Abstract: At present, the decision-making of coal mine roof disaster prevention and control measures and the analysis of accident causes mainly rely on manual experience, and the level of intelligence is relatively low. The knowledge graph of roof disaster prevention and control can integrate knowledge and experience of roof disaster prevention and control, assist in analyzing the causes of roof disaster accidents and making decisions on roof disaster prevention and control measures. A method for constructing a knowledge graph of coal mine roof disaster prevention and control has been proposed. The ontology method is used to complete the knowledge modeling of coal mine roof disaster prevention and control. The concepts in the field of roof disaster prevention and control are divided into mine geology, mining technology, prevention and control measures, and accident characterization. The relationships between concepts are defined as usage, triggering, susceptibility, control, prevention, and applicability. The knowledge modeling lays the foundation for the knowledge extraction of coal mine roof disaster prevention and control (entity extraction and relationship extraction). Based on the characteristics of entity overlapping between a large number of nested entities and relationships in the field of coal mine roof disaster prevention and control, a span based entity extraction method and a dependency syntax tree guided entity representation based relationship extraction method are determined. The method constructs a corpus in the field of roof disaster prevention and control, and uses the Neo4j graph database to store data, providing data source support for the application of knowledge graph of roof disaster prevention and control. The partial construction results of the knowledge graph of coal mine roof disaster prevention and control are displayed. It indicates that this knowledge graph can assist in the analysis of roof disaster accident causes and decision-making of prevention and control measures, thereby improving the intelligence level of roof management. It is pointed out that based on this knowledge graph, combined with natural language processing and knowledge reasoning technologies, knowledge Q&A on roof management can be achieved.