Personalized exercise prescription generation method based on analytic hierarchy process

Abstract

The invention provides a personalized exercise prescription generation method based on an analytic hierarchy process, which comprises the following steps of: acquiring body index information, psychological state information, exercise preference information and exercise environment information of a user, determining a physiological health index, a psychological health index, environment suitability and user preference of the user according to the collected user information, and recommending a plurality of candidate exercises; constructing an analytic hierarchy process evaluation model based on four factors of a physiological health index, a psychological health index, environmental suitability and user preference of the user so as to comprehensively score candidate motions; an exercise prescription is generated for the user according to the comprehensive score of the candidate exercises, and parameters in the exercise prescription comprise recommended exercises, exercise intensity, exercise frequency and duration; and acquiring exercise execution data and tracking feedback data of the user, and adjusting parameters in the current exercise prescription.

Description

Technical Field

[0001] The present invention relates to the technical field of health management, and in particular to a method for generating personalized exercise prescriptions based on a hierarchical analysis method. Background Art

[0002] With the accelerated pace of modern life and the increasing work pressure, sub-health problems caused by long-term sitting and lack of exercise are becoming increasingly prominent. This problem is particularly significant among groups that do intensive mental work. This group generally has characteristics such as fragmented exercise time, high work pressure, and high risk of emotional exhaustion. Scientific and reasonable exercise intervention has become an important means to improve physical and mental health and relieve occupational fatigue.

[0003] However, traditional exercise prescriptions have the following limitations: First, most plans are based on a single physical indicator (such as BMI or heart rate), lacking comprehensive consideration of the user's psychological state, exercise preferences, and environmental conditions; second, the prescription generation process relies on the physician's experience and judgment, lacking the support of a quantitative decision-making model, resulting in insufficient personalization of the plan; finally, existing systems generally adopt a static recommendation model and are unable to dynamically adjust the plan based on user feedback, making it difficult to ensure long-term intervention effects. Although some current studies have attempted to improve exercise recommendations by combining wearable device data or questionnaires, there are still defects such as data dimensionality fragmentation and a highly subjective decision-making process. For example, existing systems often ignore the impact of psychological state on exercise tolerance, or fail to consider the constraints of environmental factors such as weather and venue on exercise feasibility, resulting in a poor match between recommended plans and actual needs.

[0004] At present, there is an urgent need for an intelligent exercise prescription generation method that can integrate multi-dimensional data and achieve dynamic optimization. Summary of the Invention

[0005] To solve the problems existing in the prior art, the present invention provides a method for generating personalized exercise prescriptions based on the analytic hierarchy process, comprising the following steps:

[0006] Step 1: Collect the user's physical indicator information, psychological state information, exercise preference information, and exercise environment information, and determine the user's physiological health indicators, psychological health indicators, environmental adaptability, and user preferences based on the collected user information, and recommend several candidate exercises. The physical indicator information includes height, weight, resting heart rate, and maximum heart rate; the psychological state information is the result of completing the occupational burnout questionnaire; the exercise preference information includes exercise experience, preferred exercise type and intensity; and the exercise environment information includes weather conditions, available sports venues, and sports equipment.

[0007] Step 2: Construct an analytic hierarchy process evaluation model based on the user's physiological health indicators, mental health indicators, environmental adaptability, and user preferences to comprehensively score the candidate sports;

[0008] Step 3: Generate an exercise prescription for the user based on the comprehensive score of the candidate exercises, wherein the parameters in the exercise prescription include recommended exercise, exercise intensity, exercise frequency and duration;

[0009] Step 4: Obtain the user's exercise execution data and tracking feedback data, and adjust the parameters in the current exercise prescription according to the dynamic adjustment rules.

[0010] Optionally, in step 1, the user's physiological health indicators, mental health indicators, environmental adaptability, and user preferences are determined based on the collected user information, and several candidate sports are recommended, including:

[0011] Calculates body mass index based on the user's height and weight;

[0012] Emotional exhaustion scores were calculated based on the results of the occupational burnout inventory;

[0013] The body mass index is used as a physiological health indicator, and the emotional exhaustion score is used as a mental health indicator. The physiological health indicators, mental health indicators, exercise environment information and exercise preference information are matched with the preset physiological health recommendation rules, mental health recommendation rules, environmental adaptability recommendation rules and user preference recommendation rules respectively to obtain several candidate exercises.

[0014] Optionally, step 2 specifically includes:

[0015] Step 2.1: Construct an analytic hierarchy process evaluation model, which includes three levels: goal level, criterion level, and solution level. The goal level is to improve the user's fatigue state. The criterion level includes four factors: physiological health indicators, mental health indicators, environmental adaptability, and user preferences. The solution level includes the generated exercise prescription.

[0016] Step 2.2: Compare the four factors of physiological health indicators, mental health indicators, environmental adaptability, and user preferences in pairs through expert scoring to obtain a judgment matrix;

[0017] Step 2.3: Use the eigenvector method to calculate the weights of the four factors: physiological health indicators, mental health indicators, environmental adaptability, and user preferences. Verify the logical rationality of the expert ratings using the judgment matrix consistency ratio. If the verification fails, adjust the weights, automatically triggering the expert to re-rating or activate the backup weight library.

[0018] Step 2.4: The user scores the performance of each candidate sport under the physiological health recommendation rule, the mental health recommendation rule, the environmental adaptability recommendation rule, and the user preference recommendation rule, and the comprehensive score of each candidate sport is calculated based on the user score and the weight values ​​of the four factors.

[0019] Optionally, step 3 specifically includes:

[0020] Step 3.1: Select a preset number of exercises based on the overall score from high to low;

[0021] Step 3.2: Determine the intensity and frequency of the selected exercise according to the exercise intensity and frequency calculation rules, wherein the exercise intensity and frequency calculation rules are as follows:

[0022] The target heart rate (THR) intensity indicator range and the perceived exertion (RPE) indicator range in the exercise intensity are determined based on the user's exercise experience level. The target heart rate (THR) intensity indicator range and the perceived exertion (RPE) indicator range are preset based on the user's exercise experience level. The THR indicator range is calculated based on the target heart rate (THR) intensity indicator range using the Karvonen formula:

[0023] THR = [(maximum heart rate - resting heart rate) × target heart rate THR intensity] + resting heart rate

[0024] Recommend exercise frequency and duration based on the user's exercise experience level, where the exercise frequency and duration are preset based on the user's exercise experience level.

[0025] Step 3.3: The user adjusts the corresponding parameters based on the current prescription according to his or her own situation.

[0026] Optionally, step 4 specifically includes:

[0027] Step 4.1: Obtaining the user's physical index information, psychological state information, and questionnaire feedback data after executing the exercise prescription, wherein the questionnaire feedback data includes the actual frequency of exercise completion and RPE (Rated Perceived Exertion);

[0028] Step 4.2: Calculating the user's body mass index and body fat percentage after the exercise prescription is executed based on the user's physical indicator information after the exercise prescription is executed;

[0029] Step 4.3: Calculate the ratio of the user's actual completion frequency to the exercise frequency in the exercise prescription to obtain the exercise adherence rate (AR), and use the perceived exertion (RPE) as the subjective fatigue level.

[0030] Step 4.4: Adjust the parameters in the current exercise prescription based on the user's physical indicator information, psychological state information, body mass index, body fat percentage, exercise persistence rate AR and subjective fatigue after executing the exercise prescription.

[0031] Beneficial effects of the present invention:

[0032] The present invention provides a personalized exercise prescription generation method based on the hierarchical analysis method, which collects the user's physical indicator information, psychological state information, exercise preference information and exercise environment information, and quickly generates a personalized exercise prescription. The personalized exercise prescription is generated based on the hierarchical analysis method and related recommendation rules, and the exercise type, intensity and frequency are recommended to the user for selection. The exercise prescription is dynamically adjusted and optimized according to the user's exercise execution data and user feedback data, thereby further reducing the user's fatigue state and improving the user's health. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0034] Figure 1 A flowchart of a method for generating personalized exercise prescriptions based on the analytic hierarchy process provided by the present invention;

[0035] Figure 2 This is the architecture diagram of the hierarchical analysis and evaluation model for personalized exercise prescription.

[0036] Figure 3 Schematic diagram of the weight calculation process of the eigenvector method for personalized exercise prescription. DETAILED DESCRIPTION

[0037] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0038] Numerous studies have been devoted to the intelligent generation of exercise prescriptions. These studies primarily focus on optimizing single-dimensional health indicators, failing to fully consider the advantages of the analytic hierarchy process (AHP) in multi-criteria decision-making and the value of dynamic feedback mechanisms for continuous prescription optimization. Existing research has the following limitations: First, most methods optimize only specific health indicators (such as BMI or heart rate) and lack the systematic integration of multiple factors such as physical health, mental health, environmental adaptability, and user preferences. Second, prescriptions often remain static after generation and fail to dynamically adjust based on real-time feedback from users during execution. Finally, existing systems rarely consider the specific needs of different user groups (such as university teachers and students, among other professional groups), limiting the applicability of recommended solutions.

[0039] In summary, current research on exercise prescription generation still has significant deficiencies. Against the backdrop of increasingly personalized and precise health management needs, there is an urgent need to propose an intelligent exercise prescription generation method based on the Analytic Hierarchy Process (AHP). By building a multi-level evaluation system to enable quantitative decision-making on exercise plans and combining it with a dynamic feedback mechanism to continuously optimize prescription content, this approach can enhance the scientific nature, personalization, and long-term effectiveness of exercise interventions, providing more effective solutions for modern health management.

[0040] like Figure 1 As shown, the embodiment of the present disclosure provides a method for generating a personalized exercise prescription based on the analytic hierarchy process, including:

[0041] Step 1: Collect the user's physical indicator information, psychological state information, exercise preference information, and exercise environment information, and determine the user's physiological health indicators, psychological health indicators, environmental adaptability, and user preferences based on the collected user information, and recommend several candidate exercises. The physical indicator information includes height, weight, resting heart rate, and maximum heart rate; the psychological state information is the result of completing the occupational burnout questionnaire; the exercise preference information includes exercise experience, preferred exercise type and intensity; and the exercise environment information includes weather conditions, available sports venues, and sports equipment.

[0042] In this step, the user's physical indicators, including height, weight, resting heart rate, and maximum heart rate, are obtained through a physical examination. The emotional exhaustion score is calculated based on the results of the user's occupational burnout questionnaire. The user's exercise preference information, including exercise experience, preferred exercise type and intensity, and exercise environment information, including weather conditions, available exercise venues, and exercise equipment, is obtained through user input.

[0043] Furthermore, the body mass index (weight / height 2 ) as a physiological health indicator, and emotional exhaustion score as a mental health indicator. Based on the physiological health indicators, mental health indicators, exercise preference information, and exercise environment information, several candidate exercises are recommended according to the following rules:

[0044] Recommended rules for physical health: Based on the body mass index (BMI) classification, if BMI < 18.5 (underweight), strength training (such as resistance training) or moderate aerobic exercise (such as brisk walking) is recommended; if BMI 18.5 ≤ BMI ≤ 24 (normal), comprehensive exercise (such as yoga, badminton, etc.) is recommended; if BMI > 24 (overweight), low-impact aerobic exercise (such as swimming, elliptical machine, etc.) is recommended;

[0045] Mental health recommendation rules: Recommendations are made based on the emotional exhaustion score: if the score is ≤10, regular exercise (such as badminton, dance, etc.) is recommended; if the score is 10<≤20, stress-relieving exercises (yoga, meditation, stretching, etc.) are added; if the score is >20, meditation, breathing training and other exercises are mandatory.

[0046] Environmental adaptability recommendation rules: Based on the weather conditions and venue and equipment restrictions within two weeks, we recommend: if it is sunny / cloudy, prioritize outdoor sports (such as brisk walking, badminton, etc.); if it is rainy / foggy, prioritize indoor sports (such as yoga, meditation, HIIT home version, etc.); if there is no gym, exclude equipment training and other sports; if there is no swimming pool, exclude swimming and other sports;

[0047] User preference recommendation rules: Based on gender preferences and group individual preferences: add yoga, dance and other options for female users, add strength training, ball games and other sports for male users, recommend group sports for those who like group sports, and recommend individual sports for those who like individual sports.

[0048] In this embodiment, the user is Ms. Liu, and four sets of data are collected about her. Among them, the physical indicator information includes: height 170 cm, weight 50 kg, resting heart rate 72 beats / minute, and maximum heart rate 186 beats / minute; the psychological state information includes: emotional exhaustion score 18 (medium to high, indicating a certain degree of fatigue); the exercise environment information includes: the weather in the next two weeks will be mainly light rain, and the available sports venues include community gyms and park trails; the exercise preference information includes: exercise experience is novice, female preference, and preference for alone exercise.

[0049] According to the recommended rules for physiological health, Ms. Liu's BMII is calculated as 50 / (1.7)²≈17.3, so the recommended exercise types include resistance training and brisk walking;

[0050] According to the mental health recommendation rules, Ms. Liu's emotional exhaustion score is 18, so the recommended exercise types include: yoga, meditation and stretching;

[0051] According to the environmental adaptability recommendation rules, since the weather in the next two weeks is mainly light rain, the only available sports venues are community gyms and park trails. Therefore, swimming and badminton are excluded, and indoor sports are recommended.

[0052] According to the user preference recommendation rules, Ms. Liu is a female and likes to exercise alone;

[0053] According to the above rules, resistance training, brisk walking, yoga, and meditation and stretching are selected as candidate exercises.

[0054] Step 2: Construct an analytic hierarchy process evaluation model based on the user's physiological health indicators, mental health indicators, environmental adaptability, and user preferences to comprehensively score the candidate sports;

[0055] Step 2.1: Construct the AHP evaluation model, such as Figure 2 As shown in the figure, it includes three levels: goal layer, criterion layer and solution layer. Among them, the goal layer is to improve the user's fatigue state, the criterion layer includes four factors: physiological health indicators, mental health indicators, environmental adaptability and user preferences, and the solution layer includes the generated exercise prescriptions;

[0056] Step 2.2: Compare the four factors of physiological health index (A), mental health index (B), environmental adaptability (C), and user preference (D) pairwise through expert scoring to obtain a judgment matrix;

[0057] In this step, a questionnaire survey was conducted among 30 experts. The 19-scale method was used to compare these factors in pairs. The scoring rules are as follows:

[0058] 1: Both factors are equally important;

[0059] 3: One factor is slightly more important than the other;

[0060] 5: One factor is significantly more important than another;

[0061] 7: One factor is strongly more important than another;

[0062] 9: One factor is extremely more important than another;

[0063] 2, 4, 6, 8: intermediate values;

[0064] The following judgment matrix is ​​obtained:

[0065] Table 1 Exercise prescription factor judgment matrix

[0066] Comparison factors A(Physical Health) B (Mental Health) C (Environmental adaptability) D (User Preference) A(Physical Health) 1 1 / 3 2 4 B (Mental Health) 3 1 4 5 C (Environmental adaptability) 1 / 2 1 / 4 1 2 D (User Preference) 1 / 4 1 / 5 1 / 2 1

[0067] Step 2.3: Use the eigenvector method to calculate the weights of the four factors: physiological health indicators, mental health indicators, environmental adaptability, and user preferences. Verify the logical rationality of the expert ratings using the judgment matrix consistency ratio. If the verification fails, adjust the weights, automatically triggering the expert to re-rating or activate the backup weight library.

[0068] In this step, if Figure 3 As shown, the judgment matrix is ​​normalized by column, and then the geometric mean of each row is calculated: GM A =1.260,GM B =2.783,GM C=0.707,GM D =0.398, Sum = GM A +GM B +GM C +GM D =5.148, then based on the average value and sum, the weight value of each factor can be obtained as: W A =GM A / Sum=0.245,W B =GM B / Sum=0,W C =GM C / Sum=0.137,W D =GM D / Sum=0.077.

[0069] The judgment matrix consistency ratio CR is calculated to be 0.0273. The judgment matrix consistency test CR is 0.0273<0.1. It can be considered that the consistency of the judgment matrix is ​​acceptable. Otherwise, the weight adjustment is required, which automatically triggers the expert to re-scoring or activate the backup weight library.

[0070] Step 2.4: The user scores the performance of each candidate sport under the physiological health recommendation rule, the mental health recommendation rule, the environmental adaptability recommendation rule, and the user preference recommendation rule, and the comprehensive score of each candidate sport is calculated based on the user score and the weight values ​​of the four factors.

[0071] In this example, Ms. Liu scores the candidate sports using a 1-5 scale, with higher scores indicating better performance. The scoring results are shown in the following table:

[0072] Table 2 Candidate sports scoring results

[0073] Candidate Movement Physical health (A) Mental Health (B) Environmental adaptability (C) User Preference (D) resistance training 5 3 4 3 Meditation stretching 4 2 3 4 Yoga 3 5 5 5

[0074] Comprehensive score = (A score × 0.245) + (B score × 0.541) + (C score × 0.137) + (D score × 0.077);

[0075] Therefore, the comprehensive score calculation results of each candidate sport are:

[0076] Resistance training: (5 × 0.245) + (3 × 0.541) + (4 × 0.137) + (3 × 0.077) = 1.225 + 1.623 + 0.548 + 0.231 = 3.627;

[0077] Meditation stretching: (4 × 0.245) + (2 × 0.541) + (3 × 0.137) + (4 × 0.077) = 0.980 + 1.082 + 0.411 + 0.308 = 2.781;

[0078] Yoga: (3 × 0.245) + (5 × 0.541) + (5 × 0.137) + (5 × 0.077) = 0.735 + 2.705 + 0.685 + 0.385 = 4.510;

[0079] Brisk walking: (2 × 0.245) + (4 × 0.541) + (5 × 0.137) + (4 × 0.077) = 0.490 + 2.164 + 0.685 + 0.308 = 3.647;

[0080] Ms. Liu's comprehensive score ranking of candidate sports is: yoga>brisk walking>resistance training>meditation stretching.

[0081] Step 3: Generate an exercise prescription for the user based on the comprehensive score of the candidate exercises, wherein the parameters in the exercise prescription include recommended exercise, exercise intensity, exercise frequency and duration;

[0082] Step 3.1: Select a preset number of exercises based on the overall score from high to low;

[0083] In this step, based on the comprehensive scores of the candidate sports, multiple sports with the highest scores are selected. If the player is a novice, two sports are recommended; otherwise, three sports are recommended.

[0084] In this embodiment, Ms. Liu is a novice, so the first two exercises are recommended: yoga and brisk walking.

[0085] Step 3.2: Determine the intensity and frequency of the selected exercise according to the exercise intensity and frequency calculation rules, wherein the exercise intensity and frequency calculation rules are as follows:

[0086] The target heart rate (THR) intensity index range and the perceived exertion (RPE) index range in exercise intensity are determined based on the user's exercise experience level: 50%-60% THR and 9-11 RPE are recommended for beginners (no exercise habits); 60%-80% THR and 12-14 RPE are recommended for advanced users (users with exercise habits); and 80%-90% THR and 15-17 RPE are recommended for advanced athletes. The THR index range is calculated based on the target heart rate (THR) intensity index range using the Karvonen formula:

[0087] THR = [(maximum heart rate - resting heart rate) × target heart rate THR intensity] + resting heart rate

[0088] The frequency and duration of exercise are recommended based on the user's level of exercise experience. For beginners, a plan of 20 minutes three times a week is recommended; for advanced users, a plan of 60 minutes six times a week is recommended; and for advanced users, a plan of 90 minutes nine times a week is recommended.

[0089] In this example, Ms. Liu is a novice, so a program of 50%-60% THR, 9-11 RPE, and 20 minutes three times a week is recommended.

[0090] Step 3.3: The user adjusts the corresponding parameters based on the current prescription according to his or her own situation.

[0091] In this embodiment, Ms. Liu did not adjust the parameters. Therefore, Ms. Liu's final personalized exercise prescription includes: brisk walking requirements 3 times a week, 20 minutes / time, RPE = 9-11 (target heart rate 128.5-139.8bpm), yoga requirements 3 times a week, 20 minutes / time, RPE = 9-11 (target heart rate 128.5-139.8bpm).

[0092] Step 4: Obtain the user's exercise execution data (through physiological monitoring devices, such as smart bracelets, height and weight scales, etc., to collect resting heart rate, height and weight data after exercise) and tracking feedback data (obtain feedback data through questionnaires), and adjust the parameters in the current exercise prescription according to dynamic adjustment rules.

[0093] Step 4.1: Obtaining the user's physical index information, psychological state information, and questionnaire feedback data after executing the exercise prescription, wherein the questionnaire feedback data includes the actual frequency of exercise completion and RPE (Rated Perceived Exertion);

[0094] Step 4.2: Calculating the user's body mass index and body fat percentage after the exercise prescription is executed based on the user's physical indicator information after the exercise prescription is executed;

[0095] Step 4.3: Calculate the ratio of the user's actual completion frequency to the exercise frequency in the exercise prescription to obtain the exercise adherence rate (AR), and use the perceived exertion (RPE) as the subjective fatigue level.

[0096] Step 4.4: Adjust the parameters in the current exercise prescription based on the user's physical indicator information, psychological state information, body mass index, body fat percentage, exercise adherence rate AR, and subjective fatigue after executing the exercise prescription, as follows:

[0097] (1) After the user executes the exercise prescription, whether the user's physical index information, psychological state information, body mass index, body fat percentage, exercise persistence rate AR and subjective fatigue meet the following conditions; if so, the adjustment needs to be stopped and the user is prompted to review the data and intervene; otherwise, execute step (2).

[0098] Case 1: The resting heart rate suddenly rises by ≥10bpm. This condition indicates that the user is overly tired. To ensure the user's physical and mental health, it is necessary to prompt the user to confirm whether the data is true. If true, the user is recommended to undergo a physical examination.

[0099] Case 2: If the RPE is continuously ≥15 and accompanied by a decline in sleep quality, it indicates that the body may be in a state of overtraining syndrome (OTS) or chronic stress. The current exercise should be stopped immediately and the user is advised to rest for a week.

[0100] Case 3: BMI decline rate > 1.5kg / week, indicating that the user may be involved in health risks, improper weight loss strategies or potential diseases. If the BMI decline rate is true, the user is recommended to undergo a physical examination.

[0101] Case 4: The user directly stops executing the exercise prescription and takes a rest;

[0102] (2) Adjust the current exercise prescription based on exercise adherence rate (AR) and subjective fatigue:

[0103] Adjust the intensity of a certain type of exercise based on the level of adherence rate (AR = actual number of times completed / recommended number of times × 100%): if AR < 30%, switch to another preferred exercise; if 30% ≤ AR < 50%, reduce the difficulty and reduce one session per week; if 50% ≤ AR < 70%, maintain the current plan but slightly adjust the intensity by RPE + 1; if 70% ≤ AR < 90%, increase the duration by + 5 minutes per session; if AR ≥ 90%, increase the intensity by THR + 5%;

[0104] In this embodiment, according to Ms. Liu's feedback, brisk walking AR = 5 / 6 = 83%, so the duration is increased by +5 minutes / time, and yoga AR = 6 / 6 = 100%, so the intensity is increased by THR + 5%;

[0105] (3) The target heart rate is adjusted according to the subjective fatigue level of a certain type of exercise (user-assessed RPE average feedback): if the RPE is continuously <12, it means that the exercise intensity is insufficient, and the target heart rate is increased by +5%; if 12≤RPE<14, it remains unchanged; if the RPE is continuously >14, it means that the exercise intensity is too high, and the target heart rate is reduced by 5%.

[0106] In this embodiment, Ms. Liu's feedback information shows that her RPE is continuously <12, so the target heart rate is increased by +5%;

[0107] (4) Adjust the target heart rate based on the user's resting heart rate: if the resting heart rate decreases by ≥5 bpm, increase the target heart rate by 5%. If this step is repeated with the previous step, ignore this additional step; if the resting heart rate increases by ≥10 bpm, decrease the target heart rate by 5%. If this step is repeated with the previous step, ignore this additional step;

[0108] In this embodiment, if Ms. Liu's feedback indicates that her resting heart rate decreased by ≥5 bpm, the target heart rate is increased by 5%, but this is repeated in step 4.2, so this additional item is ignored.

[0109] (5) Adjust the exercise frequency according to the user's body fat percentage (body fat percentage = weight / height): if the body fat percentage decreases by ≥1%, it remains unchanged; otherwise, the exercise frequency is increased by +1 time / week;

[0110] In this embodiment, Ms. Liu's feedback information shows that her body fat percentage has not changed, so the exercise frequency is +1 time / week.

[0111] (6) Adjust the current exercise prescription based on psychological data: If the emotional exhaustion score increases by ≥3 points, a 10-minute meditation session will be mandatory.

[0112] In this embodiment, in Ms. Liu's feedback, her emotional exhaustion score dropped from 18 to 15, indicating that her mood was relieved, indicating that her mental fatigue was significantly alleviated.

[0113] In this embodiment, Ms. Liu's feedback does not meet the above four conditions. Adjustments are made according to the above steps (2)-(6) to obtain a new exercise prescription: brisk walking 4 times a week, 25 minutes / time, RPE = 9-11 (target heart rate 128.5-139.8bpm); yoga 3 times a week, 20 minutes / time, RPE = 9-11 (target heart rate 134.9-146.8bpm).

[0114] Although the present invention has been disclosed above by way of embodiments, they are not intended to limit the present invention. Any person skilled in the art may make slight changes and modifications without departing from the spirit and scope of the present invention. Therefore, the scope of protection of the present invention shall be determined by the claims.

Claims

1. A method for generating personalized exercise prescription based on analytic hierarchy process, characterized in that: The following steps are involved: Step 1: Collect the user's physical indicator information, psychological state information, exercise preference information, and exercise environment information, and determine the user's physiological health indicators, psychological health indicators, environmental adaptability, and user preferences based on the collected user information, and recommend several candidate exercises. The physical indicator information includes height, weight, resting heart rate, and maximum heart rate; the psychological state information is the result of completing the occupational burnout questionnaire; the exercise preference information includes exercise experience, preferred exercise type and intensity; and the exercise environment information includes weather conditions, available sports venues, and sports equipment. Step 2: Construct an analytic hierarchy process evaluation model based on the user's physiological health indicators, mental health indicators, environmental adaptability, and user preferences to comprehensively score the candidate sports; Step 3: Generate an exercise prescription for the user based on the comprehensive score of the candidate exercises, wherein the parameters in the exercise prescription include recommended exercise, exercise intensity, exercise frequency and duration; Step 4: Obtain the user's exercise execution data and tracking feedback data, and adjust the parameters in the current exercise prescription according to the dynamic adjustment rules.

2. The method for generating personalized exercise prescription based on analytic hierarchy process according to claim 1, characterized in that: In step 1, the user's physiological health indicators, mental health indicators, environmental adaptability, and user preferences are determined based on the collected user information, and several candidate sports are recommended, including: Calculates body mass index based on the user's height and weight; Emotional exhaustion scores were calculated based on the results of the occupational burnout inventory; The body mass index is used as a physiological health indicator, and the emotional exhaustion score is used as a mental health indicator. The physiological health indicators, mental health indicators, exercise environment information and exercise preference information are matched with the preset physiological health recommendation rules, mental health recommendation rules, environmental adaptability recommendation rules and user preference recommendation rules respectively to obtain several candidate exercises.

3. The method for generating personalized exercise prescription based on analytic hierarchy process according to claim 1, characterized in that: The step 2 specifically includes: Step 2.1: Construct an analytic hierarchy process evaluation model, which includes three levels: goal level, criterion level, and solution level. The goal level is to improve the user's fatigue state. The criterion level includes four factors: physiological health indicators, mental health indicators, environmental adaptability, and user preferences. The solution level includes the generated exercise prescription. Step 2.2: Compare the four factors of physiological health indicators, mental health indicators, environmental adaptability, and user preferences in pairs through expert scoring to obtain a judgment matrix; Step 2.3: Use the eigenvector method to calculate the weights of the four factors: physiological health indicators, mental health indicators, environmental adaptability, and user preferences. Verify the logical rationality of the expert ratings using the judgment matrix consistency ratio. If the verification fails, adjust the weights, automatically triggering the expert to re-rating or activate the backup weight library. Step 2.4: The user scores the performance of each candidate sport under the physiological health recommendation rule, the mental health recommendation rule, the environmental adaptability recommendation rule, and the user preference recommendation rule, and the comprehensive score of each candidate sport is calculated based on the user score and the weight values ​​of the four factors.

4. The method for generating personalized exercise prescription based on analytic hierarchy process according to claim 1, characterized in that: The step 3 specifically includes: Step 3.1: Select a preset number of exercises based on the overall score from high to low; Step 3.2: Determine the intensity and frequency of the selected exercise according to the exercise intensity and frequency calculation rules, wherein the exercise intensity and frequency calculation rules are as follows: The target heart rate (THR) intensity indicator range and the perceived exertion (RPE) indicator range in the exercise intensity are determined based on the user's exercise experience level. The target heart rate (THR) intensity indicator range and the perceived exertion (RPE) indicator range are preset based on the user's exercise experience level. The THR indicator range is calculated based on the target heart rate (THR) intensity indicator range using the Karvonen formula: THR = [(maximum heart rate - resting heart rate) × target heart rate THR intensity] + resting heart rate Recommend exercise frequency and duration based on the user's exercise experience level, where the exercise frequency and duration are preset based on the user's exercise experience level. Step 3.3: The user adjusts the corresponding parameters based on the current prescription according to his or her own situation.

5. The method for generating personalized exercise prescription based on analytic hierarchy process according to claim 1, characterized in that: The step 4 specifically includes: Step 4.1: Obtaining the user's physical index information, psychological state information, and questionnaire feedback data after executing the exercise prescription, wherein the questionnaire feedback data includes the actual frequency of exercise completion and RPE (Rated Perceived Exertion); Step 4.2: Calculating the body mass index and body fat percentage of the user after the exercise prescription is executed based on the user's physical indicator information after the exercise prescription is executed; Step 4.3: Calculate the ratio of the user's actual completion frequency to the exercise frequency in the exercise prescription to obtain the exercise adherence rate (AR), and use the perceived exertion (RPE) as the subjective fatigue level. Step 4.4: Adjust the parameters in the current exercise prescription based on the user's physical indicator information, psychological state information, body mass index, body fat percentage, exercise persistence rate AR and subjective fatigue after executing the exercise prescription.

Images