如何为用户提供更为满意的、符合其个性化的信息过滤,已成为一个重要的研究课题。针对这一情况,本文提出了一个基于隐式反馈的个性化信息过滤的设计思路和实现方法即通过观察用户与系统交互的动作学习用户的兴趣,根据用户兴趣帮助用户过滤掉那些他不感兴趣的信息。并对其涉及的关键技术用户兴趣建模,文档的表示和信息的过滤等方面进行了详细描述,并对当前存在的问题进行了探讨。 How to provide users with more satisfied, personalized information filtering, has become an important research topic. In view of this situation, this paper presents a design idea and implementation method of personalized information filtering based on implicit feedback that learns users’ interests by observing the interaction between users and the system, and helps users filter out those users that are not interested according to their interests information. It also describes in detail the modeling of key user interests, the representation of documents and the filtering of information. The existing problems are also discussed.