An Ontology Constructing Technology Oriented on Massive Social Security Policy Documents

Abstract Because of the huge number of policy documents in the field of social security, there is a need to manage these information. In this paper, ontology is used to represent and store information in files. In order to ensure the accuracy of ontology structure, this paper first constructs ontology framework manually, and then extends ontology framework by the inclusion relationship between attribute set and object set. At the same time, this paper adopts the idea of statistics and rules in the field of natural language processing, extracts hierarchical and non-hierarchical concepts from the lexicon of social security field to construct ontology, and then puts forward the statistical models of concept phrase vector and high-frequency phrase vector. The experimental results show that the semi-automatic ontology construction process in the field of social security can effectively propose social security ontology from a large number of policy documents. The experimental results play a reference role for ontology construction in other fields.