Civil Aviation Travel Question and Answer Method Using Knowledge Graphs and Deep Learning

In this paper, a civil aviation travel question and answer (Q&A) method based on integrating knowledge graphs deep learning technology is proposed to establish highly efficient information Q&A platform quickly accurately obtain give corresponding answers passengers. the method, rule-based approach employed extract triads from acquired dataset construct graph. Then, ELECTRA-BiLSTM-CRF model constructed recognize entity, an improved ALBERT-TextCNN used for intent classification. Finally, Cypher query templates are transformed into statements retrieved in Neo4j database, returns result, which realizes new method. A self-built selected prove effectiveness of The experimental results show that can achieve better results, it has generalization high accuracy.