Exercise prescription generation method and device

Abstract

The invention provides an exercise prescription generation method and device. The method comprises the following steps: acquiring health data and physical fitness index data of a user; based on the health data and the physical fitness index data, a user portrait is constructed, and the user portrait is used for representing the health condition, the exercise ability and the potential exercise risk of the user; and based on the user portrait and the exercise guide, an exercise prescription of the user is generated, and the exercise guide refers to suggestions and specifications for guiding different crowds to do scientific exercises. The exercise prescriptions can be customized and generated for different users, individual differences are fully considered, the limitation of a general recommendation scheme is avoided, and the applicability and effectiveness of the exercise prescriptions are improved, so that the exercise compliance and the exercise effect of the users are improved, and health management and rehabilitation of chronic disease patients are facilitated.

Description

Technical Field

[0001] The present invention relates to the technical field of sports health management, and in particular to a method and device for generating an exercise prescription. Background Art

[0002] Chronic diseases have become a major factor affecting people's health. Scientific and rational exercise intervention has a significant effect on controlling the progression of chronic diseases. Therefore, developing personalized exercise prescriptions for patients with chronic diseases has important clinical significance and application value.

[0003] Existing exercise prescription generation methods are mostly based on general recommendations or empirical judgments, and lack a deep understanding of individual differences, resulting in inappropriate exercise plans, poor patient compliance, and poor exercise effects. Summary of the Invention

[0004] The present invention provides a method and device for generating an exercise prescription, which are used to solve the defects in the prior art.

[0005] The present invention provides a method for generating an exercise prescription, comprising the following steps: Obtain users' health data and physical fitness index data; Building a user profile based on the health data and the physical fitness index data, wherein the user profile is used to characterize the user's health status, exercise ability, and potential exercise risks; Based on the user portrait and the exercise guide, an exercise prescription for the user is generated. The exercise guide refers to suggestions and specifications for guiding different groups of people to perform scientific exercise.

[0006] According to a method for generating an exercise prescription provided by the present invention, constructing a user profile based on the health data and the physical fitness index data includes: extracting user features from the health data and the physical fitness index data; Based on the user characteristics, the user portrait is constructed.

[0007] According to a method for generating an exercise prescription provided by the present invention, generating the user's exercise prescription based on the user portrait and the exercise guide includes: Inputting the user portrait into an exercise prescription generation model to obtain the exercise prescription output by the exercise prescription generation model; The exercise prescription generation model is obtained based on sample user portraits, sample exercise prescriptions and the exercise guide training.

[0008] According to a method for generating an exercise prescription provided by the present invention, the method generates an exercise prescription for the user based on the user portrait and the exercise guide, and then further includes: Sending the exercise prescription to a mobile terminal; Receiving the user's actual motion data and user's subjective feedback data returned by the mobile terminal; The exercise prescription is updated based on the user's actual exercise data and the user's subjective feedback data.

[0009] According to a method for generating an exercise prescription provided by the present invention, the updating of the exercise prescription further comprises: Based on the user portrait and the updated exercise prescription, the exercise prescription generation model is updated.

[0010] According to a method for generating an exercise prescription provided by the present invention, obtaining the user's health data and physical fitness index data includes: obtaining the health data; Based on the health data, it is determined whether to generate an exercise prescription for the user, and if so, the physical fitness index data is obtained.

[0011] The present invention also provides an exercise prescription generating device, comprising the following modules: An acquisition unit, used to obtain the user's health data and physical fitness index data; A construction unit, configured to construct a user profile based on the health data and the physical fitness index data, wherein the user profile is used to characterize the user's health status, exercise ability, and potential exercise risks; A generating unit is used to generate an exercise prescription for the user based on the user portrait and the exercise guide, where the exercise guide refers to suggestions and specifications for guiding different groups of people to perform scientific exercise.

[0012] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for generating an exercise prescription as described above is implemented.

[0013] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described methods for generating an exercise prescription.

[0014] The present invention also provides a computer program product, comprising a computer program, which, when executed by a processor, implements any of the above-described methods for generating an exercise prescription.

[0015] The exercise prescription generation method and device provided by the present invention constructs a user profile based on the user's health data and physical fitness index data, which comprehensively reflects the user's health status, exercise ability, and potential exercise risks. Combining the user profile with the exercise guide, a personalized exercise prescription is generated. Therefore, the present invention can generate customized exercise prescriptions for different users, fully considering individual differences, avoiding the limitations of universal recommendation schemes, and improving the applicability and effectiveness of exercise prescriptions, thereby improving users' exercise compliance and exercise results, and facilitating health management and rehabilitation for patients with chronic diseases. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0017] Figure 1 This is one of the flow charts of the exercise prescription generation method provided by the present invention.

[0018] Figure 2 This is the second flow chart of the exercise prescription generation method provided by the present invention.

[0019] Figure 3 It is a structural schematic diagram of the exercise prescription generating device provided by the present invention.

[0020] Figure 4 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0021] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0022] Currently, exercise prescriptions are mostly generated based on general recommendations, such as exercise guidelines issued by authoritative organizations. However, these exercise guidelines ignore individual differences and fail to fully consider factors such as the patient's age, gender, physical condition, disease type, disease severity, exercise ability, lifestyle habits and preferences, which may lead to exercise plans that are not suitable for patients.

[0023] Alternatively, there are exercise prescriptions based on empirical judgment, such as those developed by doctors or exercise experts based on their clinical experience or professional expertise. However, empirical judgments are highly subjective and lack objective data support, making it difficult to guarantee the scientific and effective nature of the exercise plan. Furthermore, differences in experience between doctors or experts can lead to different exercise recommendations for the same patient, causing confusion.

[0024] Furthermore, the aforementioned approach fails to achieve closed-loop optimization, resulting in low efficiency and accuracy in exercise intervention. It is difficult to effectively assess the patient's exercise effectiveness, and the exercise plan cannot be dynamically adjusted based on the patient's actual condition.

[0025] To address this issue, the present invention provides a method for generating exercise prescriptions, establishing a fully closed-loop exercise intervention process from "assessment-intervention-feedback-evolution." Based on multimodal data input and an artificial intelligence decision-making engine, the present invention enables personalized, intelligent, and dynamically adjustable exercise prescription generation.

[0026] in, Figure 1 This is one of the flow charts of the method for generating an exercise prescription provided by the present invention, such as Figure 1 As shown, the method includes step 110 , step 120 and step 130 .

[0027] Step 110: Obtain the user's health data and physical fitness index data.

[0028] Here, the user's health data refers to various data that can reflect the user's physical health status, which is used to characterize the user's overall health level and potential health risks. For example, the user's health data may include eating habits, drinking habits, smoking habits, use of walkers, number of falls within 1 year, implant conditions, surgical history within 1 year, trauma conditions, illness conditions, body pain conditions, medication conditions, etc.

[0029] Fitness index data refers to various data that reflect the user's physical adaptability and athletic ability. It is used to characterize the user's physical quality and athletic ability. For example, fitness index data may include height (cm), weight (kg), body mass index, BMI (kg / m 2 ), body fat percentage (%), grip strength (kg), 6m walking speed (m / s), vital capacity (ml), timed stand-up, TUG (sec), choice reaction time (sec), chair forward bend (cm), 30-second sit-to-stand (times), back scratching (cm), 2-minute stepping (times), one-legged stand with eyes closed (sec), etc. As an optional embodiment, the user's health data can be obtained in the following ways: collecting the user's living habits, past medical history, family medical history, medication status, symptom description and other information through questionnaires, electronic medical record systems, wearable devices or physical examination reports.

[0030] As an optional embodiment, the user's physical fitness index data can be obtained by having a professional perform various physical fitness tests on the user using professional fitness testing equipment or scales, and recording the test results. For example, grip strength can be measured using a handgrip dynamometer, 6-meter gait speed can be measured using a stopwatch and tape measure, and vital capacity can be measured using a spirometer.

[0031] In addition, the trigger conditions for obtaining the user's health data and physical fitness index data may be the user's first use of the exercise prescription system, the user's regular review, or a change in the user's health status. That is, the user's health data and physical fitness index data can be obtained when the user registers for the first time, undergoes a health assessment, or there is a significant fluctuation in the user's health status.

[0032] Step 120: Build a user profile based on the health data and physical fitness index data. The user profile is used to characterize the user's health status, exercise ability, and potential exercise risks.

[0033] Specifically, a user portrait refers to a structured description of user characteristics. It abstracts various user information into labels and assigns corresponding weights, thereby comprehensively and three-dimensionally displaying the user's characteristics. Considering that if a user portrait is constructed based solely on health data, the user portrait may be one-sided due to the strong subjectivity of health data, which is easily limited by the patient's own cognitive and expressive abilities, and cannot objectively reflect the user's athletic ability. It is difficult to accurately assess the user's exercise risk and formulate a personalized exercise plan. If a user portrait is constructed based solely on physical fitness index data, the user portrait may be incomplete and unable to fully assess the user's health status and exercise risk issues because the physical fitness index data can only reflect the user's current physical function status and cannot understand the user's past medical history and potential health risks.

[0034] To this end, the embodiments of the present invention combine health data and physical fitness index data to construct a user portrait, so that the health data can reflect the user's overall health status and potential health risks from a macro level, and the physical fitness index data can reflect the user's physical quality and athletic ability from a micro level. The resulting user portrait can more comprehensively and accurately reflect the user's health status, athletic ability and potential sports risks, providing a reliable basis for the generation of personalized exercise prescriptions.

[0035] For example, a 65-year-old elderly woman with mild hypertension, who rarely exercises, has a high body fat percentage, and weak grip strength, may have a corresponding user profile of "risk of hypertension, weak exercise ability, needs to use low-intensity aerobic exercise and strength training as the starting exercise intensity, and should avoid heavy weights overhead or exercise training movements with the head below the level of the heart."

[0036] Constructing a user profile can be achieved by: ① Inputting health data and fitness index data into a profile generation model, which performs feature extraction, data fusion, and label generation, ultimately outputting a corresponding user profile. The model can be trained based on sample health data, sample fitness index data, and corresponding user profile labels, and can employ a deep neural network (DNN), convolutional neural network (CNN), or recurrent neural network (RNN) structure. ② Utilizing an expert system to analyze and judge health data and fitness index data based on preset rules and a knowledge base, automatically generating a user profile. ③ Utilizing a clustering algorithm, users with similar health data and fitness index data are clustered, generating a corresponding user profile for each cluster group. The above is an example of constructing a user profile; the embodiments of the present invention do not specifically limit the method for constructing a user profile.

[0037] Step 130: Generate an exercise prescription for the user based on the user portrait and the exercise guide. The exercise guide refers to suggestions and specifications for guiding different groups of people to perform scientific exercise.

[0038] Specifically, an exercise guide refers to exercise recommendations and specifications for different groups of people (such as specific age groups, genders, health conditions, etc.) issued by an authoritative organization or expert team, which aims to guide people to engage in safe and effective exercise to promote health and prevent disease. An exercise prescription refers to a personalized exercise plan developed based on an individual's health status, physical fitness level, exercise goals and preferences, as well as the recommendations of the exercise guide. It may include exercise type (aerobic training, resistance training, flexibility training, rhythmic training), exercise equipment (various types of smart aerobic training equipment, smart resistance training equipment, smart flexibility training equipment, smart rhythmic training equipment for different muscle groups), exercise intensity (subjective exertion, maximum heart rate intensity range, reserve heart rate intensity range), exercise frequency (times / week), exercise time (minutes), number of exercises (times / set), exercise cycle (week), exercise progression (incremental values ​​of exercise intensity, exercise frequency, exercise time and number of exercises), etc.

[0039] Based on the user profile, a selection of candidate exercise guides can be used to identify the most suitable exercise guide for the user, and an exercise prescription can be generated based on the selected exercise guide. Alternatively, the selection process can be as follows: The user profile's features are matched against the target demographic characteristics of each exercise guide, a similarity score is calculated, and the exercise guide with the highest similarity score is selected as the matching exercise guide for the user. For example, if the user profile indicates that the user suffers from high blood pressure, an exercise guide specifically designed for those with high blood pressure will be prioritized.

[0040] After obtaining the user portrait and exercise guide, personalized exercise goals and exercise risk prompts are generated based on the health status and exercise ability information in the user portrait. The exercise type, intensity, frequency and duration information in the exercise guide guides the specific content of the exercise prescription, and finally generates an exercise prescription that matches the user.

[0041] The exercise prescription generation method provided by the embodiments of the present invention constructs a user profile based on the user's health data and physical fitness index data, which comprehensively reflects the user's health status, exercise ability, and potential exercise risks. Combining the user profile with the exercise guide, a personalized exercise prescription is generated. Therefore, the embodiments of the present invention can generate customized exercise prescriptions for different users, fully considering individual differences, avoiding the limitations of universal recommendation schemes, and improving the applicability and effectiveness of exercise prescriptions, thereby improving users' exercise compliance and exercise results, and facilitating the health management and rehabilitation of patients with chronic diseases.

[0042] Based on the above embodiment, a user profile is constructed based on health data and physical fitness index data, including: Extract user features from health data and physical fitness index data; Build user portraits based on user characteristics.

[0043] Specifically, user characteristics refer to key information extracted from the user's health data and physical fitness index data that can represent the user's health status, athletic ability and potential sports risks. It is used to characterize multiple aspects of the user's physical condition, athletic ability, health risks, and sports preferences, and is the basis for building a user portrait.

[0044] To more effectively construct user profiles, it's necessary to extract user features from raw health and fitness metrics data. Raw data is often messy and contains a large amount of redundant information. Using this data directly to construct user profiles can reduce the accuracy and interpretability of the profiles. User feature extraction transforms raw data into concise, meaningful feature vectors, reducing data dimensionality, improving computational efficiency, and better highlighting key user attributes, facilitating subsequent profile construction and analysis.

[0045] Among them, user features can be extracted in the following ways: ① Domain experts manually select and combine features from the raw data based on their experience and knowledge. For example, a user's BMI value can be categorized as "underweight," "normal," "overweight," or "obese" as a feature.

[0046] ② Use machine learning algorithms to automatically extract features from raw data. For example, an autoencoder can be used to learn potential feature representations from a user’s health data.

[0047] Since user features are simpler, more representative, and have lower dimensions than raw data, when constructing user portraits based on user features, the construction efficiency and accuracy can be improved, the computational complexity can be reduced, and the key attributes of the user can be better highlighted, thereby obtaining a more interpretable and operational user portrait, providing a more reliable basis for the subsequent generation of exercise prescriptions. Optionally, user features can include health status features, physical fitness level features, exercise preference features, etc. These features can be normalized and assigned different weights, and then the weighted feature vectors are input into the pre-trained user portrait model. The model automatically generates a user portrait and displays it visually to construct a user portrait. The weights here can be determined based on the importance of the features, expert experience, or a machine learning algorithm.

[0048] Based on any of the above embodiments, generating an exercise prescription for the user based on the user profile and the exercise guide includes: Input the user profile into the exercise prescription generation model to obtain the exercise prescription output by the exercise prescription generation model; The exercise prescription generation model is obtained based on sample user portraits, sample exercise prescriptions and exercise guide training.

[0049] Specifically, the exercise prescription generation model is trained based on sample user portraits, sample exercise prescriptions, and exercise guidelines. The training process is as follows: First, a large amount of sample data is collected, including sample user portraits, corresponding sample exercise prescriptions, and related exercise guidelines. Then, the sample user portraits and exercise guidelines are used as the input of the model, and the sample exercise prescriptions are used as the output of the model. The parameters of the model are continuously adjusted through the back-propagation algorithm, so that the model can accurately predict the exercise prescriptions corresponding to the sample user portraits and exercise guidelines. Among them, the exercise prescription generation model has learned the relevant knowledge and rules of the exercise guide during the training process, so that the trained exercise prescription generation model can generate personalized exercise prescriptions that meet the recommendations of the exercise guide, ensuring the safety and effectiveness of exercise.

[0050] If the exercise prescription generation model does not use exercise guidelines as training data during training, but is trained based on sample user portraits and sample exercise prescriptions, and then the user portraits and exercise guidelines are input into the exercise prescription generation model, the model needs to learn the knowledge of the exercise guidelines during the inference stage, which increases the learning difficulty of the model and easily causes the exercise prescriptions generated by the model to not meet the recommendations of the exercise guidelines. Compared with the solution that uses exercise guidelines as samples when training the exercise prescription generation model, this solution has the problems of low model training efficiency, poor accuracy of generated exercise prescriptions, and difficulty in ensuring safe and effective exercise.

[0051] Therefore, in the embodiment of the present invention, the model obtains the exercise prescription generation model based on sample user portraits, sample exercise prescriptions and exercise guide training, which enables the model to fully learn the knowledge of the exercise guide during the training stage, improve the accuracy and safety of the exercise prescription generated by the model, and reduce the learning difficulty of the model, thereby realizing the rapid and accurate generation of exercise prescriptions that meet the user's personalized needs.

[0052] Based on any of the above embodiments, generating an exercise prescription for the user based on the user profile and the exercise guide, and then further comprising: Send exercise prescriptions to mobile devices; Receive the user's actual movement data and subjective feedback data returned by the mobile terminal; Update exercise prescription based on user's actual exercise data and user's subjective feedback data.

[0053] Specifically, a mobile terminal refers to a portable electronic device that can install applications and exchange data with a server. Mobile terminals may include smartphones, tablet computers, smart watches, etc. Considering that after an exercise prescription is generated, it is necessary to make the user aware of and execute the exercise prescription, and to collect user feedback data after exercise in order to dynamically adjust and optimize the exercise prescription, the embodiment of the present invention sends the exercise prescription to the mobile terminal, so that the user can conveniently view the exercise prescription at any time and use the convenience of the mobile terminal to record and feedback exercise data.

[0054] After receiving the exercise prescription on the mobile device, the user can exercise according to the exercise prescription. During the exercise, the mobile device can record the user's actual exercise data in real time. Alternatively, the user's actual exercise data can be collected through a monitoring tool (such as a heart rate monitor, sports bracelet, smart treadmill, etc.) and sent to the mobile device. The user's actual exercise data refers to the objective data generated during the user's exercise, which is used to represent the user's exercise status, exercise load, and exercise effect.

[0055] In addition, the user's actual exercise data is used to objectively reflect the user's exercise intensity, exercise duration, exercise trajectory and other objective indicators, while the user's subjective feedback data is the user's subjective feelings and experience of the exercise process, which is used to subjectively evaluate subjective feelings such as exercise comfort, fatigue level, and interest. Combining the two can reflect the user's exercise situation from both objective data and subjective feelings, and thus can update the exercise prescription more comprehensively and accurately, ensuring that the updated exercise prescription can fit the user's actual situation and subjective feelings.

[0056] Optionally, after the exercise prescription is updated, the updated exercise prescription can be sent to the mobile terminal so that the user can perform subsequent exercises according to the updated exercise prescription, and the user's exercise data and feedback can be continuously tracked to form a closed-loop optimization.

[0057] It can be seen that the embodiment of the present invention realizes dynamic adjustment and optimization of exercise prescription by sending exercise prescription to mobile terminal and receiving actual exercise data and subjective feedback data of user returned by mobile terminal, which can improve the efficiency and accuracy of exercise intervention and enhance the user's exercise compliance and exercise effect.

[0058] Based on any of the above embodiments, updating the exercise prescription further includes: Based on the user profile and the updated exercise prescription, update the exercise prescription generation model.

[0059] Specifically, the updated exercise prescription is adjusted based on the user's actual exercise data and subjective feedback, incorporating real-world feedback from the user on their exercise. Using this information to update the exercise prescription generation model allows the model to learn which exercise plans are more effective for a specific user and which ones should be avoided, thereby improving the quality of the model-generated exercise prescriptions.

[0060] It can be seen that the embodiment of the present invention, by combining the updated exercise prescription (i.e., the adjusted exercise plan that is more suitable for the user) with the user portrait as new training data, can enable the exercise prescription generation model to learn more detailed individual differences and improve the model's adaptability to different users.

[0061] Based on any of the above embodiments, obtaining the user's health data and physical fitness index data includes: Access to health data; Based on the health data, determine whether to generate an exercise prescription for the user. If so, obtain physical fitness index data.

[0062] Specifically, considering that not all users require or are suitable for exercise prescription intervention, by first acquiring health data, users who require exercise prescription can be preliminarily screened. For example, if a user's health is poor (such as suffering from a serious illness or physical weakness), immediate exercise intervention may not be appropriate. In this case, the collection of physical fitness index data is unnecessary, saving time and resources.

[0063] After determining that an exercise prescription needs to be generated for the user based on health data, physical fitness index data is obtained, thereby avoiding unnecessary physical fitness tests on the user and reducing data collection costs.

[0064] Based on any of the above embodiments, Figure 2 This is the second flow chart of the method for generating an exercise prescription provided by the present invention. Figure 2 As shown, the method includes: The user's health data is obtained and input into the health assessment and exercise risk identification module. The health assessment and exercise risk identification module determines whether to generate an exercise prescription for the user based on the health data. If so, the multi-source data acquisition and feature extraction module collects physical fitness index data and extracts user features from the health data and physical fitness index data.

[0065] The user profile is sent to the Crowd Portrait Database Construction Module, which constructs a user profile. The user profile is then sent to the Personalized Exercise Prescription Generation Module, where the exercise prescription generation model generates an exercise prescription and sends it to the mobile device. The exercise prescription generation model is trained based on sample user profiles, sample exercise prescriptions, and exercise guidelines.

[0066] The wearable device motion data acquisition module receives the user's actual motion data from the mobile device, while the user feedback collection and model learning module receives the user's subjective feedback data from the mobile device. The artificial intelligence training and prescription optimization module updates the exercise prescription based on the user's actual motion data and subjective feedback data, and updates the exercise prescription generation model based on the user profile and the updated exercise prescription. The user's actual motion data includes exercise heart rate, blood pressure before and after exercise, exercise type, exercise equipment usage, exercise intensity, exercise frequency, exercise time, number of exercises, exercise cycles, and exercise progression. The exercise prescription generation model can use recurrent neural networks (RNNs), long short-term memory networks (LSTMs), convolutional neural networks (CNNs), and other models.

[0067] Take Mr. Zhang, a 65-year-old male, for example. He suffers from hypertension and diabetes, with complications of diabetic foot. He has a history of medication, no recent surgery, and low physical activity levels. Hoping to improve his health through exercise, he participated in an AI-based personalized exercise intervention program for chronic diseases.

[0068] A medical screening questionnaire and risk assessment scale revealed Mr. Zhang's health data: he has a history of hypertension (stage II), diabetes, and diabetic foot; he typically engages in less than 30 minutes of physical activity per day; he occasionally experiences mild dizziness (exercise-induced); and he avoids exercise that places excessive strain on his feet and exercise during periods when hypoglycemic medications are most effective. Based on this health data, an exercise prescription is generated for Mr. Zhang.

[0069] Next, the physical fitness index data were collected: height: 170cm, weight: 78kg, BMI: 26.9 (overweight); body fat percentage: 28% (average), grip strength: 28kg (low), 6m walking speed: 0.7m / s (slow); vital capacity: 1800ml (low), TUG: 8.5s (slightly slow); choice reaction time: 0.456s (good), sit and stand 10 times in 30 seconds (average), back scratching: -12.2cm (low); 2-minute stepping: 48 times (average), standing on one leg with eyes closed: 5.6s (poor balance ability).

[0070] Based on the above health data and physical fitness index data, the constructed user portrait is: portrait of elderly men with hypertension; diabetes combined with diabetic foot; irregular exercise habits; medium to low exercise risk, suitable for starting with medium to low exercise intensity; poor cardiopulmonary function, poor balance, decreased flexibility, slow walking speed, and poor flexibility.

[0071] Based on this user profile, the corresponding exercise prescription is generated as follows: {Exercise Type: Aerobic Training (Smart Recumbent Exercise Bike), Resistance Training (Lower Limb Resistance Training), Flexibility Training (especially Shoulder Stretching Exercises)}. Table 1 shows the exercise prescription list.

[0072] Table 1 The exercise prescription is pushed to Mr. Zhang's smartphone through the APP. For this exercise prescription, the smartphone provides daily reminders and weekly progress tracking, displays exercise teaching videos, provides a real-time monitoring interface for the heart rate armband, and provides specific parameters for matching sports equipment.

[0073] For example, when Mr. Zhang used a smart recumbent exercise bike at 40 RPM, his exercise intensity reached RPE 11-13, with a slight to moderate effort. He achieved 50%-60% of his 1RM using the smart knee flexion and extension resistance training device, the smart lower limb abduction and adduction resistance training device, the smart push-up and pull-down resistance training device, and the smart chest press and rowing resistance training device at loads of 25kg, 10kg, 15kg, and 20kg, respectively. The smart shoulder stretching training device, the smart back stretching training device, and the smart hip and leg stretching training device reached their target stretching intensity at 150°, 45°, and 35°, respectively. Mr. Zhang reached his target exercise intensity when the horizontal rhythm bed reached a vibration frequency of 5Hz. Therefore, when Mr. Zhang exercises, the aforementioned training devices automatically adjust their parameters to that value.

[0074] Mr. Zhang uses a smart device to exercise according to the exercise prescription, wears a heart rate armband, and has his blood pressure checked before and after exercise. At the same time, the user's actual exercise data and subjective feedback data are collected.

[0075] The user's actual exercise data includes heart rate curves for each exercise session, blood pressure before and after exercise (measured by a wrist blood pressure monitor), actual exercise time, frequency, equipment usage records, and resistance weight training progress records. User subjective feedback data includes Mr. Zhang's subjective feelings, for example, feeling slightly tired after exercise. Based on the actual exercise time, Mr. Zhang's exercise time did not meet the recommended exercise time in the exercise prescription, indicating that the amount of exercise was too high. Therefore, the next AI exercise prescription automatically adjusts the exercise duration and intensity and uploads the adjusted values ​​to the system.

[0076] Based on the user's actual exercise data and subjective feedback data, Mr. Zhang's exercise prescription and the exercise prescription generation model are updated.

[0077] The exercise prescription generating device provided by the present invention is described below. The exercise prescription generating device described below and the exercise prescription generating method described above can be referenced to each other.

[0078] Based on any of the above embodiments, Figure 3 This is a schematic diagram of the structure of the exercise prescription generating device provided by the present invention. Figure 3 As shown, the device includes: An acquisition unit 310 is used to acquire the user's health data and physical fitness index data; A construction unit 320 is used to construct a user profile based on the health data and physical fitness index data, where the user profile is used to characterize the user's health status, exercise ability, and potential exercise risks; The generating unit 330 is used to generate an exercise prescription for the user based on the user portrait and the exercise guide. The exercise guide refers to suggestions and specifications for guiding different groups of people to perform scientific exercise.

[0079] Based on any of the above embodiments, constructing a user profile based on health data and physical fitness index data includes: Extract user features from health data and physical fitness index data; Build user portraits based on user characteristics.

[0080] Based on any of the above embodiments, generating an exercise prescription for the user based on the user profile and the exercise guide includes: Input the user profile into the exercise prescription generation model to obtain the exercise prescription output by the exercise prescription generation model; The exercise prescription generation model is obtained based on sample user portraits, sample exercise prescriptions and exercise guide training.

[0081] Based on any of the above embodiments, generating an exercise prescription for the user based on the user profile and the exercise guide, and then further comprising: Send exercise prescriptions to mobile devices; Receive the user's actual movement data and subjective feedback data returned by the mobile terminal; Update exercise prescription based on user's actual exercise data and user's subjective feedback data.

[0082] Based on any of the above embodiments, updating the exercise prescription further includes: Based on the user profile and the updated exercise prescription, update the exercise prescription generation model.

[0083] Based on any of the above embodiments, obtaining the user's health data and physical fitness index data includes: Access to health data; Based on the health data, determine whether to generate an exercise prescription for the user. If so, obtain physical fitness index data.

[0084] Figure 4 Schematic diagram of the structure of the electronic device provided by the present invention, such as Figure 4 As shown, the electronic device may include: a processor 410, a communications interface 420, a memory 430, and a communication bus 440, wherein the processor 410, the communications interface 420, and the memory 430 communicate with each other via the communications bus 440. The processor 410 may call logic instructions in the memory 430 to execute an exercise prescription generation method, which includes: obtaining a user's health data and physical fitness index data; constructing a user profile based on the health data and the physical fitness index data, wherein the user profile is used to characterize the user's health status, exercise ability, and potential exercise risks; and generating an exercise prescription for the user based on the user profile and an exercise guide, wherein the exercise guide refers to suggestions and specifications for guiding different groups of people to perform scientific exercise.

[0085] Furthermore, the logic instructions in the aforementioned memory 430 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product, stored in a storage medium, includes instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0086] On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the exercise prescription generation method provided by the above methods, which includes: obtaining the user's health data and physical fitness index data; based on the health data and the physical fitness index data, constructing a user portrait, and the user portrait is used to characterize the user's health status, exercise ability and potential exercise risks; based on the user portrait and the exercise guide, generating the user's exercise prescription, and the exercise guide refers to suggestions and specifications for guiding different groups of people to perform scientific exercise.

[0087] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the exercise prescription generation method provided by the above-mentioned methods, the method comprising: obtaining the user's health data and physical fitness index data; constructing a user portrait based on the health data and the physical fitness index data, the user portrait being used to characterize the user's health status, exercise ability and potential exercise risks; generating the user's exercise prescription based on the user portrait and the exercise guide, the exercise guide referring to suggestions and specifications for guiding different groups of people to perform scientific exercise.

[0088] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0089] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0090] 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 make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for generating an exercise prescription, characterized in that: include: Obtain users' health data and physical fitness index data; Building a user profile based on the health data and the physical fitness index data, wherein the user profile is used to characterize the user's health status, exercise ability, and potential exercise risks; Based on the user portrait and the exercise guide, an exercise prescription for the user is generated. The exercise guide refers to suggestions and specifications for guiding different groups of people to perform scientific exercise.

2. The method for generating an exercise prescription according to claim 1, wherein: The constructing of a user profile based on the health data and the physical fitness index data includes: extracting user features from the health data and the physical fitness index data; Based on the user characteristics, the user portrait is constructed.

3. The method for generating an exercise prescription according to claim 1, wherein: Generating an exercise prescription for the user based on the user portrait and the exercise guide includes: Inputting the user portrait into an exercise prescription generation model to obtain the exercise prescription output by the exercise prescription generation model; The exercise prescription generation model is obtained based on sample user portraits, sample exercise prescriptions and the exercise guide training.

4. The method for generating an exercise prescription according to claim 3, wherein: The step of generating an exercise prescription for the user based on the user portrait and the exercise guide further includes: Sending the exercise prescription to a mobile terminal; Receiving the user's actual motion data and user's subjective feedback data returned by the mobile terminal; The exercise prescription is updated based on the user's actual exercise data and the user's subjective feedback data.

5. The method for generating an exercise prescription according to claim 4, wherein: The updating of the exercise prescription further includes: Based on the user portrait and the updated exercise prescription, the exercise prescription generation model is updated.

6. The method for generating an exercise prescription according to claim 1, wherein: The acquisition of the user's health data and physical fitness index data includes: obtaining the health data; Based on the health data, it is determined whether to generate an exercise prescription for the user, and if so, the physical fitness index data is obtained.

7. An exercise prescription generating device, characterized in that: include: An acquisition unit, used to obtain the user's health data and physical fitness index data; A construction unit, configured to construct a user profile based on the health data and the physical fitness index data, wherein the user profile is used to characterize the user's health status, exercise ability, and potential exercise risks; A generating unit is used to generate an exercise prescription for the user based on the user portrait and the exercise guide, where the exercise guide refers to suggestions and specifications for guiding different groups of people to perform scientific exercise.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the exercise prescription generating method according to any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the exercise prescription generating method according to any one of claims 1 to 6 is implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the exercise prescription generating method according to any one of claims 1 to 6 is implemented.

Images