Intelligent question answering system for automobile field

Abstract

The invention discloses an intelligent question answering system for the automobile field. The system comprises a knowledge base module, a visual interaction module, an intention recognition module, a graph matching module, a template matching module, a retrieval module and an end-to-end module. The knowledge base module stores a knowledge graph and a corpus of the automobile field; after a user inputs a question, the input content of the user is judged, corresponding modules of the system are called for processing according to different judged user purposes, and an answer to the question is obtained. User purposes are divided into automobile field questions and chats, and for the automobile field questions, question answers are obtained by using a question answering method based on an automobile field knowledge graph; and for the chat, an end-to-end module based on deep learning is used to generate an answer. The method can improve the classification precision, and can accurately recognize the user intention.

Description

technical field [0001] The invention relates to the field of intelligent technology, and more specifically relates to an intelligent question answering system oriented to the field of automobiles. Background technique [0002] At this stage, artificial intelligence is undoubtedly one of the most popular research topics. As a main direction of artificial intelligence, natural language processing, one of its application methods is intelligent question answering. Intelligent question answering refers to the computer automatically answering the questions raised by users by analyzing the questions asked by users, which is an advanced form of information service. [0003] In recent years, major Internet companies are gradually launching and improving their own intelligent question-answering systems, such as Apple's "Siri", Google's "Assistant", Amazon's "Alexa", Alibaba's "Ali Xiaomi", Xiaomi's "Xiao Ai Classmate" and so on. Although the existing question answering methods at th...

AI Technical Summary

Problems solved by technology

[0005] At present, the intelligent question answering system in the automotive field has a single constraint on the part-of-speech recognition conditions of the user input words, the recognition accuracy is low, and the semantic structure information of the input question and the dependency relationship between words are not considered, and only shallow semantic analysis is realized. Difficulty answering more complex questions

Images