通过自适应的方式构建超级节点,完成对网络的逻辑划分以及推荐信任度的传递,避免了网络瓶颈的出现。
The outcome of neck in network is avoided by constructing super node, partitioning the network logically and transmitting the trust value in adaptive mode.
提出一种基于信任机制的协同过滤推荐算法,其中,直接信任度基于共同评价项目得出,推荐信任度通过对项目的预测得出。
This paper proposes a collaborative filtering recommendation algorithm based on trust mechanism. Direct trust is based on common rating data and indirect trust is based on the predict data.
此外,考虑到节点推荐信任度受多个因素的影响,我们引入了正态分布概率密度函数来对节点推荐信任度的分布作进一步分析。
Besides, considering the fact that peer's recommended trust is affected by many factors, we introduce normal probability density function to analyze the stability of the peer's trustworthiness.
应用推荐