Respiratory training health education system based on VR technology

Abstract

The invention relates to the field of VR health education, and discloses a respiratory training health education system based on a VR technology, which comprises a VR health education system, and the VR health education system comprises a data collection module. A highly real VR immersive respiratory training scene is constructed, and the immersion feeling of a user is improved through fine 3D modeling and a vivid light and shadow effect; secondly, according to the physical condition and training requirements of the user, designing a personalized breathing training mode, including breathing rhythm adjustment, deep breathing practice and the like, and giving corresponding training guidance by monitoring breathing data of the user in real time; and finally, establishing a training effect evaluation mechanism, and by collecting and analyzing data of the user in the training process and generating a training report, providing visual training effect feedback for the user, providing a VR respiratory training environment with more realistic and immersive feeling, realizing a personalized and targeted respiratory training mode, and providing training effect feedback capable of being quantitatively evaluated.

Description

Technical Field

[0001] The present invention relates to the field of VR health education technology, and in particular to a breathing training health education system based on VR technology. Background Art

[0002] With the continuous development of VR technology, its application in the field of medical health is becoming more and more extensive. VR technology can provide an immersive experience environment, which has significant advantages for training such as breathing training that requires high concentration and simulation of real scenes. However, most of the VR breathing training models on the market are single-function, lack of targeted and personalized settings, and cannot meet the needs of different users; existing VR breathing training models usually use basic virtual reality scenes combined with simple breathing guidance functions, and users train by wearing VR devices. However, these models have shortcomings in terms of scene realism, interactivity, and training effect evaluation. Summary of the invention

[0003] In view of the shortcomings of the existing technology, the present invention provides a respiratory training health education system based on VR technology, which solves the problems of single training mode, lack of personalization and pertinence, difficulty in quantifying and evaluating the training effect, and inability to provide effective feedback to users.

[0004] To achieve the above objectives, the present invention is implemented through the following technical solutions: A respiratory training health education system based on VR technology, including a VR health education system, wherein the VR health education system includes:

[0005] Data collection module: uses high-precision breathing sensors and physiological status monitoring sensors to collect users' breathing data and physiological indicators in real time; generates user breathing data sets;

[0006] Feature extraction module: Based on the collected data, principal component analysis (PCA) and convolutional neural network (CNN) are used to extract key features related to breathing; feature extraction results are generated;

[0007] Model training module: Based on the feature extraction results, the decision tree and long short-term memory network LSTM are used for model training; a personalized training model is generated;

[0008] Program generation module: according to the personalized training model, input the user's current data and dynamically generate an adaptive training program; generate a personalized breathing training program;

[0009] Effect evaluation module: Based on user feedback and comparison of physiological indicators, evaluate the effectiveness and accuracy of the training program; generate an evaluation report;

[0010] User feedback module; collects user feedback on training programs, analyzes satisfaction and compliance; generates user satisfaction reports.

[0011] Preferably, the data collection module includes the following submodules:

[0012] Data recording submodule: uses high-precision breathing sensors and physiological status monitoring sensors to collect users' breathing data and physiological indicators in real time; generates user breathing data sets;

[0013] Environmental monitoring submodule: uses environmental sensors to monitor the temperature, humidity and air quality of the user's environment; generates environmental monitoring data sets;

[0014] Physiological indicators submodule: collects the user's heart rate, blood oxygen saturation and other physiological indicators to ensure a comprehensive assessment of the user's health status; generates a user physiological indicator data set.

[0015] Preferably, the feature extraction module includes the following submodules:

[0016] Feature analysis submodule: Based on the user breathing dataset and the user physiological index dataset, principal component analysis (PCA) is used to extract key features related to breathing; and feature extraction results are generated;

[0017] Pattern recognition submodule: Based on the feature extraction results, a convolutional neural network (CNN) is used for pattern recognition to identify the user's breathing patterns and changes; and pattern recognition results are generated;

[0018] Feature screening submodule: based on the pattern recognition results, screen out the optimal features related to the training effect; generate an optimized feature set.

[0019] Preferably, the model training module includes the following submodules:

[0020] Model building submodule: Based on the optimized feature set, build a decision tree model for easy understanding and interpretation; generate a decision tree model;

[0021] Parameter optimization submodule: Use the long short-term memory network (LSTM) to optimize the parameters of the decision tree model to improve the prediction performance of the model; generate an optimized LSTM model;

[0022] Training evaluation submodule: cross-validate the optimized LSTM model, evaluate the accuracy and generalization ability of the model; generate a model evaluation report.

[0023] Preferably, the solution generation module includes the following submodules:

[0024] Scheme adjustment submodule: adjust the training scheme to suit the user's current needs based on the model evaluation report; generate the adjusted training scheme;

[0025] Training intensity submodule: Set the intensity of adaptive training according to the adjusted training plan to ensure that users can accept and complete the training; generate training intensity settings;

[0026] Training rhythm submodule: Based on the training intensity setting, dynamically generate a training rhythm suitable for the user to improve user participation; generate personalized breathing training plans.

[0027] Preferably, the effect evaluation module includes the following submodules:

[0028] User survey submodule: collect user feedback on the personalized breathing training program through questionnaire survey; generate user feedback data set;

[0029] Physiological data comparison submodule: compares the user's physiological indicator data sets before and after training, analyzes the training effect; generates physiological data comparison results;

[0030] Expert evaluation submodule: Invite experts to analyze the physiological data comparison results and provide professional suggestions; generate expert evaluation reports.

[0031] Preferably, the user feedback module includes the following submodules:

[0032] Feedback collection submodule: collect user satisfaction feedback on the personalized breathing training program; generate a user satisfaction data set;

[0033] Data analysis submodule: analyze user satisfaction data sets, evaluate user compliance and improvement directions; generate satisfaction analysis reports;

[0034] Improvement suggestion submodule: Based on the satisfaction analysis report, propose improvement suggestions for the personalized breathing training program; generate an improvement suggestion report.

[0035] The present invention provides a breathing training health education system based on VR technology. It has the following beneficial effects:

[0036] The present invention constructs highly realistic VR immersive breathing training scenes, including natural environments and urban landscapes, and enhances the user's sense of immersion through fine 3D modeling and realistic light and shadow effects; secondly, according to the user's physical condition and training needs, a personalized breathing training mode is designed, including breathing rhythm adjustment, deep breathing exercises, etc., and the user's breathing data is monitored in real time and corresponding training guidance is given; finally, a training effect evaluation mechanism is established, and a training report is generated by collecting and analyzing the user's data during the training process, so as to provide the user with intuitive training effect feedback, provide a more realistic and immersive VR breathing training environment, realize personalized and targeted breathing training modes, and provide quantifiable and evaluable training effect feedback. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is a system framework diagram of the present invention;

[0038] Figure 2 It is a data collection module framework diagram of the present invention;

[0039] Figure 3 It is a framework diagram of the feature extraction module of the present invention;

[0040] Figure 4 This is a framework diagram of the model training module of the present invention;

[0041] Figure 5 Generate a module framework diagram for the solution of the present invention;

[0042] Figure 6 This is a framework diagram of the effect evaluation module of the present invention;

[0043] Figure 7 This is a framework diagram of the user feedback module of the present invention.

[0044] Among them, 1. VR health education system; 11. Data collection module; 101. Data recording submodule; 102. Environmental monitoring submodule; 103. Physiological indicator submodule; 12. Feature extraction module; 201. Feature analysis submodule; 202. Pattern recognition submodule; 203. Feature screening submodule; 13. Model training module; 301. Model construction submodule; 302. Parameter optimization submodule; 303. Training evaluation submodule; 14. Program generation module; 401. Program adjustment submodule; 402. Training intensity submodule; 403. Training rhythm submodule; 15. Effect evaluation module; 501. User survey submodule; 502. Physiological data comparison submodule; 503. Expert evaluation submodule; 16. User feedback module; 601. Feedback collection submodule; 602. Data analysis submodule; 603. Improvement suggestion submodule. DETAILED DESCRIPTION

[0045] 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.

[0046] Example:

[0047] Please see attached Figure 1 -Attached Figure 7The embodiment of the present invention provides a respiratory training health education system based on VR technology, including a VR health education system 1, wherein the VR health education system 1 includes:

[0048] Data collection module 11; using high-precision breathing sensors and physiological status monitoring sensors to collect user's breathing data and physiological indicators in real time; generating user breathing data set;

[0049] Feature extraction module 12: Based on the collected data, principal component analysis PCA and convolutional neural network CNN are used to extract key features related to breathing; and feature extraction results are generated;

[0050] Model training module 13: Based on the feature extraction results, use decision tree and long short-term memory network LSTM for model training; generate personalized training model;

[0051] Program generation module 14: according to the personalized training model, input the user's current data and dynamically generate an adaptive training program; generate a personalized breathing training program;

[0052] Effect evaluation module 15: Based on user feedback and comparison of physiological indicators, evaluate the effectiveness and accuracy of the training program; generate an evaluation report;

[0053] User feedback module 16; collects user feedback on the training program, analyzes satisfaction and compliance; and generates a user satisfaction report.

[0054] Furthermore, the data collection module 11 includes the following submodules:

[0055] Data recording submodule 101: uses a high-precision breathing sensor and a physiological status monitoring sensor to collect the user's breathing data and physiological indicators in real time; generates a user breathing data set;

[0056] Environmental monitoring submodule 102: using environmental sensors to monitor the temperature, humidity and air quality of the user's environment; generating an environmental monitoring data set;

[0057] Physiological indicator submodule 103: collects physiological indicators such as the user's heart rate and blood oxygen saturation to ensure a comprehensive assessment of the user's health status; generates a user physiological indicator data set;

[0058] By adopting higher-precision respiratory sensors, the user's respiratory data can be monitored more accurately, including respiratory rate, respiratory depth and respiratory rhythm. These data will provide a more accurate basis for personalized training plans and help users adjust and optimize their breathing methods more effectively. In addition to respiratory data, other physiological status monitoring sensors can also be introduced, including heart rate monitoring and blood oxygen saturation monitoring. These sensors can reflect the user's physiological changes during respiratory training in real time, providing more comprehensive data support for evaluating training effects.

[0059] Furthermore, the feature extraction module 12 includes the following submodules:

[0060] Feature analysis submodule 201: Based on the user breathing data set and the user physiological index data set, principal component analysis PCA is used to extract key features related to breathing; and feature extraction results are generated;

[0061] Pattern recognition submodule 202: Based on the feature extraction result, a convolutional neural network (CNN) is used to perform pattern recognition to identify the user's breathing pattern and changes; and a pattern recognition result is generated;

[0062] Feature screening submodule 203: based on the pattern recognition results, screen out the best features related to the training effect; generate an optimized feature set;

[0063] By introducing machine learning algorithms, we can deeply analyze and learn the user's historical breathing data, so as to generate more accurate and personalized breathing training plans for users. At the same time, machine learning algorithms can also dynamically adjust the training difficulty and rhythm according to the user's real-time feedback and data changes, ensuring that the training process always meets the user's actual needs.

[0064] Furthermore, the model training module 13 includes the following submodules:

[0065] Model building submodule 301: based on the optimized feature set, building a decision tree model for easy understanding and interpretation; generating a decision tree model;

[0066] Parameter optimization submodule 302: Use the long short-term memory network LSTM to optimize the parameters of the decision tree model to improve the prediction performance of the model; generate an optimized LSTM model;

[0067] Training evaluation submodule 303: cross-validate the optimized LSTM model to evaluate the accuracy and generalization ability of the model; generate a model evaluation report;

[0068] A personalized breathing training generator based on deep learning, which uses a combination of convolutional neural networks (CNN) and long short-term memory networks (LSTM) to capture the temporal and spatial features in the user's breathing data. The model first extracts the local features of the breathing data through the CNN layer, and then uses the LSTM layer to learn the dependencies of these features in the time dimension. During the training process, we used the back propagation algorithm and Adam to adjust the model parameters to minimize the gap between the predicted breathing training plan and the actual needs. Finally, the model can generate a personalized, scientific and effective breathing training plan based on the user's historical breathing data.

[0069] Furthermore, the solution generation module 14 includes the following submodules:

[0070] Scheme adjustment submodule 401: adjust the training scheme to adapt to the current needs of the user according to the model evaluation report; generate an adjusted training scheme;

[0071] Training intensity submodule 402: according to the adjusted training program, setting the intensity of adaptive training to ensure that the user can accept and complete the training; generating training intensity settings;

[0072] Training rhythm submodule 403: based on the training intensity setting, dynamically generate a training rhythm suitable for the user to improve the user's participation; generate a personalized breathing training program;

[0073] In order to enhance the user's immersion and interactive experience in the virtual environment, virtual reality scene optimization algorithms can be introduced. These algorithms can adjust the visual and auditory multimedia elements in the virtual scene in real time according to the user's breathing data and physiological state, creating a more realistic and comfortable breathing training environment for users.

[0074] Furthermore, the effect evaluation module 15 includes the following submodules:

[0075] User survey submodule 501: collect user feedback on the personalized breathing training program through a questionnaire survey; generate a user feedback data set;

[0076] Physiological data comparison submodule 502: compares the user's physiological indicator data sets before and after training, analyzes the training effect; generates physiological data comparison results;

[0077] Expert evaluation submodule 503: invite experts to analyze the physiological data comparison results and make professional suggestions; generate an expert evaluation report;

[0078] By collecting real feedback from users, we can intuitively understand whether the training program meets user needs and the user's actual experience; before and after the user uses the training program, measure and record relevant physiological indicators, including respiratory rate, blood oxygen saturation, and heart rate. By comparing the changes in these indicators, we can objectively evaluate the improvement effect of the training program on the user's respiratory function; invite experts in the field of respiratory therapy to evaluate the training program. Experts can conduct a comprehensive analysis of the scientificity, rationality and potential risks of the program based on their professional knowledge and experience, and provide professional evaluation opinions.

[0079] Furthermore, the user feedback module 16 includes the following submodules:

[0080] Feedback collection submodule 601: collect user satisfaction feedback on the personalized breathing training program; generate a user satisfaction data set;

[0081] Data analysis submodule 602: Analyze user satisfaction data sets, evaluate user compliance and improvement directions; generate satisfaction analysis reports;

[0082] Improvement suggestion submodule 603: Propose improvement suggestions for the personalized breathing training program based on the satisfaction analysis report; and generate an improvement suggestion report.

[0083] Although 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 variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A breathing training health education system based on VR technology, comprising a VR health education system (1), characterized in that: The VR health education system (1) comprises: The data collection module (11) uses a high-precision breathing sensor and a physiological status monitoring sensor to collect the user's breathing data and physiological indicators in real time and generate a user breathing data set; Feature extraction module (12): based on the collected data, principal component analysis PCA and convolutional neural network CNN are used to extract key features related to breathing; and feature extraction results are generated; Model training module (13): Based on the feature extraction results, a decision tree and a long short-term memory network (LSTM) are used for model training; a personalized training model is generated; Program generation module (14): according to the personalized training model, input the user's current data and dynamically generate an adaptive training program; generate a personalized breathing training program; Effect evaluation module (15): based on user feedback and comparison of physiological indicators, evaluate the effectiveness and accuracy of the training program; generate an evaluation report; User feedback module (16); collects user feedback on the training program, analyzes satisfaction and compliance; and generates a user satisfaction report.

2. A breathing training health education system based on VR technology according to claim 1, characterized in that: The data collection module (11) comprises the following submodules: Data recording submodule (101): using a high-precision breathing sensor and a physiological status monitoring sensor to collect the user's breathing data and physiological indicators in real time; generating a user breathing data set; Environmental monitoring submodule (102): using environmental sensors to monitor the temperature, humidity and air quality of the user's environment; generating an environmental monitoring data set; Physiological index submodule (103): collects physiological indexes such as heart rate and blood oxygen saturation of the user to ensure a comprehensive assessment of the user's health status; Generate user physiological indicator dataset.

3. The breathing training health education system based on VR technology according to claim 1 is characterized in that: The feature extraction module (2) comprises the following submodules: Feature analysis submodule (201): based on the user breathing data set and the user physiological index data set, principal component analysis PCA is used to extract key features related to breathing; Generate feature extraction results; Pattern recognition submodule (202): Based on the feature extraction result, a convolutional neural network (CNN) is used to perform pattern recognition to identify the user's breathing pattern and changes; Generate pattern recognition results; Feature screening submodule (203): screening out the best features related to the training effect according to the pattern recognition results; Generate optimized feature sets.

4. The breathing training health education system based on VR technology according to claim 1 is characterized in that: The model training module (3) includes the following submodules: Model building submodule (301): based on the optimized feature set, building a decision tree model for easy understanding and interpretation; generating a decision tree model; Parameter optimization submodule (302): using a long short-term memory network (LSTM) to optimize the parameters of the decision tree model to improve the prediction performance of the model; generating an optimized LSTM model; Training evaluation submodule (303): cross-validate the optimized LSTM model to evaluate the accuracy and generalization ability of the model; generate a model evaluation report.

5. The breathing training health education system based on VR technology according to claim 1 is characterized in that: The solution generation module (4) includes the following submodules: Scheme adjustment submodule (401): adjusts the training scheme to suit the current needs of the user according to the model evaluation report; Generate an adjusted training plan; Training intensity submodule (402): according to the adjusted training program, setting the intensity of adaptive training to ensure that the user can accept and complete the training; generating training intensity settings; Training rhythm submodule (403): based on the training intensity setting, dynamically generates a training rhythm suitable for the user to improve the user's participation; Generate a personalized breathing training program.

6. The breathing training health education system based on VR technology according to claim 1 is characterized in that: The effect evaluation module (5) comprises the following submodules: User survey submodule (501): collects user feedback on the personalized breathing training program through a questionnaire survey; generates a user feedback data set; Physiological data comparison submodule (502): compares the user's physiological index data set before and after training to analyze the training effect; Generate physiological data comparison results; Expert evaluation submodule (503): inviting experts to analyze the physiological data comparison results and make professional suggestions; Generate expert evaluation reports.

7. The breathing training health education system based on VR technology according to claim 1 is characterized in that: The user feedback module (6) comprises the following submodules: Feedback collection submodule (601): collects user satisfaction feedback on the personalized breathing training program; Generate user satisfaction dataset; Data analysis submodule (602): analyzing user satisfaction data sets to evaluate user compliance and improvement directions; Generate satisfaction analysis report; Improvement suggestion submodule (603): based on the satisfaction analysis report, propose improvement suggestions for the personalized breathing training program; Generate a report with improvement suggestions.

Images