中文摘要：

由于网络知识资源的异构性，知识融合系统需要对多源数据、信息进行集成与整合并消除歧义。在知识融合过程中，由于知识科学的复杂性和模糊性，需要对多源知识的不一致、不完整等不确定性问题进行处理。基于此，提出了一种基于置信度理论的网络知识融合系统模型，弥补了传统知识融合系统在不确定性处理上的不足，并使用反馈自适应机制自动校正置信度因子以避免初始置信度设置的主观性。针对互联网药品违规主体追查问题，解决了主体融合过程中信息冗余和矛盾，为互联网药品监管部门提供了有效可靠的药品主体信息。

英文摘要：

As a result of heterogeneity of network knowledge resources, knowledge fusion systems have to integrate and combine the multi-source data and information and reduce the ambiguity. Inconsistency and incompleteness leads to uncertainty in the knowledge fusion procedure due to complexity and ambiguity of the knowledge science. A web knowledge fusion system based on certainty factor theory is proposed, making up the defect on uncertainty processing of traditional knowledge systems. The subjectivity of the initial setup of the certainty factor is reduced by the feedback and self-adaption mechanism. The system is then applied to the online drug subject tracking problem, which solves the redundancy and contradiction in the drug subject fusion procedure and provides reliable drug subject information for the online drug supervisory board.