Knowledge Graph Civil Aviation Question Answering Based on Deep Learning

With the continuous expansion of the scale of civil aviation, the passenger traffic volume of civil aviation has increased year by year, and the demand of passengers for civil aviation travel information has also increased sharply. The traditional manual customer service has problems such as heavy customer service pressure and untimely message response, which can no longer meet the development of modern civil aviation service industry. Therefore, this paper proposes a knowledge graph question answering method for civil aviation based on deep learning, which is used to quickly and accurately obtain the information of civil aviation question and match the question answers. Firstly based on the collected civil aviation data, the method extracts triples based on rules to complete the civil aviation knowledge graph, then the Aho-Corasick(AC)automata is constructed for entity recognition, and Convolutional Neural Network(CNN)is used for classifying user intention. Finally, according to the recognized entities and the results of user intention classification, the question is converted into a query sentence of the knowledge graph, and the answer is returned after querying in the knowledge graph. The experimental results show that the proposed method in this paper can better understand user’s intention and accurately answer the relevant questions compared with the comparative methods, which proves the validity of the method.