Intelligent design teaching resource recommendation system based on AI and knowledge graph

Abstract

The invention relates to the field of nonlinear multi-agent control, in particular to an intelligent design teaching resource recommendation system based on AI and a knowledge graph, which comprises a student data analysis module, a knowledge graph construction module, a resource recommendation module, an intelligent cooperation module, a teacher aid decision module and an AI recommendation algorithm. An overall data flow formed by the student data analysis module, the knowledge graph construction module, the resource recommendation module, the intelligent cooperation module, the teacher aid decision-making module and the AI recommendation algorithm is composed of an input layer, a processing layer and an output layer, and knowledge graphs of related majors are constructed according to the knowledge graph construction module; the student learning data is collected by the student data analysis module, the collected student data is transmitted to the knowledge graph construction module to form associated knowledge points, the associated knowledge points flow to the resource recommendation module to form a recommendation result, and then the intelligent cooperation module provides cooperation support by using the recommendation result. And the teacher auxiliary decision-making module provides teaching optimization by using the recommendation result.

Description

Technical Field

[0001] The present invention relates to the field of non - linear multi - agent control, specifically to an intelligent design teaching resource recommendation system based on AI and knowledge graph. Background Art

[0002] With the rapid development of artificial intelligence (AI) and knowledge graph technology, the field of educational technology has witnessed an unprecedented transformation. As a discipline highly dependent on resource integration and personalized guidance, design teaching has an especially obvious reliance on technology. Traditional design teaching resource recommendations mainly rely on manual screening by teachers or static course recommendations, suffering from problems such as fragmented resource acquisition and low matching degree, making it difficult to meet the personalized learning needs of students. Especially since the design discipline involves cross - disciplinary knowledge from multiple fields, the complexity of resource recommendation is further increased.

[0003] Due to its advantages in constructing complex association networks, knowledge graph technology can effectively sort out the knowledge points and their associated logics in the design discipline, providing a solid technical support for resource recommendation. At the same time, the deep learning algorithm of AI technology can analyze students' behavioral data and learning preferences to form personalized recommendation schemes. Therefore, constructing an intelligent design teaching resource recommendation system by combining AI and knowledge graph to provide accurate learning resources for students and optimize teachers' teaching efficiency is one of the core directions of educational technology innovation. It is necessary to propose an intelligent design teaching resource recommendation system based on AI and knowledge graph. Summary of the Invention

[0004] In view of the problems in the prior art, the present invention provides an intelligent design teaching resource recommendation system based on AI and knowledge graph.

[0005] The technical solution adopted by the present invention to solve its technical problems is: an intelligent design teaching resource recommendation system based on AI and knowledge graph, including a student data analysis module, a knowledge graph construction module, a resource recommendation module, an intelligent collaboration module, a teacher - assisted decision - making module, and an AI recommendation algorithm. The overall data flow formed by the student data analysis module, the knowledge graph construction module, the resource recommendation module, the intelligent collaboration module, the teacher - assisted decision - making module, and the AI recommendation algorithm consists of an input layer, a processing layer, and an output layer, constructing a complete data interaction logic.

[0006] The student data analysis module: responsible for collecting students' learning behavior data, including learning progress, resource usage frequency, and interest point analysis, providing data support for subsequent knowledge graph construction and resource recommendation.

[0007] The knowledge graph construction module: the core module of the system, constructing a knowledge network for the design discipline, dynamically associating discipline knowledge points with learning resources, and supporting cross - disciplinary knowledge integration and real - time update.

[0008] The resource recommendation module: Utilize the student data analysis results and the knowledge graph to provide personalized learning resource recommendations, covering various resource forms such as textbooks, case studies, design tools, etc.;

[0009] The intelligent collaboration module: According to the students' abilities and project requirements, intelligently allocate team tasks and provide collaboration suggestions to improve collaboration efficiency;

[0010] The teacher-assisted decision-making module: Provide a visual analysis report based on students' behavior data to help teachers adjust teaching strategies in real time;

[0011] The knowledge graph construction module includes data collection, knowledge point extraction, knowledge point association, and graph dynamic update mechanism. The data collection: Collect students' learning behavior data and subject knowledge base data, and extract the association information between learning resources and knowledge points; The knowledge point extraction: Identify the key knowledge points in the design discipline through text mining technology and classify them; The knowledge point association: Use machine learning algorithms to establish the association relationship between knowledge points to form a preliminary knowledge network; The graph dynamic update mechanism: Dynamically adjust the knowledge point content and association relationship according to the real-time input data to ensure the accuracy and integrity of the knowledge graph;

[0012] The resource recommendation module includes student data collection, behavior analysis and interest modeling, recommendation algorithm execution, dynamic adjustment, and result output. The student data collection: Collect students' learning behavior data, including course access records, learning feedback, and learning goals, etc.; The behavior analysis and interest modeling: Use deep learning algorithms to analyze students' learning behavior and generate a personalized learning interest model; The recommendation algorithm execution: Based on the student interest model and the knowledge graph, execute the recommendation algorithm to match the most suitable learning resources for the students' current needs; The dynamic adjustment and result output: Dynamically adjust the recommendation strategy according to students' learning feedback, optimize the recommendation results, and output a customized resource list;

[0013] The intelligent collaboration module includes task requirement analysis, member ability matching, collaboration completion, and feedback. The task requirement analysis: The system analyzes the team task requirements and generates a resource requirement list; The member ability matching: According to the skills and abilities of team members, allocate tasks to the best-matched members; The collaboration completion and feedback: Track the task progress and completion status, and adjust the task allocation according to the actual performance of team members;

[0014] The AI recommendation algorithm: Use the collaborative filtering algorithm to analyze the similarity between students and recommend highly relevant resources.

[0015] Specifically, the input layer includes students' behavior data: including learning progress, interest points, etc., as the basic data for the personalized learning portrait;

[0016] Knowledge resource data: covering diverse teaching resources such as textbooks and cases, supporting the construction of the knowledge graph;

[0017] Teacher feedback data: recording teachers' evaluations of resource recommendations and suggestions for curriculum optimization, assisting in algorithm optimization.

[0018] Specifically, the processing layer includes a student data analysis module: collecting and analyzing student behavior data to generate a learning interest model;

[0019] Knowledge graph construction module: dynamically updating the knowledge point network to achieve interdisciplinary knowledge point integration;

[0020] Resource recommendation module: providing personalized recommendations for users based on the knowledge graph and student portraits.

[0021] Specifically, the output layer includes recommended results: generating a list of learning resources (such as cases, tutorials);

[0022] Learning optimization suggestions: providing solutions for adjusting learning paths and supplementing knowledge points;

[0023] Team task allocation: generating a task allocation plan to improve team collaboration efficiency.

[0024] Specifically, the AI recommendation algorithm matches the student interest model with resource characteristics based on the content-based recommendation algorithm, and the deep learning model optimizes the recommended results to generate high-precision learning resources.

[0025] Specifically, the knowledge graph construction mechanism includes dynamic update: adjusting the content and association relationships of the knowledge graph according to real-time input data;

[0026] Interdisciplinary integration: associating the design discipline with other disciplines (such as architecture, materials) to form a multi-dimensional knowledge network;

[0027] Intelligent collaboration optimization algorithm;

[0028] Task allocation model: generating an optimal task allocation plan according to the capabilities of team members and task requirements;

[0029] Collaboration monitoring and feedback: real-time tracking of task progress and dynamic adjustment of allocation strategies.

[0030] The beneficial effects of the present invention: The intelligent design teaching resource recommendation system based on AI and knowledge graph according to the present invention first constructs a knowledge graph of relevant majors by the knowledge graph construction module, and the data of students' learning is collected by the student data analysis module, and then the collected student data is transmitted to the knowledge graph construction module, forms associated knowledge points and flows to the resource recommendation module to form recommended results, and then the intelligent collaboration module uses the recommended results to provide collaboration support, while the teacher auxiliary decision-making module uses the recommended results to provide teaching optimization. Brief Description of the Drawings

[0031] The present invention will be further described below in conjunction with the drawings and embodiments.

[0032] Figure 1 It is a system architecture diagram of the intelligent design teaching resource recommendation system based on AI and knowledge graph provided by the present invention;

[0033] Figure 2 It is a knowledge graph construction flowchart of the intelligent design teaching resource recommendation system based on AI and knowledge graph provided by the present invention;

[0034] Figure 3 It is a resource recommendation flowchart of the intelligent design teaching resource recommendation system based on AI and knowledge graph provided by the present invention;

[0035] Figure 4 It is a schematic diagram of optimizing the student learning path of the intelligent design teaching resource recommendation system based on AI and knowledge graph provided by the present invention;

[0036] Figure 5 It is a team collaboration support flowchart of the intelligent design teaching resource recommendation system based on AI and knowledge graph provided by the present invention;

[0037] Figure 6 It is an algorithm flowchart of the intelligent design teaching resource recommendation system based on AI and knowledge graph provided by the present invention. Detailed Embodiments

[0038] In order to make the technical means, creative features, achieved purposes and effects of the present invention easy to understand, the present invention will be further described below in conjunction with specific embodiments.

[0039] As Figures 1-6 shown, the intelligent design teaching resource recommendation system based on AI and knowledge graph described in the present invention includes a student data analysis module, a knowledge graph construction module, a resource recommendation module, an intelligent collaboration module, a teacher auxiliary decision-making module, and an AI recommendation algorithm. The overall data flow formed by the student data analysis module, the knowledge graph construction module, the resource recommendation module, the intelligent collaboration module, the teacher auxiliary decision-making module, and the AI recommendation algorithm is composed of an input layer, a processing layer, and an output layer, constructing a complete data interaction logic.

[0040] Student data analysis module: responsible for collecting student learning behavior data, including learning progress, resource usage frequency, and interest point analysis, providing data support for subsequent knowledge graph construction and resource recommendation;

[0041] Knowledge Graph Construction Module: The core module of the system, which constructs a knowledge network for the design discipline, dynamically associates discipline knowledge points with learning resources, and supports interdisciplinary knowledge integration and real-time updates;

[0042] Resource Recommendation Module: Utilizes the analysis results of student data and the knowledge graph to provide personalized learning resource recommendations, covering various resource forms such as textbooks, case studies, and design tools;

[0043] Intelligent Collaboration Module: According to students' abilities and project requirements, intelligently assigns team tasks and provides collaboration suggestions to improve collaboration efficiency;

[0044] Teacher Assistant Decision-making Module: Provides a visual analysis report based on students' behavioral data to help teachers adjust teaching strategies in real time;

[0045] The Knowledge Graph Construction Module includes data collection, knowledge point extraction, knowledge point association, and the mechanism for dynamic update of the graph. Data collection: Collects students' learning behavior data and data from the subject knowledge base, and extracts the association information between learning resources and knowledge points; Knowledge point extraction: Identifies key knowledge points in the design discipline through text mining techniques and classifies them; Knowledge point association: Uses machine learning algorithms to establish the association relationships between knowledge points to form a preliminary knowledge network; The mechanism for dynamic update of the graph: Dynamically adjusts the content and association relationships of knowledge points according to the real-time input data to ensure the accuracy and integrity of the knowledge graph;

[0046] The Resource Recommendation Module includes student data collection, behavior analysis and interest modeling, execution and dynamic adjustment of the recommendation algorithm, and result output. Student data collection: Collects students' learning behavior data, including course access records, learning feedback, and learning goals, etc.; Behavior analysis and interest modeling: Uses deep learning algorithms to analyze students' learning behaviors and generate personalized learning interest models; Execution of the recommendation algorithm: Based on the students' interest models and the knowledge graph, executes the recommendation algorithm to match the learning resources most suitable for the students' current needs; Dynamic adjustment and result output: Dynamically adjusts the recommendation strategy according to students' learning feedback, optimizes the recommendation results, and outputs a customized resource list;

[0047] The Intelligent Collaboration Module includes task requirement analysis, member ability matching, collaboration completion and feedback. Task requirement analysis: The system analyzes the task requirements of the team and generates a list of resource requirements; Member ability matching: Assigns tasks to the best-matched members according to the skills and abilities of team members; Collaboration completion and feedback: Tracks the progress and completion of tasks and adjusts task assignments according to the actual performance of team members;

[0048] AI Recommendation Algorithm: Utilizes collaborative filtering algorithms to analyze the similarities among students and recommends highly relevant resources.

[0049] Among them, the input layer includes student behavior data, including learning progress, interests, etc., which serve as the basic data for the personalized learning profile;

[0050] Knowledge resource data, covering diverse teaching resources such as textbooks and cases, to support the construction of the knowledge graph;

[0051] Teacher feedback data, recording teachers' evaluations of resource recommendations and suggestions for curriculum optimization to assist in algorithm optimization.

[0052] Among them, the processing layer includes a student data analysis module, which collects and analyzes student behavior data to generate a learning interest model;

[0053] A knowledge graph construction module, which dynamically updates the knowledge point network to achieve interdisciplinary knowledge point integration;

[0054] A resource recommendation module, which provides personalized recommendations for users based on the knowledge graph and the student profile.

[0055] Among them, the output layer includes recommended results, generating a list of learning resources (such as cases, tutorials);

[0056] Learning optimization suggestions, providing learning path adjustment and knowledge point supplementation plans;

[0057] Team task allocation, generating a task allocation plan to improve team collaboration efficiency.

[0058] Among them, the AI recommendation algorithm matches the student interest model with resource characteristics based on the content-based recommendation algorithm, and the deep learning model optimizes the recommended results to generate high-precision learning resources.

[0059] Among them, the knowledge graph construction mechanism includes dynamic updates, adjusting the content and association relationships of the knowledge graph according to real-time input data;

[0060] Interdisciplinary integration, associating the design discipline with other disciplines (such as architecture, materials) to form a multi-dimensional knowledge network;

[0061] An intelligent collaboration optimization algorithm;

[0062] A task allocation model, generating an optimal task allocation plan according to the capabilities of team members and task requirements;

[0063] Collaboration monitoring and feedback, real-time tracking of task progress and dynamically adjusting the allocation strategy.

[0064] The basic principles, main features and advantages of the present invention have been shown and described above. Those skilled in the art should understand that the present invention is not limited by the above embodiments, and the above embodiments and the descriptions in the specification only illustrate the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of protection required by the present invention. The scope of protection required by the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent design teaching resource recommendation system based on AI and knowledge graph, including a student data analysis module, a knowledge graph construction module, a resource recommendation module, an intelligent collaboration module, a teacher decision-making assistance module and an AI recommendation algorithm, characterized in that: The overall data flow formed by the student data analysis module, knowledge graph construction module, resource recommendation module, intelligent collaboration module, teacher decision-making assistance module and AI recommendation algorithm consists of an input layer, a processing layer and an output layer, building a complete data interaction logic. The student data analysis module is responsible for collecting student learning behavior data, including learning progress, resource usage frequency, and interest point analysis, providing data support for subsequent knowledge graph construction and resource recommendation; The knowledge graph construction module is the core module of the system, which constructs a design discipline knowledge network, dynamically associates discipline knowledge points with learning resources, and supports cross-disciplinary knowledge integration and real-time updating; The resource recommendation module: uses the student data analysis results and knowledge graph to provide personalized learning resource recommendations, covering a variety of resource forms such as textbooks, case analysis, and design tools; The intelligent collaboration module: intelligently allocates team tasks and provides collaboration suggestions based on student capabilities and project requirements to improve collaboration efficiency; The teacher decision-making assistance module provides a visual analysis report based on student behavior data to help teachers adjust teaching strategies in real time. The knowledge graph construction module includes data collection, knowledge point extraction, knowledge point association and graph dynamic update mechanism. The data collection: collects students' learning behavior data and subject knowledge base data, extracts the association information between learning resources and knowledge points; the knowledge point extraction: identifies key knowledge points in the design subject through text mining technology and classifies them; the knowledge point association: uses machine learning algorithms to establish the association relationship between knowledge points to form a preliminary knowledge network; the graph dynamic update mechanism: dynamically adjusts the knowledge point content and association relationship according to the real-time input data to ensure the accuracy and completeness of the knowledge graph; The resource recommendation module includes student data collection, behavior analysis and interest modeling, recommendation algorithm execution and dynamic adjustment and result output. The student data collection: collect students' learning behavior data, including course access records, learning feedback and learning goals; the behavior analysis and interest modeling: use deep learning algorithms to analyze students' learning behaviors and generate personalized learning interest models; the recommendation algorithm execution: based on the student interest model and knowledge graph, execute the recommendation algorithm to match the learning resources that best suit the students' current needs; the dynamic adjustment and result output: according to students' learning feedback, dynamically adjust the recommendation strategy, optimize the recommendation results, and output a customized resource list; The intelligent collaboration module includes task requirement analysis, member capability matching, and collaboration completion and feedback. The task requirement analysis: the system analyzes the team's task requirements and generates a resource requirement list; the member capability matching: assigns tasks to the best matching members based on the skills and capabilities of team members; the collaboration completion and feedback: tracks task progress and completion, and adjusts task assignments based on the actual performance of team members; The AI ​​recommendation algorithm uses a collaborative filtering algorithm to analyze similarities between students and recommend highly relevant resources.

2. The intelligent design teaching resource recommendation system based on AI and knowledge graph according to claim 1 is characterized by: The input layer includes student behavior data: including learning progress, points of interest, etc., as basic data for personalized learning portraits; Knowledge resource data: covers a variety of teaching resources such as textbooks and cases, supporting the construction of knowledge graphs; Teacher feedback data: records teachers’ evaluation of resource recommendations and course optimization suggestions to assist algorithm optimization.

3. The intelligent design teaching resource recommendation system based on AI and knowledge graph according to claim 1 is characterized by: The processing layer includes a student data analysis module: collecting and analyzing student behavior data to generate a learning interest model; Knowledge graph construction module: dynamically update the knowledge point network to achieve cross-disciplinary knowledge point integration; Resource recommendation module: Provides personalized recommendations to users based on knowledge graph and student portraits.

4. The intelligent design teaching resource recommendation system based on AI and knowledge graph according to claim 1 is characterized by: The output layer includes recommendation results: generating a list of learning resources (such as cases and tutorials); Learning optimization suggestions: provide learning path adjustment and knowledge point supplementation solutions; Team task allocation: Generate task allocation plans to improve team collaboration efficiency.

5. The intelligent design teaching resource recommendation system based on AI and knowledge graph according to claim 1 is characterized by: The AI ​​recommendation algorithm matches student interest models with resource features based on the content recommendation algorithm, and the deep learning model optimizes the recommendation results to generate high-precision learning resources.

6. The intelligent design teaching resource recommendation system based on AI and knowledge graph according to claim 1 is characterized by: The knowledge graph construction mechanism includes dynamic updating: adjusting the knowledge graph content and association relationships according to real-time input data; Interdisciplinary integration: linking design disciplines with other disciplines (such as architecture and materials) to form a multi-dimensional knowledge network; Intelligent collaborative optimization algorithm; Task allocation model: Generate the optimal task allocation plan based on team member capabilities and task requirements; Collaborative monitoring and feedback: Track task progress in real time and dynamically adjust allocation strategies.

Images