Research on the Construction Method of Rice Knowledge Graph

With the development of technologies such as the IoT and remote sensing and their wide application in the agricultural field, resulting in large-scale agricultural data, how to organize and utilize agricultural big data effectively has become a key problem to be solved. This article studies the knowledge graph representation method of agricultural data in rice. First of all, using crawler and government open data to obtain data in rice. Secondly of all, classification and processing according to data characteristics: Structured data calls D2R for RDF mode conversion; Unstructured data uses semantic dictionary to build templates, define rules to extract entities and their attribute values, and extract nontaxonomic relationships from texts based on pattern matching method. Finally, with the participation and guidance of expert in rice, the knowledge complement and correction are carried out to complete the construction of the rice knowledge graph. In order to verify the method in this paper, we build a knowledge query system based on rice knowledge graph, construct query examples, and analyze the experimental results. The verification results show that the knowledge graph constructed by the method in this paper can effectively improve the accuracy of domain knowledge query.