高级检索

    基于Kendall tau距离的在线服务信誉度量方法

    Online Service Reputation Measurement Method Based on Kendall tau Distance

    • 摘要: 用户偏好及评价准则不一致导致不同用户对同一服务的评分不可比较,基于评价准则一致性假定的信誉机制不能保证不同服务信誉间具有可比较性,从而用户利用这种信誉进行服务选择时会产生不客观的结果.为此提出一种基于Kendall tau距离的在线服务信誉度量方法.该方法首先定义距离指标以衡量2个评分向量之间的一致性,然后将在线服务信誉度量建模为寻找一个与用户〖CD*2〗服务评分矩阵距离最小的信誉向量的最优化问题,最后采用模拟退火算法来求解该优化问题,将得到的信誉向量作为服务信誉.通过实验验证了该方法的合理性和有效性.实验结果表明:该方法能够满足大多数用户的偏好,从而使得用户可以参考该信誉结果做出正确的服务选择决策,并且方法在保证信誉度量效率的同时提高了信誉度量方法的抗操纵性.

       

      Abstract: Due to the inconsistent user preferences and the inconsistent rating criteria, the ratings given by different users to one service are actually incomparable, and the reputation mechanism based on assumption of the consistent rating criteria cannot guarantee the comparability among different service reputations, which will result in unobjective outcome when the reputations are used to choose services. To improve the objectivity of online services reputation measurement under the circumstance referred above, this paper presents a method of online service reputation measurement based on Kendall tau distance. Firstly, a distance metric is defined to measure the consistency between the two rating vectors. Secondly, the measurement of online service reputation is modeled as an optimization problem to find a reputation vector that minimizes the Kendall tau distance between the reputation vector and the user-service rating matrix. Finally, simulated annealing algorithm is used to solve the optimization problem and the reputation vector is served as a service reputation. The rationality and effectiveness of the method have been verified by experimental study. The experiments show that the method can meet the preferences of most users, so that users can make right services choice decision, and ensure the efficiency while improving the manipulation resistance ability of the reputation measurement method.

       

    /

    返回文章
    返回