CONFLICT RESOLUTION STRATEGIES FOR COOPERATION IN MULTI-EXPERT SYSTEMS
In the knowledge system with multi-expert systems collaborated together, , different expert systems always reason to dissimilar conclusions on solving the same problem, which have disparate expression styles given by different inference methods. How to synthesize the different conclusions in one collaboration group into a unified decision representing the whole group is a key problem in the research of distributed knowledgebase Systems. In this paper we present a new synthesizing algorithm to solve this problem. The algorithm can classifies the conflicts and synthesize the conclusions based on rule-based, Bayesian network or Evidence Theory. It distinguishes ordered proposition and common problem when disposes consistency. The convex function model in Evidence Theory was used to deal with the ordered proposition and the common problem was solved by the optimistically and conservatively synthetic strategy. Experiments show the correctness and efficiency of our algorithm.
cooperation conflict resolution multi-ezpert systems
Jing Huang Dayou Liu Bo Yang Jiaying Lu
College of Computer Science and Technology, Jilin University, Changchun 130012, China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun 130012, China
国际会议
北京
英文
30-33
2005-10-14（万方平台首次上网日期，不代表论文的发表时间）