基于案例推理系统中案例检索算法的探索

Study on a Case Retrieval Algorithm in Case-based Reasoning System

案例检索是基于案例推理系统的中心环节,目前应用最多的欧氏距离检索算法在实际应用中经常出现计算的相似度结果偏离工程实际的情况。文章利用一种归一化效用函数在最近邻法原理基础上提出一种改进的欧氏距离检索算法。实际工程应用结果说明,这种改进的算法不仅有效,而且简单实用。

Case retrieval is a focus of the Case-based Reasoning（CBR） system ,The similarity results calculated by the Euclidean Distance retrieval algorithm,which is widely used in the CBR system,often deviate from the fact in engineering.Based on the Nearest Neighbor approach,a modified Euclidean Distance retrieval algorithm is put forward by using a normalization utility function.It is shown from application results that the algorithm is simple and practical.