Research on domain knowledge graph based on the large scale online knowledge fragment

Knowledge Graph is a powerful tool to manage large scale knowledge, and is an important means to deal with the problem of the knowledge fragment. Knowledge Graph can be applied to Semantic Search, Question Answering System, Deep Reading and other. The current research mainly focuses on the information fusion of broad-spectrum knowledge, and aims at improving the recall ratio of the knowledge. Based on the previous research, we propose a method for constructing the domain knowledge Graph. We use information extraction technology to extract entities and relationships from open network documents. Meanwhile, we mine the multidimensional relationships between entities, and solve the information conflicts generated by multi-source information fusion. These are important to rich the information and improve the recall ratio and precision ratio of domain knowledge. So the method has important significance to build knowledge graph of specific areas.