assessment, joint injury risk assessment, and metabolic abnormality risk assessment. The cardiovascular risk assessment is completed through resting blood pressure measurement, electrocardiogram screening, and modified Bruce exercise test. The joint injury risk assessment is completed through WOMAC score, lower limb alignment assessment, and verification of previous joint injury history. The metabolic abnormality risk assessment is completed through fasting blood glucose, glycated hemoglobin, and blood lipid index detection. Based on the above three-dimensional risk screening results, the assessment unit determines the exercise safety boundary and marks high-risk contraindications.

[0047] The aerobic exercise parameter determination unit determines the upper and lower limits of target heart rate in the aerobic exercise type parameters based on the evaluation results. The target heart rate is calculated using the heart rate reserve method, and the calculation formula is as follows: Lower limit of target heart rate = (220 - age - resting heart rate) × lower limit of intensity percentage + resting heart rate; Upper target heart rate = (220 - age - resting heart rate) × upper limit of intensity percentage + resting heart rate; The intensity percentage in the aerobic exercise type parameters is determined by using the weighted fusion of body composition characteristics and muscle strength characteristics to obtain the body-muscle combination index. When the Body Muscle Combination Index (BCMI) is < -1.0, the intensity percentage is set at 40-50%. When -1.0 ≤ BCMI < 0, set to 50-60%; When 0 ≤ BCMI < 1.0, set it to 60-70%; When BCMI ≥ 1.0, set it to 65-75%; Duration per session: Initial stage: 20-30 minutes; Adaptation phase: 30-45 minutes; Enhancement phase: 45-60 minutes; Frequency per week: 3-5 times.

[0048] At the same time, the target heart rate range is adjusted for safety based on the risk assessment results.

[0049] The resistance training parameter determination unit is used to determine the resistance training type parameters in the initial exercise prescription based on the assessment results and muscle strength level. Specifically: Load intensity calculation (%1RM): Low muscle strength: 30-50% of 1RM; Normal muscle strength level: 50-70% 1RM; Good muscle strength layer: 60-80% 1RM.

[0050] 1RM prediction formula (based on muscle strength test): Upper limb 1RM = grip strength (kg) × 3.5; Lower limb 1RM = peak torque of knee extensor muscles (Nm) × 0.15.

[0051] Training volume configuration: 2-3 sets per muscle group; Repeats per set: 8-15 times; Rest between sets: 60-90 seconds.

[0052] Prioritize muscle group training (for sarcopenic obesity): First priority: lower limb muscle groups (quadriceps, hamstrings, glutes); Second priority: Core muscles (abdominal muscles, back muscles); Third priority: Upper limb muscle groups (chest muscles, latissimus dorsi, deltoid muscles).

[0053] By combining risk assessment results to avoid high-risk resistance exercises and load settings, the aerobic exercise parameters and resistance training parameters are integrated to generate a complete FITT-VP format target exercise prescription that includes frequency, intensity, time, type, total volume, progression, and precautions. The output format is shown in Table 4. Table 4 Exercise Prescription Output Format (FITT-VP)

[0054] In this embodiment, the exercise prescription generation device further includes: a visualization unit for visualizing the target exercise prescription to generate any one or more visualization results such as a body composition radar chart, muscle strength comparison chart, exercise intensity curve, and advanced roadmap; and a video generation unit for generating a guidance video corresponding to the target exercise prescription; wherein the guidance video includes a warm-up exercise video, a main training exercise video, and a cool-down exercise video.

[0055] The exercise prescription generation device also includes a visualization unit and a video generation unit. The visualization unit is used to visualize the target exercise prescription, generating one or more visualization results such as body composition radar charts, muscle strength comparison charts, exercise intensity curves, and progressive roadmaps. The body composition radar chart visually displays the comparison between measured and reference values ​​of multidimensional body composition indicators such as body fat percentage, muscle mass, visceral fat, and waist-to-hip ratio in obese subjects. The muscle strength comparison chart presents the difference between individual measured muscle strength values ​​and standard reference values ​​for the same sex and age. The exercise intensity curve shows the dynamic change of target heart rate over time during a single exercise session. The progressive roadmap clearly displays a gradually increasing plan for exercise intensity, duration, and load over a 4- to 12-week period, achieving a visually intuitive and easily understandable presentation of the various parameters and intervention plans of the target exercise prescription. The visualization chart output is as follows: Body composition radar chart: Displays multiple indicators such as body fat percentage, muscle mass, visceral fat, and waist-to-hip ratio; Muscle strength comparison chart: Comparison of individual measured values ​​with reference values ​​of the same sex and age; Exercise intensity curve: The curve showing the change of target heart rate over time during a single exercise session; Advanced Roadmap: A 4-12 Week Plan for Increasing Exercise Intensity and Duration The video generation unit generates instructional videos corresponding to the target exercise prescription. These videos include warm-up videos, main training videos, and cool-down videos. The warm-up videos are 5-10 minutes long, demonstrating proper dynamic stretching techniques to help obese subjects fully activate muscles and reduce injury risk before exercise. The main training videos provide standard movement demonstrations and corrections for common errors in the aerobic and resistance training exercises within the target exercise prescription, ensuring effective and standardized training. The cool-down videos are 5-10 minutes long, demonstrating static stretching techniques to relax muscles, relieve fatigue, and promote recovery after exercise. These three types of instructional videos are precisely matched to the exercise type, intensity, and movement requirements of the target exercise prescription, providing obese subjects with comprehensive, visual operational guidance for safely and correctly implementing the exercise prescription. The video instructional output is as follows: Warm-up video: 5-10 minutes of dynamic stretching; Main training video: standard movement demonstration and correction of common mistakes; Finishing exercise video: 5-10 minutes of static stretching.

[0056] The exercise reassessment module 14 is used to obtain the reassessment results generated when the obese subject performs the target exercise prescription. The exercise reassessment module 14 includes an execution monitoring unit and a reassessment triggering unit. The wearable device used in the monitoring unit is a smart fitness tracker or watch that supports heart rate monitoring, step counting, and energy consumption estimation. It can collect real-time monitoring indicators such as heart rate, steps, calorie expenditure, and exercise duration, and synchronize the data to the management system via Bluetooth. It is also equipped with a monitoring and early warning mechanism. When the real-time heart rate exceeds the target heart rate limit, it will vibrate to remind the user. When the daily calorie expenditure is less than 50% of the target value, it will push an insufficient exercise notification. When the exercise duration exceeds 90 minutes for three consecutive days, it will issue an overexertion rest reminder. The re-evaluation trigger unit has a dual mechanism of automatic re-evaluation cycle and early re-evaluation trigger conditions. The automatic re-evaluation cycle is the first re-evaluation after 4 weeks of the initial prescription to assess adaptability and safety. The subsequent routine re-evaluation is conducted every 8 weeks to assess the intervention effect and adjust the prescription. The early re-evaluation trigger conditions are: when the subject's weight loss exceeds 5%, the re-evaluation of body composition changes is carried out immediately when pain or discomfort occurs during exercise, and the re-evaluation of metabolic risk is carried out immediately when the disease status changes, such as the diagnosis of diabetes. This realizes intelligent management of the entire prescription execution monitoring and re-evaluation scheduling.

[0057] The prescription adjustment module 15 is used to adjust the target exercise prescription based on the reassessment results to obtain the target exercise prescription for the next execution cycle. The prescription adjustment module 15 is used to automatically adjust the target exercise prescription according to preset quantitative decision rules based on changes in body composition indicators, muscle strength indicators, and risk screening results obtained from the reassessment, to obtain a target exercise prescription for the next execution cycle that is suitable for the subject's current physical condition. Specific adjustment decision rules are shown in Table 5. Table 5 Adjustment Decision Rules

[0058] In other words, if the reassessment shows a decrease in body fat percentage of ≥2% and muscle mass remains unchanged, the current prescription will be maintained and the program will proceed to the next stage as planned. If the decrease in body fat percentage is <2% and muscle mass remains unchanged, the duration or intensity of aerobic exercise will be increased. If the decrease in body fat percentage is ≥2% but muscle mass decreases by ≥1kg, the proportion of resistance training will be increased and protein supplementation will be recommended. If the decrease in body fat percentage is <2% and muscle mass decreases by ≥1kg, the type, intensity, and total amount of exercise will be comprehensively adjusted, while resistance training will be strengthened and nutritional combinations and adherence management will be optimized. If muscle strength increases by ≥10%, the load intensity of resistance training will be increased. At the same time, the proportion of exercise types, aerobic exercise intensity, and resistance training parameters will be rematched based on the updated obesity classification, muscle strength stratification, risk status, and changes in the Body Mass Index (BCMI) during the reassessment. Finally, a personalized target exercise prescription that conforms to the FITT-VP standard and is suitable for the next cycle will be generated.

[0059] The beneficial effects of this application are as follows: This application is applied to a computer device, comprising: a feature extraction module, used to simultaneously collect body composition data and muscle strength data of obese subjects, preprocess and extract features from the body composition data and muscle strength data to obtain body composition features and muscle strength features; a preliminary generation module, used to perform hierarchical determination of the body composition features and muscle strength features to determine the obesity type and muscle strength level of the obese subject, and generate a preliminary exercise prescription based on the combination result of the obesity type and the muscle strength level; wherein, the preliminary exercise prescription includes exercise type and exercise ratio; and a prescription generation module, used for... The aerobic exercise type parameter in the preliminary exercise prescription is determined by using the weighted fusion of the body composition characteristics and the muscle strength characteristics to obtain the body muscle joint index, and the resistance training type parameter in the preliminary exercise prescription is determined according to the muscle strength level, so as to generate the target exercise prescription for the current execution cycle based on the aerobic exercise type parameter and the resistance training type parameter; the exercise review module is used to obtain the review results generated by the obese subject executing the target exercise prescription; the prescription adjustment module is used to adjust the target exercise prescription according to the review results to obtain the target exercise prescription for the next execution cycle. Therefore, this application, through the feature extraction module, simultaneously collects and preprocesses body composition and muscle strength features, ensuring data accuracy and feature effectiveness. This provides a reliable data foundation for subsequent prescription generation. The preliminary generation module performs hierarchical judgment based on body composition and muscle strength features and combines obesity type and muscle strength level to generate a preliminary exercise prescription, which can significantly improve the targeting and personalization of the exercise program. The prescription generation module determines the parameters of aerobic exercise and resistance training based on the body-muscle combination index and muscle strength level, which can achieve precise quantitative matching of exercise intensity and training load, effectively reducing the subjectivity and experience dependence of prescription formulation, and improving the scientificity and safety of exercise prescriptions. The exercise review module and the prescription adjustment module work together to obtain review results and dynamically adjust the exercise prescription, forming a complete closed loop of assessment, decision-making, execution, feedback and optimization, continuously ensuring the effectiveness and suitability of exercise intervention, and improving the intelligence and standardization level of exercise prescription management for obese people.

[0060] Reference Figure 2 As shown, this embodiment of the invention discloses a specific exercise prescription generation device module framework, applied to a computer device. Compared to the previous embodiment, this embodiment further explains and optimizes the technical solution. Specifically: The preliminary generation module 12 includes: a first judgment unit 1211, used to determine whether the muscle mass index is less than a first preset muscle mass threshold if the body fat percentage level is greater than a preset level; a first obesity judgment unit 1212, used to determine that the obesity type of the obese subject is a preset simple obesity type if the muscle mass index is not less than the first preset muscle mass threshold; a second judgment unit 1213, used to determine whether the grip strength index is less than a preset grip strength threshold if the muscle mass index is less than the first preset muscle mass threshold; a second obesity judgment unit 1214, used to determine that the obesity type of the obese subject is a preset sarcopenic obesity type if the grip strength index is less than the preset grip strength threshold; and a third obesity judgment unit 1215, used to determine that the obesity type of the obese subject is a preset hidden obesity type if the grip strength index is not less than the preset grip strength threshold.

[0061] The initial generation module 12 includes a first judgment unit 1211, a first obesity judgment unit 1212, a second judgment unit 1213, a second obesity judgment unit 1214, and a third obesity judgment unit 1215. For example... Figure 3 As shown, the first judgment unit 1211 is used to further determine whether the muscle mass index is less than a first preset muscle mass threshold if the body fat percentage level is greater than a preset level. The preset level is set according to the obesity determination criteria, where a body fat percentage ≥25% for men and ≥30% for women is considered greater than the preset level. The first preset muscle mass threshold is 7.0 kg / m² for men and 5.7 kg / m² for women. The first obesity determination unit 1212 is used to determine the obesity type of the obese subject as a preset simple obesity type if the muscle mass index is not less than the first preset muscle mass threshold. This type is characterized by a high body fat percentage but normal muscle mass. The second judgment unit 1213 is used to determine whether the muscle mass index is less than the first preset muscle mass threshold. If the grip strength index is less than the preset grip strength threshold, the second obesity determination unit 1214 determines whether the obesity type of the obese subject is sarcopenic obesity if the grip strength index is less than the preset grip strength threshold. This type is characterized by high body fat percentage, low muscle mass, and low muscle strength. The third obesity determination unit 1215 determines whether the obesity type of the obese subject is hidden obesity if the grip strength index is not less than the preset grip strength threshold. This type is characterized by low muscle mass but relatively normal muscle strength. Through the above three-level progressive judgment logic, the accurate classification of obese subjects is completed, providing a classification basis for the initial generation of subsequent personalized exercise prescriptions. The details are as follows: Table 6. Characteristics and key intervention points of each type

[0062] The preliminary generation module 12 includes: a first muscle strength determination unit 1221, used to determine the muscle strength level of the obese subject as a preset good muscle strength type if the muscle mass index is not less than a first preset muscle mass threshold; a second muscle strength determination unit 1222, used to determine the muscle strength level of the obese subject as a preset normal muscle strength type if the muscle mass index is less than the first preset muscle mass threshold and not less than a second preset muscle mass threshold; and a third muscle strength determination unit 1223, used to determine the muscle strength level of the obese subject as a preset low muscle strength type if the muscle mass index is less than the second preset muscle mass threshold.

[0063] The initial generation module 12 includes a first muscle strength determination unit 1221, a second muscle strength determination unit 1222, and a third muscle strength determination unit 1223. The first muscle strength determination unit 1221 determines the obese subject's muscle strength level as a preset "good" type if the muscle mass index is not less than a first preset muscle mass threshold, and the grip strength meets the standard of males greater than 40kg, females greater than 30kg, and the lower limb muscle strength index is greater than 80%. The second muscle strength determination unit 1222 determines the obese subject's muscle strength level as a preset "good" type if the muscle mass index is less than the first preset muscle mass threshold but not less than the second preset muscle mass threshold, and the grip strength is within the standard of males 28-40kg, females 20-30kg, and the lower limb muscle strength index is in the range of 60%-80%. The third muscle strength assessment unit 1223 is used to determine the muscle strength level of obese subjects as the preset low muscle strength type if the muscle mass index is less than the second preset muscle mass threshold, and combined with the grip strength being less than 28 kg for men and 20 kg for women, and the lower limb muscle strength index being less than 60%. The first and second preset muscle mass thresholds correspond to the boundary standards for good, normal, and low muscle strength, respectively. Combining muscle mass index, grip strength, and lower limb muscle strength index completes a dual-stratification assessment, accurately determining the muscle strength level of obese subjects and providing a basis for the preliminary matching of subsequent exercise types and proportions. Details are as follows: Table 7 Stratification Criteria

[0064] A preliminary exercise prescription is generated based on the combination of obesity type and muscle strength level. Specifically, three obesity types—simple obesity, sarcopenic obesity, and occult obesity—are cross-combined with three muscle strength levels—low muscle strength, normal muscle strength, and good muscle strength—to form nine matching scenarios. Then, according to a preset exercise type decision matrix, a corresponding exercise type and exercise ratio are matched for each combination, as shown in Table 8. Table 8 Decision Matrix

[0065] When the combination presents with simple obesity and normal or good muscle strength, an exercise program primarily based on aerobic exercise and supplemented by resistance training should be determined, with an exercise ratio of 60% aerobic exercise and 40% resistance training. When the combination presents with simple obesity and low muscle strength, an exercise program combining low-intensity aerobic exercise with light resistance training should be determined, with an exercise ratio of 70% aerobic exercise and 30% resistance training. When the combination presents with sarcopenic obesity and low muscle strength, an exercise program primarily based on resistance training and supplemented by aerobic exercise should be determined, with an exercise ratio of 60% resistance training and 40% aerobic exercise. When the combination is sarcopenic obesity with normal muscle strength, a balanced exercise program combining resistance training and aerobic exercise is determined, with an exercise ratio of 50% resistance training and 50% aerobic exercise. When the combination is occult obesity with low muscle strength, an exercise program mainly based on resistance training and moderately supplemented with aerobic exercise is determined, with an exercise ratio of 70% resistance training and 30% aerobic exercise. Finally, based on the above combination matching rules, a preliminary exercise prescription containing clear exercise types and corresponding exercise ratios is generated, providing a core framework for subsequent accurate calculation of exercise parameters and generation of a complete target exercise prescription.

[0066] Reference Figure 4 As shown, this embodiment of the invention discloses a method for generating exercise prescriptions, applied to a computer device, comprising: Step S11: Simultaneously collect body composition data and muscle strength data of obese subjects, and preprocess and extract features from the body composition data and muscle strength data to obtain body composition features and muscle strength features.

[0067] Body composition and muscle strength data were collected simultaneously from obese subjects. Body composition data was acquired using an eight-electrode bioelectrical impedance analyzer, including indicators such as body fat percentage, total muscle mass, limb muscle mass, visceral fat area, and waist-to-hip ratio. Muscle strength data was acquired simultaneously using an electronic grip strength meter and an isokinetic muscle strength testing system, including indicators such as upper limb grip strength, lower limb knee extensor peak torque, and core trunk flexion-extension peak torque ratio. Subsequently, the two types of raw data underwent preprocessing operations, including integrity checks, logical verification, outlier removal, and standardization. Body composition features such as body fat percentage grade, muscle mass index, visceral fat grade, body-to-muscle ratio, and sarcopenia index, as well as muscle strength features such as grip strength index, lower limb muscle strength index, core stability index, and muscle balance index, were extracted to provide high-quality feature data for subsequent decision-making.

[0068] Step S12: Hierarchically determine the body composition characteristics and muscle strength characteristics to identify the obesity type and muscle strength level of the obese subject, and generate a preliminary exercise prescription based on the combination of the obesity type and the muscle strength level; wherein, the preliminary exercise prescription includes exercise type and exercise ratio.

[0069] A hierarchical assessment of obesity was conducted based on body composition and muscle strength characteristics, employing a three-tiered obesity classification and dual muscle strength stratification. Three obesity types were identified: simple obesity, sarcopenic obesity, and occult obesity, based on body fat percentage, muscle mass index, and grip strength index, respectively. These were further divided into three muscle strength levels: low muscle strength, normal muscle strength, and good muscle strength, based on grip strength and lower limb muscle strength index. The obesity type and muscle strength level were then combined and matched, generating a preliminary exercise prescription that included the exercise type and corresponding exercise ratio according to a pre-defined exercise type decision matrix. For example, simple obesity with good muscle strength was treated with 60% aerobic exercise and 40% resistance exercise, while sarcopenic obesity with low muscle strength was treated with 60% resistance exercise and 40% aerobic exercise, forming the core framework of the prescription.

[0070] Step S13: Determine the aerobic exercise type parameter in the preliminary exercise prescription using the weighted fusion index of the body composition features and the muscle strength features, and determine the resistance training type parameter in the preliminary exercise prescription according to the muscle strength level, so as to generate the target exercise prescription for the current execution cycle based on the aerobic exercise type parameter and the resistance training type parameter.

[0071] The Body-Muscle Combination Index (BCMI) is calculated by weighted fusion of body composition and muscle strength characteristics. Based on the BCMI classification, the percentage of aerobic exercise intensity in the preliminary exercise prescription is determined. Aerobic exercise type parameters such as the upper and lower limits of target heart rate are calculated by combining the subject's age and resting heart rate. At the same time, resistance training type parameters such as %1RM load intensity, trained muscle groups, and number of sets and repetitions are determined according to muscle strength level. 30-50%1RM is used for low muscle strength level, 50-70%1RM for normal muscle strength level, and 60-80%1RM for good muscle strength level. Safety adjustments are made based on the results of multi-dimensional exercise risk assessment. Finally, the two types of parameters are integrated to generate a target exercise prescription for the current execution cycle that conforms to the FITT-VP standard.

[0072] Step S14: Obtain the re-evaluation results generated when the obese subject performs the target exercise prescription.

[0073] Wearable devices monitor subjects' heart rate, exercise duration, calorie consumption, and other data in real time as they execute the target exercise prescription. The review process is triggered according to preset rules. The first review is conducted 4 weeks after the initial prescription is implemented, and routine reviews are conducted every 8 weeks thereafter. If there is a weight loss of more than 5%, exercise pain or discomfort, or changes in disease status, the review will be conducted earlier. The review content includes retesting body composition indicators, retesting muscle strength indicators, and reassessing exercise risks, so as to comprehensively obtain the review results of the subjects' physical condition and intervention effect after the implementation of the prescription.

[0074] Step S15: Adjust the target exercise prescription according to the review results to obtain the target exercise prescription for the next execution cycle.

[0075] Based on the changes in body fat percentage, muscle mass, and muscle strength obtained from the reassessment, the current target exercise prescription is automatically optimized according to five preset adjustment rules. If body fat decreases by ≥2% and muscle mass is maintained, the prescription is upgraded; if body fat decreases insufficiently but muscle mass is maintained, the aerobic intensity is increased; if body fat reaches the target but muscle mass is lost, the resistance ratio is increased; and if muscle strength increases by ≥10%, the resistance load is increased. Combined with the updated obesity classification, muscle strength level, and BCMI index, a comprehensive adjustment is completed to generate a target exercise prescription for the next execution cycle that is suitable for the subject's current physical condition, thus realizing dynamic and personalized closed-loop management of exercise intervention.

[0076] The above approach improves accuracy: 1) The accuracy of obesity classification has been significantly improved. Using the Body Mass Index (BCMI) and a three-level decision tree classification, obese people are subdivided into three phenotypes: simple obesity, sarcopenic obesity, and hidden obesity. Traditional methods rely solely on BMI classification and cannot identify sarcopenic obesity (high body fat + low muscle), with a false negative rate of about 15-20%. This application improves the detection rate of sarcopenic obesity to over 95% and the detection rate of hidden obesity from <5% to 12-15% through combined assessment of body composition and muscle strength. This avoids further muscle loss caused by simply performing aerobic exercise on patients with sarcopenic obesity and ensures that the goal of "fat reduction and muscle preservation" is accurately achieved.

[0077] 2) Improved accuracy in matching exercise intensity: The target heart rate percentage is dynamically determined based on the BCMI four-level classification (40-75% HRR), enabling individualized intensity prescriptions. Traditional methods use a fixed 50-70% HRR or 220-age formula, ignoring individual differences. The actual exercise heart rate deviates from the target range by up to 35% (on-site test data). Under the BCMI linkage mechanism of this application, the heart rate falling within the target range increases to 82%, and the incidence of exercise safety events (chest tightness, palpitations) decreases from 8% to 2%. In this way, given the large differences in cardiovascular load among obese individuals, precise intensity matching can reduce exercise risks and improve training tolerance.

[0078] The above approach ensures safety by: 1) Significantly reducing exercise-related adverse events through a three-dimensional risk screening (cardiovascular + joint injury + metabolic abnormalities) linkage mechanism, establishing a safety boundary for exercise. Traditional methods only use the PAR-Q questionnaire for screening, resulting in a 10% missed rate for occult cardiovascular diseases and a lack of systematic assessment of joint injury risks. This application adds blood pressure, electrocardiogram, exercise test, WOMAC score, and lower limb alignment assessment, increasing the identification rate of high-risk individuals to 98%, with zero cardiovascular events during exercise (pilot application data, n=500). This allows for proactive risk management, especially given the high risk of sudden cardiac arrest during exercise in obese individuals after prolonged sitting. 2) Reducing the rate of exercise injury in individuals with low muscle strength. A dual stratification of muscle strength (grip strength + lower limb muscle strength index) identifies individuals with low muscle strength (<60%), matching them with low starting loads (30-50% 1RM). Traditional methods uniformly start at 60% of 1RM, resulting in a joint injury rate of 18% (knee pain, muscle strain) in individuals with low muscle strength. This application uses stratified starting loads, reducing the injury rate in individuals with low muscle strength to 4%, and after 8 weeks, the muscle strength improvement rate surpasses that of the high starting group (+28% vs +19%). In this way, joint function is protected in obese individuals with low muscle strength, preventing them from dropping out of exercise due to excessive load.

[0079] The above approach optimizes the intervention effect: 1) Improved fat loss efficiency: The exercise type decision matrix (9 combinations) optimizes the aerobic / resistance ratio. Comparisons are shown in Table 9 (12-week intervention trial, n=120): Table 9. Comparison of Fat Reduction Efficiency

[0080] For simple obesity, the regimen is 60% aerobic exercise and 40% resistance training; for sarcopenic obesity, the regimen is 60% resistance training and 40% aerobic exercise. This type of matching improves fat loss efficiency by 62% while preventing muscle loss.

[0081] 2) Muscle protection effect in sarcopenic obesity, muscle group priority ranking (lower limbs first → core second → upper limbs last), targeted strengthening of functionally deficient muscle groups. Comparative studies (sarcopenic obesity subgroup, n=40, 12 weeks) show that lower limb function is the foundation of daily activities in obese individuals, and prioritizing strengthening significantly improves quality of life.

[0082] The above solutions improve operational efficiency as follows: 1) The assessment-prescription process is shortened, and the five-module closed-loop architecture automates the flow from data collection to prescription generation. Traditional manual processes: body composition measurement (5 minutes) + muscle strength test (20 minutes) + data analysis (15 minutes) + manual prescription (20 minutes) = 60 minutes / person. This application's system process: synchronous data collection (25 minutes) + automatic processing and decision-making (2 minutes) + prescription output (1 minute) = 28 minutes / person. Efficiency improvement: single-person assessment-prescription time is reduced by 53%, and the average number of people served per day increases from 8 to 16. This increases the service capacity of medical institutions / fitness centers and reduces labor costs. 2) Prescription adjustment response speed is improved, and the dynamic triggering mechanism for the reassessment cycle (fixed 4-8 weeks + conditional triggering) enables timely intervention and optimization. Traditional fixed cycle (12-week reassessment): those with a weight loss of <2% are delayed for 8 weeks before adjustment, missing the optimal intervention period. This application's dynamic triggering: immediate reassessment for a 5% weight loss or exercise pain, shortening the adjustment response time from 84 days to 28 days. Avoid the accumulation of ineffective training cycles and improve intervention compliance and effectiveness.

[0083] The above approach improves long-term management effectiveness: 1) Improved intervention adherence, supported by a multi-dimensional support system of FITT-VP structured output + video guidance + wearable monitoring. Comparative evidence (24-week follow-up, n=200): Table 10. Comparison of Intervention Compliance Demonstration

[0084] Visualized prescriptions, real-time monitoring, and dynamic adjustments create positive feedback, significantly reducing the rate of exercise withdrawal.

[0085] 2) Continuous improvement in health outcomes; the dynamic management module enables long-term optimization of body composition and muscle strength. Comparative evidence (52-week follow-up, sarcopenic obesity group, n=60): Table 11 Comparison of Health Outcomes

[0086] The BCMI improved continuously from -1.3 to +0.8, the body muscle condition jumped from "poor" to "good", and the risk of metabolic syndrome decreased by 67%.

[0087] This application achieves significant improvements in six dimensions—accurate classification, safety management, effect optimization, efficiency enhancement, long-term management, and cost control—through the deep integration of body composition analysis and muscle strength assessment. It provides a scientific, standardized, and scalable technical solution for personalized exercise intervention for obese individuals.

[0088] The following example illustrates the development of an exercise prescription for individuals with simple obesity and normal muscle strength. Basic information about the subjects is shown in Table 12. Table 12 Basic Information of Subjects

[0089] 1) Body composition measurement (bioelectrical impedance analyzer), details are shown in Table 13: Table 13 Body Composition Measurement

[0090] 2) Muscle strength test, as shown in Table 14: Table 14 Muscle Strength Test

[0091] Muscle strength stratification: A grip strength > 40 kg and a lower limb muscle strength index > 80% are considered to be in the good muscle strength stratification.

[0092] 3) Data processing and feature extraction: ①Standardization process: Standardized body fat percentage = (32.5-20) / 10 = 1.25; Standardized muscle mass index = (58.2 / 1.75² - 25) / 5 = 1.36; Standardized grip strength index = 105% / 20 = 0.525.

[0093] ② Calculation of Body Combination Index (BCMI): BCMI=-0.4×1.25+0.3×1.36+0.3×0.525 =-0.5+0.408+0.158 =0.066≈0.1 (Good level) 4) Intelligent decision-making: ① Obesity classification: High body fat percentage (32.5%) → Normal muscle mass (58.2kg) → Normal grip strength (42kg) → classified as simple obesity.

[0094] ② Risk screening: Blood pressure: 128 / 82 mmHg (normal); Electrocardiogram: Sinus rhythm, no abnormalities; WOMAC score: 8 (normal).

[0095] ③ Exercise type decision: Simple obesity + good muscle strength → 60% aerobic + 40% resistance.

[0096] 5) Exercise prescription generation, as shown in Table 15: Table 15 Exercise Prescription

[0097] The detailed resistance training plan is shown in Table 16: Table 16 Detailed Resistance Training Program

[0098] 6) Execution and Dynamic Management: ① Wearable device configuration: Huawei Band 8, real-time heart rate monitoring.

[0099] ② Results of the 4-week follow-up review: Body fat percentage: 32.5% → 30.1% (a decrease of 2.4%); Muscle mass: 58.2kg → 58.0kg (maintenance); Grip strength: 42kg → 44kg (4.8% increase).

[0100] ③Prescription adjustment: Once the standard of "body fat reduction ≥2% and muscle mass maintenance" is achieved, implement the advanced plan, that is, increase the aerobic duration to 50 minutes and increase the resistance load to 65-75% 1RM.

[0101] Furthermore, embodiments of this application also provide an electronic device. Figure 5 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content of the diagram should not be construed as limiting the scope of this application.

[0102] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Specifically, it may include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 stores a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the exercise prescription generation method performed by the electronic device disclosed in any of the foregoing embodiments.

[0103] In this embodiment, the power supply 23 is used to provide operating voltage for various hardware devices on the electronic device; the communication interface 24 can create a data transmission channel between the electronic device and external devices, and the communication protocol it follows can be any communication protocol applicable to the technical solution of this application, and is not specifically limited here; the input / output interface 25 is used to acquire external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs, and is not specifically limited here.

[0104] The processor 21 may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor 21 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 21 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor 21 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, the processor 21 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0105] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, disk or optical disk, etc. The resources stored on it include operating system 221, computer program 222 and data 223, etc., and the storage method can be temporary storage or permanent storage.

[0106] The operating system 221 manages and controls the various hardware devices and computer programs 222 on the electronic device to enable the processor 21 to perform calculations and processing on the massive amounts of data 223 in the memory 22. The operating system can be Windows, Unix, Linux, etc. The computer program 222, in addition to including a computer program capable of performing the exercise prescription generation method executed by the electronic device as disclosed in any of the foregoing embodiments, may further include computer programs capable of performing other specific tasks. The data 223 may include data received by the electronic device from external devices, as well as data collected by its own input / output interface 25.

[0107] Furthermore, this application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the aforementioned disclosed exercise prescription generation method. Specific steps of this method can be found in the corresponding content disclosed in the foregoing embodiments, and will not be repeated here.

[0108] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0109] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application. The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly in hardware, software modules executed by a processor, or a combination of both. The software module may be located in random access memory (RAM), memory, read-only memory (ROM), electrically programmable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), register, hard disk, removable disk, CD-ROM (Compact Disc Read-Only Memory), or any other form of storage medium known in the art.

[0110] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0111] The above provides a detailed description of the exercise prescription generation device, method, equipment, and medium provided by the present invention. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only intended to help understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A device for generating exercise prescriptions, characterized in that, Applied to computer devices, including: The feature extraction module is used to simultaneously collect body composition data and muscle strength data of obese subjects, and to preprocess and extract features from the body composition data and muscle strength data to obtain body composition features and muscle strength features. A preliminary generation module is used to hierarchically determine the body composition characteristics and muscle strength characteristics to identify the obesity type and muscle strength level of the obese subject, and generate a preliminary exercise prescription based on the combination of the obesity type and muscle strength level; wherein, the preliminary exercise prescription includes exercise type and exercise ratio; The prescription generation module is used to determine the aerobic exercise type parameter in the preliminary exercise prescription by using the body muscle joint index obtained by weighted fusion of the body composition features and the muscle strength features, and to determine the resistance training type parameter in the preliminary exercise prescription according to the muscle strength level, so as to generate the target exercise prescription for the current execution cycle based on the aerobic exercise type parameter and the resistance training type parameter. The exercise reassessment module is used to obtain the reassessment results generated when the obese subject performs the target exercise prescription; The prescription adjustment module is used to adjust the target exercise prescription based on the review results to obtain the target exercise prescription for the next execution cycle.

2. The exercise prescription generation device according to claim 1, characterized in that, The feature extraction module includes: The first receiving unit is used to receive raw body composition data of obese subjects collected by a bioelectrical impedance analyzer; wherein, the raw body composition data includes body fat percentage, total muscle mass, limb muscle mass, visceral fat area and waist-to-hip ratio. The second receiving unit is used to synchronously receive the raw muscle strength data of obese subjects collected by the hand grip strength meter / isokinetic muscle strength testing system; wherein, the raw muscle strength data includes upper limb muscle strength, lower limb muscle strength and core muscle strength; The preprocessing unit is used to preprocess the original body composition data and the original muscle strength data to obtain target body composition data and target muscle strength data; wherein, the preprocessing includes integrity check, logical verification, outlier removal and standardization processing; The feature extraction unit is used to extract features from the target body composition data and the target muscle strength data to obtain body composition features and muscle strength features; wherein, the body composition features include body fat percentage level, muscle mass index, visceral fat level, body muscle ratio and sarcopenia index, and the muscle strength features include grip strength index, lower limb muscle strength index, core stability index and muscle balance index.

3. The exercise prescription generation device according to claim 2, characterized in that, The exercise prescription generation device further includes: The weighting determination unit is used to determine the negative weight of the body fat percentage level in the body composition feature, the positive weight of the muscle mass index in the body composition feature, and the positive weight of the grip strength index in the muscle strength feature. The weighted fusion unit is used to weight and fuse the body fat percentage level, the muscle mass index, and the grip strength index to obtain the body-muscle combined index.

4. The exercise prescription generation device according to claim 2, characterized in that, The preliminary generation module includes: The first judgment unit is used to determine whether the muscle mass index is less than a first preset muscle mass threshold if the body fat percentage level is greater than a preset level. The first obesity determination unit is used to determine the obesity type of the obese subject as a preset simple obesity type if the muscle mass index is not less than the first preset muscle mass threshold. The second judgment unit is used to determine whether the grip strength index is less than the preset grip strength threshold if the muscle mass index is less than the first preset muscle mass threshold. The second obesity determination unit is used to determine the obesity type of the obese subject as a preset sarcopenic obesity type if the grip strength index is less than a preset grip strength threshold. The third obesity determination unit is used to determine that the obesity type of the obese subject is a preset hidden obesity type if the grip strength index is not less than a preset grip strength threshold.

5. The exercise prescription generation device according to claim 2, characterized in that, The preliminary generation module includes: The first muscle strength determination unit is used to determine the muscle strength level of the obese subject as a preset good muscle strength type if the muscle mass index is not less than the first preset muscle mass threshold. The second muscle strength determination unit is used to determine the muscle strength level of the obese subject as a preset normal muscle strength type if the muscle mass index is less than the first preset muscle mass threshold and not less than the second preset muscle mass threshold. The third muscle strength determination unit is used to determine the muscle strength level of the obese subject as a preset low muscle strength type if the muscle mass index is less than the second preset muscle mass threshold.

6. The exercise prescription generation device according to any one of claims 1 to 5, characterized in that, The types of exercise include aerobic exercise and resistance training. The prescription generation module includes: An assessment unit is used to obtain a multi-dimensional exercise risk assessment of the obese subject to obtain assessment results; The aerobic exercise parameter determination unit is used to determine the upper and lower limits of target heart rate in the aerobic exercise type parameters based on the evaluation results, and to determine the intensity percentage in the aerobic exercise type parameters using the body-muscle joint index obtained by weighted fusion of the body composition characteristics and the muscle strength characteristics. The resistance training parameter determination unit is used to determine the resistance training type parameters in the preliminary exercise prescription based on the evaluation results and the muscle strength level.

7. The exercise prescription generation device according to claim 1, characterized in that, The exercise prescription generation device further includes: The visualization unit is used to visualize the target exercise prescription to generate one or more visualization results, such as body composition radar chart, muscle strength comparison chart, exercise intensity curve, and advanced route chart. The video generation unit is used to generate a guidance video corresponding to the target exercise prescription; wherein the guidance video includes a warm-up exercise video, a main training exercise video, and a cool-down exercise video.

8. A method for generating an exercise prescription, characterized in that, Applied to computer devices, including: Body composition data and muscle strength data of obese subjects were collected simultaneously. The body composition data and muscle strength data were preprocessed and feature extracted to obtain body composition features and muscle strength features. The body composition characteristics and muscle strength characteristics are hierarchically determined to identify the obesity type and muscle strength level of the obese subject, and a preliminary exercise prescription is generated based on the combination of the obesity type and the muscle strength level; wherein, the preliminary exercise prescription includes exercise type and exercise ratio; The aerobic exercise type parameter in the preliminary exercise prescription is determined by using the weighted fusion of the body composition features and the muscle strength features to obtain the body-muscle joint index, and the resistance training type parameter in the preliminary exercise prescription is determined according to the muscle strength level, so as to generate the target exercise prescription for the current execution cycle based on the aerobic exercise type parameter and the resistance training type parameter; Obtain the reassessment results generated when the obese subject performs the target exercise prescription; The target exercise prescription is adjusted based on the review results to obtain the target exercise prescription for the next execution cycle.

9. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the steps of the exercise prescription generation method as described in claim 8.

10. A computer-readable storage medium, characterized in that, Used to store a computer program; wherein, when the computer program is executed by a processor, it implements the steps of the exercise prescription generation method as described in claim 8.

Images