基于知识密集型的CBR构件检索方法研究与实现

The Implement and Research of a Method of Component Retrieval Based on Knowledge-intensive CBR

传统的构件检索方法假定用户的查询需求是清晰且准确的,然而用户往往并不能准确地定义自己的查询需求。本文提出了一种基于知识密集型会话式案例推理的构件检索方法,并重点阐述如何以主动的"询问—应答"方式通过基于知识密集型会话式案例推理方法帮助用户构造增量式查询。实验结果表明:该方法是行之有效的,能够大幅度提高构件的检索效率。

The limitations of traditional component retrieval methods is that assumption of users＇component queries is clear and accurate, however, they usually can not well define their queries accurately, so a Method of Component Retrieval Based on Knowledge-intensive Conversational Case Reasoning is proposed in this paper. It emphasizes a knowledge-intensive conversational case-based reasoning method to help users to construct their queries incrementally through a mixed--initiate question-answering manner. The experimental results prove that this algorithm is feasible and can improve component retrieval efficiency greatly.