Knee joint movement injury rehabilitation mode generation system based on virtual reality

Abstract

The invention discloses a knee joint movement injury rehabilitation mode generation system based on virtual reality, and belongs to the technical field of virtual reality. The problems that in the prior art, doctor-patient proportion is imbalance, and rehabilitation conditions are difficult to accurately judge are solved, corresponding rehabilitation plans are made according to prediction results of knee joints of different users through the neural network model, a corresponding virtual training scene is constructed in combination with the VR technology, and the rehabilitation effect is improved. Classifying various injury results and rehabilitation plans through a decision tree classification model; therefore, after a medical worker diagnoses the knee joint injury factor of the user or knows the rehabilitation demand required by the user, a personalized rehabilitation training plan can be automatically made according to the personal condition of the user, and the rehabilitation training effect is monitored in real time; compared with a traditional treatment method, the method is more efficient, and corresponding adjustment can be made according to the specific conditions of the patient, so that the pertinence and effectiveness of rehabilitation training are improved, and the user is helped to recover body health faster and better.

Description

Technical Field

[0001] The present invention relates to the field of virtual reality technology, and in particular to a system for generating a rehabilitation method for knee joint sports injuries based on virtual reality. Background Art

[0002] With the aging population and the rise of sports and fitness culture, more and more people are suffering from knee diseases and sports injuries, and the demand for knee surgery is gradually increasing. Postoperative rehabilitation training is very important for the patient's recovery. If it is not treated and rehabilitated in time, it may lead to permanent knee damage in the long run. In the field of medical treatment and rehabilitation, traditional treatment plans usually need to be formulated based on the patient's personal information such as symptoms, medical history and health status.

[0003] However, there are many problems in the existing knee sports injury rehabilitation technology, such as: first, it is difficult to collect data during rehabilitation training; second, it is difficult for patients to make accurate judgments about their own recovery status, resulting in some patients with good recovery conditions occupying a large amount of medical resources, while patients who need emergency treatment do not receive timely intervention. Therefore, the existing needs are not met, so we propose a virtual reality-based knee sports injury rehabilitation method generation system. Summary of the invention

[0004] The purpose of the present invention is to provide a system for generating rehabilitation methods for knee sports injuries based on virtual reality, formulate corresponding rehabilitation plans based on the predicted results of knee joints of different users through a neural network model, build corresponding virtual training scenes in combination with VR technology, and then classify various injury results and rehabilitation plans through a decision tree classification model; therefore, after medical staff diagnose the user's knee joint injury factors or learn about the user's rehabilitation needs, a personalized rehabilitation training plan can be automatically formulated according to the user's personal situation, and the rehabilitation training effect can be monitored in real time; compared with traditional treatment methods, this method is not only more efficient, but also can make corresponding adjustments according to the patient's specific situation, thereby improving the pertinence and effectiveness of rehabilitation training, so as to help users recover their health faster and better, and solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions: A system for generating rehabilitation methods for knee sports injuries based on virtual reality, including: Data acquisition unit for By collecting sports data and health data of different users under different injury factors, sports data includes: user's weight, body posture, exercise habits, interests and hobbies; health data includes: user's symptoms, medical history, physical condition; Etiology Analysis Unit, used for Preprocess the motion data and health data of various users, use the neural network model to train and test the preprocessed motion data and health data, predict the injury results of various users, and obtain the rehabilitation needs of various users based on the injury results; Mode generation unit, used for According to the predicted injury results and rehabilitation needs, a corresponding rehabilitation plan is formulated to form a rehabilitation training library; the rehabilitation plan includes: rehabilitation training goals, user groups, training content and virtual reality scenarios; and a decision tree classification model is used to classify various injury results, rehabilitation needs and corresponding rehabilitation plans; Environment creation unit for Use 3D graphics and simulation technologies to create virtual sports scenes for various injury outcomes, and provide personalized rehabilitation training programs based on the user's specific circumstances to ensure the effectiveness and safety of the training; Rehabilitation delivery unit, used for According to the current user's injury results, the corresponding rehabilitation needs are learned, and an appropriate rehabilitation plan is selected. Rehabilitation training is carried out by wearing VR equipment to enter the corresponding sports scene.

[0006] Furthermore, the data acquisition unit includes: The data storage module is used to classify and store the collected sports data and health data of various users according to time series and attributes to form a data database; The data encryption module is used to encrypt the access rights to the data database using a symmetric key method and inform the person in charge of the access password.

[0007] Furthermore, the data acquisition unit further includes: An encryption operation parameter real-time monitoring module is used to monitor the encryption operation parameters of the data encryption module in real time, wherein the encryption operation parameters include the number of bits contained in the key, the type of elements contained in the key, the key generation time, the anti-attack success rate and the similarity between every two keys in the generated keys; An encryption generation quality evaluation coefficient acquisition module is used to obtain the encryption generation quality evaluation coefficient by using the number of bits contained in the key, the type of elements contained in the key and the key generation time; The encryption quality evaluation coefficient is obtained by the following formula: Where Q represents the encryption generation quality evaluation coefficient; n represents the number of keys generated by the data encryption module; T i Indicates the generation time corresponding to the i-th key; E b K represents the standard deviation of the number of elements corresponding to n keys;i Indicates the number of bits contained in the i-th key; K i-1 Indicates the number of bits contained in the i-1th key; K b Indicates the standard deviation of the number of bits contained in n keys; T si Indicates the time difference between the generation times of the i-th pair of keys; A coefficient comparison module, used for comparing the encryption generation quality evaluation coefficient with a preset encryption generation quality evaluation coefficient threshold; The encryption operation abnormality judgment module is used to judge the encryption operation abnormality by using the anti-attack success rate and the similarity between every two keys in the generated keys combined with the encryption generation quality evaluation coefficient when the encryption generation quality evaluation coefficient is lower than the preset encryption generation quality evaluation coefficient threshold.

[0008] Furthermore, the encryption operation abnormality determination module includes: A parameter retrieval module, used for extracting the anti-attack success rate and the similarity between every two keys in the generated keys when the encryption generation quality evaluation coefficient is lower than a preset encryption generation quality evaluation coefficient threshold; The encryption generation quality evaluation coefficient calling module is used to call the encryption generation quality evaluation coefficient; An encryption operation quality evaluation parameter acquisition module is used to obtain encryption operation quality evaluation parameters by using the anti-attack success rate and the similarity between every two keys in the generated keys and the encryption generation quality evaluation coefficient; The encryption operation quality evaluation parameter is obtained by the following formula: Where R represents the encryption operation quality evaluation parameter; Q represents the encryption generation quality evaluation coefficient; Q y represents the preset encryption generation quality evaluation coefficient threshold; P represents the anti-attack success rate; m represents the number of key pairs contained in n keys; S i represents the similarity of the i-th pair of keys; T si represents the time difference between the generation times of the i-th pair of keys; K min and K max Indicates the minimum and maximum number of bits contained in n keys; E min and E max Indicates the minimum and maximum values ​​of the elements contained in n keys; A parameter comparison module, used for comparing the encryption operation quality evaluation parameter with a preset evaluation parameter threshold; The abnormal operation determination and alarm module is used to determine that the encrypted operation is abnormal and issue an encrypted abnormal alarm when the encrypted operation quality evaluation parameter is lower than a preset evaluation parameter threshold.

[0009] Furthermore, the etiology analysis unit comprises: The model building module is used to divide the cleaned data into training sets and test sets, and to build a neural network model. The training sets and test sets are sequentially imported into the neural network model for training and testing, and the damage prediction results of different users under various types of data are obtained; The cluster analysis module is used to extract features related to rehabilitation needs from the user's health data, and to obtain the user's rehabilitation needs by clustering the feature information through the establishment of a neural network model.

[0010] Furthermore, the etiology analysis unit further includes: The data cleaning module is used to remove duplicate data from sports data and health data, correct erroneous information in the data, supplement missing values ​​in the data, and convert data in different formats into a unified standard format; The model iteration module is used to continuously obtain various types of data under different damage factors, and to update and iterate the neural network model, continuously optimize the feature layer of the neural network model, and ensure the accuracy of the neural network model prediction.

[0011] Furthermore, the mode generating unit includes: The data analysis module is used to analyze the sports data and health data of various users using descriptive analysis and statistical analysis. The descriptive analysis method is used to analyze the basic information of users, including height, weight, and exercise frequency; the statistical analysis method is used to determine the performance of users in different aspects, including heart rate range and strength level; The plan making module is used to make a personalized knee rehabilitation plan based on the predicted injury results and rehabilitation needs, combined with the user data analysis results; the rehabilitation plan includes: exercise type, intensity, frequency, and time arrangement; The method classification module is used to create a decision tree classification model, and divide the injury results of different users according to injury factors and rehabilitation needs through the classification model, so that each type of injury factor is divided into corresponding rehabilitation needs and rehabilitation plans, and each type of rehabilitation needs is divided into corresponding rehabilitation plans.

[0012] Furthermore, the environment creation unit includes: The environment construction module is used to build a virtual sports development environment using 3D graphics technology and simulation technology combined with virtual reality (VR) technology, so that users can enter the corresponding sports scene for rehabilitation training by wearing VR equipment; The content selection module is used to obtain a corresponding rehabilitation plan based on the results of the decision tree classification model according to the user's injury factors or rehabilitation needs, and assist medical staff in selecting corresponding rehabilitation training content and virtual sports scenes according to the rehabilitation plan; ‌Feedback mechanism module, used to instantly display the user's training performance in the system, including: completion, stability and endurance indicators.

[0013] Furthermore, the rehabilitation implementation unit includes: ‌Motion monitoring module, which is used to monitor the user's movements in the virtual environment in real time through sensors, including: joint angle, speed and strength, to ensure the correctness and safety of the movements; A rehabilitation assessment module is used to assess the user's knee joint function and determine the user's status and progress in the rehabilitation process; The rehabilitation follow-up module is used to regularly follow up and adjust the user's knee rehabilitation plan and monitor the progress and effect of the rehabilitation plan.

[0014] Furthermore, it also includes: System optimization unit for After the system development is completed, the system will be optimized and tested regularly, including: functional testing, performance testing and user experience testing. Optimization will be carried out based on the test results to ensure system stability and user experience. After the system is deployed to the actual use environment, necessary maintenance and update services will be provided to ensure the long-term stable operation of the system.

[0015] Compared with the prior art, the present invention has the following beneficial effects: The present invention formulates corresponding rehabilitation plans based on the prediction results of knee joints of different users through a neural network model, builds corresponding virtual training scenes in combination with VR technology, and then classifies and divides various types of injury results and rehabilitation needs and corresponding rehabilitation plans through a decision tree classification model; therefore, after the system is put into actual use, after the medical staff diagnoses the injury factors of the user's knee joints or learns the rehabilitation needs required by the user, the most suitable personalized rehabilitation training plan can be automatically formulated according to the user's personal situation and rehabilitation needs, and the rehabilitation training effect can be monitored in real time; compared with traditional treatment methods, this method is not only more efficient, but also can make corresponding adjustments according to the patient's specific situation, allowing users to immerse themselves in the rehabilitation training process, thereby improving the pertinence and effectiveness of rehabilitation training, so as to help users recover their health faster and better. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A system composition diagram for generating a virtual reality-based knee sports injury rehabilitation method according to the present invention. DETAILED DESCRIPTION

[0017] 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.

[0018] In order to solve the following technical problems in the existing knee sports injury rehabilitation technology, for example: first, it is difficult to collect data during rehabilitation training; second, it is difficult for patients to make accurate judgments on their own rehabilitation status, resulting in some patients with good recovery conditions occupying a large amount of medical resources, while patients who need emergency treatment do not receive timely intervention, please refer to Figure 1 , this embodiment provides the following technical solutions: A system for generating rehabilitation methods for knee sports injuries based on virtual reality, including: Data acquisition unit for By collecting motion data and health data of different users under different injury factors, the motion data includes: the user's weight, body posture, exercise habits, interests and hobbies; the health data includes: the user's symptoms, medical history, physical condition, such as arthritis, etc.; specifically, in this embodiment: for example, when obtaining various data of historical users, it can be obtained through different channels, such as: visiting medical institutions, health applications, online surveys, etc. to obtain motion data and health data of different users under different injury factors, and use them as training samples for the neural network model; for example: when obtaining various data of the current user, the user's knee joint can be tested and diagnosed by medical staff, such as: further obtaining structural images of the knee joint by taking CT and MRI, so as to accurately diagnose the degree and factors of injury to the user's knee joint.

[0019] The data acquisition unit comprises: The data storage module is used to classify and store the collected sports data and health data of various users according to time series and attributes to form a data database; specifically, the data is classified according to time series and attributes. The time series includes: data date, time, day of the week, etc., and the attributes include: action type, exercise intensity, exercise duration, patient gender, age, etc. The above classification can assist medical staff to better search and analyze data; the classified data is then stored in a data database with good scalability and high performance, such as: relational database, distributed file system or graph database, etc., to facilitate the addition of new data and users.

[0020] The data encryption module is used to encrypt the access rights of the data database using the symmetric key method and inform the person in charge of the access password; specifically, after storing each data in the database, measures can be taken to ensure the security and privacy of user data; for example: using the symmetric key method to control access rights, thereby preventing data leakage caused by unauthorized access.

[0021] Specifically, the data acquisition unit further includes: An encryption operation parameter real-time monitoring module is used to monitor the encryption operation parameters of the data encryption module in real time, wherein the encryption operation parameters include the number of bits contained in the key, the type of elements contained in the key, the key generation time, the anti-attack success rate and the similarity between every two keys in the generated keys; An encryption generation quality evaluation coefficient acquisition module is used to obtain the encryption generation quality evaluation coefficient by using the number of bits contained in the key, the type of elements contained in the key and the key generation time; The encryption quality evaluation coefficient is obtained by the following formula: Where Q represents the encryption generation quality evaluation coefficient; n represents the number of keys generated by the data encryption module; T i Indicates the generation time corresponding to the i-th key; E b K represents the standard deviation of the number of elements corresponding to n keys; i Indicates the number of bits contained in the i-th key; K i-1 Indicates the number of bits contained in the i-1th key; K b Indicates the standard deviation of the number of bits contained in n keys; T si Indicates the time difference between the generation times of the i-th pair of keys; A coefficient comparison module, used for comparing the encryption generation quality evaluation coefficient with a preset encryption generation quality evaluation coefficient threshold; The encryption operation abnormality judgment module is used to judge the encryption operation abnormality by using the anti-attack success rate and the similarity between every two keys in the generated keys combined with the encryption generation quality evaluation coefficient when the encryption generation quality evaluation coefficient is lower than the preset encryption generation quality evaluation coefficient threshold.

[0022] The technical effect of the above technical solution is: through the real-time monitoring module of encryption operation parameters, the operation status of the data encryption module can be captured in real time, including the specific attributes of the key (such as the number of bits, element types) and the time parameters of the generation process (such as the key generation time). This real-time monitoring provides a data basis for subsequent encryption quality evaluation and abnormality determination. Refined control is reflected in the monitoring of multiple dimensions of key generation to ensure that each key link can be effectively monitored and evaluated. The encryption generation quality evaluation coefficient acquisition module combines the parameters such as the number of bits, element types, and generation time of the key through formula calculation to form a quantitative encryption generation quality evaluation coefficient. This coefficient can intuitively reflect the overall quality level of key generation. The formula takes into account multiple aspects of key generation, such as the number of keys, generation time, standard deviation of the number of elements, standard deviation of the number of bits, and time difference of generation time, ensuring the comprehensiveness and accuracy of the evaluation. The coefficient comparison module and the encryption operation abnormality determination module together constitute the abnormality determination mechanism. By comparing the encryption generation quality evaluation coefficient with the preset threshold, potential problems in the encryption operation process can be quickly identified. When the encryption generation quality evaluation coefficient is lower than the threshold, it is further judged in combination with parameters such as anti-attack success rate and key similarity, which improves the accuracy and reliability of abnormal judgment. Through real-time monitoring and quantitative evaluation of key generation quality, potential security risks can be discovered and corrected in a timely manner, thereby improving the security of the entire data encryption module. In particular, in the monitoring of anti-attack success rate and key similarity, it helps to prevent cracking attacks and reuse attacks on keys, further enhancing the defense capabilities of the encryption system. This technical solution not only provides real-time monitoring and evaluation functions, but also provides data support for subsequent optimization and improvement. Through the analysis of the encryption generation quality evaluation coefficient and the abnormal judgment results, the key generation strategy and parameter settings can be adjusted in a targeted manner, thereby continuously improving the performance and security of the encryption system.

[0023] In summary, the technical effects of this technical solution in terms of performance indicators are mainly reflected in real-time monitoring and refined control, quantitative evaluation of encryption generation quality, efficient anomaly determination, security improvement, optimization and improvement, etc. These effects together constitute the important advantages of this technical solution in the field of data encryption.

[0024] Specifically, the encryption operation abnormality determination module includes: A parameter retrieval module, used for extracting the anti-attack success rate and the similarity between every two keys in the generated keys when the encryption generation quality evaluation coefficient is lower than a preset encryption generation quality evaluation coefficient threshold; The encryption generation quality evaluation coefficient calling module is used to call the encryption generation quality evaluation coefficient; An encryption operation quality evaluation parameter acquisition module is used to obtain encryption operation quality evaluation parameters by using the anti-attack success rate and the similarity between every two keys in the generated keys and the encryption generation quality evaluation coefficient; The encryption operation quality evaluation parameter is obtained by the following formula: Where R represents the encryption operation quality evaluation parameter; Q represents the encryption generation quality evaluation coefficient; Q y represents the preset encryption generation quality evaluation coefficient threshold; P represents the anti-attack success rate; m represents the number of key pairs contained in n keys; S i represents the similarity of the i-th pair of keys; T si represents the time difference between the generation times of the i-th pair of keys; K min and K max Indicates the minimum and maximum number of bits contained in n keys; E min and E max Indicates the minimum and maximum values ​​of the elements contained in n keys; A parameter comparison module, used for comparing the encryption operation quality evaluation parameter with a preset evaluation parameter threshold; The abnormal operation determination and alarm module is used to determine that the encrypted operation is abnormal and issue an encrypted abnormal alarm when the encrypted operation quality evaluation parameter is lower than a preset evaluation parameter threshold.

[0025] The technical effect of the above technical solution is: through the parameter retrieval module, when the encryption generation quality evaluation coefficient is lower than the preset threshold, the key encryption operation parameters, such as the anti-attack success rate and key similarity, can be quickly extracted to provide data support for subsequent abnormality determination. This comprehensive parameter extraction mechanism ensures the accuracy and comprehensiveness of abnormality detection and can capture multiple aspects that may affect the quality of encryption operation. The encryption operation quality evaluation parameter acquisition module uses multiple dimensions (such as anti-attack success rate, key similarity, encryption generation quality evaluation coefficient, etc.) to comprehensively calculate the encryption operation quality evaluation parameters, providing a quantitative indicator to evaluate the health of encryption operation. The calculation formula of the evaluation parameter comprehensively considers multiple attributes of the key (such as the number of bits, element types, generation time, etc.), as well as the relationship between them, so as to more accurately reflect the actual situation of encryption operation. The parameter comparison module compares the encryption operation quality evaluation parameters with the preset evaluation parameter threshold, and can quickly identify abnormal situations in encryption operation. When the abnormality is detected, the abnormal determination operation and alarm module can immediately trigger the alarm mechanism to notify relevant personnel to take timely measures to intervene and handle, thereby effectively preventing potential security risks. The evaluation parameters and thresholds in this technical solution can be flexibly adjusted and optimized according to actual needs. This flexibility enables the technical solution to adapt to different encryption environments and needs, improving its practicality and applicability. By real-time monitoring and evaluating the quality of encryption operations, timely discovering and dealing with potential security risks, this technical solution can significantly enhance the security and reliability of the encryption system. In particular, in terms of monitoring the success rate of counterattacks and key similarity, it helps to prevent cracking attacks and reuse attacks on keys, further enhancing the defense capabilities of the encryption system.

[0026] In summary, the technical effects of this technical solution in terms of performance indicators are mainly reflected in comprehensive anomaly detection capabilities, accurate encryption operation quality evaluation, efficient anomaly determination and alarm, flexible parameter adjustment and optimization, and enhanced security and reliability. These effects together constitute the important advantages of this technical solution in the field of encryption operation anomaly detection and alarm.

[0027] Etiology Analysis Unit, used for Preprocess the motion data and health data of various users, use the neural network model to train and test the preprocessed motion data and health data, predict the injury results of various users, and obtain the rehabilitation needs of various users based on the injury results; etiology analysis unit, including: The model building module is used to divide the cleaned data into training sets and test sets, and to build a neural network model. The training sets and test sets are sequentially imported into the neural network model for training and testing to obtain damage prediction results for different users under various types of data. Specifically, the training set contains most of the data points for model training; the test set contains a small number of data points for model evaluation and testing. After the division is completed, the data is normalized so that all features are on the same scale. Then a neural network model is constructed, such as a convolutional neural network. After the model is built, it is compiled and optimized so that it can run on a GPU or other hardware acceleration device. The training set and test set are sequentially imported into the neural network model for training and testing, and the performance of the model is evaluated by monitoring indicators such as loss and accuracy. If the performance of the model is found to be not ideal, some parameters can be adjusted, such as learning rate, batch size, etc. When the model training is completed, its accuracy is evaluated, such as accuracy, precision, recall rate, F1 score, etc. to measure the performance of the model.

[0028] The cluster analysis module is used to extract features related to rehabilitation needs from the user's health data, such as symptoms, medical history, physical condition, etc., and to obtain the user's required rehabilitation needs by clustering the feature information through the establishment of a neural network model; specifically, by analyzing the pre-processed motion data, features related to rehabilitation needs are extracted, such as indicators of exercise type, exercise intensity, exercise duration, exercise frequency, etc., and their features are used as the input set of the model to predict the user's required rehabilitation needs; secondly, clustering algorithms are used, such as K-means clustering, to perform cluster analysis on the features in the user data, thereby reflecting the similarity between the user and the motion data.

[0029] The data cleaning module is used to remove duplicate data from sports data and health data, correct erroneous information in the data, supplement missing values ​​in the data, and convert data in different formats into a unified standard format; specifically, the collected data is cleaned, deduplicated, converted, and other operations are performed to facilitate subsequent analysis and modeling, thereby ensuring the accuracy of the neural network model prediction.

[0030] The model iteration module is used to continuously obtain various types of data under different damage factors, and to update and iterate the neural network model, continuously optimize the feature layer of the neural network model, and ensure the accuracy of the neural network model prediction; specifically, when new damage factor data is added to the model, the model feature layer needs to be updated; therefore, in each iteration cycle, the neural network model will be continuously optimized to improve its prediction accuracy.

[0031] Mode generation unit, used for According to the predicted various injury results and rehabilitation needs, a corresponding rehabilitation plan is formulated to form a rehabilitation training library; the rehabilitation plan includes: rehabilitation training goals, user groups, training content and virtual reality scenarios; and a decision tree classification model is used to classify various injury results, rehabilitation needs and corresponding rehabilitation plans; the method generation unit includes: The data analysis module is used to analyze the sports data and health data of various users by using descriptive analysis and statistical analysis. The descriptive analysis method is used to analyze the basic information of the user, including: height, weight, and exercise frequency; the statistical analysis method is used to determine the user's performance in different aspects, including: heart rate range, strength level; specifically, by analyzing various types of data, the classification of various injury factors is defined according to the analysis results, such as: musculoskeletal diseases, nervous system diseases, joint diseases, etc., and each classification corresponds to a specific set of injury data; and a personalized rehabilitation training plan is formulated based on each specific set of injury data and the analysis results; the plan direction must have the user's personal characteristics and rehabilitation needs, as well as the categories obtained in the cluster analysis; in this embodiment, the rehabilitation training plan can be divided into different levels or stages to meet the needs of different users.

[0032] The plan making module is used to make a personalized knee rehabilitation plan based on the predicted injury results and rehabilitation needs combined with the results of user data analysis; the rehabilitation plan includes: exercise type, intensity, frequency, and time arrangement; specifically, a basic template for knee rehabilitation plan is made according to the user's basic information, injury condition and rehabilitation needs. The basic template includes: exercise type, intensity, frequency, time arrangement, etc. The basic template is a general template that is suitable for most patients, but some adjustments can also be made according to the patient's specific situation; such as: a personalized knee rehabilitation plan is made according to the predicted results and user data combined with the basic template of the knee rehabilitation plan. The plan should take into account the user's daily living habits and living environment, such as: cause of disease, hobbies and interests, workplace, family environment, social activities, etc., to improve the enthusiasm and feasibility of the execution of the plan; for example: for exercise type, some exercises that help to enhance joint stability can be selected, such as: yoga, Pilates, etc.; for intensity, exercises that gradually increase the load can be selected to avoid injury and fatigue; for frequency, the time and number of exercises can be arranged according to the patient's physical condition and personal preferences.

[0033] The method classification module is used to create a decision tree classification model, and divide the injury results of different users according to injury factors and rehabilitation needs through the classification model, so that each type of injury factor is divided into corresponding rehabilitation needs and rehabilitation plans, and each type of rehabilitation need is divided into corresponding rehabilitation plans; specifically, the user data and the characteristics of injury factors and rehabilitation needs are classified and trained through the decision tree classification model to ensure that its model can effectively identify different types of users and recommend corresponding rehabilitation plans for each type of user; secondly, when new user data is added, the new data can be added to the classification model and the model can be updated to make the model better adapt to the changing user data and improve its accuracy and reliability; through this classification method, the most suitable rehabilitation plan can be provided for each user, so as to help medical staff quickly identify and distinguish different types of users and formulate corresponding rehabilitation plans.

[0034] Environment creation unit for Use 3D graphics technology and simulation technology to create virtual sports scenes required for various injury results, and provide personalized rehabilitation training programs based on the user's specific situation to ensure the effectiveness and safety of training; environment creation unit, including: The environment construction module is used to use 3D graphics technology and simulation technology, combined with virtual reality VR technology to build a virtual sports development environment, ensure that the system can run on a variety of devices, and provide a good user experience, so that users can wear VR equipment to enter the corresponding sports scene for rehabilitation training; specifically, by using 3D graphics technology and simulation technology to create a more realistic virtual sports scene, the scene contains a variety of common sports elements, such as: treadmill, fitness equipment, fitness courses, etc.; and the elements in the scene are highly interactive and customizable to meet the rehabilitation needs of different users; secondly, use VR technology to allow users to wear VR helmets or other equipment to enter the virtual sports environment for rehabilitation training, VR technology can help users better Immersing in virtual scenes can enhance the effect and fun of rehabilitation training, allowing users to immerse themselves in the rehabilitation training process; at the same time, when users conduct rehabilitation training in a virtual sports environment, detailed sports guidance and feedback can be provided to users, including: information on how to perform exercises, sports techniques, breathing techniques, etc.; through the above operations, the system can provide users with an intuitive, interactive virtual sports development environment with a good user experience; in this environment, users can develop rehabilitation plans suitable for themselves through sports scenes, sports guidance and feedback, and conduct rehabilitation training; at the same time, due to the use of VR technology, users can train on multiple devices, thereby improving the convenience and sustainability of training and ensuring the feasibility of the system.

[0035] The content selection module is used to obtain the corresponding rehabilitation plan based on the user's injury factors or rehabilitation needs according to the results of the decision tree classification model, and assist medical staff in selecting the corresponding rehabilitation training content and virtual sports scenes according to the rehabilitation plan; specifically, the module is connected to the decision tree classification model, and the corresponding rehabilitation plan is automatically obtained according to the results generated by the model; secondly, the module can obtain the corresponding rehabilitation plan from the decision tree classification model according to the user's injury factors or rehabilitation needs, as well as the content and goals of the rehabilitation plan, and recommend appropriate rehabilitation training content and virtual sports scenes based on this information; at the same time, the module can manage and organize the content of rehabilitation training The module can automatically provide users with corresponding rehabilitation training content according to the rehabilitation plan, including: creating, editing, deleting, updating and other content; finally, the module is combined with virtual reality VR equipment to provide users with an immersive rehabilitation training environment, including various types of virtual sports scenes, such as: indoor gyms, outdoor parks, beach resorts, etc. Each scene is customizable and diversified to meet the rehabilitation needs of different users; through the above operations, medical staff can quickly and accurately select appropriate rehabilitation training content and virtual sports scenes according to the user's injury factors or rehabilitation needs, as well as the content and goals of the rehabilitation plan, so as to provide users with the best rehabilitation training effect.

[0036] The feedback mechanism module is used to instantly display the user's training performance in the system, including completion, stability and endurance indicators, to help users understand their rehabilitation progress and adjust the training plan according to the training performance data; specifically, this module can display various indicators and data in the system user interface, including the number of completed tasks, average speed, standard deviation, maximum heart rate, etc., to help users understand their performance in each training session and guide users on how to adjust their training plans to better achieve their rehabilitation goals; secondly, the feedback mechanism module can also provide users with suggestions to adjust their training plans based on the data analysis results; for example, if the user's completion rate in each training session is low, it will be recommended to increase the intensity or difficulty of the training; if the user's stability is poor, it will be recommended to use a more stable training mode, etc.; furthermore, the feedback mechanism module needs to record the user's various data and indicators in each training session, and save these data in the database so that users can view them at any time; the recorded training data can be used to analyze and optimize the training plan, and provided to medical staff and other users for reference, so that users can understand their rehabilitation progress in a timely manner and adjust their training plans according to performance data. Rehabilitation delivery unit, used for According to the current user's injury results, the corresponding rehabilitation needs are learned, and an appropriate rehabilitation plan is selected. Rehabilitation training is performed by wearing VR equipment to enter the corresponding sports scene. Specifically, according to the request of the user or medical staff, the data is queried and analyzed to provide the user with a personalized rehabilitation training plan.

[0037] Rehabilitation implementation unit, including: The motion monitoring module is used to monitor the user's movements in the virtual environment in real time through sensors, including: joint angles, speeds and strengths, to ensure the correctness and safety of the movements; specifically, through continuous monitoring and improvement of the user's rehabilitation training plan, to ensure its effectiveness and practicality; secondly, during the monitoring process, the user's data is collected in real time, and the rehabilitation training plan can be evaluated and improved to improve the effectiveness of the training plan; at the same time, the data database is continuously enriched to provide data support for the update and iteration of the neural network model.

[0038] The rehabilitation assessment module is used to evaluate the user's knee joint function and determine the user's status and progress in the rehabilitation process; specifically, it is achieved by calculating knee joint indicators, such as flexion angle, extension range, bending times, single-leg standing stability, etc. The above indicators can be used to measure the user's progress and improvement in the knee joint. The exercise type, intensity, frequency and other parameters are set according to their exercise data and goals; at the same time, medical staff can evaluate the patient's rehabilitation progress through data analysis and adjust the training plan as needed.

[0039] The rehabilitation follow-up module is used to regularly follow up and adjust the user's knee rehabilitation plan and monitor the progress and effect of the rehabilitation plan. Specifically, if the plan is found to be inappropriate or insufficient, medical staff can make corresponding adjustments to it to make it more in line with the user's needs and goals. For example, if the user feels pain or difficulty when performing a certain action, the intensity or frequency of the exercise can be appropriately reduced. If the user's knee joint function does not improve significantly, some exercise types or plans can be changed.

[0040] System optimization unit for After the system development is completed, the system will be optimized and tested regularly, including: functional testing, performance testing and user experience testing. Optimization will be carried out based on the test results to ensure system stability and user experience. After the system is deployed to the actual use environment, necessary maintenance and update services will be provided to ensure the long-term stable operation of the system.

[0041] The beneficial effects achieved by the above content: Through the above operations, the system can automatically formulate a personalized rehabilitation training plan based on the user's personal situation or rehabilitation needs, and monitor the rehabilitation training effect in real time during the rehabilitation training process; compared with traditional treatment methods, this method is not only more efficient, but can also make corresponding adjustments according to the patient's specific situation, allowing users to immerse themselves in the rehabilitation training process, thereby improving the pertinence and effectiveness of rehabilitation training, so as to help users recover their health faster and better.

[0042] Working principle: The knee joint data of different users are trained through the neural network model to obtain different prediction results, and corresponding rehabilitation plans are formulated according to the prediction results, and the corresponding virtual training scenes are constructed in combination with VR technology; various injury results, rehabilitation needs and corresponding rehabilitation plans are classified and divided through the decision tree classification model. Therefore, after the system is put into actual use, medical staff will diagnose the injury factors of the user's knee joint or learn about the rehabilitation needs of the user, and use the decision tree classification model to cluster the injury factors or rehabilitation needs, so as to provide users with corresponding rehabilitation plans; users wear VR equipment to enter the selected virtual sports scene for rehabilitation training to help users recover their health faster and better.

[0043] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0044] While the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and alterations may be made to the embodiments without departing from the principles and spirit of the invention.

Claims

1. A system for generating rehabilitation methods for knee joint sports injuries based on virtual reality, characterized in that: include: Data acquisition unit for By collecting sports data and health data of different users under different injury factors, sports data includes: user's weight, body posture, exercise habits, interests and hobbies; health data includes: user's symptoms, medical history, physical condition; Etiology Analysis Unit, used for Preprocess the motion data and health data of various users, use the neural network model to train and test the preprocessed motion data and health data, predict the injury results of various users, and obtain the rehabilitation needs of various users based on the injury results; Mode generation unit, used for According to the predicted injury results and rehabilitation needs, a corresponding rehabilitation plan is formulated to form a rehabilitation training library; the rehabilitation plan includes: rehabilitation training goals, user groups, training content and virtual reality scenarios; and a decision tree classification model is used to classify various injury results, rehabilitation needs and corresponding rehabilitation plans; Environment creation unit for Use 3D graphics and simulation technology to create virtual sports scenes for various injury results, and provide personalized rehabilitation training programs based on the user's specific situation; Rehabilitation delivery unit, used for According to the current user's injury results, the corresponding rehabilitation needs are learned, and an appropriate rehabilitation plan is selected. Rehabilitation training is carried out by wearing VR equipment to enter the corresponding sports scene.

2. The system for generating knee joint sports injury rehabilitation methods based on virtual reality according to claim 1, characterized in that: The data acquisition unit comprises: The data storage module is used to classify and store the collected sports data and health data of various users according to time series and attributes to form a data database; The data encryption module is used to encrypt the access rights to the data database using a symmetric key method and inform the person in charge of the access password.

3. The virtual reality-based knee joint sports injury rehabilitation method generation system according to claim 2, characterized in that: The data acquisition unit further includes: An encryption operation parameter real-time monitoring module is used to monitor the encryption operation parameters of the data encryption module in real time, wherein the encryption operation parameters include the number of bits contained in the key, the type of elements contained in the key, the key generation time, the anti-attack success rate and the similarity between every two keys in the generated keys; An encryption generation quality evaluation coefficient acquisition module is used to obtain the encryption generation quality evaluation coefficient by using the number of bits contained in the key, the type of elements contained in the key and the key generation time; The encryption quality evaluation coefficient is obtained by the following formula: Where Q represents the encryption generation quality evaluation coefficient; n represents the number of keys generated by the data encryption module; T i Indicates the generation time corresponding to the i-th key; E b K represents the standard deviation of the number of elements corresponding to n keys; i Indicates the number of bits contained in the i-th key; K i-1 Indicates the number of bits contained in the i-1th key; K b Indicates the standard deviation of the number of bits contained in n keys; T si represents the generation time difference corresponding to the i-th pair of keys; a coefficient comparison module, used to compare the encryption generation quality evaluation coefficient with a preset encryption generation quality evaluation coefficient threshold; The encryption operation abnormality judgment module is used to judge the encryption operation abnormality by using the anti-attack success rate and the similarity between every two keys in the generated keys combined with the encryption generation quality evaluation coefficient when the encryption generation quality evaluation coefficient is lower than the preset encryption generation quality evaluation coefficient threshold.

4. The system for generating knee joint sports injury rehabilitation methods based on virtual reality according to claim 3 is characterized in that: The encryption operation abnormality determination module includes: A parameter retrieval module, used for extracting the anti-attack success rate and the similarity between every two keys in the generated keys when the encryption generation quality evaluation coefficient is lower than a preset encryption generation quality evaluation coefficient threshold; The encryption generation quality evaluation coefficient calling module is used to call the encryption generation quality evaluation coefficient; The encryption operation quality evaluation parameter acquisition module is used to obtain the encryption operation quality evaluation parameter by using the anti-attack success rate and the similarity between every two keys in the generated keys and the encryption generation quality evaluation coefficient; wherein the encryption operation quality evaluation parameter is obtained by the following formula: Where R represents the encryption operation quality evaluation parameter; Q represents the encryption generation quality evaluation coefficient; Q y represents the preset encryption generation quality evaluation coefficient threshold; P represents the anti-attack success rate; m represents the number of key pairs contained in n keys; S i represents the similarity of the i-th pair of keys; T si represents the time difference between the generation times of the i-th pair of keys; K min and K max Indicates the minimum and maximum number of bits contained in n keys; E min and E max Indicates the minimum and maximum values ​​of the elements contained in n keys; A parameter comparison module, used for comparing the encryption operation quality evaluation parameter with a preset evaluation parameter threshold; The abnormal operation determination and alarm module is used to determine that the encrypted operation is abnormal and issue an encrypted abnormal alarm when the encrypted operation quality evaluation parameter is lower than a preset evaluation parameter threshold.

5. The system for generating knee joint sports injury rehabilitation methods based on virtual reality according to claim 1, characterized in that: The etiology analysis unit comprises: The model building module is used to divide the cleaned data into training sets and test sets, and to build a neural network model. The training sets and test sets are sequentially imported into the neural network model for training and testing, and the damage prediction results of different users under various types of data are obtained; The cluster analysis module is used to extract features related to rehabilitation needs from the user's health data, and to obtain the user's rehabilitation needs by clustering the feature information through the establishment of a neural network model.

6. The system for generating knee joint sports injury rehabilitation methods based on virtual reality according to claim 1, characterized in that: The etiology analysis unit further includes: The data cleaning module is used to remove duplicate data from sports data and health data, correct erroneous information in the data, supplement missing values ​​in the data, and convert data in different formats into a unified standard format; The model iteration module is used to continuously obtain various types of data under different damage factors, update and iterate the neural network model, and continuously optimize the feature layer of the neural network model.

7. The system for generating knee joint sports injury rehabilitation methods based on virtual reality according to claim 1, characterized in that: The mode generating unit comprises: The data analysis module is used to analyze the sports data and health data of various users using descriptive analysis and statistical analysis. The descriptive analysis method is used to analyze the basic information of users, including height, weight, and exercise frequency; the statistical analysis method is used to determine the performance of users in different aspects, including heart rate range and strength level; The plan making module is used to make a personalized knee rehabilitation plan based on the predicted injury results and rehabilitation needs, combined with the user data analysis results; the rehabilitation plan includes: exercise type, intensity, frequency, and time arrangement; The method classification module is used to create a decision tree classification model, and divide the injury results of different users according to injury factors and rehabilitation needs through the classification model, so that each type of injury factor is divided into corresponding rehabilitation needs and rehabilitation plans, and each type of rehabilitation needs is divided into corresponding rehabilitation plans.

8. The system for generating knee joint sports injury rehabilitation methods based on virtual reality according to claim 1, characterized in that: The environment creation unit includes: The environment construction module is used to build a virtual sports development environment using 3D graphics technology and simulation technology combined with virtual reality (VR) technology, so that users can enter the corresponding sports scene for rehabilitation training by wearing VR equipment; The content selection module is used to obtain a corresponding rehabilitation plan based on the results of the decision tree classification model according to the user's injury factors or rehabilitation needs, and assist medical staff in selecting corresponding rehabilitation training content and virtual sports scenes according to the rehabilitation plan; ‌Feedback mechanism module, used to instantly display the user's training performance in the system, including: completion, stability and endurance indicators.

9. The system for generating knee joint sports injury rehabilitation methods based on virtual reality according to claim 1, characterized in that: The rehabilitation implementation unit comprises: ‌Action monitoring module, which is used to monitor the user's actions in the virtual environment in real time through sensors, including: joint angle, speed and strength; A rehabilitation assessment module is used to assess the user's knee joint function and determine the user's status and progress in the rehabilitation process; The rehabilitation follow-up module is used to regularly follow up and adjust the user's knee rehabilitation plan and monitor the progress and effect of the rehabilitation plan.

10. The virtual reality-based knee joint sports injury rehabilitation method generation system according to claim 1, characterized in that: Also includes: System optimization unit for After the system development is completed, the system will be optimized and tested regularly, including functional testing, performance testing and user experience testing, and optimized according to the test results; After the system is deployed to the actual usage environment, necessary maintenance and update services will be provided.

Images