作者: Bo Zong , Feng Xu , Jun Jiao , Jian Lv
DOI: 10.1109/ICSMC.2009.5346098
关键词:
摘要: Due to the dynamic and anonymous nature of open environments, it is critically important for agents identify trustful cooperators which work consistently as they claim. In e-services e-commerce communities, trust reputation systems are applied broadly one kind decision support systems, aim cope with consistency problems caused by uncertain relationships. However, challenges still exist: on hand, we require more flexible computation models satisfy various personal requirements since in these communities heterogeneous; other calculate trustworthiness based agents' past behavior. The environments dynamic, records about behavior distributed so have search required through due their lack valid information. Thus, efficient, scalable effective information collection strategies address issues. this paper present a system challenges. We propose novel model artificial neural networks. With advantages ANN, our tunes parameters automatically adapt requirements. broker-assisting strategy clustering method. brokers, subcommunities managed mechanism an efficient way help members collect high quality. show performance simulation.