Exercise assisting method and system based on big data

Abstract

The invention provides an exercise assisting method and system based on big data. The method comprises the steps of obtaining personal health data of a user; generating a personalized exercise plan by combining the personal health data and historical exercise records of the user through a big data analysis algorithm; collecting real-time physiological index data of the user by utilizing an internet of things technology and wearable equipment, and comparing the real-time physiological index data with the personalized exercise plan; dynamically adjusting the personalized exercise plan according to the feedback of the real-time physiological index data so as to ensure the safety and effectiveness of exercise; real-time guidance and feedback are provided for a user through intelligent terminal equipment, the safety and effectiveness of exercise can be improved, the exercise experience of the user can also be improved, and the method integrates personal health data, historical exercise records and real-time physiological index data of the user, utilizes a big data analysis algorithm and a machine learning technology, and improves the exercise experience of the user. According to the invention, highly personalized exercise plan generation and dynamic adjustment are realized, so that the exercise effect and experience are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to an exercise assistance method and system based on big data. Background Art

[0002] Although the current big data fitness assistance methods have improved the efficiency and effectiveness of personalized exercise to a certain extent, there are still many shortcomings. Traditional fitness guidance methods often rely on static, one-size-fits-all exercise plans, lack consideration of individual differences, and cannot fully meet the specific needs of different users. In addition, most of the existing fitness assistance systems fail to make full use of the user's real-time physiological index data to dynamically adjust the exercise plan, resulting in poor exercise results or safety risks. Specifically, the existing methods fail to effectively combine big data analysis and machine learning technologies to generate highly personalized exercise plans, which not only limits the adaptability and flexibility of exercise plans, but also fails to fully tap the potential of Internet of Things technology and wearable devices. For example, the existing calorie consumption calculation method is usually relatively simple, ignoring the influence of factors such as age and gender on the heart rate recovery speed, resulting in inaccurate calculation of calorie consumption. In addition, the lack of an effective real-time feedback mechanism is also a shortcoming of the existing technology, which limits the user's self-regulation ability and exercise efficiency during exercise. Summary of the invention

[0003] The embodiments of the present invention provide a big data-based exercise assistance method and system, which can at least solve the technical problems in the prior art that limit the user's self-regulation ability during exercise and the improvement of exercise efficiency.

[0004] A first aspect of an embodiment of the present invention provides an exercise assistance method based on big data, comprising:

[0005] Obtaining the user's personal health data, including age, gender, weight, height, blood pressure, and heart rate;

[0006] Generate a personalized exercise plan through big data analysis algorithms, combining the user's personal health data and historical exercise records;

[0007] Using Internet of Things technology and wearable devices to collect real-time physiological index data of users, and comparing the data with the personalized exercise plan;

[0008] Dynamically adjust the personalized exercise plan according to the feedback of real-time physiological index data to ensure the safety and effectiveness of the exercise;

[0009] Provide real-time guidance and feedback to users through smart terminal devices.

[0010] Furthermore, the personalized exercise plan also includes:

[0011] Recommend appropriate exercise movements and intensity based on the user's goal setting, such as muscle building, fat loss, and endurance improvement;

[0012] Develop reasonable exercise frequency and duration based on the user's exercise preferences and schedule;

[0013] The exercise plan is continuously optimized through machine learning algorithms to adapt to the user's physical changes and development needs.

[0014] Furthermore, the generating of a personalized exercise plan by a big data analysis algorithm includes:

[0015] Analyze the user's personal health data and historical exercise records to determine the user's health status and exercise habits;

[0016] Compare the health status and exercise habits with the user groups in the big data to find similar cases and successful experiences;

[0017] Use cluster analysis, association rule mining and other methods to recommend the most suitable exercise methods and diet suggestions for users;

[0018] Calculate the user's cardiovascular index (CVI), where CVI is defined as:

[0019]

[0020] Among them, HR rest The user's resting heart rate, HR max is the maximum heart rate, which can be estimated by the formula 220-age, where age is the user's age;

[0021] Using the user's historical exercise data, the user's physical recovery function R(t) is fitted by the least squares method, where t is the recovery time. This function describes the trend of the user's physical recovery over time.

[0022] Furthermore, the real-time physiological index data of the user is collected through the Internet of Things technology and wearable devices, including:

[0023] Use wearable devices such as smart bracelets and smart watches to monitor users' heart rate, steps, sleep quality and other data;

[0024] Measure the user's weight, body fat percentage and other information through devices such as smart body fat scales;

[0025] The collected data is transmitted to a cloud server for processing and analysis;

[0026] The user's calorie consumption is calculated based on the user's real-time heart rate data, where the calorie consumption C is defined as:

[0027]

[0028] Where MET is metabolic equivalent, W is the user's weight (kg), T is the exercise time (hours), HR rest The user's resting heart rate, HR max is the maximum heart rate;

[0029] A nonlinear regression model is used to predict the user's heart rate trend over a period of time in the future to predict possible health risks.

[0030] Further, the dynamically adjusting the personalized exercise plan includes:

[0031] Evaluate exercise effects based on users’ real-time physiological indicator data;

[0032] When the user's physiological indicators deviate from the normal range, adjust the intensity and type of exercise;

[0033] Gradually increase the difficulty of exercise after users reach their short-term goals to avoid plateaus;

[0034] Dynamically adjust the intensity and duration of exercise in the exercise plan based on the user's calorie consumption and target consumption;

[0035] Leverage reinforcement learning algorithms to optimize users’ exercise plans to maximize long-term health benefits.

[0036] Furthermore, it also includes: introducing an age adjustment factor and calculating the user's calorie consumption according to the user's real-time heart rate data, wherein the calorie consumption C is defined as:

[0037]

[0038] Where MET is metabolic equivalent, W is the user's weight (kg), T is the exercise time (hours), HR rest The user's resting heart rate, HR max is the maximum heart rate, and α is the age adjustment factor, defined as:

[0039]

[0040] The age adjustment factor takes into account the difference in heart rate recovery speed of users of different age groups to more accurately calculate calorie consumption. The age adjustment factor is used to reflect the difference in heart rate recovery speed of users of different age groups.

[0041] Use nonlinear regression model to predict the user's heart rate trend in the future.

[0042] Furthermore, providing real-time guidance and feedback to users through intelligent terminal devices also includes:

[0043] Providing immersive exercise experiences based on virtual reality (VR) or augmented reality (AR) technology;

[0044] Share users' exercise results through social networks to promote community interaction and support;

[0045] Integrate mental health counseling functions to help users relieve stress and anxiety.

[0046] In a second aspect, an embodiment of the present invention provides an exercise assistance system based on big data, comprising:

[0047] An acquisition module is used to acquire the user's personal health data, wherein the personal health data includes age, gender, weight, height, blood pressure and heart rate;

[0048] A generation module, which is used to generate a personalized exercise plan by combining the user's personal health data and historical exercise records through a big data analysis algorithm;

[0049] A comparison module, for collecting real-time physiological index data of the user using Internet of Things technology and wearable devices, and comparing the data with the personalized exercise plan;

[0050] An adjustment module, used to dynamically adjust the personalized exercise plan according to the feedback of real-time physiological index data to ensure the safety and effectiveness of the exercise;

[0051] The feedback module is used to provide real-time guidance and feedback to users through smart terminal devices.

[0052] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to perform any big data-based exercise assistance as described in the first aspect.

[0053] In a fourth aspect, an embodiment of the present invention further provides a readable storage medium, wherein the readable storage medium stores a computer program, wherein the computer program includes a program code for controlling a process to execute a process, wherein the process includes any one of the big data-based exercise assistance methods described in the first aspect.

[0054] The embodiment of the present invention obtains the user's personal health data, which includes age, gender, weight, height, blood pressure and heart rate; generates a personalized exercise plan by combining the user's personal health data and historical exercise records through a big data analysis algorithm; collects the user's real-time physiological indicator data using Internet of Things technology and wearable devices, and compares it with the personalized exercise plan; dynamically adjusts the personalized exercise plan based on the feedback of the real-time physiological indicator data to ensure the safety and effectiveness of the exercise; and provides real-time guidance and feedback to the user through smart terminal devices, which can not only improve the safety and effectiveness of the exercise, but also enhance the user's exercise experience and help the user achieve fitness goals more scientifically and efficiently. This method integrates the user's personal health data, historical exercise records and real-time physiological indicator data, and uses big data analysis algorithms and machine learning technologies to achieve highly personalized exercise plan generation and dynamic adjustment, thereby significantly improving the effect and experience of exercise.

[0055] The beneficial effects of the embodiments of the present invention can refer to the technical effects corresponding to the technical features in the specific implementation methods, which will not be described in detail here. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 A schematic diagram of an exercise assistance process based on big data provided by an embodiment of the present invention;

[0057] Figure 2 A schematic diagram of a module of an exercise assistance system based on big data provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0059] The technical solution of the present invention is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0060] First, the embodiment of the present invention provides a training assistance method based on big data, such as Figure 1 As shown, including:

[0061] Step S1, obtaining the user's personal health data;

[0062] Collect users' personal health data, including but not limited to basic information such as age, gender, weight, height, blood pressure, and heart rate. This data can be obtained through questionnaires filled out by users in mobile applications, or automatically read through wearable devices connected to users.

[0063] Step S2, generating a personalized exercise plan by combining the user's personal health data and historical exercise records through a big data analysis algorithm;

[0064] Generate personalized exercise plans through big data analysis algorithms: Use big data analysis algorithms to combine the user's personal health data and historical exercise records to generate a highly personalized exercise plan; the plan takes into account the user's fitness goals (such as weight loss, muscle gain, improving endurance, etc.), preferences (such as favorite types of exercise), physical condition (such as whether there are chronic diseases, etc.), and past exercise habits to develop the most suitable exercise plan for the user.

[0065] Step S3, using Internet of Things technology and wearable devices to collect real-time physiological index data of the user, and compare it with the personalized exercise plan;

[0066] Collect real-time physiological index data of users: Through IoT technology and wearable devices, real-time collection of users' physiological index data, such as heart rate, blood oxygen saturation, number of steps, exercise intensity, etc. These data can help the system monitor the real-time status of users and determine whether they are suitable to continue the current exercise activities.

[0067] Step S4: dynamically adjust the personalized exercise plan based on the feedback of real-time physiological index data to ensure the safety and effectiveness of the exercise

[0068] Based on the real-time physiological indicator data collected, the system can automatically evaluate the user's exercise status and dynamically adjust the personalized exercise plan accordingly. For example, if the user's heart rate is detected to be out of the safe range, the system may recommend reducing the intensity of exercise or suspending exercise for a period of time to ensure the user's exercise safety; conversely, if the user's heart rate indicates that they can withstand greater challenges, the system may recommend increasing the difficulty of exercise.

[0069] Step S5, providing real-time guidance and feedback to the user through the smart terminal device;

[0070] Provide real-time guidance and feedback through smart terminal devices: Use smart terminal devices such as smart watches and smartphones to provide users with real-time guidance and feedback. This includes but is not limited to reminding users when to start or stop exercising, suggestions for adjusting exercise intensity, nutritional intake suggestions, etc. In addition, users can also view their progress, achievements and next goals through applications, thereby motivating users to keep exercising.

[0071] Through the above steps, this embodiment provides a personalized exercise assistance method based on big data, which can not only improve the safety and effectiveness of exercise, but also enhance the user's exercise experience and help users achieve fitness goals more scientifically and efficiently. This method integrates the user's personal health data, historical exercise records and real-time physiological index data, and uses big data analysis algorithms and machine learning technology to achieve highly personalized exercise plan generation and dynamic adjustment, thereby significantly improving the effect and experience of exercise.

[0072] The method proposed in this embodiment comprehensively considers the user's personal health data, historical exercise records and real-time physiological index data, and uses big data analysis algorithms and machine learning technology to generate and dynamically adjust personalized exercise plans, thereby ensuring the safety and effectiveness of exercise. In addition, real-time guidance and feedback are provided through smart terminal devices, which greatly improves the user's exercise experience and motivation, helping users to achieve their fitness goals more effectively. Specific embodiment 2:

[0074] Collect user sports preference information: Collect user sports preference information through questionnaires, user selection behaviors in the application, etc. For example, users may prefer outdoor running to indoor aerobic exercise, or team sports to individual training, etc.

[0075] Customized exercise content: Customize the specific activities in the exercise plan based on the user's sports preference information. For example, if the user prefers outdoor activities, the exercise plan can include more outdoor running, hiking and other activities; if the user prefers team sports, some group sports courses such as badminton and basketball can be arranged.

[0076] Recommend suitable exercise places based on real-time location information: The system obtains the user's real-time location information through the user's smartphone or wearable device, and combines it with map services to recommend suitable exercise places near the user. For example, if the user is near a park, the system may recommend jogging in the park; if the user is near a gym, the system may recommend going to the gym for strength training.

[0077] Providing opportunities for social interaction: Considering the user's need for social interaction, the system can provide opportunities to exercise with friends. This can be achieved through an invitation mechanism, where users can invite their friends to join a specific exercise activity or challenge. In addition, the system can also provide functions such as social leaderboards and achievement sharing to encourage healthy competition and mutual support between users and their friends.

[0078] Integration of the above functions: Integrate the above functions into the applications of smart terminal devices so that users can easily access and use these services. Users can view customized exercise plans, receive exercise reminders, view recommendations for nearby exercise venues, and interact with friends through the application.

[0079] Implementation case description:

[0080] User A is a young man who loves outdoor sports. He uses the app to fill out a questionnaire about his personal health data and selects "outdoor running" and "hiking" in the sports preference settings. Based on his preferences, the system generates a workout plan for him that includes outdoor running and hiking. At the same time, based on his real-time location information, the system recommends nearby parks as running locations and sends reminders through the app.

[0081] User B wants to make new friends through exercise, so he sets the option of "finding exercise partners" in the app. The system finds nearby users who also use the app based on his location information and recommends several people who are also interested in finding exercise partners. User B sends an invitation to a weekend morning run through the app and successfully organizes a small-scale morning run event.

[0082] Through the above embodiments, it can be seen that this method can not only generate a personalized exercise plan based on the user's personal health data, but also further optimize the exercise plan according to the user's exercise preferences, real-time location information and social interaction needs, provide more considerate services, and encourage users to persist in exercise and achieve better fitness results. Specific embodiment 3:

[0084] Analyze the user's personal health data and historical exercise records: First, the system needs to collect the user's personal health data, including but not limited to height, weight, BMI (Body Mass Index, body mass index), resting heart rate (RestingHeart Rate, HR rest ), blood pressure and other basic information. In addition, the system also needs to obtain the user's historical exercise records, such as exercise frequency, duration of each exercise, exercise type (such as running, swimming, yoga, etc.), exercise intensity, etc. Through these data, the system can comprehensively analyze the user's health status and exercise habits.

[0085] Compare the health status and exercise habits with the user groups in the big data: The system compares the user's personal data with the large amount of user data stored in the big data platform to find cases with similar health status and exercise habits as the user. These cases can help the system understand the successful exercise experience and improvement suggestions of similar individuals, and provide reference for users to develop more suitable exercise plans.

[0086] Using cluster analysis, association rule mining and other methods: Through cluster analysis, the system can classify users into groups with similar characteristics, thereby providing users with exercise recommendations that match the group. Association rule mining is used to discover potential connections between user health data and exercise habits, such as discovering the rule that "muscle growth speeds up after users increase protein intake", and then providing users with dietary recommendations.

[0087] Calculate the user's cardiovascular index (CVI): Calculate the user's CVI value according to the given formula:

[0088]

[0089] Among them, HR rest is the user's resting heart rate, HR max is the maximum heart rate, which can be estimated by the formula 220-age, where age is the user's age. The CVI value can be used to evaluate the user's cardiopulmonary health and provide the user with appropriate exercise intensity recommendations.

[0090] Using the user's historical exercise data, the system fits the user's physical recovery function R(t) through the least squares method: The system collects the user's recovery data after past exercise and uses the least squares method to fit a function R(t), where t represents the recovery time. This function can describe the user's physical recovery trend and help the system plan reasonable rest intervals and recovery periods for the user to avoid injuries caused by overtraining.

[0091] Through the above steps, the system can provide users with a personalized exercise plan based on big data analysis. The plan not only takes into account the user's personal health status and exercise habits, but also makes full use of the successful cases and experience in big data to ensure that the exercise plan is both scientific and personalized. In addition, by calculating CVI and fitting the physical recovery function, the system can better guide users on how to exercise and recover effectively, so as to achieve the best fitness effect.

[0092] Example

[0093] User A is a 30-year-old male, 180cm tall, 80kg in weight, with a BMI of 24.7 and a resting heart rate of 65 beats / minute. In the past year, he has exercised an average of 3 times a week, 45 minutes each time, mainly doing aerobic exercise (such as running and swimming). The system calculates his CVI value based on this information and uses cluster analysis to classify him into a similar group of active users. Through association rule mining, it was found that the members of this group had improved muscle endurance and recovery ability after increasing their protein intake. Therefore, the system recommends a diet plan for user A to increase protein intake appropriately, and provides an aerobic exercise and strength training plan suitable for him.

[0094] User B is a 25-year-old female with a height of 165cm, a weight of 55kg, a BMI of 20.2, and a resting heart rate of 70 beats / minute. She exercises 5 times a week for 1 hour each time, mainly doing yoga. The system fits a physical recovery function based on her historical exercise data and finds that she needs at least 24 hours to fully recover after exercise. Therefore, the system recommends that she leave enough recovery time between high-intensity training days and provides a workout plan that combines yoga and light aerobic exercise.

[0095] It can be seen from the above embodiments that the present method can provide users with personalized exercise plans through big data analysis, including appropriate exercise methods, dietary recommendations and recovery time arrangements, thereby helping users achieve their fitness goals more effectively.

[0096] Use wearable devices such as smart bracelets and smart watches to monitor the user's heart rate, number of steps, sleep quality and other data: Users wear devices such as smart bracelets or smart watches, which can continuously monitor the user's heart rate changes, number of steps taken per day, and sleep quality (such as the proportion of time spent in deep sleep and light sleep, etc.).

[0097] Measure the user's weight, body fat percentage and other information through smart body fat scales and other devices: Users can regularly use smart body fat scales to measure their weight, body fat percentage and other information. These data help the system understand the user's weight change trends and changes in body fat levels.

[0098] Transmit the collected data to the cloud server for processing and analysis: All data collected by wearable devices and smart body fat scales will be automatically uploaded to the cloud server, and the big data analysis software on the server will process and analyze the data to further generate personalized exercise recommendations.

[0099] Calculate the user's calorie consumption based on the user's real-time heart rate data: Calculate the user's calorie consumption C according to the given formula:

[0100]

[0101] HR rest The user's resting heart rate, HR max is the maximum heart rate, MET is metabolic equivalent (can be adjusted according to different types of activities), W is the user's weight (kg), and T is the exercise time (hours). This formula can help users understand how many calories they burn during a specific activity, so as to better control their energy balance.

[0102] Use nonlinear regression models to predict the user's heart rate trend in the future: By collecting the user's heart rate data at different times and in different activities, a nonlinear regression model can be built to predict the future heart rate change trend. This helps the system identify potential health risks, such as abnormal heart rate increases or decreases, and adjust exercise plans in time to prevent health problems.

[0103] Furthermore, the exercise effect is evaluated based on the user's real-time physiological indicator data: the system evaluates the effectiveness of the current exercise plan and the user's progress by analyzing the user's real-time physiological indicator data (such as heart rate, number of steps, sleep quality, etc.).

[0104] Adjust exercise intensity and type when the user's physiological indicators deviate from the normal range: If some of the user's physiological indicators are monitored to be out of the normal range (such as heart rate is too high or too low), the system will automatically adjust the intensity and type of the exercise plan to ensure the user's health and safety.

[0105] After the user reaches a short-term goal, gradually increase the difficulty of exercise to avoid plateaus: Once the user reaches a short-term goal, the system will gradually increase the difficulty of exercise to prevent the user from entering a plateau and ensure continuous progress and improvement.

[0106] Dynamically adjust the intensity and duration of exercise in the exercise plan based on the user's calorie consumption and target consumption: The system will dynamically adjust the intensity and duration of exercise in the exercise plan based on the difference between the user's actual calorie consumption and target consumption to help users achieve their goals more effectively.

[0107] Utilize reinforcement learning algorithms to optimize users’ exercise plans to maximize long-term health benefits: The system uses reinforcement learning algorithms to continuously optimize exercise plans based on user feedback and behavioral data, aiming to maximize users’ long-term health benefits through reward mechanisms (such as positive feedback after achieving goals) and punishment mechanisms (such as adjustments when deviating from goals).

[0108] In another embodiment provided by the present invention, an age adjustment factor is introduced, and the user's calorie consumption is calculated based on the user's real-time heart rate data**: In order to more accurately estimate the user's calorie consumption C, we introduce an age adjustment factor α. The calculation formula of calorie consumption C is updated to:

[0109]

[0110] in,

[0111] HR rest Resting heart rate for the user

[0112] HR max Maximum heart rate

[0113] MET stands for metabolic equivalent

[0114] W is the user's weight (kg)

[0115] T is the exercise time (hours)

[0116] α is the age adjustment factor

[0117] 2. Definition of age adjustment factor α**:

[0118]

[0119] This age adjustment factor takes into account the differences in heart rate recovery speed of users of different ages to more accurately calculate calorie consumption. The age adjustment factor α is used to reflect the differences in heart rate recovery speed of users of different ages. Older users usually have slower heart rate recovery speed, so a larger adjustment factor is needed to compensate for this difference.

[0120] Use nonlinear regression model to predict the user's heart rate trend in the future: Continue to use nonlinear regression model to predict the user's real-time heart rate trend in the future to predict possible health risks. This step can further help the system understand the user's health status and adjust the user's personalized exercise plan when necessary.

[0121] By introducing the age adjustment factor, the differences in physical conditions of users of different age groups can be more accurately taken into account, thereby more accurately estimating the user's calorie consumption. In this way, the system's personalized exercise plan can not only be dynamically adjusted based on the user's real-time physiological data, but also be more carefully optimized according to the user's age factor to provide a more personalized health management plan.

[0122] In another embodiment provided by the present invention, it also includes:

[0123] Provide an immersive exercise experience based on virtual reality (VR) or augmented reality (AR) technology: Use virtual reality (VR) or augmented reality (AR) technology to provide users with an immersive exercise experience. Users can exercise in a virtual environment, such as running on a virtual mountain track or doing strength training in a virtual gym. This experience can not only increase the fun of exercise, but also allow users to focus more on the exercise process and improve exercise results.

[0124] Share users' exercise results through social networks to promote community interaction and support: The system allows users to share their exercise results (such as the number of exercises completed, the number of calories burned, the milestones achieved, etc.) on social networking platforms such as WeChat and Weibo. This sharing can not only enhance the user's sense of achievement, but also inspire other users' exercise motivation and form a positive community atmosphere.

[0125] Integrated mental health counseling function to help users relieve stress and anxiety: The system integrates mental health counseling functions, including meditation guidance, relaxation training, psychological counseling services, etc. Users can meditate or relax before and after exercise to help reduce stress and anxiety in daily life. In addition, the system also provides psychological counseling services, and users can consult mental health experts online to get professional psychological counseling and support.

[0126] Through the above functions, the system can not only provide personalized exercise guidance, but also enhance the user's exercise experience, promote community interaction, and pay attention to the user's overall health, including mental health. This allows users to enjoy exercise while also getting emotional support and help with mental health, thereby comprehensively improving the user's health status and quality of life.

[0127] In another embodiment of the present invention, a big data-based exercise assistance system is characterized by comprising:

[0128] Acquisition module 01, used to acquire the user's personal health data, the personal health data including age, gender, weight, height, blood pressure and heart rate;

[0129] A generation module 02 is used to generate a personalized exercise plan by combining the user's personal health data and historical exercise records through a big data analysis algorithm;

[0130] Comparison module 03, for collecting real-time physiological index data of the user using Internet of Things technology and wearable devices, and comparing the data with the personalized exercise plan;

[0131] An adjustment module 04, for dynamically adjusting the personalized exercise plan according to the feedback of real-time physiological index data to ensure the safety and effectiveness of the exercise;

[0132] Feedback module 05 is used to provide real-time guidance and feedback to users through smart terminal devices.

[0133] An embodiment of the present invention further provides an electronic device, including:

[0134] processor;

[0135] a memory for storing processor-executable instructions;

[0136] The processor is configured to call the instructions stored in the memory to execute the aforementioned method.

[0137] A fourth aspect of the embodiments of the present invention is:

[0138] A computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the aforementioned method is implemented.

[0139] The present invention may be a method, an apparatus, a system and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for executing various aspects of the present invention.

[0140] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A training assistance method based on big data, characterized in that: include: Obtaining the user's personal health data, including age, gender, weight, height, blood pressure, and heart rate; Generate a personalized exercise plan through big data analysis algorithms, combining the user's personal health data and historical exercise records; Using Internet of Things technology and wearable devices to collect real-time physiological index data of users, and comparing the data with the personalized exercise plan; Dynamically adjust the personalized exercise plan according to the feedback of real-time physiological index data to ensure the safety and effectiveness of the exercise; Provide real-time guidance and feedback to users through smart terminal devices.

2. The method according to claim 1, characterized in that The personalized exercise program also includes: Recommend appropriate exercise movements and intensity based on the user's goal setting, such as muscle building, fat loss, and endurance improvement; Develop reasonable exercise frequency and duration based on the user's exercise preferences and schedule; The exercise plan is continuously optimized through machine learning algorithms to adapt to the user's physical changes and development needs.

3. The method according to claim 1 or 2, characterized in that: The method of generating a personalized exercise plan through a big data analysis algorithm includes: Analyze the user's personal health data and historical exercise records to determine the user's health status and exercise habits; Compare the health status and exercise habits with the user groups in the big data to find similar cases and successful experiences; Use cluster analysis, association rule mining and other methods to recommend the most suitable exercise methods and diet suggestions for users; Calculate the user's cardiovascular index (CVI), where CVI is defined as: Among them, HR rest The user's resting heart rate, HR max is the maximum heart rate, which can be estimated by the formula 220-age, where age is the user's age; Using the user's historical exercise data, the user's physical recovery function R(t) is fitted by the least squares method, where t is the recovery time. This function describes the trend of the user's physical recovery over time.

4. The method according to claim 3, characterized in that The real-time physiological index data of users are collected through the Internet of Things technology and wearable devices, including: Use wearable devices such as smart bracelets and smart watches to monitor users' heart rate, steps, sleep quality and other data; Measure the user's weight, body fat percentage and other information through devices such as smart body fat scales; The collected data is transmitted to a cloud server for processing and analysis; The user's calorie consumption is calculated based on the user's real-time heart rate data, where the calorie consumption C is defined as: Where MET is metabolic equivalent, W is the user's weight (kg), T is the exercise time (hours), HR rest The user's resting heart rate, HR max is the maximum heart rate; A nonlinear regression model is used to predict the user's heart rate trend over a period of time in the future to predict possible health risks.

5. The method according to claim 4, characterized in that The dynamically adjusting the personalized exercise plan includes: Evaluate exercise effects based on users’ real-time physiological indicator data; When the user's physiological indicators deviate from the normal range, adjust the intensity and type of exercise; Gradually increase the difficulty of exercise after users reach their short-term goals to avoid plateaus; Dynamically adjust the intensity and duration of exercise in the exercise plan based on the user's calorie consumption and target consumption; Leverage reinforcement learning algorithms to optimize users’ exercise plans to maximize long-term health benefits.

6. The method according to claim 4, characterized in that Also includes: An age adjustment factor is introduced, and the user's calorie consumption is calculated based on the user's real-time heart rate data, where the calorie consumption C is defined as: Where MET is metabolic equivalent, W is the user's weight (kg), T is the exercise time (hours), HR rest The user's resting heart rate, HR max is the maximum heart rate, and α is the age adjustment factor, defined as: The age adjustment factor takes into account the difference in heart rate recovery speed of users of different age groups to more accurately calculate calorie consumption. The age adjustment factor is used to reflect the difference in heart rate recovery speed of users of different age groups. Use nonlinear regression model to predict the user's heart rate trend in the future.

7. The method according to claim 1, characterized in that The providing real-time guidance and feedback to the user through the intelligent terminal device also includes: Providing immersive exercise experiences based on virtual reality (VR) or augmented reality (AR) technology; Share users' exercise results through social networks to promote community interaction and support; Integrate mental health counseling functions to help users relieve stress and anxiety.

8. A training assistance system based on big data, characterized in that: include: An acquisition module is used to acquire the user's personal health data, wherein the personal health data includes age, gender, weight, height, blood pressure and heart rate; A generation module, which is used to generate a personalized exercise plan by combining the user's personal health data and historical exercise records through a big data analysis algorithm; A comparison module, for collecting real-time physiological index data of the user using Internet of Things technology and wearable devices, and comparing the data with the personalized exercise plan; An adjustment module, used to dynamically adjust the personalized exercise plan according to the feedback of real-time physiological index data to ensure the safety and effectiveness of the exercise; The feedback module is used to provide real-time guidance and feedback to users through smart terminal devices.

9. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to perform the big data-based exercise assistance according to any one of claims 1 to 7.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, wherein the computer program includes a program code for controlling a process to execute a process, wherein the process includes the big data-based exercise assistance according to any one of claims 1 to 7.

Images