User personalized cardiopulmonary function evaluation method based on VR fitness bicycle

Abstract

The invention discloses a user personalized cardiopulmonary function evaluation method based on a VR fitness bicycle, and belongs to the technical field of exercise health management, and the method comprises the following steps: S1, a user selects a cardiopulmonary function evaluation module in a system, and prepares to start a test; s2, preparing questionnaire data according to the gender, age, height, weight and physical activity of the user, and performing virtual rider matching; s3, after the test is started, the user stares at a matched virtual target rider in the system along with the VR bicycle test program, and bicycle riding is carried out for 12 minutes, so that the user can ride the farthest distance as much as possible; s4, acquiring riding speed, riding distance and riding output power data in the exercise process of the user; s5, the maximum oxygen uptake is calculated according to a formula obtained through calculation of a large number of tests in the early stage, and the cardio-pulmonary function is evaluated; according to the method, a professional sports laboratory or a medical institution is not needed for testing, the method is simple and convenient, meanwhile, the testing scheme has adaptability, real-time visual feedback of a VR virtual target rider is utilized, the potential of a user is stimulated, and the cardiopulmonary assessment accuracy is improved.

Description

Technical Field

[0001] This invention belongs to the field of sports and health management technology, specifically relating to a personalized cardiopulmonary function assessment method based on a VR exercise bike. Background Technology

[0002] Cardiopulmonary function is one of the important indicators of human health. It reflects the ability of the heart and lungs to work together and is of vital importance to personal health management, exercise training and disease prevention.

[0003] In terms of health management, good cardiopulmonary function is the foundation for maintaining normal metabolism and physiological functions. People with strong cardiopulmonary function can more efficiently deliver oxygen and nutrients to various tissues and organs, keeping their bodies in good condition and energetic enough to cope with various challenges in daily life and work. Conversely, poor cardiopulmonary function may lead to problems such as fatigue, shortness of breath, and decreased immunity, affecting quality of life. Cardiopulmonary function assessment allows people to understand their physical condition in a timely manner, discover potential health risks, and take corresponding measures to adjust and improve, such as a reasonable diet, appropriate exercise, quitting smoking and limiting alcohol consumption, thereby achieving effective health management.

[0004] In terms of sports training, different sports and intensities have different requirements for cardiopulmonary function. Cardiopulmonary assessment can help coaches and athletes determine the appropriate type, intensity, and duration of exercise for each individual, and avoid sports injuries or over-fatigue caused by improper exercise.

[0005] In terms of disease prevention, poor cardiopulmonary function is an important risk factor for chronic diseases such as cardiovascular diseases, respiratory diseases, and metabolic diseases. Cardiopulmonary function can detect abnormalities in a timely manner and take active intervention measures, such as improving lifestyle and carrying out rehabilitation training, which can effectively reduce the risk of developing chronic diseases and delay the progression of diseases.

[0006] Current cardiopulmonary assessment methods include direct and indirect methods. Direct methods require the body to reach its limits, which is highly dangerous and is generally conducted by professional sports laboratories or medical institutions. Indirect methods require guidance from testers, and the implementation of test protocols varies. Test results are highly dependent on heart rate and have low measurement accuracy, which in turn leads to inaccurate exercise plans and poor personalized exercise guidance.

[0007] Therefore, a user-specific cardiopulmonary function assessment method based on VR exercise bikes is designed to be convenient and accurate, and personalized fitness plans can be provided based on this method to solve the above problems. Summary of the Invention

[0008] To address the problems mentioned in the background section, this invention provides a personalized cardiopulmonary function assessment method based on a VR exercise bike. This method is simple and convenient, requiring no professional sports laboratory or medical institution for testing, and its adaptive testing scheme improves the accuracy of cardiopulmonary assessment.

[0009] To achieve the above objectives, the present invention provides the following technical solution: a personalized cardiopulmonary function assessment method based on a VR exercise bike, comprising the following steps:

[0010] S1: The user selects the cardiopulmonary function assessment module within the system and prepares to start the test;

[0011] S2: Prepare questionnaire data based on user gender, age, height, weight, and physical activity to match virtual riders;

[0012] S3: After the test begins, the user follows the VR bike test program, keeps a close eye on the virtual target rider matched in the system, and rides the bike for 12 minutes, trying to ride the farthest distance possible.

[0013] S4: Acquire data on the user's cycling speed, cycling distance, and cycling power output during exercise;

[0014] S5: Based on the formula derived from extensive prior testing, the maximum oxygen uptake is calculated, and cardiopulmonary function is assessed.

[0015] Furthermore, the specific steps for virtual rider matching in step S2 include:

[0016] S201: Retrieve the user's physical activity preparation questionnaire results. If one or more questions are answered "yes", the user is considered not to meet the low-risk group criteria. If the user does not meet the low exercise risk criteria, they will be refused entry into the cardiopulmonary function assessment module and will be directly redirected to the health exercise program. Other test takers will warm up for 30 seconds before the cardiopulmonary test, including setting the default test resistance level based on gender, age, height, and weight data, and allowing test takers to change to a suitable resistance level within 30 seconds.

[0017] S202: After the user determines the resistance level in the test, the system sets the data of 4 virtual cyclists based on gender, age, height and weight data, as well as the minimum standards for different levels of maximum oxygen uptake. These data correspond to the maximum oxygen uptake level table, including the excellent threshold value, the good threshold value, the moderate threshold value and the poor threshold value. The system also sets the constant riding speed for 12 minutes.

[0018] Furthermore, in step S3, the user enters the test interface, where the screen displays the meaning of the levels represented by the four virtual riders. During the 12-minute ride, the tester can monitor their own level at any time to adjust their riding strategy, maximize their ability to reach the farthest distance, and ensure that the test is effective and accurate.

[0019] Furthermore, in step S4, the steps for obtaining cycling speed, cycling distance, and cycling output power include:

[0020] S401: Hall effect sensors installed on the wheel positions of VR exercise bikes;

[0021] S402: During VR exercise on a stationary bike, the Hall sensor collects the wheel's rotation speed and number of rotations in real time;

[0022] S403: Based on wheel rotation speed, calculate cycling speed, cycling distance, cycling output power, and total power gained in 12 minutes of cycling. The expression is:

[0023] Angular velocity to rotational speed conversion:

[0024] w=2πn

[0025] Where: n represents the wheel speed, in revolutions per second;

[0026] Relationship between linear velocity and angular velocity:

[0027] v = w × r

[0028] Where: v represents the riding speed, in m / s; w represents the wheel angular velocity, in rad / s; r represents the wheel radius, in m;

[0029] Cycling output power:

[0030] P = F × v

[0031] Where: P is the output power, in W; F is the resistance value, in N;

[0032] Total effort calculation for 12-minute cycling:

[0033]

[0034] Where: W is total work, unit: J; P i is the power value at the i-th sampling point, in W; n is the number of samplings.

[0035] Further, in step S5, the actual values ​​of VO2 max are obtained by directly measuring the VO2 max of people of different ages and genders in the early stage. Machine learning is used to fit the equation, with 85% of the data used for fitting and 15% used for prediction and verification. After dividing the age groups into 20-29, 30-39, 40-49, 50-59, 60-69, and ≥70, tests are conducted with no less than 100 people in each group. Based on the measured VO2 max values, equations are fitted according to different genders, with independent variables being height H, weight BW, and total power of 12 minutes of cycling W, and the dependent variable being VO2 max. Finally, a third-order polynomial fitting equation with good fitting degree and predictive ability is obtained. The final formula for calculating VO2 max is:

[0036] VO2max = f + a1W + b1H + c1BW + a2W 2 +b2H 2 +c2BW 2 +a3W×H+b3W×BW+c3H×

[0037] BW+a3W 3 +b3H 3 +c3BW 3

[0038] Where: a1, a2, a3, b1, b2, b3, c1, c2, c3, and f are fitting coefficients.

[0039] Compared with the prior art, the beneficial effects of the present invention are:

[0040] This invention does not require testing in a professional sports laboratory or medical institution, making it simple and convenient. At the same time, the testing scheme is adaptive, utilizing real-time visual feedback from VR virtual target riders to stimulate user potential and improve the accuracy of cardiopulmonary assessment. Detailed Implementation

[0041] The technical solutions of the present invention will be clearly and completely described below with reference to the embodiments of the present invention. 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.

[0042] This invention provides the following technical solution: a personalized cardiopulmonary function assessment method based on a VR exercise bike, comprising the following steps:

[0043] S1: The user selects the cardiopulmonary function assessment module within the system and prepares to start the test;

[0044] S2: Prepare questionnaire data based on user gender, age, height, weight, and physical activity to match virtual riders;

[0045] S3: After the test begins, the user follows the VR bike test program, keeps a close eye on the virtual target rider matched in the system, and rides the bike for 12 minutes, trying to ride the farthest distance possible.

[0046] S4: Acquire data on the user's cycling speed, cycling distance, and cycling power output during exercise;

[0047] S5: Based on the formula derived from extensive prior testing, the maximum oxygen uptake is calculated, and cardiopulmonary function is assessed.

[0048] Specifically, the steps for virtual rider matching in step S2 include:

[0049] S201: Retrieve the user's physical activity preparation questionnaire results. If one or more questions are answered "yes", the user is considered not to meet the low-risk group criteria. If the user does not meet the low exercise risk criteria, they will be refused entry into the cardiopulmonary function assessment module and will be directly redirected to the health exercise program. Other test takers will warm up for 30 seconds before the cardiopulmonary test, including setting the default test resistance level based on gender, age, height, and weight data, and allowing test takers to change to a suitable resistance level within 30 seconds.

[0050] Table 1 Physical Preparation Questionnaire

[0051]

[0052]

[0053] S202: After the user determines the resistance level in the test, the system sets the data of 4 virtual cyclists based on gender, age, height and weight data, as well as the minimum standards of different levels of maximum oxygen uptake, and sets the constant speed for 12 minutes of riding, corresponding to the maximum oxygen uptake level table, including the excellent threshold value, the good threshold value, the moderate threshold value and the poor threshold value.

[0054] Table 2 Maximum Oxygen Uptake Levels

[0055]

[0056] Note: The table above is based on The submaximal test method (1960) was derived.

[0057] Specifically, in step S3, the user enters the test interface, and the screen displays the meaning of the levels represented by the four virtual riders. During the 12-minute ride, the tester can pay attention to their own level at any time to adjust their riding strategy, maximize their ability to reach the farthest distance, and ensure that the test is effective and accurate.

[0058] Specifically, in step S4, the steps for obtaining cycling speed, cycling distance, and cycling output power include:

[0059] S401: Hall effect sensors installed on the wheel positions of VR exercise bikes;

[0060] S402: During VR exercise on a stationary bike, the Hall sensor collects the wheel's rotation speed and number of rotations in real time;

[0061] S403: Based on wheel rotation speed, calculate cycling speed, cycling distance, cycling output power, and total power gained in 12 minutes of cycling. The expression is:

[0062] Angular velocity to rotational speed conversion:

[0063] w=2πn

[0064] Where: n represents the wheel speed, in revolutions per second;

[0065] Relationship between linear velocity and angular velocity:

[0066] v = w × r

[0067] Where: v represents the riding speed, in m / s; w represents the wheel angular velocity, in rad / s; r represents the wheel radius, in m;

[0068] Cycling output power:

[0069] P = F × v

[0070] Where: P is the output power, in W; F is the resistance value, in N;

[0071] Total effort calculation for 12-minute cycling:

[0072]

[0073] Where: W is total work, unit: J; P i is the power value at the i-th sampling point, in W; n is the number of samplings.

[0074] Specifically, in step S5, the actual values ​​of VO2max are obtained by directly measuring the VO2max of people of different ages and genders. Machine learning is used to fit the equation, with 85% of the data used for fitting and 15% used for prediction and validation. After dividing the age groups into 20-29, 30-39, 40-49, 50-59, 60-69, and ≥70, tests are conducted with no fewer than 100 people in each group. Based on the measured VO2max values, equations are fitted according to gender, with independent variables being height (H), weight (BW), and total power (W) of 12 minutes of cycling, and the dependent variable being VO2max. Finally, a third-order polynomial fitting equation with good fitting and predictive ability is obtained. The final formula for calculating VO2max is:

[0075] VO2max = f + a1W + b1H + c1BW + a2W 2 +b2H 2 +c2BW 2 +a3W×H+b3W×BW+c3H×

[0076] BW+a3W 3 +b3H 3 +c3BW 3

[0077] Where: a1, a2, a3, b1, b2, b3, c1, c2, c3, and f are fitting coefficients.

[0078] We also propose an adaptive personalized motion scheme generation system, the specific steps of which are as follows:

[0079] S6: Collect and analyze users' basic information, test data, fitness goals, and other information;

[0080] S7: Perform data analysis on users and generate an initial exercise plan, setting two virtual cyclists as the upper and lower limits of the plan's intensity;

[0081] S8: After the initial implementation of the program, the program will be adjusted to individual needs based on post-exercise feedback;

[0082] S9: Long-term plan archive.

[0083] Specifically, the basic information in step S6 includes:

[0084] Basic information: gender, age, height, weight;

[0085] Test data: The results and level of the most recent maximum oxygen uptake test;

[0086] Fitness Goals: The system offers three options: "Exercise for Fat Loss", "Improve Cardiopulmonary Health", and "Health and Rehabilitation". If the physical activity preparation questionnaire indicates that there is a risk of exercise, the user will be directed to the health and rehabilitation module.

[0087] Specifically, the initial scheme generation steps in step S7 are as follows:

[0088] For exercise to reduce fat and improve cardiorespiratory function, follow the contents of Tables 3 and 4, and determine the parameters of the initial exercise program in the "entry line" column according to the cardiorespiratory level. The resistance setting is the same as the resistance selected during the cardiorespiratory function test.

[0089] Health and rehabilitation: Based on the upper limit of the "very poor" level for the same age and gender, the estimated maximum oxygen uptake is used, and the resistance level is fixed to recommend exercise intensity.

[0090] Table 3 Exercise-Based Fat Loss Program Gradient Table

[0091]

[0092]

[0093] Table 4 Gradient Table of Increasing Cardiopulmonary Exercise Programs

[0094]

[0095] Formulas for calculating cycling speed in Tables 3 and 4:

[0096]

[0097] P = F × v

[0098] Where: P is the output power, unit: W; BW is the body weight, unit: kg; F is the resistance value, unit: N;

[0099] Specifically, the motion scheme adjustment and generation steps in step S8 are as follows:

[0100] When the program is first implemented, the upper and lower limits of the exercise intensity range are set to the virtual rider. If the user exceeds the upper limit, a "Danger, slow down" message is displayed. Training data and post-training evaluation are collected after the first training session.

[0101] Training data: Calculate the VO2 value level for the current ride;

[0102] Post-training evaluation: Intensity (high, moderate, low);

[0103] Adjustment logic:

[0104] Adjust according to the gradient table: if the evaluation after training is "large", then reduce the gradient by 2 for recommendation; if it is already 1-2 gradients, then keep the lowest gradient and execute.

[0105] If the post-training evaluation is "moderate," a program recommendation will be made based on the current VO2 level; if the post-training evaluation is "low," the recommendation will be increased by 1 level.

[0106] Specifically, the motion scheme archiving step in step S9 is as follows:

[0107] If the training plan is not implemented within 1 month, all data will be archived and will not be referenced or adjusted again. The cardiopulmonary function test must be re-executed before entering the training mode. For the rest of the time, the training will be increased step by step according to the gradient table.

[0108] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A personalized cardiopulmonary function assessment method based on a VR exercise bike, characterized in that, Includes the following steps: S1: The user selects the cardiopulmonary function assessment module within the system and prepares to start the test; S2: Prepare questionnaire data based on user gender, age, height, weight, and physical activity to match virtual riders; S3: After the test begins, the user follows the VR bike test program, keeps a close eye on the virtual target rider matched in the system, and rides the bike for 12 minutes, trying to ride the farthest distance possible. S4: Acquire data on the user's cycling speed, cycling distance, and cycling power output during exercise; S5: Based on the formula derived from extensive prior testing, the maximum oxygen uptake is calculated, and cardiopulmonary function is assessed.

2. The personalized cardiopulmonary function assessment method based on a VR exercise bike according to claim 1, characterized in that: The specific steps for virtual rider matching in step S2 include: S201: Retrieve the user's physical activity preparation questionnaire results; one or more questions were answered correctly. If the answer is "yes", it means that the testee does not meet the criteria for low-risk individuals. If the testee does not meet the criteria for low exercise risk, they will be refused entry into the cardiopulmonary function assessment module and will be directly redirected to the health exercise program. Other testees will have 30 seconds to warm up before the cardiopulmonary test, including setting the default resistance level based on their gender, age, height and weight data, and allowing them to change to a suitable resistance level within 30 seconds. S202: After the user determines the resistance level in the test, the system sets the data of 4 virtual cyclists based on gender, age, height and weight data, as well as the minimum standards for different levels of maximum oxygen uptake. These data correspond to the maximum oxygen uptake level table, including the excellent threshold value, the good threshold value, the moderate threshold value and the poor threshold value. The system also sets the constant riding speed for 12 minutes.

3. The personalized cardiopulmonary function assessment method based on a VR exercise bike according to claim 2, characterized in that: In step S3, the user enters the test interface, where the screen displays the meaning of the levels represented by the four virtual riders. During the 12-minute ride, the tester can monitor their own level at any time to adjust their riding strategy, maximize their ability to reach the farthest distance, and ensure that the test is effective and accurate.

4. The personalized cardiopulmonary function assessment method based on a VR exercise bike according to claim 3, characterized in that: In step S4, the steps for obtaining cycling speed, cycling distance, and cycling output power include: S401: Hall effect sensors installed on the wheel positions of VR exercise bikes; S402: During VR exercise on a stationary bike, the Hall sensor collects the wheel's rotation speed and number of rotations in real time; S403: Based on wheel rotation speed, calculate cycling speed, cycling distance, cycling output power, and total power gained in 12 minutes of cycling. The expression is: Angular velocity to rotational speed conversion: w = 2πn Where: n represents the wheel speed, in revolutions per second; Relationship between linear velocity and angular velocity: v = w × r Where: v represents the riding speed, in m / s; w represents the wheel angular velocity, in rad / s; r represents the wheel radius, in m; Cycling output power: P = F × v Where: P is the output power, in W; F is the resistance value, in N; Total effort calculation for 12-minute cycling: Where: W is total work, unit: J; P i is the power value at the i-th sampling point, in W; n is the number of samplings.

5. The personalized cardiopulmonary function assessment method based on a VR exercise bike according to claim 4, characterized in that: In step S5, the actual values ​​of VO2 max are obtained by directly measuring the VO2 max of people of different ages and genders. Machine learning is used to fit the equation, with 85% of the data used for fitting and 15% used for prediction and validation. After dividing the age groups into 20-29, 30-39, 40-49, 50-59, 60-69, and ≥70, tests are conducted with no fewer than 100 people in each group. Based on the measured VO2 max values, equations are fitted according to gender, with independent variables being height (H), weight (BW), and total energy (W) of 12 minutes of cycling, and the dependent variable being VO2 max. Finally, a third-order polynomial fitting equation with good fit and predictive ability is obtained. The final formula for calculating VO2 max is: VO2max=f+a1W+b1H+c1BW+a2W 2 +b2H 2 +c2BW 2 +a3W×H+b3W×BW+c3H× BW+a3W 3 +b3H 3 +c3BW 3 Where: a1, a2, a3, b1, b2, b3, c1, c2, c3, and f are fitting coefficients.

Images