Question answering device and method for vehicles

Abstract

One embodiment of the invention provides a question answering device and method for vehicles, belonging to the field of vehicles. The device comprises a receiving module for receiving questions brought out by users; an application scene classification module for performing application scene classification on the questions brought out by the users, wherein the application scene comprises one or many of the followings: fault type, general knowledge type, handbook type, car purchasing type and insurance type; a semantic comprehension module for semantic recognition of the questions brought out by the users according to the classified application scene to obtain feature information; an answer assuring module for determining answers corresponding to the questions brought by the users according to the feature information; and an answer outputting module for outputting the answers corresponding to the questions brought by the users. The method and device effectively solve the problem of low accuracy of FAQ-based question answering mode.

Description

technical field [0001] The present invention relates to the field of vehicles, in particular to a question answering device and method for vehicles. Background technique [0002] The question answering system is an artificial intelligence application that combines natural language analysis and machine learning, such as Microsoft's Xiaoice robot, iPhone's Siri, Jingdong's Jimi customer service robot, Baidu's Dumi, etc. These question answering systems have won recognition in different fields. achieved certain results. [0003] Q&A systems can be divided into open domain scenarios and limited domain scenarios according to usage scenarios. Xiaoice, Siri, Dumi, etc. belong to open domain Q&A systems, that is, there are no scene restrictions on the content of Q&A. JD.com’s Jimi is a limited domain robot , only limited to JD.com’s customer service, and cannot give friendly answers to questions in other fields. Currently, open domain question answering systems are more difficult ...

AI Technical Summary

Problems solved by technology

Of course, its learning technology is more difficult and requires more training corpus and basic equipment to support

[0007] Each industry has its own characteristics, and open-field question-and-answer techniques are not fully applicable to problem-solving methods in the automotive field.

At present, technology companies and scientific research institutes pay more attention to the research of question answering system technology in the open field. This kind of technology cannot be directly applied to specific vertical fields. For example, it cannot be applied to the automotive field. Even if it is applied to the automotive field, its effect cannot be achieved Meet the needs of the market

Images