Online education background data management system based on data interaction

Abstract

The invention relates to the technical field of education platform management, in particular to an online education background data management system based on data interaction. The system comprises a situation data preprocessing module, a situation information exchange layer, a real-time stream processing module, an intelligent cache and personalized prediction module and a feedback and adaptive adjustment module. The situation data preprocessing module is responsible for collecting and processing original learning behavior data from multiple sources and extracting situation information. The situation information exchange layer receives the data, standardizes the data and efficiently distributes the data to subsequent modules. And the real-time stream processing module analyzes learning behaviors of the user in real time by using technologies such as a sliding window model and the like, generates a personalized learning feature data set, transmits the personalized learning feature data set to a subsequent module, and finally provides instant feedback and support. According to the method, efficient data interaction among all modules of the system is realized by introducing the situational information exchange layer, and the real-time response capability of the system is ensured, so that the support capability of personalized learning is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of education platform management, and in particular to an online education background data management system based on data interaction. Background Art

[0002] With the rapid development of information technology, online education has gradually become an indispensable part of the modern education system. Early online education platforms mainly relied on static learning resources and simple interactive tools. These platforms met the needs of basic education to a certain extent, but they were obviously insufficient in terms of personalized learning experience. In order to better support students' learning needs, more and more online education platforms have begun to adopt advanced technologies such as big data analysis and machine learning, trying to provide more personalized learning paths and resource recommendations by collecting and analyzing students' behavioral data.

[0003] Although current online education backend data management systems have made some progress in personalized learning, they still have certain deficiencies in real-time context awareness and dynamic adjustment. Existing data management systems usually rely on centralized data processing architectures, which may lead to data processing delays when facing large-scale concurrent users, and due to the lack of responsiveness to real-time context changes, it is difficult to make timely adjustments based on students' immediate learning status. This limitation may limit the system's ability to provide a highly personalized learning experience, thereby affecting teaching effectiveness and students' learning enthusiasm to a certain extent. Summary of the invention

[0004] The purpose of the present invention is to provide an online education background data management system based on data interaction to solve the problems of data processing delay and lack of real-time situation response capability in the case of large-scale concurrent users, so that the system can make timely adjustments according to the students' immediate learning status. Specifically, the situation information exchange layer, as the core hub of the system, receives the original situation data and converts it into standardized data, and then distributes it efficiently to subsequent modules. By adopting standardized formats and protocols, supporting multiple transmission methods, and using asynchronous message queue mechanisms to alleviate high concurrency bottlenecks, this layer can quickly respond to students' learning behaviors and situation changes, and realize real-time monitoring and dynamic adjustment. Therefore, the situation information exchange layer significantly enhances the system's real-time situation perception and instant response capabilities in a large-scale concurrent user environment, better supports personalized learning experience, and thus recommends optimized learning resources to students.

[0005] To achieve the above purpose, an online education backend data management system based on data interaction is provided, including a context data preprocessing module, which collects original learning behavior data from multiple learning behavior data sources, performs preliminary processing through an edge computing unit, and extracts valuable original context data. It also includes:

[0006] Context information exchange layer: The context information exchange layer receives the original context data from the context data preprocessing module and converts the original context data into standardized context data. The context information exchange layer defines a set of standardized data formats and protocols. The asynchronous message queue mechanism receives data based on standardized data formats and protocols to provide a data flow channel for the intelligent routing algorithm. The intelligent routing algorithm dynamically allocates standardized context data according to the subscribed topics to optimize the data transmission path. The context information exchange layer passes the standardized context data to the real-time stream processing module, and conducts in-depth analysis and application of it to recommend optimized learning resources to students.

[0007] As a further improvement of the present technical solution, the edge computing unit extracts valuable context information based on the original learning behavior data to form original context data.

[0008] As a further improvement of the technical solution, an asynchronous message queue mechanism in the context information exchange layer distributes the standardized context data.

[0009] As a further improvement of the present technical solution, the intelligent routing algorithm in the context information exchange layer automatically identifies the target module according to the subject of the data, and accurately distributes the standardized context data to the real-time stream processing module.

[0010] As a further improvement of the present technical solution, the real-time stream processing module includes a data subscriber, which subscribes to a data stream of a specific topic from the context information exchange layer and passes the data stream to the stream processor, and the data subscriber selects and receives data based on predefined topics.

[0011] As a further improvement of the present technical solution, the real-time stream processing module also includes a stream processor, which performs in-depth analysis on the received standardized contextual data, identifies the user's behavior patterns and the contextual factors behind them, and converts the standardized contextual data into a personalized learning feature data set. The stream processor applies a sliding window model to parse the data for identifying the user's behavior patterns.

[0012] As a further improvement of the present technical solution, the real-time stream processing module also includes a feedback controller, which dynamically adjusts the recommendation algorithm according to the generated personalized learning feature data set.

[0013] As a further improvement of the present technical solution, the real-time stream processing module transmits the personalized learning feature data set to the intelligent cache and personalized prediction module. The intelligent cache and personalized prediction module identifies the user's interests and learning patterns by analyzing these data, and predicts the learning content that the user is interested in, and caches it in the local storage in advance.

[0014] As a further improvement of the present technical solution, the intelligent caching and personalized prediction module dynamically adjusts the caching strategy according to factors such as the access frequency of learning resources and the content update cycle, so as to ensure the freshness and relevance of the cached content.

[0015] As a further improvement of the present technical solution, the intelligent caching and personalized prediction module transmits the personalized learning feature data set to the feedback and adaptive adjustment module. The feedback and adaptive adjustment module continuously monitors the user's learning progress and effect, dynamically adjusts the learning path and content, and automatically pushes relevant auxiliary materials when it detects that the user encounters difficulties, and at the same time introduces changes in learning strategies.

[0016] Compared with the prior art, the present invention has the following beneficial effects:

[0017] 1. By introducing the context information exchange layer, the system enhances the real-time context perception and immediate response capabilities in a large-scale concurrent user environment. This layer converts the original context data into standardized context data, and uses standardized data formats and protocols to ensure data consistency and interoperability. The asynchronous message queue mechanism receives data based on standardized data formats and protocols, providing an efficient and reliable data flow channel for the intelligent routing algorithm, which ensures that data can be transmitted stably and timely in a high-concurrency environment. The intelligent routing algorithm uses this channel to dynamically allocate standardized context data according to subscribed topics, optimize the data transmission path, thereby reducing delays and improving the transmission success rate. Therefore, this close collaboration significantly improves the system's real-time response capability and data processing efficiency, enabling the system to quickly respond to students' learning behaviors and context changes in the case of large-scale concurrent users, and provide a highly personalized and smooth learning experience. This mechanism not only enhances the reliability of data flow, but also greatly improves the overall performance and user experience of the system.

[0018] 2. In the online education backend data management system based on data interaction, the intelligent cache and personalized prediction module receives personalized learning feature data transmitted by the real-time stream processing module, identifies user interests and learning patterns, predicts and caches content that users may be interested in, reduces loading time and improves response speed. The module also dynamically adjusts the cache strategy based on access frequency and content update cycle to ensure the freshness and relevance of the content. At the same time, the feedback and adaptive adjustment module continuously monitors learning progress and results, dynamically adjusts the learning path, automatically pushes auxiliary materials and suggests changes in learning strategies when users encounter difficulties. This closed-loop system improves learning outcomes, optimizes personalized resource recommendations and service quality, and improves overall teaching effectiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a flow chart of the online education backend data management system based on data interaction of the present invention;

[0020] Figure 2 It is a schematic diagram of the context information exchange layer process of the present invention;

[0021] Figure 3 It is a flowchart of the real-time stream processing module of the present invention.

[0022] The meaning of each number in the figure is:

[0023] Among them: 100, situational data preprocessing module; 200, situational information exchange layer; 300, real-time stream processing module; 400, intelligent caching and personalized prediction module; 500, feedback and adaptive adjustment module; 600, original situational data; 700, standardized situational data; 800, personalized learning feature data set. DETAILED DESCRIPTION

[0024] 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.

[0025] At the same time, some technical terms are explained here:

[0026] The Sliding Window Model is a method for processing continuous data streams or time series data, and is particularly suitable for scenarios that require real-time analysis and response. It intercepts a portion of the data stream through a fixed-size time window and performs calculations or analysis based on the data in this window. As new data arrives, the window moves forward at the set sliding interval, thereby updating the contained data set.

[0027] Intelligent routing refers to a mechanism that automatically determines the optimal distribution path based on the subject of the data in a data interaction system. It can identify the subject of data association, select the appropriate target module for data distribution, and ensure that data can be efficiently and accurately transmitted even in high concurrency situations through technologies such as asynchronous message queues. This mechanism dynamically adjusts strategies based on system status, optimizes data transmission efficiency and response speed, and enhances system flexibility and scalability.

[0028] See also Figure 1As shown, an online education background data management system based on data interaction is provided, which aims to provide users with customized learning suggestions and optimize the overall learning experience by integrating the context data preprocessing module 100, the context information exchange layer 200, the real-time stream processing module 300, the intelligent cache and personalized prediction module 400 and the feedback and adaptive adjustment module 500.

[0029] First, the context data preprocessing module 100 is responsible for collecting raw learning behavior data from a variety of learning behavior data sources, and preliminarily processing it through edge computing technology to extract valuable raw context data 600 for use by subsequent modules. Specifically, the collection process of raw context data 600 includes the collection of multi-dimensional data such as the length of time students watch videos, homework completion, and degree of participation in discussions. These data not only reflect the students' learning progress, but also provide important clues about their learning habits and current status.

[0030] To improve the efficiency of data processing and reduce the burden on central servers, we used edge computing technology. Edge devices (such as students' mobile devices or local servers) can perform preliminary processing tasks close to the data source, such as data filtering, compression, and contextual information extraction. To evaluate students' learning activities, we used video viewing time and pause times as key indicators. To calculate effective viewing time, we used the following formula:

[0031] ;

[0032] In the formula, Indicates the effective viewing time;

[0033] Indicates the video viewing time;

[0034] Indicates the number of pauses;

[0035] Indicates the average duration of each pause.

[0036] Through the above comprehensive formula, not only the amount of data that needs to be uploaded is reduced, but also more valuable information is provided for subsequent situational awareness.

[0037] In addition, the module uses sensors (e.g., cameras, microphones) to capture additional contextual information, such as ambient noise levels. and user attention span In order to dynamically adjust the data collection strategy, when a high level of ambient noise is detected (i.e. ,in is the set ambient noise threshold), the system automatically pays less attention to audio input and relies more on visual and text input to assess the user's state. Similarly, when the attention level is low (i.e. ,in is the set attention threshold), the system can trigger a reminder mechanism to suggest students to take a break or switch learning content to improve learning efficiency. Through these methods, the situational data preprocessing module 100 not only improves the speed and efficiency of data processing and reduces unnecessary data transmission, but also ensures that the system can make more accurate responses according to real-time situations, laying a solid foundation for personalized learning experience.

[0038] In summary, the situational data preprocessing module 100 realizes effective analysis and processing of student learning behavior by adopting edge computing technology and machine learning models. This not only significantly improves the speed and efficiency of data processing, reduces unnecessary data transmission burden, but also ensures that the system can make more accurate responses based on real-time situations, laying a solid foundation for personalized learning experience. However, in order to further optimize the performance of the entire system and achieve higher-level situational awareness and data interaction capabilities, the present invention introduces a situational information exchange layer 200. As the core hub of the system, the situational information exchange layer 200 receives the original situational data 600 from the situational data preprocessing module 100, converts it into standardized situational data 700, and then distributes it to subsequent functional modules efficiently and intelligently. This process ensures the consistency and timeliness of data between modules, so that the entire online education platform can provide a smoother and more personalized user experience. Through this conversion and distribution, the system can dynamically adjust service strategies and provide accurate personalized learning support.

[0039] As the core improvement of the present invention, the context information exchange layer 200 not only enhances the response speed and flexibility of the system, but also particularly enhances the data interaction capability, ensuring that the functional modules can efficiently and accurately share the standardized context data 700. The design concept of this layer is to build an intelligent and dynamic data bridge to promote the circulation and utilization of real-time context information.

[0040] See also Figure 2 As shown, in terms of data interaction, the context information exchange layer 200 first defines a set of standardized data formats and protocols to facilitate seamless docking between different modules. This includes the standardization of input and output data structures (such as JSON or XML format) and support for multiple transmission protocols (such as HTTP / HTTPS, WebSocket, etc.). For example, when processing learning behavior data from edge computing nodes, the context information exchange layer 200 converts the original context data 600 into a unified format:

[0041] ;

[0042] In the formula, It is the situational data after standardization;

[0043] It refers to the normalization processing function;

[0044] Represents raw, unprocessed context data 600 collected from various sources.

[0045] In order to further improve the efficiency of data interaction, the context information exchange layer (200) introduces an asynchronous message queue mechanism. Based on the defined standardized data format and protocol, the mechanism can ensure data consistency and efficient communication between different modules. Specifically, due to the use of standardized data formats and transmission protocols, the asynchronous message queue mechanism can be optimized on the basis of these unified standards, so that each module can subscribe to the data stream of a specific topic according to its own needs. This not only improves the efficiency of data processing, but also provides a reliable data flow channel for the intelligent routing algorithm, thereby achieving efficient and accurate distribution of data and enhancing the real-time response capability and flexibility of the system. Specifically, when a module generates new context data or needs to update existing data, it can notify other modules subscribed to the topic by sending messages to the message queue of a specific topic. The formula is expressed as follows:

[0046] ;

[0047] In the formula, Represents a message queue for a certain topic;

[0048] Represents the i-th message in the queue. Each message contains the context data and metadata (such as timestamp, priority, etc.) that need to be distributed.

[0049] In addition, the context information exchange layer (200) also integrates an intelligent routing algorithm that dynamically adjusts the data flow according to the needs of the receiver. Based on the data consistency and interoperability ensured by the standardized data format and protocol and the stable data transmission channel guaranteed by the asynchronous message queue mechanism, the intelligent routing algorithm can optimize the data transmission path according to the current network status and the load of each module, thereby significantly reducing the delay and improving the transmission success rate. This close collaboration not only enhances the real-time response capability of the system, but also improves the overall data processing efficiency. Assume Indicates The optimal routing selection can be expressed as follows:

[0050] ;

[0051] In the formula, represents the optimal routing selection;

[0052] Indicates The resource status of each recipient;

[0053] Indicates the total number of receivers;

[0054] It is the optimal routing selection function based on the evaluation of the receiver's resource status.

[0055] Although the situational information exchange layer 200 has greatly optimized the data interaction mechanism within the system through standardized data formats, efficient asynchronous message queues, and intelligent routing strategies, there is still a problem of insufficient real-time response when facing rapidly changing learning situations and user behaviors. The existing design is unable to cope with scenarios with high requirements for immediacy, such as instant feedback on learning progress and dynamic adjustment of learning paths, and cannot meet the real-time requirements of personalized learning. Therefore, in order to make up for this deficiency and improve the real-time analysis and response capabilities of the system, it is necessary to introduce a real-time stream processing module 300. This module can monitor and analyze students' learning behaviors and the situational factors behind them in real time, and dynamically adjust service strategies based on these real-time data, thereby ensuring that learning support and services are more accurate and timely, and truly optimizing personalized learning experience. By introducing this module, the system not only enhances the real-time control capability of the learning process, but also provides unlimited possibilities for future advanced function expansion.

[0056] The real-time stream processing module 300 is designed to solve the challenges faced by existing systems when processing scenarios with high immediacy requirements. Figure 3As shown, this module mainly consists of three parts: data subscriber, stream processor and feedback controller, which aims to realize real-time analysis and dynamic response to students' learning behavior and the contextual factors behind it. First, the data subscriber is responsible for subscribing to the data stream of specific topics from the context information exchange layer 200, such as students' learning progress, test scores and behavior of participating in discussions, etc., to ensure that the acquired information is highly relevant and timely. Then, the stream processor conducts in-depth analysis on the received standardized context data 700, identifies the user's behavior pattern and the contextual factors behind it by applying sliding window models and other advanced data analysis techniques, and converts these standardized context data 700 into personalized learning feature data sets 800, which include key information such as user's interests, learning preferences, learning units to be completed, and potential learning paths. This conversion process enables the system to understand the learning needs of each student more accurately, laying the foundation for providing highly personalized learning support in the future. Finally, the feedback controller dynamically adjusts the recommendation algorithm or triggers the instant feedback mechanism according to the generated personalized learning feature data set 800 to achieve real-time optimization and support for the learning process.

[0057] The stream processor uses advanced technology to perform real-time analysis on the received standardized situational data 700. The sliding window model is applied here to process the continuously arriving data stream. Based on this model, at any time , in order to calculate the nearest The average learning performance over the time period, we used the following formula:

[0058] ;

[0059] In the formula, Each element in the data stream represents a specific learning activity or performance indicator;

[0060] is the time window size, which indicates the length of the time period we are concerned about;

[0061] Indicates any moment;

[0062] Is an index variable used to identify each element in the data stream.

[0063] When we calculate the average learning performance, The value from Change to , which means we are calculating the average value within a certain time window. The purpose of this formula is to evaluate students' learning performance in the recent period of time, so as to dynamically adjust the learning path or provide personalized suggestions based on this information. This calculation method can not only capture the short-term fluctuations of students' learning behavior, but also identify long-term trends, providing an important basis for the optimization of personalized learning paths. In addition, by dynamically adjusting the window size and sliding interval , the system can flexibly adapt to the needs of data analysis accuracy and timeliness in different scenarios. For example, a smaller window size It can improve the sensitivity to short-term changes, while a larger sliding interval s may reduce the calculation frequency and optimize resource usage. Such a mechanism ensures that the system can provide more accurate and personalized learning support while maintaining efficient performance.

[0064] In order to cope with the shortcomings of large-scale user concurrent access and providing highly personalized learning content, especially the problem of increased server load during peak hours leading to extended resource loading time, the real-time stream processing module 300 transmits the personalized learning feature data set 800 to the intelligent cache and personalized prediction module 400, thereby improving resource allocation efficiency and personalized service level. The intelligent cache and personalized prediction module 400 uses the personalized learning feature data set 800 received from the real-time stream processing module 300 to analyze the user's learning behavior and preferences to provide a more efficient and personalized learning resource access experience. The module first uses a sliding window model to monitor and analyze the user's learning activities in real time to identify the user's points of interest and learning patterns. Based on these analysis results, the system can predict the learning content that the user may be interested in next, and cache it in local storage in advance to reduce loading time and improve response speed. At the same time, personalized content prediction not only relies on the behavior data of a single user, but also comprehensively considers the learning habits and preferences of similar user groups, and enhances the accuracy of prediction through recommendation algorithms such as collaborative filtering. In addition, the intelligent cache mechanism will dynamically adjust the cache strategy according to factors such as the access frequency of learning resources and the content update cycle to ensure the freshness and relevance of the cached content. This method, which combines personalized prediction and intelligent caching, not only greatly improves the user experience, but also optimizes the efficiency of network resource utilization, providing strong support for the sustainable development of online education platforms.

[0065] In order to further improve the ability to dynamically respond to user instant feedback and automatically adjust according to learning progress, the intelligent cache and personalized prediction module 400 transmits the personalized learning feature data set 800 to the feedback and adaptive adjustment module 500. This module continuously monitors the user's learning progress and results, uses these data to dynamically adjust the learning path and content, and recommends optimized learning resources to students. Based on the user's actual learning situation, the system can provide personalized suggestions and feedback in a timely manner. For example, when it is detected that the user has difficulties in a certain knowledge point, the system will automatically push relevant auxiliary materials or suggest changes in learning strategies.

[0066] In addition, with the help of machine learning algorithms, this module can continuously learn and optimize its own adjustment rules to better meet the unique needs of each user, ensuring that the learning process is both efficient and enjoyable. This closed-loop control system not only improves learning effectiveness, but also enhances the flexibility and service capabilities of the system by recommending the most suitable learning resources in real time, providing more powerful and flexible support for online education platforms. In this way, the system can accurately recommend learning resources based on each student's learning progress and performance, maximize personalized learning needs, and improve overall teaching effectiveness.

[0067] In summary, by introducing the context information exchange layer 200, the present invention effectively solves the delay problem faced by traditional online education systems when dealing with large-scale concurrent users and the limitation of lacking real-time context response capabilities. The context information exchange layer 200 realizes efficient and accurate context data transmission, ensuring that each module can dynamically adjust and provide personalized services according to the students' immediate learning status. This not only improves the system's response speed and personalized learning experience, but also optimizes the teaching effect and students' learning enthusiasm.

[0068] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and descriptions are only preferred examples of the present invention and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. An online education backend data management system based on data interaction, comprising a context data preprocessing module (100), wherein the context data preprocessing module (100) collects original learning behavior data from a variety of learning behavior data sources, and performs preliminary processing through an edge computing unit to extract valuable original context data (600), characterized in that: Also includes: A context information exchange layer (200), wherein the context information exchange layer (200) receives the original context data (600) from the context data preprocessing module (100) and converts the original context data (600) into standardized context data (700). The context information exchange layer (200) defines a set of standardized data formats and protocols. The asynchronous message queue mechanism receives data based on the standardized data formats and protocols, and is used to provide a data flow channel for the intelligent routing algorithm. The intelligent routing algorithm dynamically allocates the standardized context data (700) according to the subscribed topics, and is used to optimize the data transmission path. The context information exchange layer (200) transmits the standardized context data (700) to the real-time stream processing module (300), and conducts in-depth analysis and application of the standardized context data, so as to recommend optimized learning resources to students.

2. The online education background data management system based on data interaction according to claim 1 is characterized by: The edge computing unit extracts valuable context information based on the original learning behavior data and calculates the effective viewing time, thereby forming the original context data (600). The effective viewing time is calculated by the following formula: ； In the formula, Indicates the effective viewing time; Indicates the video viewing time; Indicates the number of pauses; Indicates the average duration of each pause.

3. The online education background data management system based on data interaction according to claim 1 is characterized by: The asynchronous message queue mechanism distributes the standardized context data (700) to ensure timely data delivery in a high-concurrency environment. The asynchronous message queue mechanism manages data flow by defining a message queue of a specific topic. The organization of messages in the message queue is implemented by the following formula: ； In the formula, Represents a message queue for a certain topic; Represents the i-th message in the queue. Each message contains the context data and metadata that need to be distributed.

4. The online education background data management system based on data interaction according to claim 1 is characterized by: The intelligent routing algorithm automatically identifies the target module according to the subject of the data, and distributes the standardized context data (700) to the real-time stream processing module (300). The intelligent routing algorithm determines the optimal data transmission path through the following formula: ； In the formula, represents the optimal routing selection; Indicates The resource status of each recipient; Indicates the total number of receivers; It is the optimal routing selection function based on the evaluation of the receiver's resource status.

5. The online education background data management system based on data interaction according to claim 4 is characterized by: The real-time stream processing module (300) comprises a data subscriber, which subscribes to a data stream of a specific topic from the context information exchange layer (200) and passes the data stream to a stream processor, wherein the data subscriber selects and receives data based on a predefined topic.

6. The online education background data management system based on data interaction according to claim 3 is characterized by: The real-time stream processing module (300) further comprises a stream processor, wherein the stream processor performs in-depth analysis on the received standardized context data (700), wherein the stream processor identifies the user's behavior pattern and the contextual factors behind it, and converts the standardized context data (700) into a personalized learning feature data set (800), wherein the stream processor applies a sliding window model to parse the data, so as to identify the user's behavior pattern and calculate the average learning performance, wherein the average learning performance is realized by the following formula: ； In the formula, Each element in the data stream represents a specific learning activity or performance indicator; is the time window size, which indicates the length of the time period we are concerned about; Indicates any moment; Is an index variable used to identify each element in the data stream.

7. The online education background data management system based on data interaction according to claim 6 is characterized by: The real-time stream processing module (300) further comprises a feedback controller, which dynamically adjusts the recommendation algorithm based on the generated personalized learning feature data set (800).

8. The online education background data management system based on data interaction according to claim 7 is characterized by: The real-time stream processing module (300) transmits the personalized learning feature data set (800) to the intelligent cache and personalized prediction module (400), and the intelligent cache and personalized prediction module (400) identifies the user's interests and learning patterns by analyzing these data, and predicts the learning content that the user is interested in, and caches it in local storage in advance.

9. The online education background data management system based on data interaction according to claim 8 is characterized by: The intelligent cache and personalized prediction module (400) dynamically adjusts the cache strategy according to factors such as the access frequency of the learning resources and the content update cycle, so as to ensure the freshness and relevance of the cached content.

10. The online education background data management system based on data interaction according to claim 9 is characterized in that: The intelligent cache and personalized prediction module (400) transmits the personalized learning feature data set (800) to the feedback and adaptive adjustment module (500), and the feedback and adaptive adjustment module (500) continuously monitors the user's learning progress, dynamically adjusts the learning path, and automatically pushes relevant auxiliary materials when it detects that the user encounters difficulties, and at the same time introduces changes in learning strategies.

Images