Bayes网络推理结论的解释机制研究  

Research on Explanation Function for Reason Conclusions with Bayesian Network

作　　者：汪荣贵[1] 张佑生[1] 高隽[1] 彭青松[1] 

机构地区：[1]合肥工业大学计算机与信息学院,合肥230009

出　　处：《计算机研究与发展》2005年第9期1527-1532,共6页Journal of Computer Research and Development

基　　金：国家自然科学基金项目(60175011;60375011);安徽省自然科学基金项目(03042207);安徽省优秀青年科技基金项目(04042044)~~

摘　　要：提出一种关于Bayes网络的解释机制,用于解释证据对推理结论的作用程度、方向及路径.引入必要性和充分性因子作为度量来评价证据对推理结论的作用程度;通过定性分析网络结构特点,找出与推理结论有关的节点,在此基础上,结合定量分析找出组成作用路径的子链,并分析这些子链对推理结论的作用,由此生成和解释证据对推理结论的作用路径.实验结果验证了方法的有效性.In this paper, an explanation function about Bayesian network is presented. With it, evidences＇ effect degree, direction and paths on reason conclusion can be explained. Necessity factor and sufficiency factor are designed as a measure approach, to valuate evidences＇ effect degree on posteriori distributions. By the way of qualitatively analysis the character of network structure, notes relative to reason conclusion are find out. Based on those notes, and combined with the quantitatively analysis, sub chains which consist of effect paths are found out, too. Those sub chains are valuated to create and explain the effect paths. Experiment results show the effectiveness of the explain function.

关 键 词：BAYES网络 后验概率分布 1-范数 作用程度 作用方向 作用路径 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]