Personalized exercise plan generation and management method and system based on user data

Abstract

The invention provides a personalized exercise plan generation and management method and system based on user data, and the method comprises the steps: obtaining multi-source user data, and carrying out the data cleaning and feature extraction; on the basis of the extracted feature data, confirming the exercise preference and the exercise target of the user; based on the exercise preference and the exercise target, a machine learning algorithm is adopted to generate a personalized exercise plan, and recommendation is carried out; and tracking user feedback for the personalized exercise plan, performing dynamic analysis on information fed back by the user, correcting exercise preferences and exercise targets, and regenerating the personalized exercise plan. Multi-source data features are extracted and analyzed to obtain a personalized exercise target of a user, a machine learning algorithm is utilized to generate a personalized exercise plan for the personalized exercise target, and finally, based on customer feedback, the goal reaching progress and the sign change of the user are analyzed, the exercise effect is evaluated, and the user experience is improved. And adjusting the motion target and the motion plan in real time, and managing the motion plan.

Description

Technical Field

[0001] The present invention relates to the technical fields of machine learning and artificial intelligence. Specifically, it relates to a method and system for generating and managing personalized exercise plans based on user data, and also relates to a corresponding computer terminal and a computer-readable storage medium. Background Art

[0002] With the continuous improvement of people's health awareness and the rapid development of technology, health management applications have gradually become the focus of attention. By using the user's medical treatment data, physical examination data, activity data from intelligent devices, etc., as well as health goals to generate personalized exercise plans, and improving the compliance of users' participation in exercise plans through user behavior incentives, the system can provide real-time feedback on exercise results and timely adjust exercise plans according to the changes in physiological index data of users in the exercise plan and the activity data collected and fed back by intelligent devices, so as to ensure that users can achieve health goals safely, as healthy and efficiently as possible.

[0003] However, existing exercise plan generation solutions usually have deficiencies in the comprehensiveness and depth of data sources. Even if multi-source user data can be obtained, due to the different formats, collection frequencies, and precisions of these data, they face the problems of multi-source data integration and data cleaning, and cannot guarantee the integrity and accuracy of the data. In addition, existing exercise plan generation solutions hardly consider the real-time data and feedback information of users, cannot adjust the intensity, frequency, and content of exercise plans personalized, cannot truly meet the general applicability requirements and accuracy requirements of exercise plan solutions, and also lack an effective data basis for optimizing the implementation of the generation solutions. At present, no description or report of similar technologies to the present invention has been found, and no similar materials at home and abroad have been collected. Summary of the Invention

[0004] In view of the above deficiencies in the prior art, the present invention provides a method and system for generating and managing personalized exercise plans based on user data, and also provides a corresponding computer terminal and a computer-readable storage medium.

[0005] According to one aspect of the present invention, there is provided a method for generating and managing a personalized exercise plan based on user data, including:

[0006] Obtaining multi-source user data, and performing data cleaning and feature extraction on the multi-source user data;

[0007] Based on the extracted feature data, confirming the user's exercise preferences and exercise goals;

[0008] Based on the exercise preferences and exercise goals, using a machine learning algorithm to generate a personalized exercise plan and make a recommendation;

[0009] Track user feedback for the personalized exercise plan, dynamically analyze the information of the user feedback, correct the exercise preferences and exercise goals, and regenerate a personalized exercise plan.

[0010] According to another aspect of the present invention, there is provided a method for generating and managing a personalized exercise plan based on user data, including:

[0011] A data processing module, which is used to obtain multi-source user data, perform data cleaning and feature extraction on the multi-source user data;

[0012] A target acquisition module, which based on the extracted feature data, confirms the exercise preferences and exercise goals of the user;

[0013] A plan generation module, which based on the exercise preferences and exercise goals, uses a machine learning algorithm to generate a personalized exercise plan and make a recommendation;

[0014] A plan correction module, which is used to track user feedback for the personalized exercise plan, dynamically analyze the information of the user feedback, correct the exercise preferences and exercise goals, and regenerate a personalized exercise plan.

[0015] According to a third aspect of the present invention, there is provided a computer terminal, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it can be used to execute the method described in the present invention, or, run the system described above in the present invention.

[0016] According to a fourth aspect of the present invention, there is provided a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it can be used to execute the method described above in the present invention, or, run the system described above in the present invention.

[0017] Due to the adoption of the above technical solutions, compared with the prior art, the present invention has at least one of the following beneficial effects:

[0018] By obtaining multi-source data of users, establishing a unified data interface and standard, effectively integrating these multi-source data, ensuring the integrity and accuracy of the data, and at the same time identifying and processing abnormal data, such as reasonably filling or interpolating missing values, etc., the present invention effectively improves the data quality, and thus realizes the integration of multi-source data and data cleaning.

[0019] The present invention generates a suitable exercise plan for users based on a personalized exercise plan recommendation model using machine learning, according to the user's health profile, exercise goals, and current physical condition. At the same time, through a dynamic adjustment algorithm, based on the user's real-time data and feedback information, the intensity, frequency, and content of the exercise plan are adjusted in a timely manner, realizing personalized exercise plan recommendation and dynamic adjustment.

[0020] The present invention realizes the advantages of real-time multi-source data and dynamic monitoring: by obtaining the user's activity data in real time, timely understanding the user's current exercise status and physical reactions, and combining with regular physical examination data and medical treatment data, it is possible to dynamically track the changes in the user's health status.

[0021] The present invention realizes comprehensive risk assessment and targeted preventive measures: by combining medical treatment data, it is possible to understand the user's existing diseases and potential health risks. Physical examination data can provide the basic health status of the body, and activity data can reflect the user's exercise habits and the body's adaptation to exercise. Based on these multi-dimensional data, health risk assessment can be carried out, and thus it is possible to more accurately identify the risks that the user may face during exercise; according to the results of the comprehensive health risk assessment, the application can provide more targeted preventive measures for the user.

[0022] The present invention realizes timely feedback and adjustment of the plan: when it is found that the user's exercise effect does not meet the expectation, or the user's health status changes, it can analyze according to the latest data in a timely manner and adjust the exercise plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Other features, objects, and advantages of the present invention will become more apparent by reading the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0024] Figure 1 It is a flowchart of the method for generating and managing a personalized exercise plan based on user data in an embodiment of the present invention.

[0025] Figure 2 It is a schematic diagram of the composition modules of the system for generating and managing a personalized exercise plan based on user data in an embodiment of the present invention.

[0026] Figure 3 It is a flowchart of the method and system for generating and managing a personalized exercise plan based on user data in a preferred embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0027] The following is a detailed description of the embodiments of the present invention: These embodiments are implemented on the premise of the technical solution of the present invention, and detailed implementation manners and specific operation processes are given. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several deformations and improvements can be made, and these all belong to the protection scope of the present invention.

[0028] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0029] Existing motion plan generation and management solutions usually have problems such as insufficient comprehensiveness and depth of data sources, untimely information updates, and insufficient personalization, and cannot truly meet the general applicability requirements and accuracy requirements of motion plan solutions. At the same time, there is also a lack of an effective data basis for optimizing the generated solutions. To address this problem, an embodiment of the present invention provides a personalized motion plan generation and management method based on user data. This method extracts and analyzes multi-source data features to obtain the user's personalized motion goals, and uses machine learning algorithms to generate personalized motion plans for the personalized operation goals. Finally, based on customer feedback, it analyzes the progress of the user's goal achievement and physical sign changes, evaluates the exercise effect, and adjusts the motion goals and motion plans in real time to manage the motion plans.

[0030] Specifically, as Figure 1 shown, the personalized motion plan generation and management method based on user data provided by this embodiment may include the following operations:

[0031] S1. Obtain multi-source user data, and perform data cleaning and feature extraction on the multi-source user data;

[0032] S2. Based on the extracted feature data, confirm the user's exercise preferences and exercise goals;

[0033] S3. Based on the exercise preferences and exercise goals, use machine learning algorithms to generate personalized motion plans and make recommendations;

[0034] S4. Track user feedback for the personalized motion plan, dynamically analyze the information feedback by the user, and correct the exercise preferences and exercise goals, and regenerate the personalized motion plan.

[0035] In order to achieve the comprehensiveness and depth of data sources, in some preferred implementation manners, the above S1, obtaining multi-source user data, may further include the following operations:

[0036] S11. Obtain the user's offline medical data, including information such as physical examination reports, medical records, diagnosis results, and treatment plans;

[0037] S12. Obtain the user activity data collected by the device, including: number of steps, exercise distance, heart rate, sleep condition, exercise type (running, walking, fitness, etc.), and exercise duration;

[0038] S13. Obtain the user's manually recorded data for data supplementation and correction.

[0039] In some preferred embodiments, the above S1, establish a unified data interface and standard to obtain multi-source user data; among them, establishing a unified data interface and standard can further include:

[0040] Create a unified data dictionary: Create a data dictionary to define detailed information such as the name, type, length, value range, etc. of each data element to ensure that data from different sources is consistent in format and semantics, which is the basis for establishing a unified data standard;

[0041] Establish the SOAP protocol (Simple Object Access Protocol): Based on the XML format, communicate by defining a strict message structure; the SOAP protocol can provide a reliable message transfer mechanism to ensure the integrity and accuracy of data;

[0042] Unify the XML format (Extensible Markup Language): It has strong scalability and standardization, and can handle business scenarios with strict data structure requirements.

[0043] In order to improve data quality, obtain the user's health portrait, exercise goals, and current physical status, in some preferred embodiments, the above S1, perform data cleaning and feature extraction on multi-source user data, and can further include the following operations:

[0044] S14. Perform data cleaning on outliers, duplicate values, and / or missing values in multi-source user data to obtain a data sample;

[0045] S15. Obtain the user activity data in the data sample, and based on the user activity data and a preset feature extraction scheme, extract corresponding exercise feature data, including: exercise type, frequency, and duration, as well as calorie consumption, heart rate variability, and sleep data.

[0046] In some preferred embodiments, the above S15, feature extraction scheme, can further include:

[0047] In a sports health program, discriminative features are extracted according to different sports types and health status categories (such as healthy, cardiovascular risk, obesity risk, etc.). For example, based on the user's physiological data (age, weight, blood pressure, etc.) and sports data (exercise intensity, frequency), linear discriminant analysis (LDA) is used to find a feature combination that can best distinguish different health risk categories, accurately locate the key factors affecting health risks, so as to provide a basis for formulating personalized exercise and health management plans, improve the accuracy of classifying the user's health status, and optimize the pertinence of exercise recommendations. For example, more gentle and rehabilitative exercise programs and intensities are recommended for high-risk users.

[0048] In order to further obtain accurate user preferences and exercise goals and be able to more accurately identify the risks that users may face during exercise, in some preferred embodiments, in the above S2, based on the extracted feature data, to confirm the user's exercise preferences and exercise goals, the following operations can further be included:

[0049] According to the extracted feature data and a preset standardized exercise guidance plan, combined with the offline medical treatment data in the multi-source user data, customized questionnaire content is generated to confirm the user's exercise preferences and exercise goals.

[0050] In some preferred embodiments, the logic of generating the customized question content in the above S2 can further include:

[0051] Based on the health status in which certain exercises are recommended to be avoided by health management practitioners due to various indicators in a physical examination (such as blood pressure, blood sugar, joint flexibility, etc.) and medical treatment data for physical diseases or injuries (such as arthritis, heart disease, lumbar injury, etc.), confirm the types and intensities of restricted exercises;

[0052] The exercise patterns and tendencies reflected by smart device data: Confirm the most frequently done exercise type or the new exercise type that the user hopes to try; Confirm the user's satisfaction with the current exercise regularity (duration and frequency) recorded by the smart device; Confirm the exercise intensity at which the user feels comfortable;

[0053] Comprehensive exploration of exercise preferences related to both: Combine the body composition analysis in a physical examination (such as muscle mass, fat percentage) and the exercise progress recorded by the smart device to confirm the user's health goals (such as rehabilitation, weight loss, physical fitness enhancement, etc.) and exercise preferences (whether they like to use exercise equipment, preferences for exercise environment and groups).

[0054] In some preferred embodiments, the above questionnaire content includes: daily diet rules, weekly free time, and expected exercise goals.

[0055] In some preferred embodiments, in order to generate an accurate exercise plan, in step S3 above, based on exercise preferences and exercise goals, a machine learning algorithm is used to generate a personalized exercise plan, which may further include the following operations:

[0056] Provide a pre-trained machine learning model, use exercise preferences and exercise goals as the input of the machine learning model, and obtain the corresponding personalized exercise plan.

[0057] In some preferred embodiments, in order to achieve timely feedback and adjustment of the plan, in step S4 above, track the user feedback for the personalized exercise plan, dynamically analyze the information feedback by the user, and correct the exercise preferences and exercise goals, which may further include the following operations:

[0058] Set multiple plan push nodes according to the user's exercise time preferences during the exercise cycle; when the user deviates from the exercise plan or reaches the set exercise reminder threshold, send an exercise reminder;

[0059] Through a reminder mechanism, prompt the user to achieve multi-channel reach for the initial personalized diet advice and obtain user feedback data;

[0060] Extract key indicators from the user feedback data, dynamically analyze the extracted key indicators, identify the user's new exercise demands, correct the user's exercise preferences and exercise goals, and generate a new personalized exercise plan;

[0061] Analyze the user feedback data, obtain the user's physical signs changes and the completion degree of the exercise plan, and correct the personalized exercise plan.

[0062] In some preferred embodiments, in order to further adjust the exercise plan in real time according to the latest data and provide more targeted preventive measures, in step S4 above, it may further include any one or more of the following operations:

[0063] - Continuously optimize the feature extraction algorithm and the content of the customized questionnaire according to the completion degree of the exercise plan for adjusting the user's exercise preferences and exercise goals;

[0064] - Provide corresponding knowledge articles and / or video content according to the offline medical treatment data in the multi-source user data and the user's exercise preferences and exercise goals.

[0065] In some preferred embodiments, the above-mentioned continuous optimization of the feature extraction algorithm may further include:

[0066] Optimize sports ability characteristics: Extract the user's sports ability characteristics from sports data, such as endurance level (judged according to the duration and speed stability of long-distance running), strength level (based on the weight used and the number of repetitions of fitness equipment). For example, calculate the average pace and the longest duration of the user's running in the past month to evaluate endurance; analyze the strength performance of different muscle groups during fitness to determine weak and strong areas of strength;

[0067] Optimize health risk characteristics: Combine physiological data and lifestyle data to extract health risk characteristics. Such as evaluating the risk of cardiovascular disease based on age, weight, body fat percentage, and blood pressure data; judging the risk of obesity or malnutrition based on diet structure and exercise volume; analyzing mental health risks (such as anxiety and depression tendencies) from sleep data and work pressure conditions. For example, if the user has a long-term high-calorie diet, lacks exercise, and has a too high body fat percentage, high obesity and related disease risk characteristics can be extracted;

[0068] Optimize sports preference characteristics: Analyze the types of sports that the user often participates in, the distribution of sports time and frequency, and extract sports preference characteristics. For example, if the user participates in yoga classes multiple times a week and the sports time is concentrated in the evening, it indicates that the user has an obvious preference for yoga and is used to exercising in the evening, and has a high acceptance of indoor and soothing sports.

[0069] Based on the same idea, in some preferred embodiments, the above continuously customized questionnaire content continuously optimizes the type and intensity of restricted sports, the exercise intensity that the user feels comfortable with, and the associated sports preferences.

[0070] Based on the same inventive concept, an embodiment of the present invention also provides a personalized exercise plan generation and management system based on user data.

[0071] Specifically, as Figure 2 shown, the personalized exercise plan generation and management system based on user data provided by this embodiment may include the following modules:

[0072] Data processing module, which is used to obtain multi-source user data, clean the multi-source user data, and extract features;

[0073] Target acquisition module, which confirms the user's sports preferences and sports goals based on the extracted feature data;

[0074] Plan generation module, which generates a personalized exercise plan based on sports preferences and sports goals, uses machine learning algorithms, and makes recommendations;

[0075] Plan correction module, which is used to track the user's feedback for the personalized exercise plan, dynamically analyze the information feedback by the user, and correct the sports preferences and sports goals, and regenerate the personalized exercise plan.

[0076] In some preferred embodiments, the above system may further include the following modules:

[0077] A user login module, which is used to obtain the account information of the currently logged-in person, verify whether the account information is legal or matching, and enter the system according to the permission information of the currently logged-in person; among them, the user login module obtains the account information through any of the following methods:

[0078] - Enter the set account information, where the account information includes the username and user password;

[0079] - Scan the QR code to cascade the relevant account information, where the account information includes the WeChat account;

[0080] A user management module, which is used to create or modify user information, where the user information includes account information, permission information, and other information set according to requirements.

[0081] In some preferred embodiments, the above system may further include the following modules:

[0082] A health knowledge popularization module, which is used to provide corresponding knowledge articles and / or video content according to the offline medical treatment data in the multi-source user data and the user's exercise preferences and exercise goals.

[0083] The personalized exercise plan generation and management system provided by the above embodiments of the present invention can be encapsulated as an application program and arranged on an intelligent terminal.

[0084] The working content of each functional module of the personalized exercise plan generation and management system provided by the above embodiments of the present invention will be further described in detail below.

[0085] The data processing module and the target acquisition module are used to implement the multi-source data feature extraction and analysis algorithm: extract the main feature data from the smart watch, mobile phone sports application, and user manual record data, such as the time distribution of exercise intensity, the regularity of exercise, heart rate variability, and main health data (body temperature, blood oxygen, blood pressure, etc.), and analyze and summarize the user's exercise ability and exercise preferences; analyze the user's physical condition and exercise taboos from the user's in-hospital medical treatment data and physical examination data, such as the exercise types not suitable for, the acceptable exercise intensity and exercise time (within the disease cycle);

[0086] The plan generation module and the plan correction module are used for exercise plan generation and effect evaluation: Using machine learning algorithms (such as decision trees, random forests, neural networks, etc.), guided by the user's medical examination data and physical activity data, and can conduct health risk assessment, help users formulate reasonable health goals, and train models to generate personalized exercise plans based on the user's exercise ability and physical signs analysis; during the plan execution process, collect the user's weight changes through reinforcement reminders and incentive tasks, as well as real-time synchronization of multi-device exercise record data, analyze and evaluate the user's progress in achieving goals and physical signs changes, evaluate exercise effects, and adjust exercise goals in real time.

[0087] As Figure 3 shown, the work content and work process of this personalized exercise plan generation and management system include the following steps:

[0088] Step 1, through the data processing module, conduct data collection and data cleaning and feature extraction; among them:

[0089] Step 1.1, data collection, including:

[0090] Build an interface connected to the in-hospital HIS system for safely obtaining the user's medical data, including information such as physical examination reports, medical records, diagnosis results, treatment plans, etc.

[0091] Build a connection with wearable devices (such as smart watches, etc.), collect the authorization of health applications, and collect the user's activity data, such as steps, exercise distance, heart rate, sleep status, exercise type (running, walking, fitness, etc.) and exercise duration.

[0092] Build a manual record module for users to manually supplement and correct data.

[0093] Step 1.2, data cleaning and feature extraction, including:

[0094] Problems such as outliers, duplicate values, or missing values may exist in the collected user activity data, and data cleaning is required to ensure the accuracy and reliability of the data. Extract valuable features from a large amount of user activity data for subsequent analysis and processing.

[0095] In the data processing module, multi-source data integration and data cleaning are implemented: The user's data sources are diverse. The activity data sources include smart watches, mobile exercise applications, etc., and the health data sources include the user's physical examinations and medical data in the hospital; the data formats, collection frequencies, and precisions of these devices and applications may vary, and a unified data interface and standard need to be established to effectively integrate these multi-source data to ensure the integrity and accuracy of the data. Identify and process abnormal data, and reasonably fill or interpolate missing values to improve data quality.

[0096] Step 2: Through the target acquisition module, customize a questionnaire to confirm the user's health goals and exercise preferences, including:

[0097] Generate customized questionnaire content based on the user's characteristic data in various aspects and a reasonable exercise guidance plan, and further confirm the specific exercise plan with the user (taking into account the achievement of reasonable health goals and the user's personal preferences).

[0098] Step 3: Through the plan generation module, generate a customized personalized exercise plan. Based on the principles of exercise physiology and machine learning algorithms, formulate a scientific and reasonable exercise plan according to the user's health goals and activity data to ensure the safety and effectiveness of the exercise plan.

[0099] Step 4: Through the plan correction module, implement task push reminders and supervision of execution, collect user feedback during the exercise plan cycle, and analyze and correct the user's exercise plan; among which:

[0100] Step 4.1: Task push reminders and supervision of execution, including:

[0101] Set multiple push nodes according to the user's exercise time preferences during the exercise plan cycle to encourage the user to complete the exercise goal in a timely manner and perform task check-ins (mainly collect and record the user's weight changes and exercise-related data); when the user deviates from the exercise plan or reaches a specific reminder threshold (such as excessive exercise intensity, too long exercise time, etc.), send reminders to the user through methods such as watch notifications and mini-program pushes.

[0102] Step 4.2: Collect user feedback during the exercise plan cycle, including:

[0103] Allow the user to feedback on the execution of the exercise plan within the application, such as the physical feelings after exercise (fatigue level, whether there is pain, etc.), whether the plan can be completed and other information;

[0104] Step 4.3: Analyze and correct the user's exercise plan, including:

[0105] Based on the user's weight changes, exercise activity data, changes in exercise habits, and changes in important physical sign indicators, compare and analyze the progress of achieving health goals, correct the exercise task plan, and promote goal achievement.

[0106] In this plan correction module, a personalized exercise plan recommendation and dynamic adjustment algorithm is implemented: develop a personalized exercise plan recommendation model, and generate a suitable exercise plan for the user according to the user's health profile, exercise goals, and current physical condition. It is necessary to develop a dynamic adjustment algorithm to timely adjust the intensity, frequency, and content of the exercise plan according to the user's real-time data and feedback information.

[0107] Furthermore, through this plan correction module, the following functions can also be achieved:

[0108] Step 4.4: Optimize data cleaning and feature extraction based on the actual progress of the user's exercise plan, as well as customize the user exercise data feature extraction algorithm and the logic of the customized questionnaire in the questionnaire, and repeat multiple times to improve the accuracy of exercise plan recommendations;

[0109] Step 4.5: According to the user feedback within the exercise plan cycle, correct the generated personalized exercise plan, adjust the content of the personalized exercise plan, and improve the optimization ability of individual exercise plan differences.

[0110] Furthermore, the above system can further include:

[0111] Step 5: Through the health knowledge popularization module, it can provide users with content such as knowledge articles and videos related to exercise and health, such as prevention of sports injuries and exercise precautions for users with different diseases. This can help users better understand the exercise plan, but it is not an essential part of generating the exercise plan.

[0112] It should be noted that the steps in the method provided by the present invention can be implemented by using the corresponding components in the system, etc. Those skilled in the art can refer to the technical solution of the system to implement the step flow of the method, or refer to the technical solution of the method to implement the composition of the system. That is, the embodiments in the system and the embodiments in the method can be understood as preferred examples of each other and will not be elaborated here.

[0113] An embodiment of the present invention also provides a computer terminal, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it can be used to execute the method of any one of the above embodiments of the present invention, or run the system of any one of the above embodiments of the present invention.

[0114] Optionally, a memory for storing programs; the memory may include volatile memory (e.g., random-access memory, such as static random-access memory (SRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDR SDRAM), etc.); the memory may also include non-volatile memory, such as flash memory. The memory is used to store computer programs (such as application programs and functional modules for implementing the above methods), computer instructions, etc. The above computer programs, computer instructions, etc. may be partitioned and stored in one or more memories. And the above computer programs, computer instructions, data, etc. may be called by the processor.

[0115] The above computer programs, computer instructions, etc. may be partitioned and stored in one or more memories. And the above computer programs, computer instructions, data, etc. may be called by the processor.

[0116] A processor for executing the computer programs stored in the memory to implement each step in the method or each module in the system according to the above embodiments. For specific details, reference may be made to the relevant descriptions in the foregoing method and system embodiments.

[0117] The processor and the memory may be of an independent structure or an integrated structure integrated together. When the processor and the memory are of an independent structure, the memory and the processor may be coupled and connected through a bus.

[0118] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it can be used to execute the method of any one of the above embodiments of the present invention, or to run the system of any one of the above embodiments of the present invention.

[0119] Among them, the computer-readable medium includes computer storage media and communication media, where the communication media includes any medium that facilitates the transmission of a computer program from one place to another. The storage media can be any available medium accessible by a general or special-purpose computer. An exemplary storage medium is coupled to the processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an ASIC. Additionally, the ASIC can be located in a user device. Of course, the processor and the storage medium can also exist as discrete components in a communication device.

[0120] The personalized exercise plan generation and management method and system based on user data provided by the above embodiments of the present invention can provide key information such as disease diagnosis and treatment plans by using medical treatment data; can reflect various physiological indicators of the body by using physical examination data; and can display daily exercise habits and exercise amounts by using activity data. Through the comprehensive analysis of multi-source data, the health status of users can be evaluated more comprehensively and accurately, providing a more solid data foundation for formulating personalized exercise plans and realizing the deep integration of multi-source data.

[0121] The personalized exercise plan generation and management method and system based on user data provided by the above embodiments of the present invention, according to the differences between healthy bodies and different disease-carrying bodies, and based on the input and integration of multi-source data, formulates an exercise plan that meets their physical endurance and can effectively promote the recovery of the corresponding physical functions, including exercise type, intensity, frequency, and duration, etc., with higher pertinence, and can better take into account individual differences, realizing the accurate understanding of users' health goals and individual differences.

[0122] The personalized exercise plan generation and management method and system based on user data provided by the above embodiments of the present invention are applicable to users for home health management. Through the exercise plan, the progress of users' disease recovery and physical fitness can be further improved; at the same time, it is applicable to healthy people or sub-healthy people, providing an effective and scientific exercise guidance plan to avoid injuries caused by improper exercise.

[0123] Matters not described in detail in the above embodiments of the present invention are all well-known technologies in the art.

[0124] The specific embodiments of the present invention have been described above. It should be understood that the present invention is not limited to the above specific embodiments, and those skilled in the art can make various deformations or modifications within the scope of the claims, which do not affect the essence of the present invention.

Claims

1. A personalized exercise plan generation and management method based on user data, characterized in that, Including: Obtain multi-source user data, and perform data cleaning and feature extraction on the multi-source user data; Based on the extracted feature data, confirm the user's exercise preferences and exercise goals; Based on the exercise preferences and exercise goals, use machine learning algorithms to generate a personalized exercise plan and make recommendations; Track user feedback for the personalized exercise plan, dynamically analyze the information of the user feedback, and correct the exercise preferences and exercise goals, and regenerate the personalized exercise plan.

2. The personalized exercise plan generation and management method based on user data according to claim 1, characterized in that The obtaining of the multi-source user data includes: Obtain the user's offline medical treatment data, including information such as physical examination reports, medical records, diagnosis results, and treatment plans; Obtain the user's activity data collected by the device, including: steps, exercise distance, heart rate, sleep condition, exercise type, and exercise duration; Obtain the user's manually recorded data for data supplementation and correction.

3. The personalized exercise plan generation and management method based on user data according to claim 1, characterized in that, The data cleaning and feature extraction of the multi-source user data includes: Perform data cleaning on outliers, duplicate values, and / or missing values in the multi-source user data to obtain a data sample; Obtain the user's activity data in the data sample, and based on the user's activity data and feature extraction algorithm, extract corresponding exercise feature data, including: exercise type, frequency, and duration, as well as calorie consumption, heart rate variability, and sleep data.

4. The personalized exercise plan generation and management method based on user data according to claim 1, characterized in that, The confirmation of the user's exercise preferences and exercise goals based on the extracted feature data includes: According to the extracted feature data and a preset standardized exercise guidance plan, combined with the offline medical treatment data in the multi-source user data, generate customized questionnaire content to confirm the user's exercise preferences and exercise goals.

5. The personalized exercise plan generation and management method based on user data according to claim 1, characterized in that The generation of a personalized exercise plan using machine learning algorithms based on the exercise preferences and exercise goals includes: Provide a pre-trained machine learning model, use the exercise preferences and exercise goals as the input of the machine learning model, and obtain the corresponding personalized exercise plan solution.

6. The personalized exercise plan generation and management method based on user data according to claim 1, characterized in that, The tracking of user feedback for the personalized exercise plan, the dynamic analysis of the user feedback information, and the correction of the exercise preferences and exercise goals include: Set multiple plan push nodes according to the user's exercise time preferences during the exercise cycle; when the user deviates from the exercise plan or reaches the set exercise reminder threshold, issue an exercise reminder; Through a reminder mechanism, prompt the user to achieve multi-channel access to the initial personalized diet advice and obtain user feedback data; Extract key indicators from the user feedback data, dynamically analyze the extracted key indicators, identify the user's new exercise demands, correct the user's exercise preferences and exercise goals, and generate a new personalized exercise plan; Perform data analysis on the user feedback data to obtain the user's physical signs changes and the completion degree of the exercise plan, and correct the personalized exercise plan.

7. The personalized exercise plan generation and management method based on user data according to claim 6, characterized in that It also includes any one or any combination of the following: - Continuously optimize the feature extraction algorithm and customized questionnaire content according to the completion degree of the exercise plan for adjusting the user's exercise preferences and exercise goals; - Provide corresponding knowledge articles and / or video content according to the offline medical treatment data in the multi-source user data, as well as the user's exercise preferences and exercise goals.

8. A personalized exercise plan generation and management method based on user data, characterized in that, Including: A data processing module, which is used to obtain multi-source user data and perform data cleaning and feature extraction on the multi-source user data; A target acquisition module, which is used to confirm the user's exercise preferences and exercise goals based on the extracted feature data; A plan generation module, which is used to generate a personalized exercise plan by using a machine learning algorithm based on the exercise preferences and exercise goals, and make a recommendation; A plan correction module, which is used to track user feedback for the personalized exercise plan, dynamically analyze the information of the user feedback, and correct the exercise preferences and exercise goals, and regenerate a personalized exercise plan.

9. A computer terminal, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, it can be used to execute the method described in any one of claims 1-7, or, run the system described in claim 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it can be used to execute the method described in any one of claims 1-7, or, run the system described in claim 8.

Images