An Intelligent System for Semantic Information Extraction and Knowledge Graph Construction from Multi-Type Data Sources

Abstract

Knowledge graph technology has been widely used in various fields and numerous platforms provides the knowledge-graph-based applications. Nevertheless, most of the applications require users to master expertise and programming ability. In this paper, a knowledge graph construction and application platform for general fields is completed in the web application form, which is user-friendly and interactive. Primarily, it can construct knowledge graphs of various fields automatically or semi-automatically from multiple types of data sources, including structured and unstructured data. Additionally, it can store, manage and update multiple versions of knowledge graphs by graph database Neo4j, and visualize specific information about each node and relationship of the knowledge graph. Finally, the system establishes a semantic parsing-based knowledge base Question Answering(KBQA) system based on the user-built knowledge graph, assisting users to realize the graph-related applications based on their own data.