开放多Agent系统的一个信任信誉系统模型

A Trust and Reputation System Model for Open Multi-Agent System

信任和信誉对于开放多Agent系统的有效交互是十分重要的.FIRE模型是最近提出的适用于开放环境下问题求解的信任信誉系统模型中的一种,在该模型中没有考虑消费者的个性特征,从而使得消费者给出的评分仅直接反映了提供者的服务质量,这就减弱了该模型的实用价值.提出了扩展模型E-FIRE,引入了消费者的个性特征.其个性特征包括两个方面:消费者对服务质量的预期和消费者采取的态度.这两方面共同影响消费者对待同一服务的评分.因此,消费者的评分不再只反映提供者的服务质量,这样使得该模型更加符合实际情况.同时,在消费者为选择提供者而计算提供者的综合信任评分时,更多地依靠提供证据的消费者对提供者的直接信任,从而减少了Agent间的通信量.实验结果表明,在交互次数较少时,E-FIRE模型的性能与FIRE模型的性能相当;随着交互次数的增多,E-FIRE模型的性能更优.

Trust and reputation are important to effective interactions in open multi-agent system. The FIRE model, which was designed for solving problems in open environment, was a most recent one. However, consumer＇s personal characteristics were not considered in this model, and so the ratings given by consumers just directly reflected the performance of providers. This has weakened the usability of this model. An extended FIRE model is proposed in this paper, in which some personal characteristics are introduced for the consumers. The personal characteristics include two aspects： the expected service quality assumed by the consumers and the attitudes taken by the consumers. Both can affect the consumers＇ ratings of the same service. As a result, the ratings given by consumers do not directly reflect the performance of the providers any more, and this makes the model closer to the reality. At the same time, when a consumer computes the trust ratings of the providers for selection purpose, the computation depends more on the interaction trust of the consumers providing evidences, and this reduces the effort of the communication between agents. The computational results show that the E-FIRE is comparable with the FIRE when fewer interactions are needed, and it is better when more interactions are needed.