基于知识图谱的通用学习路径生成研究

Research on Generation Method of the General-purpose Learning Path based on Knowledge Graph

针对当前在线学习容易产生的“学习迷航”“信息过载”等问题,满足大多数在线学习者的需求提出一种通用、可行的在线学习路径自动生成的方法.以多重属性特征为基础设计了知识图谱模式层,结合TextRank算法对爬虫获取到的文本资源构建知识图谱;提取知识图谱中知识点属性与关系,应用拓扑排序算法,设计了通用学习路径自动生成方法.实验结果表明自动生成的通用路径与专家路径的相似度较高,在线学习过程中可取代专家制定的学习路径,路径设计的学习逻辑符合认知规律,并为个性化学习路径的构建与学习资源的推荐提供基础.

A generic and feasible method for the automatic generation of online learning paths is proposed to resolve some problems of online learning,such as"get lost disorientation in studying","information overload",etc.The knowledge graph pattern layer was designed based on multiple attribute features,and the text resources obtained by the crawler were combined with the TextRank algorithm to build a knowledge graph;the attributes and relationships of knowledge points in the knowledge graph were extracted,and a topological sorting algorithm was applied to design a generic learning path automatic generation method.The experimental results show that the automatically generated generic paths have a high similarity to the expert paths and can replace the learning paths developed by experts in the online learning process.The learning logic of the path design conforms to the cognitive law and provides a basis for the construction of personalized learning paths and the recommendation of learning resources.