一种基于可信度的迭代信念修正方法  

Believability based Iterated Belief Revision

作　　者：杨佩[1] 高阳[1] 陈兆乾[1] 

机构地区：[1]计算机软件新技术国家重点实验室

出　　处：《计算机研究与发展》2005年第8期1293-1298,共6页Journal of Computer Research and Development

基　　金：国家自然科学基金项目(60103012)

摘　　要：信念修正主要解决在接收到新信息时,如何对原有知识库进行操作的问题.经典的迭代信念修正主要关注信念修正的一致性,并未考虑多agent系统中信息具有不可靠性,以及信念修正过程对修正结果的影响.基于可信度的迭代信念修正方法,通过证据理论以及信度函数方法估计信息的可信度,并由此确定最优的最大协调子集作为信念修正的结果.基于可信度的迭代信念修正算子具有历史依赖性,即修正结果不仅与当前的信念集和接收到的新信息有关,也与信念集中曾经接收到的信息相关.The theory of belief revision describes how the beliefs of an agent should change upon receiving the new information. Classical iterated belief revision methods mainly focus on the consistency of belief change, with little concern of the impact of the uncertain information in multi-agent system and the process of revision. In this paper, an approach of believability based iterated belief revision is presented. This approach relates the belief revision in the multi-agent system to the believability of information, which plays an important role in the revision process. Based on the Dempster-Shafer theory of evidence and believability function formalism, the believability of information can be obtained, and thus the maximal consistent subset with the biggest believability is chosen to compose the revised belief set. The revised belief set by believability based iterated belief revision is dependent on the history of revision, namely, on the information received prior to the current belief set.

关 键 词：迭代信念修正 可信度 证据理论 历史依赖性 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]