Research And Construction On A Knowledge Graph Integrated Question Answering System Of Forestry Laws And Regulations

The development of forestry is related to the construction of China’s ecological civilization and the sustainability of social development.Forestry informatization,however,as one of the most important goals in China’s "Thirteenth Five-Year Plan",requires promotion by Internet technology.At present,there is still no effective way to obtain information and knowledge related to forestry laws and regulations in China.This article applies relevant technologies of knowledge graph to the area of forestry laws and regulations.In this paper,the knowledge graph of forestry laws and regulations is extracted and established firstly.Then,a question answering system for forestry laws and regulations is constructed and implemented based on knowledge graph.The main research results are as follows:(1)Construct a knowledge graph of forestry laws and regulations.The forestry laws and regulations texts are first obtained、cleaned and extracted.Then a method integrating dependency syntactic analysis and semantic role labeling is used to extract entities and pre-defined 9 types of relationships.The 9 types of relationships covered more than 67% of the law terms.Ultimately,a knowledge graph of forestry laws and regulations has well achieved.(2)A question answering algorithm for forestry laws and regulations based on knowledge graph is designed and implemented.The Bi LSTM-CRF model is used for entity recognition,and the similarity calculation method based on TF-IDF and word vectors is used for relation recognition and question template matching.Finally,different answers can be obtained according to different queries.As two important indicators for estimating question answering algorithm,the F1 value of entity recognition model is 89.72%,and the accuracy of relation recognition algorithm is 85.47%.(3)A question answering system for forestry laws and regulations is designed and built.Based on the above implementation,we uses Vue.js,Java Spring Boot,and Python the front and back ends to build a question answering system of forestry laws and regulations based on knowledge graph.Intelligent question answering,knowledge graph visualization,and full text retrieval of laws and regulations etc.are implemented in this system.This paper is a preliminary attempt and application of the knowledge graph in forestry laws and regulations,providing users with intelligent and relatively accurate knowledge of forestry laws.It can underpin the development of smart forestry and smart court,and can be applied to other applications in forestry laws and regulations.