Construction And Application Of Earthquake Knowledge Graph

China is located at the junction of the Pacific Ocean,the Indian Ocean and the three Asian and European plates,and earthquake disasters are frequent.The information on earthquakes and their secondary hazards comes from a wide range of sources,is diverse,large in quantity and loosely organized,and there is a phenomenon of "massive data,information explosion and difficult to find knowledge",which makes it difficult to meet users’ demand for knowledge services.Knowledge Graph Technology organizes and stores multi-source heterogeneous data in the form of graph structure,realizes the association of multiple information elements,and supports the intelligent information service of earthquake disasters through the transformation of data to knowledge.At present,the existing research on earthquake disaster knowledge mainly focuses on the construction of knowledge graphs for earthquake disaster emergency ontology and unconsidered spatio-temporal elements.In this paper,we take the construction and application of earthquake disaster knowledge graph as the starting point,study and construct a knowledge map of earthquake disaster taking into account geographic elements,and realize a knowledge retrieval system based on the knowledge graph.The main research contents of this paper include:(1)Construction of the model layer of earthquake hazard knowledge graph.We analyze four basic elements of earthquake disaster knowledge,namely,basic background,disaster-causing factors,disaster situation and risk situation,and emergency response,and describe the concepts and attributes of each element and the relationships among them by using the top-down method to form a hierarchical conceptual framework and knowledge system,which provides the basis for the subsequent construction of the data layer of the knowledge graph.(2)Construction of the data layer of earthquake hazard knowledge graph.Under the guidance of the unified conceptual framework of the model layer,the data layer is constructed in a bottom-up manner.Firstly,we adopt different methods to extract entities,attributes and their relationships from various data sources such as existing historical databases,domain information literature,Internet text resources and geospatial data;then we define suitable similarity measures to solve the problems of entity isolation and ambiguity and realize entity alignment;finally,we deposit the resulting triads into the graph database and use manual verification methods to evaluate the quality of the knowledge graph,so as to lay a solid foundation for the application of the knowledge graph.Finally,the resulting triples are stored in the graph database,and the quality of the knowledge graph is evaluated by manual verification method to lay a solid data foundation for the application of the knowledge graph.(3)Application of seismic hazard knowledge graph.Based on the constructed earthquake disaster knowledge graph,firstly,the core elements of earthquake disasters and their associated knowledge are queried and visualized by using the knowledge graph query language;then,the knowledge search is realized by path calculation and rule inference,and the earthquake disaster knowledge graph is extended to realize the knowledge complement and update;finally,the earthquake disaster knowledge visualization and retrieval system based on the knowledge graph is realized to provide users with more convenient Finally,a knowledge visualization and retrieval system based on the knowledge graph is implemented to provide users with more convenient knowledge retrieval services.This paper adopts a top-down and bottom-up approach to construct the schema layer and data layer of the earthquake disaster knowledge graph,explore the update and reasoning of the earthquake disaster knowledge map,and realize the visualization and retrieval of the graph,and the research results can be used in the intelligent knowledge service for earthquake disaster emergency.