Abstract: The trust fraud in E-commerce market has restricted the rapid development of the O2O E-commerce. This paper proposes a value-based trust evaluation model for O2O E-commerce in order to balance the interests of three transactions partners. In this model, to compute the trust score of offline businesses and consumers, the belief factor is introduced to integrate the local reputation with the global reputation, and many factors are considered, such as transaction feedback, transaction time, transaction amount, the number of transactions, existing reputation value, reliability of transaction evaluation, through the integration of local and global reputations predict offline trust businesses and consumers. The experimental results show that the proposed trust model can effectively calculate the dynamic trust scores of offline businesses and consumers, and has the strong ability of against dishonest transactions, and can update the trust scores of O2O transactions partners in real time.

Key words: E-commerce, O2O, trust evaluation, trust score, composite services

摘要： 电子商务市场所面临的信用欺诈制约了O2O电子商务的快速发展。针对电子商务交易各方利益不平衡的问题，设计了一种面向价值的O2O电子商务信任预测模型。在该模型中，综合考虑了交易评价、交易时间、交易金额、交易次数、已有声誉值、评价的可信度等多种影响因素，利用置信因子对局部声誉和全局声誉进行整合，预测线下商家和消费者的信任度。实验证明，该信任模型能够有效计算线下商家和消费者的动态信任度，并对不诚信交易行为具有较强的防御能力，可实时更新O2O电子商务交易各方的信任度。

关键词: 电子商务, O2O, 信任预测, 信任度, 组合服务