Abstract: Abstract: Based on the knowledge graph technology, the knowledge of gas emergencies and their emergency disposal information was extracted and represented, and the construction method of knowledge graph for gas emergency disposal was put forward, so as to provide technical support for complete emergency disposal management in the later stage. In order to solve the problem of few samples of gas emergency cases, this paper adopts Web crawler technology to crawl online gas emergency cases. Taking the crawling gas emergency case and the gas emergency case provided by a gas company as the research object, the top-down hierarchical model of gas emergency disposal is established. The BiLSTM-CRF model and topology network diagram are used to extract entities in the case, and the effectiveness of entity extraction is verified by experiments. The relationship between entities is defined and classified by semi supervised collaborative training method. The neo4j graph database is used to visualize the knowledge graph of gas emergencies and emergency disposal methods. Through the verification and analysis of three practical cases, it is proved that the above method has good effect.

Key words: Key words: gas, emergency accident, emergency management, knowledge graph, Neo4j