Research And Realization Of Intelligent Health Knowledge Question-Answering System

With the development of information technology, people have been used to getting all kinds of information from the Internet. These are because of the development of the search engine technology. But there are still some unresolved problems to the search engine. Firstly, when the users search for the information, too much relevant and imprecise information returned. Secondly, the retrieval depended on the keyword matching, which could not actually express what people really meant.Because of these problems, Question-Answering System (Q&A) which is based on retrieval technologies came into being. Compared with foreign Q&A System, Chinese Q&A System started late, but it still has some problems. For example, slow reaction rate, low correct rate, poor reasoning ability, etc.In view of these problems of Q&A system, in this paper, some key technical problems were studied of Q&A System which was in the health field. A Q&A System model based on multi-strategies was presented. The major research content is as follows:First, construct the specialized terms library of health field, AIML(Artificial Intelligence Markup Language)knowledge base, question base, etc:Second, on the basis of the existing Chinese word segmentation, pos tagging, synonym substitution, pruning process, etc. And then put forward sentence similarity algorithm based on weight and recommendation algorithm which are suitable for the field of medical and health; Finally to improve the ALICE system to support Chinese, and on the basis of its own matching reasoning, extend interface semantic reasoning.Compare to the existing Q&A System based on sentence similarity through experiments to verify the performance of the Q&A System. The experimental results show that, to some extent, the Q&A System in this paper can improve recall rate and precision rate of Q&A System, and therefore promote the research and development of information retrieval and intelligent answer system.