Online education platform management system

Abstract

The invention relates to the technical field of online education, and discloses an online education platform management system, which integrates five modules, namely a data management layer, a scene rendering layer, a user interaction layer, a behavior analysis layer and a user feedback layer, and aims to provide richer, interactive and personalized online learning experience. Through the educational resource integration and platform data center module, comprehensive integration and management of educational data are realized. The application of real-time scene rendering and visual optimization technology creates a vivid virtual learning environment for students. By means of virtual reality and augmented reality technologies, the user interaction layer greatly enhances interactivity and immersion of learning. The behavior analysis layer can count and analyze learning behaviors of students in real time and predict learning effects. And the user feedback layer provides detailed learning progress and effect reports, gives personalized learning suggestions and course recommendations, and comprehensively optimizes online learning experience.

Description

Technical Field

[0001] This invention relates to the field of online education technology, specifically to an online education platform management system. Background Technology

[0002] Online education platforms have become an important part of the education field, providing convenient learning pathways for a wide range of students.

[0003] Traditional online education platforms often use static images, text, or videos to display teaching content, lacking real-time rendering technology and scene simulation capabilities, thus failing to provide students with a highly interactive learning experience. Furthermore, most online education platforms can only simply record students' learning time and login activity, lacking comprehensive and real-time statistics and analysis of student learning behavior. Therefore, we propose an online education platform management system. Summary of the Invention

[0004] The purpose of this invention is to provide an online education platform management system to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: an online education platform management system, comprising a data management layer, a scene rendering layer, a user interaction layer, a behavior analysis layer, and a user feedback layer;

[0006] The data management layer is used for data integration, storage, and management, including:

[0007] The educational resource integration module is used to integrate data from different educational resources;

[0008] The platform's data center module is used to store and manage all the data required by the online education platform.

[0009] The scene rendering layer utilizes real-time rendering technology to achieve scene simulation and visualization effects, including:

[0010] The real-time scene rendering module is used to perform real-time rendering based on the data provided by the data management layer, generating virtual scenes;

[0011] The visual optimization module is used to optimize rendering effects and provides fine-tuning of lighting and material details;

[0012] The user interaction layer provides users with an interactive experience through virtual reality and augmented reality technologies, including:

[0013] The virtual interaction module is used to enable users to interact with virtual scenes;

[0014] The user interface design module is used to provide an operating interface so that users can perform various operations and controls;

[0015] The behavior analysis layer is responsible for analyzing learning behavior, including:

[0016] The learning behavior statistics module is used to acquire and analyze students' learning behavior data in real time, including login time, learning duration, course access frequency, homework submission status, and participation in interactive Q&A.

[0017] The learning outcome prediction module is used to predict students' learning outcomes based on the results of the learning behavior statistics module.

[0018] The user feedback layer is used to provide learning information to users, including:

[0019] The learning progress feedback module is used to track and record the user's learning progress in real time and generate learning progress reports;

[0020] The learning outcome assessment module is used to evaluate students' learning outcomes based on the output data of the learning outcome prediction module and generate a learning outcome report.

[0021] The personalized learning suggestion module is used to provide personalized learning suggestions and course recommendations based on the user's learning progress and preferences;

[0022] The user notification module is used to promptly notify users of learning progress reports, learning effectiveness reports, and personalized learning suggestions.

[0023] Preferably, the educational resource integration module establishes data interfaces with various educational resources, regularly obtains the latest educational resource data from various data sources, formats and standardizes the data, and finally imports the processed educational resource data into the platform data center module. The platform data center module uses database technology to persistently store various types of educational resource data and formulates data security measures, including data encryption, access control, and backup strategies.

[0024] Preferably, the real-time scene rendering module acquires and parses scene data transmitted from the data management layer by defining a standardized data interface; uses a 3D modeling engine to create corresponding 3D objects and scene structures based on the educational resource content and layout information in the scene data; and uses a graphics rendering engine to render the created 3D objects and scene structures in real time.

[0025] Preferably, the visual optimization module receives scene image data from the real-time scene rendering module, the scene image data including objects, lighting, and materials in the scene; performs lighting analysis on the scene image, and calculates the impact of lighting effects on the object surface based on the position, intensity, and color of the light source in the scene, as well as the material properties of the object; further, it finely adjusts the material of the object in the scene, including adjusting the texture map, reflectivity, and refractive index parameters of the object, so that the object surface presents a more realistic texture and detail.

[0026] Preferably, the virtual interaction module is implemented in the following ways:

[0027] Receive interactive commands from users via input devices, including devices such as mice, keyboards, and VR controllers;

[0028] Parse interactive commands and identify user intent, including moving, selecting, and manipulating objects in the virtual scene;

[0029] Based on the user's intent, invoke the relevant functions of the scene rendering layer to update the state of the virtual scene;

[0030] The updated virtual scene status will be fed back to the user.

[0031] Preferably, the user interface design module is implemented in the following ways:

[0032] Design the layout and style of the user interface based on the needs and user habits of the online education platform;

[0033] Develop various elements of the user interface, including buttons, text boxes, sliders, selection boxes, and display areas, and define the functions and event responses of all elements;

[0034] The user interface is connected to the virtual interaction module so that the commands issued by the user through the user interface can be correctly parsed and processed.

[0035] Preferably, the learning performance prediction module uses machine learning technology to build and train a score prediction model. The score prediction model is used to obtain the correlation between learning behavior data and corresponding learning score changes, and to predict learning score changes in the future based on current user learning behavior data.

[0036] Preferably, the steps for building and training a score prediction model include:

[0037] Step 1, Data Collection: Collect historical learning behavior data and corresponding learning score change data as training data; the historical learning behavior data includes students' login time, learning duration, course access frequency, homework submission status, and interactive Q&A participation; the corresponding learning score change data includes students' exam scores in different time periods;

[0038] Step 2, Data Cleaning: Clean the collected historical data to handle missing and outlier values;

[0039] Step 3, Data Preprocessing: Standardize the cleaned data to form a training dataset;

[0040] Step 4: Dataset partitioning: Divide the training dataset into a training set and a validation set;

[0041] Step 5, Model Selection and Initialization: Select the Long Short-Term Memory (LSTM) network model to build the score prediction model, and initialize the model parameters. The initialized parameters include the model's structural parameters, weights and biases, as well as setting the model's activation function and the learning rate parameters of the optimization algorithm.

[0042] Step 6, Model Training and Evaluation: Iteratively train the selected model using the training set data. During the training process, periodically evaluate the model performance using the validation set until the model's performance meets the requirements.

[0043] Step 7, Model Saving and Deployment: After training is complete, save the model's weights and biases, and deploy the model for subsequent prediction of learning score changes.

[0044] Preferably, in the data cleaning step 2, for missing values, a linear interpolation algorithm is used to fill them; for outliers, a threshold judgment method is used to regard data points that exceed a preset threshold range as outliers and replace them with the mean of their neighboring points.

[0045] In step 3, data preprocessing uses the Z-score standardization method, subtracting the mean from each numerical data point and dividing by its standard deviation to ensure the processed data conforms to a standard normal distribution. The standardization formula is as follows: ,in, The original data, The mean of the original data. The standard deviation of the original data. This is the standardized data.

[0046] Preferably, the mean squared error (MSE) algorithm is used to evaluate the performance of the score prediction model. The specific algorithm is as follows:

[0047]

[0048] Where n is the number of data points. Predict scores for the model, The actual score is used to evaluate the model's prediction accuracy. The smaller the MSE value, the higher the model's prediction accuracy.

[0049] Compared with the prior art, the beneficial effects of the present invention are:

[0050] It provides an immersive learning experience. The scene rendering layer utilizes real-time rendering technology and visualization effects to generate realistic virtual learning scenarios. The combination of virtual reality and augmented reality technologies further enhances the interactivity of learning, increasing student interest and engagement.

[0051] It enables comprehensive, real-time analysis of learning behavior. The behavior analysis layer can acquire and statistically analyze detailed student learning behavior data in real time, including login time, learning duration, course access frequency, assignment submission, and participation in interactive Q&A. Through the learning outcome prediction module, the system can accurately predict students' learning outcomes based on their learning behavior data, providing teachers with targeted teaching feedback.

[0052] Optimize personalized learning paths. The user feedback layer generates personalized learning suggestions and course recommendations based on students' learning outcomes and preferences. It tracks and records students' learning progress in real time, generating detailed progress reports and performance evaluation reports, enabling both students and teachers to clearly understand the learning situation. Attached Figure Description

[0053] Figure 1 This is a diagram showing the relationships between the layers of this invention;

[0054] Figure 2 This is a structural diagram of the present invention;

[0055] Figure 3 Implementation steps for the virtual interaction module;

[0056] Figure 4 This is a flowchart of the training process for the score prediction model. Detailed Implementation

[0057] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0058] Please see Figure 1-4 The present invention provides a technical solution: an online education platform management system, including a data management layer, a scene rendering layer, a user interaction layer, a behavior analysis layer, and a user feedback layer.

[0059] The data management layer includes an educational resource integration module and a platform data center module.

[0060] The education resource integration module is responsible for integrating data from different education resources, including course materials, teaching videos, and exercise banks, to ensure the diversity and richness of the data.

[0061] The platform's data center module is used to store and manage all the data required by the online education platform, including user information, learning records, and course information.

[0062] The scene rendering layer includes a real-time scene rendering module and a visual optimization module.

[0063] The real-time scene rendering module generates virtual scenes, such as classrooms and laboratories, based on data provided by the data management layer, using real-time rendering technology to provide a realistic learning environment.

[0064] The visual optimization module is responsible for optimizing rendering effects, providing fine-tuning of lighting and material details to enhance the realism and immersion of the scene.

[0065] The user interaction layer includes a virtual interaction module and a user interface design module.

[0066] The virtual interaction module uses virtual reality and augmented reality technologies to enable users to interact with virtual scenes, such as operating virtual experimental equipment and conversing with virtual characters.

[0067] The user interface design module provides an intuitive and easy-to-use interface, enabling users to easily perform various operations and controls, such as selecting courses and viewing learning progress.

[0068] The behavior analysis layer includes a learning behavior statistics module and a learning effectiveness prediction module.

[0069] The learning behavior statistics module is used to acquire and analyze students' learning behavior data in real time, including login time, learning duration, course access frequency, assignment submission status, and participation in interactive Q&A, in order to gain a comprehensive understanding of students' learning status.

[0070] The learning outcome prediction module is used to predict students' learning outcomes based on the results of the learning behavior statistics module, employing machine learning algorithms.

[0071] The user feedback layer includes a learning progress feedback module, a learning effectiveness evaluation module, a personalized learning suggestion module, and a user notification module.

[0072] The learning progress feedback module is used to track and record users' learning progress in real time and generate learning progress reports so that students can understand their learning status in a timely manner.

[0073] The learning effectiveness assessment module is used to evaluate students' learning effectiveness based on the output data of the learning effectiveness prediction module, and generate a learning effectiveness report to provide students with clear learning feedback.

[0074] The personalized learning suggestion module provides personalized learning suggestions and course recommendations based on students' learning outcomes and preferences, in order to help students improve their learning more effectively.

[0075] The user notification module is responsible for promptly notifying users of learning progress reports, learning outcome reports, and personalized learning suggestions, ensuring that students can obtain important learning information in a timely manner.

[0076] The present invention will be further described below with reference to Examples 1 to 3:

[0077] Example 1:

[0078] The educational resource integration module first establishes data interfaces with multiple educational resource providers (such as textbook publishers and online course platforms). These data interfaces are based on RESTful API or GraphQL standard protocols to ensure the stability and reliability of data exchange. Through scheduled tasks, the educational resource integration module retrieves the latest educational resource data from various data sources daily, including course materials, teaching videos, and exercise banks.

[0079] The acquired educational resource data may come from different systems, and their formats and standards may differ. Therefore, the educational resource integration module formats and standardizes this data, such as by unifying file formats, data encoding, and metadata descriptions, to ensure data consistency and usability. The processed educational resource data is then imported into the platform's data center module for subsequent storage and management.

[0080] The platform's data center module uses relational database (such as MySQL) technology to persistently store various educational resource data, ensuring data security and accessibility.

[0081] To ensure data security, the platform's data center module has implemented the following data security measures:

[0082] Data encryption. Sensitive data is encrypted during storage and transmission using the AES encryption algorithm to ensure data confidentiality.

[0083] Access control. Through authentication and permission management mechanisms, users accessing data are authenticated, and appropriate data access permissions are granted based on their roles and permissions.

[0084] Backup strategy. Establish a regular backup strategy, such as performing a full backup of the database daily and an incremental backup weekly, to prevent data loss or corruption.

[0085] The real-time scene rendering module first defines a standardized data interface to acquire and parse scene data transmitted from the data management layer. This scene data includes the content and layout information of educational resources, as well as related metadata. By parsing this data, the real-time scene rendering module understands the specific requirements and details of the scene to be rendered. Utilizing an advanced 3D modeling engine, the real-time scene rendering module creates corresponding 3D objects and scene structures based on the educational resource content and layout information in the scene data, transforming abstract scene data into concrete 3D models, including the shape, texture, lighting, and other attributes of the objects. Using a high-performance graphics rendering engine, the real-time scene rendering module performs real-time rendering of the created 3D objects and scene structures, including applying lighting effects, performing material mapping, and implementing real-time animations to generate interactive virtual scenes. The specific method is as follows:

[0086] The real-time scene rendering module first defines a standardized data interface based on JSON format to obtain scene data from the data management layer. The scene data is transmitted in the form of JSON objects and includes content descriptions of educational resources, 3D coordinates, and texture information.

[0087] After acquiring the scene data, the real-time scene rendering module uses Unity 3D as its 3D modeling engine to create corresponding 3D objects and scene structures based on the educational resources and layout information in the scene data. For example, if the scene data describes a virtual classroom, the real-time scene rendering module will create a 3D model of the classroom in Unity, including objects such as desks, chairs, blackboards, and windows, and arrange them according to the layout information.

[0088] The real-time scene rendering module further utilizes Unity's built-in graphics rendering engine to render the created 3D objects and scene structures in real time. During rendering, the real-time scene rendering module applies lighting effects to make the scene more realistic, and also performs texture mapping on the objects to enhance their realism. To improve rendering performance, the real-time scene rendering module uses optimization techniques provided by Unity, such as LOD (Level of Detail) technology, to dynamically adjust the rendering details of objects based on their distance and importance in the scene.

[0089] The visual optimization module receives scene image data from the real-time scene rendering module. This data is transmitted in a structured format and includes information about objects in the scene, lighting information, and material information of the objects.

[0090] Upon receiving the data, the visual optimization module begins lighting analysis. First, it analyzes the light source information in the scene, including the light source's position, intensity, and color. Then, combining this with the object's material properties, such as reflectivity, refractive index, and diffuse color, it calculates the impact of the lighting effect on the object's surface. Lighting models, such as the PBR (Physically Based Rendering) model, are used to simulate real-world lighting phenomena.

[0091] Based on the lighting analysis results, the visual optimization module further refines the materials of objects in the scene. Using image processing techniques, it optimizes the texture maps of objects to enhance texture detail and clarity. Simultaneously, it adjusts the reflectivity and refractive index parameters of objects to simulate the reflection and refraction of light on object surfaces in the real world.

[0092] Example 2:

[0093] The implementation steps of the virtual interaction module include: The virtual interaction module receives interaction commands from the user via input devices, including but not limited to a mouse, keyboard, and VR controllers, through a predefined data interface. The module continuously monitors the input from these devices to ensure timely response to user actions. Upon receiving an interaction command, the virtual interaction module immediately parses the command to identify the user's intent, including decoding and classifying the command to determine whether the user wants to move, select, or manipulate objects in the virtual scene. By parsing the command, the module can accurately understand the user's desired operation. Based on the parsed user intent, the virtual interaction module calls relevant functions in the scene rendering layer to update the state of the virtual scene. For example, if the user wants to move a virtual object, the module calls the move function in the scene rendering layer and passes the corresponding parameters to achieve the object's movement. The virtual interaction module feeds back the updated virtual scene state to the user and transmits the rendered scene image to the user's display device so that the user can see the results of their actions. Through this feedback mechanism, users can perceive their influence and control over the virtual scene in real time.

[0094] Based on the needs and user habits of the online education platform, the user interface design module designs the layout and style of the user interface, including the arrangement of interface elements, color matching, and font selection, to ensure the interface is aesthetically pleasing and easy to use. It develops various elements of the user interface, including but not limited to buttons, text boxes, sliders, selection boxes, and display areas. For each element, its function and response events are defined. For example, click events are added to buttons, input events are defined for text boxes, and slide events are added to sliders, enabling interface elements to interact with the user and achieve the required functions. The user interface design module connects the user interface to the virtual interaction module, mapping interface elements to the functions of the virtual interaction module to ensure that user commands issued through the user interface are correctly parsed and processed. For example, when a user clicks a button, the virtual interaction module receives the corresponding command and executes the corresponding operation. Through this connection, the user interface design module and the virtual interaction module jointly realize the interaction between the user and the virtual scene.

[0095] Example 3:

[0096] The learning behavior statistics module implements a data collection mechanism that integrates with other components of the online education platform to capture students' learning behavior data in real time, including but not limited to students' login time, learning duration, course access frequency, and assignment submission status.

[0097] The learning behavior statistics module organizes and analyzes the collected data. For login time, it records the timestamp of each student's login and calculates the login frequency and time period distribution. For learning duration, it tracks students' learning time on the platform and generates learning duration reports to understand students' learning engagement. For course access frequency, it counts the number of times and duration students access each course to analyze students' attention and learning interest in different courses. For assignment submission, it records the time, frequency, and quality of student assignment submissions to assess students' learning attitudes and assignment completion. Finally, the organized data is presented to teachers or administrators in a visual format. Through intuitive charts and reports, students can clearly understand their learning behavior patterns, learning progress, and learning outcomes.

[0098] The learning performance prediction module uses machine learning technology to build and train a score prediction model. This model is used to obtain the correlation between learning behavior data and corresponding changes in learning scores, and based on current user learning behavior data, predicts changes in learning scores over a future period. The steps for building and training the score prediction model include:

[0099] Step 1: Data Collection. Student learning behavior data is collected from the online education platform's historical records. This data includes login time, study duration, course access frequency, assignment submission, and participation in interactive Q&A sessions. Simultaneously, students' exam scores corresponding to this behavior data at different time periods are collected as learning score change data. Together with the learning behavior data, this forms the foundational dataset required for training the score prediction model.

[0100] Step 2, Data Cleaning: The collected historical data is cleaned to remove missing and outlier values. For missing values, linear interpolation is used to fill them in; for outliers, a threshold method is used to identify data points that exceed a preset threshold range and replace them with the mean of their nearest neighbors.

[0101] Step 3: Data Preprocessing: Based on data cleaning, the remaining data is standardized to eliminate the influence of different units and orders of magnitude on data modeling. The Z-score standardization method is used, subtracting the mean from each numerical data point and dividing by its standard deviation to ensure the processed data conforms to a standard normal distribution. The standardization formula is: ,in, The original data, The mean of the original data. The standard deviation of the original data. This involves standardizing the data. For example, students' study time is converted from minutes to hours, and the time data for all students is normalized to be distributed between 0 and 1. After preprocessing, the data is organized into a format suitable for model training, forming the training dataset.

[0102] Step 4: Dataset Splitting: Divide the preprocessed dataset into a training set and a validation set in a 7:3 ratio. The training set is used for iterative training of the model, while the validation set is used to periodically evaluate the model's performance during training to prevent overfitting.

[0103] Step 5: Model Selection and Initialization: A Long Short-Term Memory (LSTM) network model is selected as the basic architecture for the score prediction model. LSTM models are advantageous in predicting score changes related to behavioral data and time series data due to their strength in processing sequential data. The parameters of the LSTM model are initialized, including the model's structural parameters (such as the number of layers and neurons), initial values ​​for weights and biases, and the learning rate parameters for the activation function and optimization algorithm. For example, a 2-layer LSTM with 128 neurons per layer is used, initializing the weights and biases to random decimals, setting the activation function to ReLU, the optimization algorithm to Adam, and the learning rate to 0.001.

[0104] Step 6, Model Training and Evaluation: Iteratively train the selected LSTM model using the training set data. During training, continuously adjust the model's weights and biases using optimization algorithms such as backpropagation and gradient descent to minimize prediction error. The Mean Squared Error (MSE) algorithm is used to evaluate the performance of the score prediction model. The specific algorithm is as follows:

[0105]

[0106] Where n is the number of data points. Predict scores for the model, The actual score is used to evaluate the model's prediction accuracy; a smaller MSE value indicates higher prediction accuracy. If the model's performance does not meet the requirements, the model structure or parameters are adjusted, and training continues until the model's performance reaches a satisfactory level, at which point training is stopped.

[0107] Step 7, Model Saving and Deployment: After training, save the key parameters of the LSTM model, such as weights and biases, and deploy the trained model to the online education platform. This allows for real-time prediction of changes in students' learning scores based on their learning behavior data. Through the model's prediction results, teachers can promptly understand students' learning status and take appropriate teaching measures for intervention and guidance.

[0108] The learning progress feedback module tracks and records users' learning progress on the online education platform in real time. This module utilizes the platform's data interfaces to collect user learning behavior data, such as course access frequency, learning duration, and assignment submission status. Based on this data, a detailed learning progress report is generated, including completed learning tasks, ongoing learning activities, and estimated remaining learning time.

[0109] The learning effectiveness assessment module conducts an in-depth evaluation of the user's learning effectiveness based on the output data of the learning effectiveness prediction module. This module first obtains the prediction results of the user's learning score changes over a future period provided by the prediction module, and then combines the user's historical learning performance and learning behavior data to quantitatively evaluate the user's learning effectiveness. The evaluation results include the user's learning progress speed and the degree of mastery of knowledge points.

[0110] The personalized learning suggestion module provides individualized learning advice and course recommendations based on the user's learning progress and preferences. This module analyzes the user's learning performance report to identify their strengths and weaknesses. Then, combining the user's learning preferences and historical learning behavior data, it uses recommendation algorithms to suggest suitable learning resources and courses. The recommendations include both intensive training to address the user's weaknesses and further development of their strengths. Through personalized learning suggestions, users can develop more scientific and efficient learning plans.

[0111] The user notification module is responsible for promptly notifying users of learning progress reports, learning effectiveness reports, and personalized learning suggestions. This module sends notifications to users through various means, including the online education platform's messaging system, email, and SMS. The notification content includes a summary and key information from the report, as well as a link or attachment to access the full report. Users can view these reports and suggestions at any time to understand their learning status and adjust their learning strategies accordingly. This timely notification service ensures that users can fully utilize feedback information to improve their learning outcomes.

[0112] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0113] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. An online education platform management system, characterized in that: It includes a data management layer, a scene rendering layer, a user interaction layer, a behavior analysis layer, and a user feedback layer; The data management layer is used for data integration, storage, and management, including: The educational resource integration module is used to integrate data from different educational resources; The platform's data center module is used to store and manage all the data required by the online education platform. The scene rendering layer utilizes real-time rendering technology to achieve scene simulation and visualization effects, including: The real-time scene rendering module is used to perform real-time rendering based on the data provided by the data management layer, generating virtual scenes; The visual optimization module is used to optimize rendering effects and provides fine-tuning of lighting and material details; The user interaction layer provides users with an interactive experience through virtual reality and augmented reality technologies, including: The virtual interaction module is used to enable users to interact with virtual scenes; The user interface design module is used to provide an operating interface so that users can perform various operations and controls; The behavior analysis layer is responsible for analyzing learning behavior, including: The learning behavior statistics module is used to acquire and analyze students' learning behavior data in real time, including login time, learning duration, course access frequency, homework submission status, and participation in interactive Q&A. The learning outcome prediction module is used to predict students' learning outcomes based on the results of the learning behavior statistics module. The user feedback layer is used to provide learning information to users, including: The learning progress feedback module is used to track and record the user's learning progress in real time and generate learning progress reports; The learning outcome assessment module is used to evaluate students' learning outcomes based on the output data of the learning outcome prediction module and generate a learning outcome report. The personalized learning suggestion module is used to provide personalized learning suggestions and course recommendations based on the user's learning progress and preferences; The user notification module is used to promptly notify users of learning progress reports, learning effectiveness reports, and personalized learning suggestions.

2. The online education platform management system according to claim 1, characterized in that: The educational resource integration module establishes data interfaces with various educational resources, regularly obtains the latest educational resource data from various data sources, formats and standardizes the data, and finally imports the processed educational resource data into the platform data center module. The platform data center module uses database technology to persistently store various types of educational resource data and formulates data security measures, including data encryption, access control, and backup strategies.

3. The online education platform management system according to claim 1, characterized in that: The real-time scene rendering module acquires and parses scene data transmitted from the data management layer by defining a standardized data interface; it uses a 3D modeling engine to create corresponding 3D objects and scene structures based on the educational resource content and layout information in the scene data, and uses a graphics rendering engine to render the created 3D objects and scene structures in real time.

4. The online education platform management system according to claim 1, characterized in that: The visual optimization module receives scene image data from the real-time scene rendering module, and the scene image data includes objects, lighting, and materials in the scene; The scene image is subjected to lighting analysis. Based on the position, intensity and color of the light source in the scene, as well as the material properties of the objects, the impact of the lighting effect on the object surface is calculated. Further fine-tuning of the object material in the scene is performed, including adjusting the texture map, reflectivity and refractive index parameters of the object, so that the object surface presents a more realistic texture and detail.

5. The online education platform management system according to claim 1, characterized in that, The virtual interaction module is implemented in the following ways: Receive interactive commands from users via input devices, including devices such as mice, keyboards, and VR controllers; Parse interactive commands and identify user intent, including moving, selecting, and manipulating objects in the virtual scene; Based on the user's intent, invoke the relevant functions of the scene rendering layer to update the state of the virtual scene; The updated virtual scene status will be fed back to the user.

6. The online education platform management system according to claim 1, characterized in that, The implementation methods of the user interface design module include: Design the layout and style of the user interface based on the needs and user habits of the online education platform; Develop various elements of the user interface, including buttons, text boxes, sliders, selection boxes, and display areas, and define the functions and event responses of all elements; The user interface is connected to the virtual interaction module so that the commands issued by the user through the user interface can be correctly parsed and processed.

7. The online education platform management system according to claim 1, characterized in that: The learning performance prediction module uses machine learning technology to build and train a score prediction model. The score prediction model is used to obtain the correlation between learning behavior data and corresponding learning score changes, and to predict learning score changes in the future based on current user learning behavior data.

8. The online education platform management system according to claim 7, characterized in that, The steps involved in building and training a score prediction model include: Step 1, Data Collection: Collect historical learning behavior data and corresponding learning score change data as training data; the historical learning behavior data includes students' login time, learning duration, course access frequency, homework submission status, and interactive Q&A participation; the corresponding learning score change data includes students' exam scores in different time periods; Step 2, Data Cleaning: Clean the collected historical data to handle missing and outlier values; Step 3, Data Preprocessing: Standardize the cleaned data to form a training dataset; Step 4: Dataset partitioning: Divide the training dataset into a training set and a validation set; Step 5, Model Selection and Initialization: Select the Long Short-Term Memory (LSTM) network model to build the score prediction model, and initialize the model parameters. The initialized parameters include the model's structural parameters, weights and biases, as well as setting the model's activation function and the learning rate parameters of the optimization algorithm. Step 6, Model Training and Evaluation: Iteratively train the selected model using the training set data. During the training process, periodically evaluate the model performance using the validation set until the model's performance meets the requirements. Step 7, Model Saving and Deployment: After training is complete, save the model's weights and biases, and deploy the model for subsequent prediction of learning score changes.

9. The online education platform management system according to claim 8, characterized in that: In the data cleaning step 2, missing values ​​are filled using a linear interpolation algorithm; outliers are identified using a threshold method, where data points exceeding a preset threshold range are considered outliers and replaced with the mean of their nearest neighbors. In step 3, data preprocessing uses the Z-score standardization method, subtracting the mean from each numerical data point and dividing by its standard deviation to ensure the processed data conforms to a standard normal distribution. The standardization formula is as follows: ,in, The original data, The mean of the original data. The standard deviation of the original data. This is the standardized data.

10. An online education platform management system according to claim 9, characterized in that, The performance of the score prediction model is evaluated using the mean squared error (MSE) algorithm. The specific algorithm is as follows: ； Where n is the number of data points. Predict scores for the model, The actual score is used to evaluate the model's prediction accuracy. The smaller the MSE value, the higher the model's prediction accuracy.

Images