Knowledge graph-based learning path design system

Abstract

The invention discloses a knowledge graph-based learning path design system, and belongs to the technical field of learning path design, and the knowledge graph-based learning path design system comprises a knowledge graph construction module which is used for collecting, sorting and representing knowledge in different fields from various sources, and constructing a knowledge graph model; the system comprises a learning module which is used for integrating knowledge levels, interests, preferences and learning style information of users into a coherent knowledge system, a user modeling module which is used for understanding and representing the knowledge levels, interests, preferences and learning style information of the users, and a learning path planning module which is used for generating personalized learning paths according to the information provided by the user modeling module. According to the method, multiple aspects of knowledge graph construction, user modeling, learning path planning, learning resource management, learning monitoring and the like are covered, and through cooperative work of the modules, the system can provide efficient, personalized and comprehensive learning path design, so that the experience and learning effect of learners are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of learning path design, and more specifically, to a learning path design system based on knowledge graph. Background Art

[0002] Knowledge graph is a structured data representation method that organizes information through nodes (entities) and edges (relationships). In the field of education, knowledge graph can be used to represent the knowledge system of a subject, including the relationship between different knowledge points, such as prerequisites, dependencies, etc. This structured method not only helps to understand and manage a huge knowledge system, but also supports intelligent teaching resource recommendations and the design of personalized learning paths.

[0003] A learning path is a sequence of learning activities or courses planned to achieve a specific learning goal. A good learning path should be able to take into account the learner's starting point, interests, abilities, and goals, and recommend the most appropriate next step of learning content. Traditional learning paths are often fixed, but with the development of technology, especially the application of artificial intelligence technology, it is possible to dynamically generate personalized learning paths.

[0004] The core idea of ​​applying knowledge graphs to learning path design is to use the rich semantic information and structured characteristics in the knowledge graph to automatically analyze the learner's current status (knowledge points, skill levels, etc.), and dynamically generate the most suitable next learning suggestions for the learner on this basis. This can not only improve learning efficiency, but also enhance learners' participation and satisfaction.

[0005] Since the knowledge systems in different fields of knowledge graphs vary greatly, and the existing design systems are not convenient for effectively integrating knowledge points in multiple fields, the practicality of the design systems is reduced. Summary of the invention

[0006] 1. Technical problems to be solved

[0007] In view of the problems existing in the prior art, the purpose of the present invention is to provide a learning path design system based on knowledge graph. The present invention covers multiple aspects such as knowledge graph construction, user modeling, learning path planning, learning resource management and learning monitoring. Through the collaborative work of these modules, the system can provide efficient, personalized and comprehensive learning path design, thereby significantly improving learners' experience and learning effects.

[0008] 2. Technical solution

[0009] To solve the above problems, the present invention adopts the following technical solutions:

[0010] A learning path design system based on a knowledge graph includes: a knowledge graph construction module, wherein the knowledge graph construction module is used to collect, organize and represent knowledge in different fields from multiple sources and integrate the knowledge into a coherent knowledge system;

[0011] A user modeling module, the user modeling module is used to understand and characterize the user's knowledge level, interest preference and learning style information;

[0012] A learning path planning module, wherein the learning path planning module is used to generate a personalized learning path according to the information provided by the user modeling module;

[0013] A learning resource management module, which is used to manage and organize various learning resources;

[0014] A learning monitoring and feedback module, which is used to monitor the progress of learners and evaluate learning effects in real time;

[0015] The cross-domain knowledge integration module is used to integrate knowledge from different fields and build a comprehensive and systematic knowledge system.

[0016] As a preferred solution of the present invention, the knowledge graph construction module includes:

[0017] A data collection unit, wherein the data collection unit is used for a web crawler to obtain raw data from databases, documents and online resources;

[0018] A data preprocessing unit, the data preprocessing unit is used to remove noise, duplicates and irrelevant data from the data, and then convert the data in different formats into a unified format;

[0019] An entity recognition linking unit, which is used to automatically recognize entities in the text and match and link the recognized entities with entities in a known knowledge base;

[0020] A relationship extraction unit, which is used to analyze semantic relationships in text using natural language processing technology to extract relationships between entities from the text, and to supplement missing relationship information through logical reasoning;

[0021] A knowledge graph construction unit, which is used to define a domain ontology and construct the processed entities and relationships into a knowledge graph;

[0022] A graph optimization verification unit, which is used to verify the consistency and integrity of the data in the knowledge graph, remove duplicate and redundant information, and further enrich the content of the knowledge graph by linking to an external knowledge base;

[0023] The knowledge updating and maintenance unit is used to update the knowledge graph in real time to maintain its timeliness.

[0024] As a preferred solution of the present invention, the user modeling module includes:

[0025] A user information collection unit, which is used to collect the user's personal information, record the user's learning activities in the system, and infer the user's learning habits and preferences through the user's behavior on the platform;

[0026] An interest preference identification unit, which is used to analyze the user's interest in different topics or types of content through a machine learning algorithm, and recommend learning resources with complex interests and preferences to the user;

[0027] The dynamic model updating unit is used to continuously monitor the user's learning progress and change trends, and update the model information in a timely manner.

[0028] As a preferred solution of the present invention, the learning path planning module includes:

[0029] A learning needs analysis unit, which is used to communicate with users to clarify their learning goals and expected outcomes;

[0030] A path generation optimization unit, wherein the path generation optimization unit is used to generate a preliminary learning path according to the user's needs and the structure in the knowledge graph, and optimize the learning path using a heuristic algorithm;

[0031] A learning resource matching unit, which is used to build and maintain a rich learning resource library and recommend corresponding learning resources according to the knowledge points in the learning path;

[0032] The adaptive adjustment unit is used to utilize machine learning and artificial intelligence technologies to dynamically adjust the learning path according to the user's learning behavior and feedback to achieve personalized adaptive learning.

[0033] As a preferred solution of the present invention, the learning resource management module includes:

[0034] The resource description and annotation unit is used to generate detailed metadata and tags for each resource, and map the resources with relevant concepts and knowledge points in the knowledge graph to establish a connection between the resources and the knowledge points.

[0035] A resource organization index unit, which is used to build a clear resource directory structure and support multi-dimensional rapid retrieval and positioning;

[0036] A resource evaluation and feedback unit, which collects user feedback on the use of learning resources and regularly updates and optimizes the resource library based on user feedback and evaluation results;

[0037] The permission management unit is used to set different access rights for different roles, protect the security of sensitive resources, and perform version control on resources.

[0038] As a preferred solution of the present invention, the learning monitoring feedback module:

[0039] A progress tracking and feedback unit, which is used to track the user's learning progress in real time, record their performance during the learning process, collect the user's learning feedback, and adjust the learning path in time according to the user's feedback to optimize the learning experience;

[0040] A knowledge status evaluation unit, which is used to regularly evaluate the user's mastery of specific knowledge points using tests and questionnaires, and dynamically adjust the difficulty of test questions according to the user's current knowledge level, more accurately locate the user's ability boundary, provide instant feedback based on the user's learning performance, help the user clarify the direction of improvement, and give the learner a learning effect score;

[0041] A learning behavior analysis unit, which uses data analysis technology to identify learners' behavior patterns, analyze individual differences of learners, identify their learning styles, and monitor whether learners have abnormal behaviors;

[0042] A real-time feedback prompt unit, which is used to provide instant feedback during the learning process to help learners correct mistakes or strengthen their understanding;

[0043] A learning community interaction unit, which is used to provide a discussion area among learners, encourage interactive communication, solve difficult problems, and invite experts in the field to participate in answering questions;

[0044] A data analysis and reporting unit is used to visualize the learning data of learners.

[0045] As a preferred solution of the present invention, the cross-domain knowledge integration module includes:

[0046] A knowledge mapping unit, which is used to identify and establish connections or mapping relationships between knowledge concepts in different fields, and automatically discover the correlation between different knowledge fields through semantic analysis and machine learning technology;

[0047] The knowledge fusion unit is used to integrate relevant knowledge in multiple fields to form a unified whole, so that users can more easily understand the connection between various parts.

[0048] As a preferred solution of the present invention, the knowledge fusion unit includes:

[0049] A semantic matching subunit, which is used to identify synonyms and abbreviations in different fields through natural language processing technology and unify them into a standard terminology system;

[0050] A content integration subunit, which is used to merge the extracted knowledge fragments into a more complete knowledge unit;

[0051] A context-aware subunit, which is used to adjust the knowledge expression form according to the specific needs of different application scenarios;

[0052] A knowledge organization subunit, wherein the knowledge organization subunit is used to construct a hierarchical knowledge structure according to a subject or subject area, and to establish connections between different knowledge nodes through hyperlinks;

[0053] The quality assessment subunit is used to regularly check whether the knowledge graph covers all knowledge points using expert review.

[0054] 3. Beneficial effects

[0055] Compared with the prior art, the advantages of the present invention are:

[0056] (1) The present invention comprehensively improves learning efficiency: by scientifically and rationally organizing learning paths, it helps learners to efficiently master knowledge points, reduce ineffective repetitive learning, and improve the pertinence and effectiveness of learning.

[0057] (2) The present invention provides personalized learning experience: It provides customized learning paths based on the specific needs and abilities of each learner, and dynamically adjusts the learning paths to better suit the learner's progress speed and style.

[0058] (3) The present invention integrates cross-domain knowledge: The system can integrate knowledge from multiple fields to form a more comprehensive learning path, helping learners establish cross-disciplinary knowledge connections and promoting the improvement of their comprehensive quality.

[0059] (4) The present invention enhances learning motivation: it provides interesting and challenging learning tasks, stimulates learners' enthusiasm, provides timely feedback on learning outcomes, and increases the sense of achievement in learning.

[0060] (5) The present invention is continuously optimized and improved: user feedback and learning data are collected, system algorithms and recommendation strategies are continuously optimized, system self-iteration and upgrade are realized, and user experience and service quality are continuously improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 This is a module diagram of the learning path design system based on the knowledge graph of the present invention. DETAILED DESCRIPTION

[0062] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. 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.

[0063] Example:

[0064] See also Figure 1 , a learning path design system based on knowledge graph, including:

[0065] Knowledge graph building module, which is used to collect, organize and represent knowledge in different fields from multiple sources and integrate them into a coherent knowledge system;

[0066] User modeling module, which is used to understand and characterize the user's knowledge level, interest preferences and learning style information;

[0067] A learning path planning module, which is used to generate a personalized learning path based on the information provided by the user modeling module;

[0068] Learning resource management module: The learning resource management module is used to manage and organize various learning resources to support the design and implementation of personalized learning paths;

[0069] Learning monitoring and feedback module: The learning monitoring and feedback module is used to monitor learners' progress in real time, evaluate learning effects, and provide timely feedback and support;

[0070] The cross-domain knowledge integration module is used to integrate knowledge from different fields and build a comprehensive and systematic knowledge system, so as to achieve more efficient and targeted learning.

[0071] In a specific embodiment of the present invention, learning efficiency is comprehensively improved: by scientifically and rationally organizing learning paths, learners are helped to master knowledge points efficiently, ineffective repetitive learning is reduced, and the pertinence and effectiveness of learning are improved; customized learning paths are provided according to the specific needs and abilities of each learner; learning paths are dynamically adjusted to better adapt to the learner's progress speed and style; the system can integrate knowledge from multiple fields to form a more comprehensive learning path, help learners establish interdisciplinary knowledge connections, promote the improvement of comprehensive quality, provide interesting and challenging learning tasks, stimulate learners' enthusiasm, provide timely feedback on learning outcomes, increase the sense of achievement in learning, collect user feedback and learning data, continuously optimize system algorithms and recommendation strategies, realize system self-iteration and upgrade, and continuously improve user experience and service quality.

[0072] Specifically, the knowledge graph construction modules include:

[0073] Data collection unit, the data collection unit is used by web crawlers to obtain raw data from databases, literature and online resources;

[0074] A data preprocessing unit is used to remove noise, duplicates and irrelevant data from the data, and then convert the data in different formats into a unified format for subsequent processing;

[0075] Entity recognition linking unit, which is used to automatically identify entities in text and match and link the identified entities with entities in the known knowledge base;

[0076] Relation extraction unit: The relation extraction unit is used to analyze the semantic relationship in the text using natural language processing technology to extract the relationship between entities from the text, and supplement the missing relationship information through logical reasoning;

[0077] The knowledge graph construction unit is used to define the domain ontology and construct the processed entities and relationships into a knowledge graph to ensure the structuring and standardization of the knowledge graph;

[0078] Graph optimization verification unit: The graph optimization verification unit is used to verify the consistency and integrity of the data in the knowledge graph, remove duplicate and redundant information, and further enrich the content of the knowledge graph by linking to external knowledge bases;

[0079] Knowledge updating and maintenance unit,The knowledge updating and maintenance unit is used to update the knowledge graph in real time to maintain its timeliness.

[0080] Specifically, the user modeling module includes:

[0081] User information collection unit, which is used to collect users' personal information, record users' learning activities in the system, and infer their learning habits and preferences through their behaviors on the platform;

[0082] An interest preference identification unit is used to analyze the user's interest in different topics or types of content through a machine learning algorithm, and recommend learning resources with compound interests and preferences to the user;

[0083] Dynamic model updating unit,The dynamic updating and maintenance unit is used to continuously monitor the user's learning progress and changing trends, and update its model information in a timely manner.

[0084] Specifically, the learning path planning module includes:

[0085] Learning Needs Analysis Unit: The learning needs analysis unit is used to communicate with users to clarify their learning goals and expected outcomes;

[0086] Path generation optimization unit: The path generation optimization unit is used to generate a preliminary learning path according to the user's needs and the structure in the knowledge graph, and optimize the learning path using a heuristic algorithm to ensure its efficiency and rationality;

[0087] Learning resource matching unit, which is used to build and maintain a rich learning resource library and recommend corresponding learning resources based on the knowledge points in the learning path;

[0088] The adaptive adjustment unit is used to utilize machine learning and artificial intelligence technologies to dynamically adjust the learning path according to the user's learning behavior and feedback to achieve personalized adaptive learning.

[0089] Specifically, the learning resource management module includes:

[0090] Resource description and annotation unit,The resource description and annotation unit is used to generate detailed metadata and tags for each resource, which facilitates quick retrieval and association, and maps the resources with relevant concepts and knowledge points in the knowledge graph to establish the connection between resources and knowledge points.

[0091] Resource organization index unit: The resource organization index unit is used to build a clear resource directory structure, which is convenient for users to browse and find, and supports multi-dimensional rapid retrieval and positioning, thereby improving the response speed of the system;

[0092] Resource evaluation and feedback unit: The resource evaluation and feedback unit collects user feedback on the use of learning resources, and regularly updates and optimizes the resource library based on user feedback and evaluation results, while removing low-quality resources and adding high-quality resources;

[0093] The permission management unit is used to set different access rights for different roles to protect the security of sensitive resources. At the same time, it performs version control on resources to ensure that users can access the latest resource versions.

[0094] Specifically, learn the monitoring feedback module:

[0095] Progress tracking and feedback unit: The progress tracking and feedback unit is used to track the user's learning progress in real time, record their performance during the learning process, collect the user's learning feedback, and adjust the learning path in time according to the user's feedback to optimize the learning experience;

[0096] The knowledge status assessment unit is used to regularly assess the user's mastery of specific knowledge points using tests and questionnaires, and dynamically adjust the difficulty of test questions based on the user's current knowledge level to more accurately locate their ability boundaries. It also provides instant feedback based on the user's learning performance, helps the user identify the direction of improvement, and gives the learner a learning effect score;

[0097] Learning behavior analysis unit: The learning behavior analysis unit uses data analysis technology to identify learners' behavior patterns, analyze individual differences of learners, identify their learning styles, and monitor whether learners have abnormal behaviors;

[0098] Real-time feedback prompt unit, which is used to provide instant feedback during the learning process to help learners correct mistakes or strengthen their understanding;

[0099] The learning community interactive unit is used to provide a discussion area among learners, encourage interactive communication, solve difficult problems, and invite experts in the field to participate in answering questions and provide professional guidance. Through the peer evaluation mechanism, it promotes mutual learning and support among learners;

[0100] Data Analysis Report Unit,The data analysis report unit is used to visualize learners’ learning data for easy understanding and analysis.

[0101] Specifically, the cross-domain knowledge integration module includes:

[0102] Knowledge mapping unit: The knowledge mapping unit is used to identify and establish the connection or mapping relationship between knowledge concepts in different fields, and automatically discover the correlation between different knowledge fields through semantic analysis and machine learning technology, laying the foundation for subsequent knowledge integration;

[0103] Knowledge fusion unit,The knowledge fusion unit is used to integrate relevant knowledge from multiple fields to form a unified whole, so that users can more easily understand the connection between the various parts.

[0104] Specifically, the knowledge fusion unit includes:

[0105] Semantic matching subunit: The semantic matching subunit is used to identify synonyms and abbreviations in different fields through natural language processing technology, and unify them into a standard terminology system to ensure that they have consistent representation in the knowledge graph;

[0106] Content integration subunit, which is used to merge the extracted knowledge fragments into a more complete knowledge unit to avoid duplication and omission;

[0107] Context-aware subunit: The context-aware subunit is used to adjust the knowledge expression form according to the specific needs of different application scenarios, so that the knowledge is closer to the actual usage scenario;

[0108] Knowledge organization subunits are used to build hierarchical knowledge structures according to themes or subject areas, so that users can access knowledge in specific areas on demand, and establish connections between different knowledge nodes through hyperlinks to enhance the relevance and navigability of knowledge.

[0109] Quality assessment subunit,The quality assessment subunit is used to regularly check whether the knowledge graph covers all knowledge points using expert reviews.

[0110] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and improved concepts of the present invention within the technical scope disclosed by the present invention, and they should be covered by the protection scope of the present invention.

Claims

1. The learning path design system based on knowledge graph is characterized by: include: A knowledge graph building module, which is used to collect, organize and represent knowledge in different fields from multiple sources and integrate them into a coherent knowledge system; A user modeling module, the user modeling module is used to understand and characterize the user's knowledge level, interest preference and learning style information; A learning path planning module, wherein the learning path planning module is used to generate a personalized learning path according to the information provided by the user modeling module; A learning resource management module, which is used to manage and organize various learning resources; A learning monitoring and feedback module, which is used to monitor the progress of learners and evaluate learning effects in real time; The cross-domain knowledge integration module is used to integrate knowledge from different fields and build a comprehensive and systematic knowledge system.

2. The learning path design system based on knowledge graph according to claim 1 is characterized in that: The knowledge graph construction module includes: A data collection unit, wherein the data collection unit is used for a web crawler to obtain raw data from databases, documents and online resources; A data preprocessing unit, the data preprocessing unit is used to remove noise, duplicates and irrelevant data from the data, and then convert the data in different formats into a unified format; An entity recognition linking unit, which is used to automatically recognize entities in the text and match and link the recognized entities with entities in a known knowledge base; A relationship extraction unit, which is used to analyze semantic relationships in text using natural language processing technology to extract relationships between entities from the text, and to supplement missing relationship information through logical reasoning; A knowledge graph construction unit, which is used to define a domain ontology and construct the processed entities and relationships into a knowledge graph; A graph optimization verification unit, which is used to verify the consistency and integrity of the data in the knowledge graph, remove duplicate and redundant information, and further enrich the content of the knowledge graph by linking to an external knowledge base; The knowledge updating and maintenance unit is used to update the knowledge graph in real time to maintain its timeliness.

3. The learning path design system based on knowledge graph according to claim 2 is characterized in that: The user modeling module includes: A user information collection unit, which is used to collect the user's personal information, record the user's learning activities in the system, and infer the user's learning habits and preferences through the user's behavior on the platform; An interest preference identification unit, which is used to analyze the user's interest in different topics or types of content through a machine learning algorithm, and recommend learning resources with complex interests and preferences to the user; The dynamic model updating unit is used to continuously monitor the user's learning progress and change trends, and update the model information in a timely manner.

4. The learning path design system based on knowledge graph according to claim 3 is characterized in that: The learning path planning module includes: A learning needs analysis unit, which is used to communicate with users to clarify their learning goals and expected outcomes; A path generation optimization unit, wherein the path generation optimization unit is used to generate a preliminary learning path according to the user's needs and the structure in the knowledge graph, and optimize the learning path using a heuristic algorithm; A learning resource matching unit, which is used to build and maintain a rich learning resource library and recommend corresponding learning resources according to the knowledge points in the learning path; The adaptive adjustment unit is used to utilize machine learning and artificial intelligence technologies to dynamically adjust the learning path according to the user's learning behavior and feedback to achieve personalized adaptive learning.

5. The learning path design system based on knowledge graph according to claim 4 is characterized in that: The learning resource management module includes: The resource description and annotation unit is used to generate detailed metadata and tags for each resource, and map the resources with relevant concepts and knowledge points in the knowledge graph to establish a connection between the resources and the knowledge points. A resource organization index unit, which is used to build a clear resource directory structure and support multi-dimensional rapid retrieval and positioning; A resource evaluation and feedback unit, which collects user feedback on the use of learning resources and regularly updates and optimizes the resource library based on user feedback and evaluation results; The permission management unit is used to set different access rights for different roles, protect the security of sensitive resources, and perform version control on resources.

6. The learning path design system based on knowledge graph according to claim 5 is characterized in that: The learning monitoring feedback module: A progress tracking and feedback unit, which is used to track the user's learning progress in real time, record their performance during the learning process, collect the user's learning feedback, and adjust the learning path in time according to the user's feedback to optimize the learning experience; A knowledge status evaluation unit, which is used to regularly evaluate the user's mastery of specific knowledge points using tests and questionnaires, and dynamically adjust the difficulty of test questions according to the user's current knowledge level, more accurately locate the user's ability boundary, provide instant feedback based on the user's learning performance, help the user clarify the direction of improvement, and give the learner a learning effect score; A learning behavior analysis unit, which uses data analysis technology to identify learners' behavior patterns, analyze individual differences of learners, identify their learning styles, and monitor whether learners have abnormal behaviors; A real-time feedback prompt unit, which is used to provide instant feedback during the learning process to help learners correct mistakes or strengthen their understanding; A learning community interaction unit, which is used to provide a discussion area among learners, encourage interactive communication, solve difficult problems, and invite experts in the field to participate in answering questions; A data analysis and reporting unit is used to visualize the learning data of learners.

7. The learning path design system based on knowledge graph according to claim 6 is characterized in that: The cross-domain knowledge integration module includes: A knowledge mapping unit, which is used to identify and establish connections or mapping relationships between knowledge concepts in different fields, and automatically discover the correlation between different knowledge fields through semantic analysis and machine learning technology; The knowledge fusion unit is used to integrate relevant knowledge in multiple fields to form a unified whole, so that users can more easily understand the connection between various parts.

8. The learning path design system based on knowledge graph according to claim 7 is characterized in that: The knowledge fusion unit comprises: A semantic matching subunit, which is used to identify synonyms and abbreviations in different fields through natural language processing technology and unify them into a standard terminology system; A content integration subunit, which is used to merge the extracted knowledge fragments into a more complete knowledge unit; A context-aware subunit, which is used to adjust the knowledge expression form according to the specific needs of different application scenarios; A knowledge organization subunit, wherein the knowledge organization subunit is used to construct a hierarchical knowledge structure according to a subject or subject area, and to establish connections between different knowledge nodes through hyperlinks; The quality assessment subunit is used to regularly check whether the knowledge graph covers all knowledge points using expert review.

Images