An architecture of interactive question answering for online diagnosing fault

IQA system has been attracted by researchers in recent years. Through interactive dialogue with the user, IQA systems can gradually clear the real intention of the user's questions. In this paper, we introduced an architecture of IQA system which is based on an IQA ontology and adopting hybrid reasoning mechanism. Our supposed IQA system can online diagnose the fault and return the corresponding solutions by interactive dialogue with the user. The method is mainly concerned about two aspects of IQA system: interactivity and the ontology knowledge base which is suitable to achieve such interactivity. The results of experiment show that the system is feasible and usable.

I. Introduction

Customer service department is an important integral part of large manufacturing company. It provides betimes responding the service request from customers when the fault of their purchased machine occurred. Previously, the manner of customer service is based on telephone system, thus, it requires a large number of service engineers to provide support and lead to waste of human and material resources. With the rapid development of Natural Language Processing (NLP) and Semantic Web technology, online machines automatic service [1] has become possible. The typical application is online customer service mode of web-based Question Answering (QA) [2].