Online learning system and method based on adaptive engine

Abstract

The invention discloses an online learning system and method based on a self-adaptive engine, and belongs to the technical field of online learning. In order to solve the problems of insufficient learning demand identification and insufficient personalized recommendation, learning demands and weak links of a user can be accurately identified by monitoring the learning progress and behavior of the user in real time, a basis is provided for personalized recommendation, a personalized learning path is generated for the user according to a learning model and progress of the user, and the user experience is improved. The most relevant resources are obtained from the learning resource management module based on the learning features and preferences of the user, optimal distribution and utilization of the learning resources are achieved, personalized learning content and teaching modes are pushed in real time according to the learning requirements of the user, it is ensured that the user can obtain the needed learning resources in time, the learning efficiency is improved, and the user experience is improved. By collecting and analyzing the feedback data of the user to the pushed content, the pushed content and the teaching mode can be dynamically adjusted, and it is ensured that the pushed content is matched with the learning progress and interest of the user.

Description

Technical Field

[0001] This invention relates to the field of online learning technology, and in particular to an online learning system and method based on an adaptive engine. Background Art

[0002] Online learning, also known as distance learning or e-learning, is a form of education conducted via the internet or other electronic media. It allows learners to access learning content without being restricted by time or location, using devices such as computers, tablets, or smartphones. Online learning can be individual self-study or group learning, with interaction through video conferencing, chat rooms, forums, and other methods.

[0003] However, the following problems still exist in actual operation:

[0004] Existing online learning systems may struggle to accurately identify each user's learning needs and weaknesses, leading to uneven distribution of learning resources, poor learning outcomes, a lack of personalized learning paths and resource recommendations, and an inability to provide customized learning content based on individual user needs. Furthermore, the lack of targeted learning resources causes users to spend excessive time on non-critical knowledge points, resulting in low learning efficiency and an inability to adjust learning strategies in a timely manner. Consequently, users fail to effectively master knowledge points, leading to minimal learning outcomes. Summary of the Invention

[0005] The purpose of this invention is to provide an online learning system and method based on an adaptive engine to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution: an online learning system based on an adaptive engine, comprising:

[0007] The user interaction management module is used for:

[0008] The system processes user interaction records, including login, course selection, and learning progress tracking. It also collects user feedback and learning behavior data, stores and manages user personal information and learning behavior data in a database, and provides data interfaces for other modules to access.

[0009] The learning resource management module is used for:

[0010] The system utilizes file storage services to store and manage learning resources, including course videos, micro-videos of knowledge points, images, documents, and exercises, and provides learning resource retrieval and distribution functions based on a resource indexing and distribution mechanism.

[0011] The adaptive recommendation module is used for:

[0012] Real-time monitoring of user learning progress; analysis of user learning status and preferences based on user learning in various knowledge points; identification of weak learning areas based on user learning progress; and generation of personalized learning recommendations and learning assistance suggestions.

[0013] The content push feedback module is used for:

[0014] Based on the output of the learning analytics and recommendation module, personalized learning content, suggestions, and teaching modes are pushed to users in real time using message queues and push services. User feedback and learning progress are tracked, and the pushed content is dynamically adjusted based on user feedback and learning progress.

[0015] Furthermore, the user interaction management module includes:

[0016] User interaction recording unit, used for:

[0017] The system constructs a user interface, receives user interaction requests through a backend API interface, records user interaction data, collects user feedback and learning behavior data, and stores the user interaction data in a database. The user interaction data includes user ID, interaction type, and interaction time. A data interface is provided for other modules to access the user interaction data.

[0018] Furthermore, the user interaction management module also includes:

[0019] The user data management unit is used for:

[0020] It stores and manages users' personal information and learning behavior data through a database, and provides functions for adding, deleting, modifying, and querying user data.

[0021] Furthermore, the learning resource management module includes:

[0022] Learning resource storage unit, used for:

[0023] The system utilizes file storage services to store and manage learning resources, establishes a resource index that includes the resource's name, type, description, associated course metadata, provides a resource retrieval interface, and allows for quick resource location based on the resource index.

[0024] Furthermore, the learning resource management module also includes:

[0025] The learning resource distribution unit is used for:

[0026] Based on a resource indexing and distribution mechanism, it provides learning resource retrieval and distribution functions. According to user requests and resource indexes, it distributes learning resources to users, establishes a user permission management mechanism, and provides a resource access interface. Users can obtain the learning resources they are authorized to through the resource access interface. Based on the user's role and permissions, it controls the user's access to learning resources.

[0027] Furthermore, the adaptive recommendation module includes:

[0028] The learning behavior analysis unit is used for:

[0029] The system monitors users' learning progress in real time, including completed courses, exercises, and watched videos. It preprocesses the learning progress data and analyzes the user's learning status on various knowledge points based on the data, including answer accuracy, learning duration, time distribution, and number of repeated learning sessions. Based on the user's learning behavior, it establishes a user learning model and extracts the user's learning characteristics and preferences. The system updates the user's learning model in real time based on the user's learning characteristics and preferences.

[0030] Furthermore, the adaptive recommendation module also includes:

[0031] Personalized recommendation generation unit, used for:

[0032] The learning behavior analysis unit obtains the user's learning model and current learning progress. Based on the user's learning model and current learning progress, it identifies learning content where the user has short learning time and high error rate on practice questions. This learning content is considered a weak point in the user's learning. Based on the user's weak points and preferences, it obtains relevant learning resources from the learning resource management module and generates personalized learning recommendations.

[0033] Furthermore, the content push feedback module includes:

[0034] Content push unit, used for:

[0035] Based on the output of the adaptive recommendation module, personalized learning recommendations are obtained, including learning resources, suggestions, and teaching modes. The recommendations are encapsulated into a message format and pushed to the user's device in real time using a push service. The status of the push service is monitored, and push logs are recorded, including push time, push content, and user feedback information.

[0036] Furthermore, the content push feedback module also includes:

[0037] Feedback processing and adjustment unit, used for:

[0038] Track and collect user feedback data on pushed content. Real-time feedback data includes click-through rate, viewing time, completion rate, likes and dislikes. Analyze user feedback data, extract user behavior characteristics and preferences, and evaluate the effectiveness and quality of pushed content.

[0039] We dynamically adjust the content and teaching mode based on user feedback and learning progress.

[0040] The adjusted push content and teaching mode are fed back to the adaptive recommendation module to optimize personalized recommendations.

[0041] Another technical problem this invention aims to solve is to provide a method for online learning based on an adaptive engine, comprising the following steps:

[0042] Step 1: Record interaction data and store it in the database. The user data management unit manages users' personal information and learning behavior data, enabling data addition, deletion, modification, and query, and controlling data access permissions.

[0043] Step 2: Upload course videos, documents, and practice questions to the file storage service, create a resource index, quickly locate resources based on the resource index, distribute resources to users according to user requests, and manage user permissions.

[0044] Step 3: Monitor the user's learning progress in real time, including completed courses, exercises, and videos watched. Preprocess the learning progress data, analyze the user's learning situation on each knowledge point, and build a user learning model to extract learning features and preferences.

[0045] Step 4: Based on the user's learning model and current learning progress, identify weak areas in learning, obtain relevant resources from the learning resource management module, generate personalized learning recommendations, encapsulate the personalized learning recommendations into a message format, and push them to the user's device in real time via the push service;

[0046] Step 5: Track and collect user feedback data on the pushed content, analyze the user feedback data, evaluate the effectiveness and quality of the pushed content, dynamically adjust the pushed content and teaching mode based on user feedback and learning progress, and feed the adjustment results back to the adaptive recommendation module to optimize personalized recommendations.

[0047] Compared with the prior art, the present invention has the following beneficial effects:

[0048] 1. This invention, by monitoring users' learning progress and behavior in real time, can accurately identify users' learning needs and weaknesses, providing a basis for personalized recommendations. Based on the user's learning model and progress, it generates personalized learning paths for the user, improving the relevance and effectiveness of learning. By identifying learning content where users have short learning times and high error rates on practice questions, the system can push relevant resources in a targeted manner to help users quickly fill knowledge gaps and improve learning efficiency. Based on users' learning characteristics and preferences, the system can obtain the most relevant resources from the learning resource management module to achieve optimal allocation and utilization of learning resources.

[0049] 2. This invention can stimulate users' learning interest and increase their participation and satisfaction with learning content through personalized recommendations. The system can update the learning model in real time based on users' learning behavior and progress, and dynamically adjust the recommendation strategy to adapt to changes in users' learning. By specifically addressing learning weaknesses, the system can help users better master knowledge points, thereby improving learning outcomes. This also helps the system to continuously learn and improve, enhancing the accuracy and efficiency of the recommendation algorithm.

[0050] 3. This invention pushes personalized learning content and teaching modes to users in real time according to their learning needs, ensuring that users can obtain the learning resources they need in a timely manner, improving learning efficiency. By collecting and analyzing user feedback data on the pushed content, the system can dynamically adjust the pushed content and teaching modes to ensure that the pushed content matches the user's learning progress and interests. Personalized pushed content and teaching modes can enhance user learning participation and satisfaction, increase user dependence and loyalty to the online learning platform, and through continuous optimization of pushed content, the system can help users better master knowledge points, improve learning effects, and thus enhance users' sense of accomplishment and self-confidence in learning. Attached Figure Description

[0051] Figure 1 This is a schematic diagram of the modules of the online learning system based on an adaptive engine according to the present invention;

[0052] Figure 2 This is a schematic diagram of the online learning process of the adaptive engine of the present invention. DETAILED DESCRIPTION

[0053] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0054] To address the technical issues that existing online learning systems may struggle to accurately identify each user's learning needs and weaknesses, leading to uneven distribution of learning resources, poor learning outcomes, a lack of personalized learning paths and resource recommendations, and an inability to provide customized learning content based on individual user needs, as well as a lack of targeted learning resources, resulting in users spending excessive time on non-critical knowledge points, low learning efficiency, and an inability to adjust learning strategies in a timely manner, ultimately hindering effective knowledge acquisition and achieving minimal learning results, please refer to [link to relevant documentation]. Figure 1-2 The present invention provides the following technical solutions:

[0055] An online learning system based on an adaptive engine includes:

[0056] The user interaction management module is used for:

[0057] The system processes user interaction records, including login, course selection, and learning progress tracking. It also collects user feedback and learning behavior data, stores and manages user personal information and learning behavior data in a database, and provides data interfaces for other modules to access.

[0058] The learning resource management module is used for:

[0059] The system utilizes file storage services to store and manage learning resources, including course videos, micro-videos of knowledge points, images, documents, and exercises, and provides learning resource retrieval and distribution functions based on a resource indexing and distribution mechanism.

[0060] The adaptive recommendation module is used for:

[0061] Real-time monitoring of user learning progress; analysis of user learning status and preferences based on user learning in various knowledge points; identification of weak learning areas based on user learning progress; and generation of personalized learning recommendations and learning assistance suggestions.

[0062] The content push feedback module is used for:

[0063] Based on the output of the learning analytics and recommendation module, personalized learning content, suggestions, and teaching modes are pushed to users in real time using message queues and push services. User feedback and learning progress are tracked, and the pushed content is dynamically adjusted based on user feedback and learning progress.

[0064] In the above embodiments, through the adaptive recommendation module, the system generates personalized learning recommendations based on each user's learning progress, behavior, and preferences, thereby providing customized learning paths to meet the learning needs of different users. By monitoring users' learning progress and weaknesses in real time, the system can push relevant learning resources in a targeted manner to help users efficiently fill knowledge gaps and improve learning efficiency.

[0065] In the above embodiments, the learning resource management module ensures the rational use and rapid access of learning resources through an effective resource storage and distribution mechanism, reducing resource waste. The real-time feedback and interactive communication functions of the user interaction management module can enhance users' sense of participation and learning motivation, promoting continuous learning. The content push feedback module can dynamically adjust the pushed content according to user feedback and learning progress, ensuring the flexibility and adaptability of the learning strategy.

[0066] In the above embodiments, the entire system provides data-driven decision support for educators and administrators based on the collection and analysis of user data, which helps to optimize teaching methods and curriculum design. Through precise personalized recommendations and learning resource pushes, the system can help users master knowledge points more effectively, thereby improving learning outcomes. The user data management unit realizes access control and security management of user data, protecting users' personal information and privacy.

[0067] The user interaction management module includes:

[0068] User interaction recording unit, used for:

[0069] The system constructs a user interface, receives user interaction requests through a backend API interface, records user interaction data, collects user feedback and learning behavior data, and stores the user interaction data in a database. The user interaction data includes user ID, interaction type, and interaction time. A data interface is provided for other modules to access the user interaction data.

[0070] The user data management unit is used for:

[0071] It stores and manages users' personal information and learning behavior data through a database, and provides functions for adding, deleting, modifying, and querying user data.

[0072] In the above embodiments, the user interaction recording unit can improve the user's operational convenience and learning experience by constructing a user-friendly interactive interface, enabling users to interact with the system more easily and record user interaction data, including user ID, interaction type and interaction time. This helps the system analyze and understand user behavior patterns, thereby providing more accurate services. By collecting user feedback and learning behavior data, the system can better understand user needs and provide users with more personalized learning content and recommendations.

[0073] In the above embodiments, a data interface is provided for other modules to access user interaction data, ensuring efficient communication and data sharing between modules within the system. The user data management unit implements data access permission control, ensuring the security of user data, enhancing user trust in the system, and providing CRUD operations for user data, enabling system administrators to flexibly manage and maintain user information and respond promptly to changes in user needs. By storing user interaction data in the database, the system can manage and back up data more effectively, improving system stability and maintainability.

[0074] In the above embodiments, the detailed recording of user interaction data provides a rich data source for user behavior analysis, which helps the adaptive recommendation module to analyze user behavior and preferences more accurately. By collecting user feedback, the system can promptly identify problems and make adjustments, thereby improving user satisfaction and retention rate.

[0075] The learning resource management module includes:

[0076] Learning resource storage unit, used for:

[0077] The system utilizes file storage services to store and manage learning resources, establishes a resource index that includes the resource's name, type, description, associated course metadata, provides a resource retrieval interface, and allows for quick resource location based on the resource index.

[0078] The learning resource distribution unit is used for:

[0079] Based on a resource indexing and distribution mechanism, it provides learning resource retrieval and distribution functions. According to user requests and resource indexes, it distributes learning resources to users, establishes a user permission management mechanism, and provides a resource access interface. Users can obtain the learning resources they are authorized to through the resource access interface. Based on the user's role and permissions, it controls the user's access to learning resources.

[0080] In the above embodiments, the learning resource storage unit establishes a resource index, including the name, type, description, and associated course metadata of the resource, which can provide a fast and accurate resource retrieval function, enabling users to easily find the learning resources they need. The learning resource storage unit uses file storage services to store and manage learning resources, supports batch uploading and updating of resources, and facilitates the maintenance and management of resources.

[0081] In the above embodiments, the learning resource distribution unit, based on the resource index distribution mechanism, can distribute learning resources to users according to user requests and resource indexes, ensuring that users can access learning resources that match their roles and permissions. By establishing a user permission management mechanism, the learning resource distribution unit can control users' access permissions to learning resources, ensuring the reasonable use of learning resources and copyright protection. Through the resource index and distribution mechanism, the learning resource management module improves the stability and maintainability of the system, ensuring efficient management and access to learning resources. The system can dynamically adjust the storage and distribution strategies of learning resources according to users' learning behavior and feedback, thereby achieving optimized configuration of learning resources.

[0082] The adaptive recommendation module includes:

[0083] The learning behavior analysis unit is used for:

[0084] The system monitors users' learning progress in real time, including completed courses, exercises, and watched videos. It preprocesses the learning progress data and analyzes the user's learning status on various knowledge points based on the data, including answer accuracy, learning duration, time distribution, and number of repeated learning sessions. Based on the user's learning behavior, it establishes a user learning model and extracts the user's learning characteristics and preferences. The system updates the user's learning model in real time based on the user's learning characteristics and preferences.

[0085] Personalized recommendation generation unit, used for:

[0086] The learning behavior analysis unit obtains the user's learning model and current learning progress. Based on the user's learning model and current learning progress, it identifies learning content where the user has short learning time and high error rate on practice questions. This learning content is considered a weak point in the user's learning. Based on the user's weak points and preferences, it obtains relevant learning resources from the learning resource management module and generates personalized learning recommendations.

[0087] In the above embodiments, the learning behavior analysis unit can accurately identify users' learning needs and weaknesses by monitoring their learning progress and behavior in real time, providing a basis for personalized recommendations. The personalized recommendation generation unit generates personalized learning paths for users based on their learning models and progress, improving the relevance and effectiveness of learning. By identifying learning content where users have short learning times and high error rates on practice questions, the system can push relevant resources in a targeted manner to help users quickly fill knowledge gaps and improve learning efficiency. Based on users' learning characteristics and preferences, the system can obtain the most relevant resources from the learning resource management module to achieve optimal allocation and utilization of learning resources.

[0088] In the above embodiments, personalized recommendations can stimulate users' learning interest, increase users' participation and satisfaction with learning content, and the system can update the learning model in real time according to users' learning behavior and progress, dynamically adjust the recommendation strategy to adapt to changes in users' learning. By addressing learning weaknesses in a targeted manner, the system can help users better master knowledge points, thereby improving learning outcomes. The continuous operation and optimization of the adaptive recommendation module helps the system to continuously learn and improve, thereby improving the accuracy and efficiency of the recommendation algorithm.

[0089] The content push feedback module includes:

[0090] Content push unit, used for:

[0091] Based on the output of the adaptive recommendation module, personalized learning recommendations are obtained, including learning resources, suggestions, and teaching modes. The recommendations are encapsulated into a message format and pushed to the user's device in real time using a push service. The status of the push service is monitored, and push logs are recorded, including push time, push content, and user feedback information.

[0092] Feedback processing and adjustment unit, used for:

[0093] Track and collect user feedback data on pushed content. Real-time feedback data includes click-through rate, viewing time, completion rate, likes and dislikes. Analyze user feedback data, extract user behavior characteristics and preferences, and evaluate the effectiveness and quality of pushed content.

[0094] We dynamically adjust the content and teaching mode based on user feedback and learning progress.

[0095] The adjusted push content and teaching mode are fed back to the adaptive recommendation module to optimize personalized recommendations.

[0096] In the above embodiments, the content push unit can push personalized learning content and teaching modes in real time according to the user's learning needs, ensuring that the user can obtain the learning resources needed in a timely manner and improve learning efficiency. The feedback processing and adjustment unit can dynamically adjust the pushed content and teaching modes by collecting and analyzing user feedback data on the pushed content, ensuring that the pushed content matches the user's learning progress and interests. Personalized pushed content and teaching modes can improve the user's learning participation and satisfaction, and increase the user's dependence on and loyalty to the online learning platform.

[0097] In the above embodiments, by continuously optimizing the pushed content, the system can help users better grasp knowledge points, improve learning effectiveness, and thus enhance users' sense of accomplishment and self-confidence in learning. The continuous operation and optimization of the content push feedback module helps the system to continuously learn and improve, improve the accuracy and efficiency of the push algorithm, and the personalized push and dynamically adjusted learning strategies can enhance the overall learning experience of users and increase users' satisfaction with the online learning platform.

[0098] In the above embodiments, by recording push logs and monitoring the status of the push service, the system can ensure the security of the push process and the privacy protection of user data. By analyzing user feedback and learning progress, the system can provide data support for educators, helping them to better understand students' learning situations and optimize teaching plans.

[0099] This embodiment proposes an online learning method based on an adaptive engine, including the following steps:

[0100] Step 1: Record interaction data and store it in the database. The user data management unit manages users' personal information and learning behavior data, enabling data addition, deletion, modification, and query, and controlling data access permissions.

[0101] Step 2: Upload course videos, documents, and practice questions to the file storage service, create a resource index, quickly locate resources based on the resource index, distribute resources to users according to user requests, and manage user permissions.

[0102] Step 3: Monitor the user's learning progress in real time, including completed courses, exercises, and videos watched. Preprocess the learning progress data, analyze the user's learning situation on each knowledge point, and build a user learning model to extract learning features and preferences.

[0103] Step 4: Based on the user's learning model and current learning progress, identify weak areas in learning, obtain relevant resources from the learning resource management module, generate personalized learning recommendations, encapsulate the personalized learning recommendations into a message format, and push them to the user's device in real time via the push service;

[0104] Step 5: Track and collect user feedback data on the pushed content, analyze the user feedback data, evaluate the effectiveness and quality of the pushed content, dynamically adjust the pushed content and teaching mode based on user feedback and learning progress, and feed the adjustment results back to the adaptive recommendation module to optimize personalized recommendations.

[0105] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. An online learning system based on an adaptive engine, characterized in that: include: User interaction management module, used to: Process the interaction records between users and the learning system, including login, course selection, and learning progress tracking, while collecting user feedback and learning behavior data, storing and managing users' personal information and learning behavior data through a database, and providing a data interface for other modules to access; Learning resource management module for: Use file storage services to store and manage learning resources, including course videos, knowledge point micro videos, pictures, documents, exercises, and provide learning resource retrieval and distribution functions based on resource index distribution mechanism; Adaptive recommendation module for: Monitor the user's learning progress in real time, analyze the user's learning situation and preferences based on the user's learning situation at each knowledge point, identify the weak links in learning based on the user's learning progress, and generate personalized learning recommendations and learning help suggestions; Content push feedback module, used for: Based on the output of the learning analysis and recommendation module, the message queue and push service are used to push personalized learning content, suggestions and teaching modes to users in real time, and user feedback and learning progress are tracked, and the push content is dynamically adjusted according to user feedback and learning progress.

2. The online learning system based on the adaptive engine as claimed in claim 1, characterized in that: The user interaction management module comprises: User interaction recording unit, used to: Build a user interaction interface, receive user interaction requests through the back-end API interface, record user interaction data, collect user feedback and learning behavior data, store user interaction data in the database, the user interaction data includes user ID, interaction type, interaction time, and provide a data interface for other modules to access user interaction data.

3. The online learning system based on the adaptive engine as claimed in claim 2, characterized in that: The user interaction management module further includes: User data management unit, used for: The user's personal information and learning behavior data are stored and managed through the database, providing the functions of adding, deleting, modifying and querying user data.

4. The online learning system based on the adaptive engine as claimed in claim 1, characterized in that: The learning resource management module includes: Learning resource storage unit, used for: Use file storage services to store and manage learning resources, establish a resource index, which includes the resource name, type, description, and associated course metadata, provide a resource retrieval interface, and quickly locate resources based on the resource index.

5. The online learning system based on the adaptive engine as claimed in claim 4, characterized in that: The learning resource management module further includes: Learning resource distribution unit for: Based on the resource index distribution mechanism, it provides learning resource retrieval and distribution functions. It distributes learning resources to users according to user requests and resource indexes. It establishes a user authority management mechanism and provides a resource access interface. Users obtain learning resources to which they have authority through the resource access interface. According to the user's role and authority, it controls the user's access to learning resources.

6. The online learning system based on the adaptive engine as claimed in claim 1, characterized in that: The adaptive recommendation module comprises: Learning Behavior Analysis Unit for: Monitor the user's learning progress in real time, the learning progress includes the courses, exercises, and videos watched by the user, pre-process the user's learning progress data, and analyze the user's learning situation on each knowledge point based on the learning progress data, the learning situation includes the accuracy of answering questions, learning time, time distribution, and number of repeated learning times; establish a user learning model based on the user's learning behavior and extract the user's learning characteristics and preferences; and update the user's learning model in real time based on the user's learning characteristics and preferences.

7. The online learning system based on the adaptive engine as claimed in claim 6, characterized in that: The adaptive recommendation module further includes: Personalized recommendation generation unit, used to: The user's learning model and current learning progress are obtained from the learning behavior analysis unit. Based on the user's learning model and current learning progress, the learning content for which the user has a short learning time and a high error rate in exercises is determined. The learning content is regarded as a weak link in learning. According to the user's weak links in learning and preferences, relevant learning resources are obtained from the learning resource management module to generate personalized learning recommendations.

8. The online learning system based on the adaptive engine as claimed in claim 1, characterized in that: The content push feedback module includes: Content push unit, used for: According to the output of the adaptive recommendation module, personalized learning recommendation content is obtained, and the learning recommendation content includes learning resources, suggestions, and teaching modes. The recommendation content is encapsulated into a message format, and the message is pushed to the user device in real time using a push service. The status of the push service is monitored, and a push log is recorded. The push log includes the push time, push content, and user feedback information.

9. The online learning system based on the adaptive engine as claimed in claim 8, characterized in that: The content push feedback module also includes: Feedback processing adjustment unit, used to: Track and collect user feedback data on pushed content. Real-time feedback data includes click-through rate, viewing time, completion rate, likes and dislikes. Analyze user feedback data, extract user behavior characteristics and preferences, and evaluate the effect and quality of pushed content. Dynamically adjust push content and teaching mode based on user feedback and learning progress; Feedback the adjusted push content and teaching mode to the adaptive recommendation module to optimize personalized recommendations.

10. An online learning method based on an adaptive engine, implemented based on the online learning system based on an adaptive engine according to any one of claims 1 to 9, characterized in that: The steps include: Step 1: Record the interaction data and store it in the database. The user data management unit manages the user's personal information and learning behavior data, implements data addition, deletion, modification and query, and controls data access rights; Step 2: Upload course videos, documents, and exercises to the file storage service, create a resource index, quickly locate resources based on the resource index, distribute resources to users based on user requests, and manage user permissions; Step 3: Monitor the user's learning progress in real time, including completed courses, exercises, and videos watched. Pre-process the learning progress data, analyze the user's learning status at each knowledge point, and establish a user learning model to extract learning features and preferences. Step 4: Determine the weak links in learning based on the user's learning model and current learning progress, obtain relevant resources from the learning resource management module, generate personalized learning recommendations, encapsulate the personalized learning recommendations into a message format, and push them to the user's device in real time through the push service; Step 5: Track and collect user feedback data on pushed content, analyze user feedback data, evaluate the effectiveness and quality of pushed content, dynamically adjust pushed content and teaching mode based on user feedback and learning progress, and feed back the adjustment results to the adaptive recommendation module to optimize personalized recommendations.

Images