Taking the diet problem of diabetic patients as an example,the paper puts forward the problems classification system based on functions in the view of users,classifies the problems put forward by patients through the Support Vector Machine (SVM) algorithm,and provides important support for the construction of the deep automatic Question Answering (QA) system.

The paper analyzes the documents related to the foreign medical automatic Question Answering (QA) system,and compares the differences between automatic QA and traditional network information retrieval,describes the automatic QA system in the aspects of application researches,common tools and relevant technologies.Combining foreign related researches,it also discusses the current key problems of medical automatic QA system and the implications for China in order to offer reference for further research.

Through the retrieval of literatures about the research and application of ontology in the diabetes field in PubMed,IEEE/ IET Electronic Library,ACM,WANFANG,CNKI,VIP and other Chinese and English databases,as well as the search engines Google Scholar and Baidu Scholar,the paper shows the current situations and summarizes the main study contents.The result shows that the study achievements of ontology in the field of diabetes increase rapidly and there are obvious advantages in semantic comprehension in recent decade.