融合多源数据的学科知识图谱构建与应用

Construction and Application of Subject Knowledge Graph Based on Multi-source Data

学科知识图谱可以给学生及教育工作者提供一个清晰、结构化的学科知识体系。本文提出一种融合多源数据的智能学科知识图谱构建方法,并在中学化学学科实现。首先进行本体设计,并依据本体设计完成了基于BERT模型的命名实体识别和基于特征提取的实体关系抽取,之后对多种数据源进行融合,最终将数据存储于Neo4j图数据库中实现可视化应用。该知识图谱有助于为中学学科智能辅助学习系统的搭建提供支撑,起到支持学生个性化学习的重要作用。

The subject knowledge graph can provide students and educators with a clear and structured subject knowledge system.This article proposes an intelligent subject knowledge graph construction method that integrates multi-source data and is implemented in middle school chemistry disciplines.Firstly,the ontology design was carried out,and named entity recognition based on the BERT model and entity relationship extraction based on feature extraction were completed based on the ontology design.Then,multiple data sources were fused,and finally,the data was stored in the Neo4j graph database for visualization applications.This knowledge graph helps to provide support for the construction of intelligent assisted learning systems for middle school subjects,playing an important role in supporting personalized learning for students.