Abstract: Aiming at the trust missing problem in mobile commerce and uncertain information in many practical situations, and recommender cannot easily express his/her judgment on the evaluation information, a multi-dimension heterogeneous recommended trust evaluation model is proposed. In this model, the conversion between heterogeneous evaluation information and intuitionistic fuzzy information is implemented for describing the subjective and fuzziness of the ratings. To overcome the double uncertainty from recommender’s subjective judgment of the weights of attributes, an entropy method is developed based on the original evaluation information. Considering the familiarity with the evaluation areas of recommender, the comprehensive trust intuitionistic fuzzy number(TIFN)of entity is obtained by using the confidence intuitionistic fuzzy aggregate operator. An example about trust evaluation problem of mobile commerce supplier is given to verify the practicality and effectiveness of the proposed model.

Key words: mobile commerce, multi-dimension heterogeneous, recommended trust evaluation model, intuitive fuzzy number, confidence

摘要： 针对移动商务环境下供应商信任缺失问题,建立了一种多维异质推荐信任评估模型。该模型实现了多种异质评价信息与直觉模糊信息的转换,较全面、细腻刻画了评价信息的主观性和模糊性。为了避免推荐者和信任属性的主观赋权带来的二次不确定性,给出了基于原始异质评价信息的熵权法。考虑到推荐者的相关领域熟悉程度,利用信心直觉模糊集成算子计算综合信任直觉模糊数,并依据相对接近度进行信任决策。最后,通过一个移动商务供应商的信任评估实例验证该模型的有效性和合理性。

关键词: 移动商务环境, 多维异质, 推荐信任模型, 直觉模糊数, 信心