一种基于共享度模型的改进Rete算法  

An Improved Rete Algorithm Using Shared Degree Model

作　　者：孙新 严西敏 尚煜茗 欧阳童 董阔 

机构地区：[1]北京理工大学计算机学院北京市海量语言信息处理与云计算应用工程技术研究中心,北京100081

出　　处：《自动化学报》2017年第9期1571-1579,共9页Acta Automatica Sinica

基　　金：国家高技术研究发展计划(863计划)(2015AA015404)资助~~

摘　　要：专家系统是人工智能领域的重要分支,其中知识表示和知识推理是专家系统的重要组成部分.Rete算法是一种高效的模式匹配算法,能够解决专家系统中推理效率的问题,但是Rete算法在构建Rete网络和推理过程中存在空间和性能方面问题.本文采取有穷自动机理论的思想,阐述了Rete算法中的模式共享度和节点共享度模型,提出了一种Rete网络构建和推理算法来降低Rete网络的复杂度,提升Rete网络推理的速度.最后实验结果表明,本算法能够降低网络复杂度,提升推理速度.Expert system is an important brunch of artificial intelligence. Knowledge representation and inference engine is an important part of the expert system. As an efficient pattern-matching algorithm, Rete algorithm can solve the ratiocination efficiency problem in expert system. However, there always exist the problems such as storage and efficiency in building and using Rete network. In this paper, we introduce the idea of finite automata, and the pattern sharing degree and node sharing degree model into Rete algorithm. We propose a Rete network construction and inference algorithm to reduce the complexity of Rete network and improve the speed of Rete network inference. Finally, experimental results show that it can reduce the complexity of the network greatly and raise the inference speed.

关 键 词：专家系统 RETE算法 有穷自动机 推理机 

分 类 号：TP182[自动化与计算机技术—控制理论与控制工程]