Orthopedic science popularization recommendation system based on smart health

Abstract

The invention discloses an orthopedic science popularization recommendation system based on smart health, and belongs to the technical field of smart health. Through the immersive interaction module, the user can check and interact in the virtual environment, the health state of the bone and the influence of movement on the bone are known in real time, through dynamic display of the personalized bone model, the user can more visually understand the bone health of the user, and the user experience is improved. The intelligent recommendation module identifies interest points and health requirements of the user by collecting behavior data of the user in the immersive interaction module, pushes personalized orthopedic knowledge content based on the interest points and the health requirements, and helps the user to obtain targeted health suggestions and popular science knowledge, so that the accuracy and effectiveness of health management are improved, and the user experience is improved. The health awareness and long-term attention of the user are improved by enhancing the sense of participation and the education effect of the user, and the user is ensured to obtain health knowledge most relevant to the own condition by analyzing the behavior data and the health condition of the user and pushing the content matched with the health requirement of the user.

Description

Technical Field

[0001] The present invention relates to the field of smart health technology, and in particular to an orthopedic science popularization recommendation system based on smart health. Background Art

[0002] Orthopedic problems such as osteoporosis, fractures, and joint diseases are becoming increasingly common health concerns, especially among the middle-aged and elderly population. Traditional orthopedic health management often relies on regular physical examinations, drug treatments, and passive medical interventions. This model has certain limitations in improving bone health and preventing bone diseases. Especially in the early stages of the disease, the lack of effective prediction and intervention methods has led to many bone diseases not being diagnosed and treated in a timely manner in the asymptomatic stage.

[0003] In recent years, with the popularization of smart health devices and the development of technologies such as virtual reality (VR) and augmented reality (AR), digital health management and virtual interactive platforms have gradually become research hotspots in the field of orthopedic health. The combination of data collection based on smart health devices and virtual reality technology can provide more accurate and personalized health management services.

[0004] However, most of the relevant technology applications on the market are still limited to the realization of a single function and lack comprehensive health management solutions, especially in bone health management, rehabilitation training, and popular science education, which have not been fully developed.

[0005] In addition, although there are certain health recommendation systems, most recommendation systems still have the problem of insufficient personalization of push content and lack of accurate health intervention measures. Traditional health science popularization content push is mostly static and one-way communication, lacks user interaction and feedback mechanism, and cannot adjust push content in time according to user's personalized needs. Summary of the invention

[0006] The purpose of the present invention is to provide an orthopedic science popularization recommendation system based on smart health to solve the problems raised in the above background technology.

[0007] To achieve the above objectives, the present invention provides the following technical solutions: an orthopedic science popularization recommendation system based on smart health, comprising: Skeletal data acquisition module for: Collect users' bone health data in real time through smart health devices, and filter, denoise and calibrate the bone health data collected in real time; Digital twin building blocks for: Generate a personalized bone model based on the user's bone health data and calibrate the dynamic parameters of the bone model; Immersive interaction modules for: The bone model is loaded through the VR device worn by the user and rehabilitation tasks are generated. The physical engine is used to control the bone model to simulate the bone response under different motion states, simulating the bone aging process and the impact of sports injuries. Smart recommendation module for: Build a content database, identify users' interests and needs based on their behavior data in the immersive interaction module, and push orthopedic knowledge content in the content database; Health monitoring feedback module for: Compare the real-time collected bone health data with the user's historical data to evaluate the trend of bone health changes and generate a health report including joint pressure distribution and bone health change trends; User management control module, used for: Establish a multi-user management mechanism, and perform user account registration, login and personalized data binding based on the multi-user management mechanism.

[0008] Furthermore, the smart health device includes a bone monitor and a gait analyzer, and the bone health data includes joint pressure, bone strength and gait characteristics.

[0009] Furthermore, the bone model includes bone structure, joint motion range and dynamic display capability, and the dynamic parameter calibration includes simulating joint pressure distribution and bone strength change trend.

[0010] Furthermore, the immersive interaction module includes: Bone model loading unit, used for: Obtain a bone model generated by a digital twin construction module based on the user's bone health data, interact with a VR device, and present the bone model in a virtual environment based on the display function of the VR device, wherein the display of the bone model includes the three-dimensional structure, joint connection, range of motion, and dynamic changes of the bone; Motion simulation unit for: The user's current action instructions are obtained. The action instructions are selected by the user through the VR device. The bone reaction of the skeleton in the specified motion state is simulated based on the action instructions. The bone reaction includes joint pressure distribution and bone load response. The physical engine is used to simulate the instant changes and effects of joint pressure distribution during motion, and the changes in bone health data of the bone model under different motion states are simulated.

[0011] Furthermore, the immersive interaction module further includes: Bone aging simulation unit for: Based on the user's bone health data, simulate the user's bone aging process, including changes in bone density and joint range of motion, calculate the load bearing capacity of the bones and possible injuries during exercise, and simulate the impact of sports injuries on bones; Rehabilitation Task Feedback Unit for: Based on the user's bone health data, the user's joint pressure and bone strength index are analyzed, and a personalized rehabilitation task is generated based on the user's joint pressure and bone strength index. The rehabilitation task includes a specified exercise and exercise intensity. The rehabilitation task is performed by the user wearing a VR device, and the rehabilitation task feedback unit provides real-time feedback based on the user's behavior and task completion status; The user's bone health data is updated based on task completion of the rehabilitation task.

[0012] Furthermore, the intelligent recommendation module includes: Database building blocks for: Constructing a content database, wherein the content database is used to store orthopedic knowledge content in the form of video, text and animation, wherein the orthopedic knowledge content includes bone anatomy, bone health maintenance, sports injury prevention and rehabilitation training content; Behavioral data collection unit, used for: During the interaction between the user and the immersive interaction module, the user's behavioral data is recorded in real time. The behavioral data includes the dynamics of the bone reaction model viewed by the user, the completed rehabilitation tasks and the status of task completion. The user's actions, choices and interactions are collected and stored, and the user's behavioral data and bone health data are associated.

[0013] Furthermore, the intelligent recommendation module further includes: Point of interest recognition unit, used to: Analyze the user's behavior data and identify the user's interests based on the user's selection patterns, viewing time, and interaction frequency indicators in the immersive interaction module, including preferences for specific types of orthopedic knowledge and attention to specific rehabilitation tasks; Combining the user's bone health data and points of interest, using content-based recommendation algorithms and collaborative filtering algorithms, a personalized recommendation strategy is generated; Content push feedback unit, used for: Search the content database according to the user's personalized recommendation strategy, and generate personalized push content based on the search results; Collect user feedback data on personalized pushed content, including whether the user watched the content, the viewing time, and the viewing completion status, and evaluate the content push effect based on the feedback data.

[0014] Furthermore, the health monitoring feedback module is also used to: Compare current real-time bone health data with historical bone health data to evaluate bone health change trends, including changes in bone strength, bone density, and distribution of joint pressure; Predicting bone health risks based on bone health change trends, wherein the bone health risks include osteoporosis and fracture risks; Generate charts and output health reports based on bone health change trends.

[0015] Furthermore, the current real-time bone health data is compared with the historical bone health data to evaluate the trend of bone health changes, including: Matching the current real-time bone health data with the historical bone health data of the previous moment to obtain the first matching result of the bone health data; Perform a preliminary analysis of the bone health data based on the first matching result of the bone health data, obtain the difference between the current real-time bone health data and the historical bone health data at the previous moment, and obtain preliminary analysis data of the current bone health data; Performing a judgment on the current preliminary analysis data of the bone health data to determine whether the current preliminary analysis data of the bone health data is zero, and obtaining a first analysis and judgment result; When the first analysis judgment result is that the preliminary analysis data of the current bone health data is not zero, the historical preliminary analysis data of the current bone health data is retrieved; The current preliminary analysis data of bone health data is combined with the historical preliminary analysis data of current bone health data to obtain a fitting curve; Perform feature analysis on the fitting curve, and make trend prediction based on the features of the fitting curve to obtain the trend of bone health changes; When the first analysis result shows that the preliminary analysis data of the current bone health data is zero, a preset number of historical bone health data are retrieved, and the historical bone health data of the previous moment are removed from the retrieved result to obtain the target analysis data; Matching the current real-time bone health data with the target analysis data to obtain a second matching result of the bone health data; Calculate the difference between the current real-time bone health data and the target analysis data based on the second matching result of the bone health data to obtain the second analysis data of the current bone health data; Judging the second analysis data of the current bone health data, determining whether the second analysis data of the current bone health data is zero, and obtaining a second analysis judgment result; When the second analysis judgment result is that the current bone health data and the second analysis data are both zero, determining that the bone health change trend is constant according to the current bone health data, the second analysis data and the current bone health data, the preliminary analysis data; When the second analysis judgment result is that the second analysis data of the current bone health data is not zero, the corresponding time is determined for the target analysis data, and the predicted data is determined by the following formula: In the above technical solution, Predictive data for bone health, For current bone health data, For the Target analysis data, is the time information corresponding to the current bone health data, For the The time information corresponding to each target analysis data.

[0016] Furthermore, bone health risks are predicted based on the trend of bone health changes, including: Obtain basic information of the user, including age information and behavior preference information; Identify the age information in the user's basic information, determine the age group of the user based on the age information, and then analyze the bone features of the age group based on the age group to obtain the user's bone feature information; Perform bone health analysis based on the user's bone feature information, determine the impact of age information on bone health, and obtain the first influencing factor; Identify the behavior preference information in the basic information of the user, and obtain a first analysis result according to whether the behavior preference information has an impact on bone health; When the first analysis result is that the behavior preference information has an impact on bone health, the behavior preference information is decomposed to obtain a plurality of behavior preference sub-actions; Analyze the influence of behavioral preference sub-actions on bone health and obtain the second influencing sub-factor; Combined with the relationship between the sub-actions of behavior preference, the second influencing sub-factor is comprehensively analyzed to obtain the second influencing factor; Conduct bone health risk analysis based on bone health change trends to obtain initial prediction information on bone health risks; The first influencing factor and the second influencing factor are used to correct the initial prediction information of bone health risk to obtain the final bone health risk prediction information.

[0017] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention provides an immersive interactive environment through virtual reality technology, allowing users to intuitively perceive their own bone health status and exercise impact, while conducting personalized rehabilitation task training. According to the user's behavioral data and bone health status, the present invention accurately pushes popular science content related to their health needs and interests, thereby improving the accuracy and effectiveness of health management. The personalized service based on the user's real-time data and interactive behavior can provide users with more scientific and customized health intervention plans, effectively helping users manage and improve bone health.

[0018] 2. The present invention greatly enhances the user's sense of participation and initiative in health learning through immersive interaction and personalized content push. Through the interactive experience in the virtual reality environment, users can not only gain a deep understanding of bone health knowledge, but also intuitively see the changes and impacts of bone health by simulating different movements and aging processes. This dynamic display and feedback mechanism enhances the user's learning interest and effect. By recommending relevant content based on the user's health data and behavioral habits, users can obtain targeted knowledge and rehabilitation suggestions in continuous learning, thereby enhancing their health awareness and encouraging continued attention to bone health issues. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a schematic diagram of the orthopedic science popularization recommendation system module of the present invention. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] See also Figure 1 , the present invention provides the following technical solutions: The orthopedic science recommendation system based on smart health includes: Skeletal data acquisition module for: Collect the user's bone health data in real time through smart health devices, and filter, denoise and calibrate the real-time collected bone health data. Smart health devices include bone monitors and gait analyzers. Bone health data includes joint pressure, bone strength and gait characteristics. Digital twin building blocks for: Generate a personalized bone model based on the user's bone health data, and calibrate the dynamic parameters of the bone model. The bone model includes bone structure, joint motion range, and dynamic display capabilities. The dynamic parameter calibration includes simulating joint pressure distribution and bone strength change trends. Immersive interaction modules for: The bone model is loaded through the VR device worn by the user and rehabilitation tasks are generated. The physical engine is used to control the bone model to simulate the bone response under different motion states, simulating the bone aging process and the impact of sports injuries. Smart recommendation module for: Build a content database, identify users' interests and needs based on their behavior data in the immersive interaction module, and push orthopedic knowledge content in the content database; Health monitoring feedback module for: Compare the current real-time bone health data with the historical bone health data, evaluate the trend of bone health changes, including changes in bone strength, bone density and distribution of joint pressure, predict bone health risks based on the trend of bone health changes, including osteoporosis and fracture risks, generate charts based on the trend of bone health changes and output health reports; User management control module, used for: Establish a multi-user management mechanism, and perform user account registration, login and personalized data binding based on the multi-user management mechanism.

[0022] In the above embodiment, by acquiring the user's bone health data in real time and combining the multi-dimensional data collected by the gait analyzer and the bone monitor, the system can comprehensively analyze the user's joint pressure, bone strength, bone density and gait characteristics, providing a solid foundation for subsequent health assessments and personalized recommendations. It compares real-time health data with historical data, dynamically assesses the user's bone health trends, and generates health reports based on this trend to predict potential health risks (such as osteoporosis or fractures), which not only ensures the accuracy of health data, but also helps users detect bone health problems in a timely manner and intervene in advance.

[0023] In the above embodiment, through the immersive interaction module combined with VR equipment, the user can interact with the personalized bone model in the virtual environment, and by receiving the user's motion instructions in real time, simulating the distribution changes of joint pressure and bone load response, it helps the user understand the impact of different motion states on the bones, and then optimize the movement posture. Based on the user's bone health data, personalized rehabilitation tasks are formulated, and real-time feedback is provided according to the task execution, thereby effectively promoting the rehabilitation effect. It can not only enhance the user's sense of participation, but also help users better adjust their exercise habits and avoid sports injuries through scientific feedback.

[0024] In the above embodiment, a personalized orthopedic science popularization content method is provided for users. By tracking the user's interactive behavior in the immersive interaction module, such as watching the model dynamics, completing the rehabilitation tasks, etc., the user's interest points are accurately identified. According to the user's preferences, the content recommendation algorithm is used to intelligently recommend orthopedic knowledge content, such as bone anatomy, bone health maintenance, sports injury prevention, etc. According to the user's feedback data, such as viewing time, viewing completion status, etc., the recommendation strategy is optimized in real time. The personalized push method can maximize the user's learning needs and improve their efficiency in absorbing health science popularization knowledge.

[0025] Immersive interactive modules, including: Bone model loading unit, used for: Obtain the bone model generated by the digital twin building module based on the user's bone health data, interact with the VR device, and present the bone model in the virtual environment based on the display function of the VR device. The display of the bone model includes the three-dimensional structure, joint connection, range of motion and dynamic changes of the bone; Motion simulation unit for: Get the user's current action command. The action command is selected by the user through the VR device. Based on the action command, simulate the bone response of the skeleton in the specified motion state. The bone response includes joint pressure distribution and bone load response. Use the physical engine to simulate the instant changes and effects of joint pressure distribution during motion, and simulate the changes in bone health data of the bone model in different motion states. Bone aging simulation unit for: Based on the user's bone health data, the system simulates the user's bone aging process, including changes in bone density and range of motion of joints, calculates the load bearing capacity of bones and possible injuries during exercise, and simulates the impact of sports injuries on bones; Rehabilitation Task Feedback Unit for: Based on the user's bone health data, the user's joint pressure and bone strength indicators are analyzed, and personalized rehabilitation tasks are generated based on the user's joint pressure and bone strength indicators. The rehabilitation tasks include specified exercises and exercise intensity. The rehabilitation tasks are performed by the user wearing VR equipment. The rehabilitation task feedback unit provides real-time feedback based on the user's behavior and task completion status; The user's bone health data is updated based on task completion of the rehabilitation task.

[0026] In the above embodiment, through the combination of the bone model loading unit and the VR device, the user can personally experience and observe his or her personalized bone model in a virtual environment, so that the user is no longer just passively receiving information, but actively participating in the process of health management. Through the dynamically displayed three-dimensional bone model, the user can see the three-dimensional structure of the bone, joint connection, range of motion and other details. At the same time, the motion state simulation unit allows the user to feel the impact of exercise on bone health in real time when performing virtual motion tasks. For example, the user can see the changes in joint pressure under different motion states in the virtual environment, which further helps him or her understand the relationship between exercise habits and bone health.

[0027] In the above embodiment, the motion state simulation of the immersive interaction module is not limited to observation and feedback, it also simulates the bone reaction in motion through the physical engine. Through this function, the user can see the immediate impact of different types of motion on bones, joints and soft tissues, such as joint pressure distribution and bone load response during motion. For example, when simulating running, jumping, walking and other movements, the system will display the distribution of joint pressure and the potential risk of sports injuries, so that users can understand how to adjust their movement through the virtual reality environment to avoid health problems such as joint injuries or fractures caused by excessive load.

[0028] In addition, the bone aging simulation unit simulates the aging process of the user's bones over time. The system allows users to see in advance the impact of health problems such as decreased bone density and limited range of joint motion. Especially in the early manifestations of osteoporosis, the aging simulation allows users to experience the bone decline process immersively. This intuitive experience can effectively arouse users' attention to health management and motivate them to take more scientific prevention and rehabilitation measures.

[0029] In the above embodiment, the rehabilitation task feedback unit intelligently generates personalized exercise tasks based on the user's bone health data. These tasks include specified exercise movements and intensities, aiming to help users perform rehabilitation training in a virtual environment. More importantly, the rehabilitation task feedback unit can monitor and feedback the user's execution in real time. When the user completes an action, the system will provide timely feedback based on the exercise effect, reminding the user to adjust the posture, control the range of motion or increase the intensity of the exercise to ensure that the execution of the rehabilitation task is more accurate and effective. Through this feedback mechanism, users can gradually improve the rehabilitation effect, maintain a healthy state, and reduce the damage to the bones that may be caused by improper exercise.

[0030] Intelligent recommendation module, including: Database building blocks for: Build a content database, which is used to store orthopedic knowledge content in the form of video, text and animation. The orthopedic knowledge content includes bone anatomy, bone health maintenance, sports injury prevention and rehabilitation training; Behavioral data collection unit, used for: During the interaction between the user and the immersive interaction module, the user's behavior data is recorded in real time. The behavior data includes the dynamics of the bone reaction model viewed by the user, the rehabilitation tasks completed and the completion status of the tasks. The user's actions, choices and interactions are collected and stored, and the user's behavior data and bone health data are associated. Point of interest recognition unit, used to: Analyze user behavior data and identify user interests based on user selection patterns, viewing time, and interaction frequency indicators in immersive interaction modules, including preferences for specific types of orthopedic knowledge and attention to specific rehabilitation tasks; Combining the user's bone health data and points of interest, using content-based recommendation algorithms and collaborative filtering algorithms, a personalized recommendation strategy is generated; Content push feedback unit, used for: Search the content database according to the user's personalized recommendation strategy, and generate personalized push content based on the search results; Collect user feedback data on personalized push content. The feedback data includes whether the user has watched the content, the viewing time, and whether the user has completed the viewing. The content push effect is evaluated based on the feedback data.

[0031] In the above embodiment, all interactive behaviors of the user in the immersive interaction module are recorded in real time, including the dynamics of the skeletal reaction model watched, the rehabilitation tasks completed, and the viewing time and task completion status. These behavioral data not only help the system to accurately understand the user's points of interest, but also provide data support for the accurate push of recommended content. By analyzing indicators such as user selection patterns, viewing time, and interaction frequency in the virtual environment, the user's preference for certain specific types of orthopedic knowledge can be identified. For example, if a user chooses to view sports injury prevention content or rehabilitation training content multiple times in the system, the system will be able to identify his interest in such content and give priority to recommending related videos, articles or animation materials. Through this precise point of interest identification, the system can tailor popular science content that best meets the needs of each user.

[0032] In the above embodiment, the intelligent recommendation module provides users with personalized orthopedic health science content through advanced content recommendation algorithms (such as content-based recommendation and collaborative filtering algorithms). For example, if a user's bone health data shows that his joint pressure is relatively high, the system can push relevant knowledge content such as joint maintenance and sports injury prevention. This recommendation strategy is not only based on the user's interests, but also combined with the user's actual health status to achieve accurate and practical information push. By analyzing the behavioral data of a large number of users, the system can predict other popular science content that a user may be interested in. For example, if other users with similar health conditions also show interest in bone density maintenance-related content, the system will recommend the content to the target user. In this way, the intelligent recommendation module can continuously adjust the recommendation strategy based on the user's feedback data to make the pushed content more in line with the user's actual needs and changes.

[0033] In the above embodiment, the content push feedback unit can optimize the recommendation strategy in real time by collecting user feedback data on the pushed content, such as whether it has been watched, the viewing time, and the completion of the viewing. This mechanism ensures the accuracy of the recommendation and adjusts the recommended content according to the changes in user interests. For example, if a user develops a new interest in a certain type of orthopedic knowledge, the system can identify and update the content in a timely manner through the analysis of feedback data, so as to provide push content that better meets the user's needs. Through this mechanism, the intelligent recommendation module not only provides a personalized learning experience, but also helps users master orthopedic health knowledge more effectively and improve their self-management capabilities.

[0034] In the above embodiment, the intelligent recommendation module improves the user's health management efficiency by providing users with accurate health science content to help them better understand the key factors of bone health management. Compared with the traditional single health guidance method, the intelligent recommendation module can respond to user needs in real time and continuously optimize the recommended content, thereby increasing the user's learning motivation and participation. Through personalized science push, users can not only better understand and deal with bone health problems in daily life, but also get more practical advice and guidance, thereby realizing the initiative and long-term nature of health management.

[0035] Compare current real-time bone health data with historical bone health data to assess bone health trends, including: Matching the current real-time bone health data with the historical bone health data of the previous moment to obtain the first matching result of the bone health data; Perform a preliminary analysis of the bone health data based on the first matching result of the bone health data, obtain the difference between the current real-time bone health data and the historical bone health data at the previous moment, and obtain preliminary analysis data of the current bone health data; Performing a judgment on the current preliminary analysis data of the bone health data to determine whether the current preliminary analysis data of the bone health data is zero, and obtaining a first analysis and judgment result; When the first analysis judgment result is that the preliminary analysis data of the current bone health data is not zero, the historical preliminary analysis data of the current bone health data is retrieved; The current preliminary analysis data of bone health data is combined with the historical preliminary analysis data of current bone health data to obtain a fitting curve; Perform feature analysis on the fitting curve, and make trend prediction based on the features of the fitting curve to obtain the trend of bone health changes; When the first analysis result shows that the preliminary analysis data of the current bone health data is zero, a preset number of historical bone health data are retrieved, and the historical bone health data of the previous moment are removed from the retrieved result to obtain the target analysis data; Matching the current real-time bone health data with the target analysis data to obtain a second matching result of the bone health data; Calculate the difference between the current real-time bone health data and the target analysis data based on the second matching result of the bone health data to obtain the second analysis data of the current bone health data; Judging the second analysis data of the current bone health data, determining whether the second analysis data of the current bone health data is zero, and obtaining a second analysis judgment result; When the second analysis judgment result is that the current bone health data and the second analysis data are both zero, determining that the bone health change trend is constant according to the current bone health data, the second analysis data and the current bone health data, the preliminary analysis data; When the second analysis judgment result is that the second analysis data of the current bone health data is not zero, the corresponding time is determined for the target analysis data, and the predicted data is determined by the following formula: In the above technical solution, Predictive data for bone health, For current bone health data, For the Target analysis data, is the time information corresponding to the current bone health data, For the The time information corresponding to each target analysis data.

[0036] In the above embodiment, matching is performed so that trend analysis and prediction can be performed synchronously on the distribution of bone strength, bone density and joint pressure, thereby improving the efficiency of evaluating the trend of bone health changes. Moreover, by performing a preliminary analysis of the bone health data based on the first matching result of the bone health data, when the first analysis judgment result is that the preliminary analysis data of the current bone health data is not zero, trend prediction can be performed directly through fitting. When the first analysis judgment result is that the preliminary analysis data of the current bone health data is zero, it can be further combined with the historical bone health data for analysis to avoid the situation where the adjacent historical bone health data is small and is ignored, which brings about an analysis illusion and reduces the error in evaluating the trend of bone health changes. Moreover, when the second analysis judgment result is that the second analysis data of the current bone health data is not zero, trend analysis and prediction are performed in combination with the time corresponding to the target analysis data and the current bone health data as a whole, thereby improving the efficiency of trend analysis and prediction, so that bone health prediction data can be obtained in a shorter time, and at the same time, the accuracy of evaluating the trend of bone health changes is also improved, thereby providing a guarantee for the health report and improving the accuracy of the orthopedic science popularization recommendation system based on smart health.

[0037] Predict bone health risks based on bone health trends, including: Obtain basic information of the user, including age information and behavior preference information; Identify the age information in the user's basic information, determine the age group of the user based on the age information, and then analyze the bone features of the age group based on the age group to obtain the user's bone feature information; Perform bone health analysis based on the user's bone feature information, determine the impact of age information on bone health, and obtain the first influencing factor; Identify the behavior preference information in the basic information of the user, and obtain a first analysis result according to whether the behavior preference information has an impact on bone health; When the first analysis result is that the behavior preference information has an impact on bone health, the behavior preference information is decomposed to obtain a plurality of behavior preference sub-actions; Analyze the influence of behavioral preference sub-actions on bone health and obtain the second influencing sub-factor; Combined with the relationship between the sub-actions of behavior preference, the second influencing sub-factor is comprehensively analyzed to obtain the second influencing factor; Conduct bone health risk analysis based on bone health change trends to obtain initial prediction information on bone health risks; The first influencing factor and the second influencing factor are used to correct the initial prediction information of bone health risk to obtain the final bone health risk prediction information.

[0038] Among them, the final bone health risk prediction information is obtained by predicting the bone health risk based on the trend of bone health changes. Behavioral preference information refers to the user's habitual behavior in daily life. When the first analysis result shows that the behavioral preference information has no effect on bone health, it is only necessary to use the first influencing factor to correct the initial bone health risk prediction information to obtain the final bone health risk prediction information.

[0039] In the above embodiment, the impact of the user's own condition on bone health is taken into account in the process of predicting bone health risks based on the trend of bone health changes, so that the orthopedic science popularization recommendation system based on smart health can make adaptive corrections according to the individual conditions of different users when predicting bone health risks, thereby improving the accuracy of bone health risk prediction, improving the protection of health reports on bone health changes, and reducing the errors of the orthopedic science popularization recommendation system based on smart health.

[0040] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. The orthopedic science recommendation system based on smart health is characterized by: include: Skeletal data acquisition module for: Collect users' bone health data in real time through smart health devices, and filter, denoise and calibrate the bone health data collected in real time; Digital twin building blocks for: Generate a personalized bone model based on the user's bone health data and calibrate the dynamic parameters of the bone model; Immersive interaction modules for: The bone model is loaded through the VR device worn by the user and rehabilitation tasks are generated. The physical engine is used to control the bone model to simulate the bone response under different motion states, simulating the bone aging process and the impact of sports injuries. Smart recommendation module for: Build a content database, identify users' interests and needs based on their behavior data in the immersive interaction module, and push orthopedic knowledge content in the content database; Health monitoring feedback module for: Compare the real-time collected bone health data with the user's historical data to evaluate the trend of bone health changes and generate a health report including joint pressure distribution and bone health change trends; User management control module, used for: Establish a multi-user management mechanism, and perform user account registration, login and personalized data binding based on the multi-user management mechanism.

2. The orthopedic science popularization recommendation system based on smart health as claimed in claim 1, characterized in that: The health monitoring feedback module is also used for: Compare current real-time bone health data with historical bone health data to evaluate bone health change trends, including changes in bone strength, bone density, and distribution of joint pressure; Predicting bone health risks based on bone health change trends, wherein the bone health risks include osteoporosis and fracture risks; Generate charts and output health reports based on bone health change trends.

3. The orthopedic science popularization recommendation system based on smart health as claimed in claim 2, characterized in that: Compare current real-time bone health data with historical bone health data to assess bone health trends, including: Matching the current real-time bone health data with the historical bone health data of the previous moment to obtain the first matching result of the bone health data; Perform a preliminary analysis of the bone health data based on the first matching result of the bone health data, obtain the difference between the current real-time bone health data and the historical bone health data at the previous moment, and obtain preliminary analysis data of the current bone health data; Performing a judgment on the current preliminary analysis data of the bone health data to determine whether the current preliminary analysis data of the bone health data is zero, and obtaining a first analysis and judgment result; When the first analysis judgment result is that the preliminary analysis data of the current bone health data is not zero, the historical preliminary analysis data of the current bone health data is retrieved; The current preliminary analysis data of bone health data is combined with the historical preliminary analysis data of current bone health data to obtain a fitting curve; Perform feature analysis on the fitting curve, and make trend prediction based on the features of the fitting curve to obtain the trend of bone health changes; When the first analysis result shows that the preliminary analysis data of the current bone health data is zero, a preset number of historical bone health data are retrieved, and the historical bone health data of the previous moment are removed from the retrieved result to obtain the target analysis data; Matching the current real-time bone health data with the target analysis data to obtain a second matching result of the bone health data; Calculate the difference between the current real-time bone health data and the target analysis data based on the second matching result of the bone health data to obtain the second analysis data of the current bone health data; Judging the second analysis data of the current bone health data, determining whether the second analysis data of the current bone health data is zero, and obtaining a second analysis judgment result; When the second analysis judgment result is that the current bone health data and the second analysis data are both zero, determining that the bone health change trend is constant according to the current bone health data, the second analysis data and the current bone health data, the preliminary analysis data; When the second analysis judgment result is that the second analysis data of the current bone health data is not zero, the corresponding time is determined for the target analysis data, and the predicted data is determined by the following formula: In the above technical solution, Predictive data for bone health, For current bone health data, For the Target analysis data, is the time information corresponding to the current bone health data, For the The time information corresponding to each target analysis data.

4. The orthopedic science popularization recommendation system based on smart health as claimed in claim 1, characterized in that: The smart health device includes a bone monitor and a gait analyzer, and the bone health data includes joint pressure, bone strength and gait characteristics.

5. The orthopedic science popularization recommendation system based on smart health as claimed in claim 1, characterized in that: The bone model includes bone structure, joint motion range and dynamic display capability, and the dynamic parameter calibration includes simulating joint pressure distribution and bone strength change trend.

6. The orthopedic science popularization recommendation system based on smart health as claimed in claim 1, characterized in that: The immersive interaction module includes: Bone model loading unit, used for: Obtain a bone model generated by a digital twin construction module based on the user's bone health data, interact with a VR device, and present the bone model in a virtual environment based on the display function of the VR device, wherein the display of the bone model includes the three-dimensional structure, joint connection, range of motion, and dynamic changes of the bone; Motion simulation unit for: The user's current action instructions are obtained. The action instructions are selected by the user through the VR device. The bone reaction of the skeleton in the specified motion state is simulated based on the action instructions. The bone reaction includes joint pressure distribution and bone load response. The physical engine is used to simulate the instant changes and effects of joint pressure distribution during motion, and the changes in bone health data of the bone model under different motion states are simulated.

7. The orthopedic science popularization recommendation system based on smart health as claimed in claim 6, characterized in that: The immersive interaction module further includes: Bone aging simulation unit for: Based on the user's bone health data, simulate the user's bone aging process, including changes in bone density and joint range of motion, calculate the load bearing capacity of the bones and possible injuries during exercise, and simulate the impact of sports injuries on bones; Rehabilitation Task Feedback Unit for: Based on the user's bone health data, the user's joint pressure and bone strength index are analyzed, and a personalized rehabilitation task is generated based on the user's joint pressure and bone strength index. The rehabilitation task includes a specified exercise and exercise intensity. The rehabilitation task is performed by the user wearing a VR device, and the rehabilitation task feedback unit provides real-time feedback based on the user's behavior and task completion status; The user's bone health data is updated based on task completion of the rehabilitation task.

8. The orthopedic science popularization recommendation system based on smart health as claimed in claim 1, characterized in that: The intelligent recommendation module includes: Database building blocks for: Constructing a content database, wherein the content database is used to store orthopedic knowledge content in the form of video, text and animation, wherein the orthopedic knowledge content includes bone anatomy, bone health maintenance, sports injury prevention and rehabilitation training content; Behavioral data collection unit, used for: During the interaction between the user and the immersive interaction module, the user's behavioral data is recorded in real time. The behavioral data includes the dynamics of the bone reaction model viewed by the user, the completed rehabilitation tasks and the status of task completion. The user's actions, choices and interactions are collected and stored, and the user's behavioral data and bone health data are associated.

9. The orthopedic science popularization recommendation system based on smart health as claimed in claim 8, characterized in that: The intelligent recommendation module further includes: Point of interest recognition unit, used to: Analyze the user's behavior data and identify the user's interests based on the user's selection patterns, viewing time, and interaction frequency indicators in the immersive interaction module, including preferences for specific types of orthopedic knowledge and attention to specific rehabilitation tasks; Combining the user's bone health data and points of interest, using content-based recommendation algorithms and collaborative filtering algorithms, a personalized recommendation strategy is generated; Content push feedback unit, used for: Search the content database according to the user's personalized recommendation strategy, and generate personalized push content based on the search results; Collect user feedback data on personalized pushed content, including whether the user watched the content, the viewing time, and the viewing completion status, and evaluate the content push effect based on the feedback data.

10. The orthopedic science popularization recommendation system based on smart health as claimed in claim 2, characterized in that: Predict bone health risks based on bone health trends, including: Obtain basic information of the user, including age information and behavior preference information; Identify the age information in the user's basic information, determine the age group of the user based on the age information, and then analyze the bone features of the age group based on the age group to obtain the user's bone feature information; Perform bone health analysis based on the user's bone feature information, determine the impact of age information on bone health, and obtain the first influencing factor; Identify the behavior preference information in the basic information of the user, and obtain a first analysis result according to whether the behavior preference information has an impact on bone health; When the first analysis result is that the behavior preference information has an impact on bone health, the behavior preference information is decomposed to obtain a plurality of behavior preference sub-actions; Analyze the influence of behavioral preference sub-actions on bone health and obtain the second influencing sub-factor; Combined with the relationship between the sub-actions of behavior preference, the second influencing sub-factor is comprehensively analyzed to obtain the second influencing factor; Conduct bone health risk analysis based on bone health change trends to obtain initial prediction information on bone health risks; The first influencing factor and the second influencing factor are used to correct the initial prediction information of bone health risk to obtain the final bone health risk prediction information.

Images