一种可信的基于协同过滤的服务选择模型

摘要

针对目前服务选择方法中基于QoS的服务选择方法较少考虑服务请求者自身的个性属性特征和基于协同过滤的服务选择方法未能考虑服务推荐者可信程度的问题,该文将协同过滤技术与信任度量方法进行有机结合,根据服务请求者的个性属性特征对服务选择过程的影响,引入用户(服务请求者)相关性,并计算推荐可信度,利用层次分析法确定服务信誉值中各因子的权重,提出了一种可信的基于协同过滤的服务选择模型.仿真实验表明该模型不仅提高了服务选择的效率,还能有效避免服务推荐者的恶意攻击.%Current Quality of Service (QoS)-based service selection approaches pay little attention to personal properties and characteristics of service requesters.However,Collaborative Filtering (CF)-based service selection approaches fail to consider the trustworthiness of recommenders and can not resist malicious feedback from recommenders.This paper introduces user correlation to embody the impact of personal characteristics of service requesters on selection process,computes creditability of recommendation,and employs analytic hierarchy process to decide the weight of each factor in service reputation.With the integration of trust evaluation methods and CF techniques,a Trustworthy Services Selection Model based on Collaborative Filtering (TSSMCF) is presented.Simulation experiments demonstrate that TSSMCF model can not only improve the efficiency of service selection but also effectively avoid malicious attack from service recommenders.