The invention discloses a
knowledge question-answer
system established on basis of a Wiki
semantic network, and an intelligent retrieval method and relates to the technical fields such as text semantic analysis, intelligent retrieval and
machine learning. According to the invention, semi-structuralized text data grasped by
vertical field Wiki in an oriented manner is used; knowledge elements are extracted automatically according to a pre-defined knowledge ontology; further, a
deep learning algorithm can be used to
train and establish an ontology semantic comprehension model; and thus, semantic comprehension of clustering relations and
inference relations of the knowledge elements could be achieved. According to the invention, advantages of
machine learning including automatic theme
inference based on context semantic understanding and expert knowledge oriented optimization are synthesized; matched retrieval results matched through rational
semantic association and expansion as well as inferred retrieval results are returned to a retrieval word input by a user; and in combination with definition of expert knowledge, accuracy and depth of the
information retrieval can be increased effectively, and knowledge navigation can be achieved. The
system and method are applicable to a medical-themed mapping knowledge domain, knowledge questioning and answering and a content recommendation
system.