论文部分内容阅读
为了提高分布式网络中各节点信任评价的准确度,提出了一种基于个体经验的信任模型.该模型通过引入经验因子和相对经验因子的方法,建立了新的信任评价体系.这种新的信任评价体系考虑了个体节点的差异问题,在计算节点的信任值时考虑了节点间的交互历史,这在一定程度上解决了由于节点的非对称性而导致的信任评价不准确的问题.算法分析表明:新模型能够针对不同的个体节点,采用不同的最大容忍评价偏差,并且对个体节点的反馈可信度进行更新时,采用不同的更新值,体现了节点的个性化特征,使信任评价更加准确合理.此外,所提出的新算法能够运用到多种信任模型中,具有很好的可扩展性.
In order to improve the accuracy of trust evaluation of every node in distributed network, this paper proposes a trust model based on individual experience, which establishes a new trust evaluation system by introducing empirical factors and relative empirical factors The trust evaluation system considers the difference of individual nodes and considers the interaction history of nodes when calculating the trust value of nodes, which solves the problem of inaccurate trust evaluation due to the asymmetry of nodes. The analysis shows that the new model can apply different maximum tolerance evaluation bias to different individual nodes and adopt different update values when updating the feedback credibility of individual nodes, which reflects the personalized characteristics of nodes and makes the trust evaluation More accurate and reasonable.In addition, the proposed new algorithm can be applied to a variety of trust models, with good scalability.