Sales And Service-oriented Design And Implementation Of The Automated Answering System

With the development and popularity of computer technology and internet, the technology of natural language processing is developing quickly. At present, more and more information are available online, providing a huge amount of information resources for people. However, it is very difficult for people to find the information they need quickly and accurately from the overwhelming information even if they make use of the popular search engines. So the question answering (QA) technology is proposed and developed to meet people's demand.QA technology is a very hot research direction in the field of natural language processing (NLP). It combines a large variety of NLP technologies. The inputs of search engines are the combinations of keywords, while QA systems enable users to input a question in natural languages. The outputs of search engines are some related web pages, while QA systems can give users concise and accurate answers. Presently, many research institutes have been investigating English QA technologies. Some mature English QA systems have been widely recognized. But few institutes are doing research on Chinese QA systems. No Chinese QA systems have been proposed up to now, especially the systems in open domain.In view of lacking of mature theory and technology of Chinese question and answer systems in open-domain, this paper proposes a Chinese QA system for market service, which is a Chat Robot. This system includes three modules: construction of question-answer database (QADB), question sentences similarity measure and answer retrieval. The main task of the question-answer database construction is to collect the frequent question sentences and corresponding answers. The question sentences similarity measure is to compute the similarity between the input sentence and the question sentences in question-answer database. The answer retrieval part is to retrieve the most accurate answer from QADB for the input sentence according to the sentences similarity measure result. The analysis, design and implementation of the system are also described detailedly in this paper.