根据检索的关键词群与文献内容的属性群的贴近度使关键词空间结构化,在先验知识空间中用模糊集合表示识别概念,使类推过程模糊化,实现人机对话识别检索要求概念的更新过程。 According to the closeness between the retrieved keyword groups and the attribute groups of the document content, the key words are structured in the space of the key words, and the fuzzy sets are used to represent the recognition concepts in the prior knowledge space. The analogical process is obscured to realize the concept of human-computer dialogue recognition retrieval requirements Update process