摘要
文章在语义集成中引入了协商—博弈机制。各个Agents由于对领域的认知程度不同,因此,他们构建本体的"可信度"也是不同的。本体"可信度"越高,基于本体语义进行的检索准确率就越高。注意到每个Agent构建的本体与最终本体之间相似度可以看作Agent的收益,Agents之间如果通过协商与博弈来形成均衡,那么这个均衡就是所有Agents最能接受的结果,即"可信度"最高的本体。因此,模拟Agents之间的协商与博弈,构建更"可信"的本体,是完全可行的。
This paper introduces negotiation-game mechanism in semantic integration. Because each agent has different knowledge of the domain, the "credibility" of their ontology construction is also different. The higher the "trustworthiness" of ontology, the higher the retrieval accuracy based on ontology semantics. Notice that the similarity between the ontology constructed by each agent and the final ontology can be regarded as the benefit of the agent. If the equilibrium between agents is formed through negotiation and game, then the equilibrium is the most acceptable result of all agents, that is, the ontology with the highest "credibility". Therefore, it is entirely feasible to simulate the negotiation and game between agents and build a more "credible" ontology.
引文
[1]KALFOGLOU Y,SCHORLEMMER M.Ontology mapping:the state of the art[J].Knowledge Engineering Review,2003(1):1-31
[2]NOY N.Semantic integration:a survey of ontology-based approaches[J].Sigmod Record,2004(4):65-70.
[3]唐杰,梁邦勇,李涓子,等.语义Web中的本体自动映射[J].计算机学报,2006(11):1956-1976.
[4]FRIDMAN N,MUSEN M A.Prompt:algorithm and tool for automated ontology merging and alignment[C].Austin:Proceedings of Seventeenth National Conference on Artificial Intelligence(AAAI-2000),2000.