知识的获取、知识库的更新是案例推理技术的应用瓶颈,而许多案例推理系统中的知识库都是静态不变的,满足不了实际问题变化的需要。首先阐述了相关概念,接着提出了一种基于动态数据流挖掘的案例推理模型,其中动态数据流挖掘算法采用改进的数据流聚类算法。通过此模型使用基于动态数据流挖掘的案例推理技术,对数据进行实时挖掘,产生连续、动态的临时案例库,实现知识库的实时更新,从而满足实际问题变化的需要。最后通过该模型在实际中的应用说明其有效性。
The application of case-based reasoning is restricted by the knowledge acquisition and the knowledge base updating.Many knowledge bases in the case-based reasoning system are static and unchangeable,and can not satisfy the change of practical problems.This paper describes the relevant concepts and presents a model of CBR based on dynamic data stream mining,and gives an improved clustering algorithm of data stream.Through this model the system can mine real-time datum, produce continuous,dynamic temporary cases,update the knowledge base in real time and meet the needs of the practical problems.Finally,the application of the model in practice verifies its efficiency.