基于网络内容和结构数据的用户浏览模型

Web推荐系统能为用户提供有针对性的个性化服务。但目前基于协同过滤和使用挖掘的推荐系统存在着诸如数据信息的不完整或不正确，推荐精度和质量不高等问题。为提高推荐系统的性能，必须将站点的内容和结构信息以及用户行为数据集成形成混合模式推荐系统，在推荐引擎里统一使用。基于此，本文提出一种新型Web推荐系统框架，能够将站点的内容，结构和用户的浏览行为综合考虑形成用户浏览模型，通过用户模型向用户推荐资源，初步实验表明该模型能有效改善推荐系统的性能。

A User Navigational Model Based on Web Content and Structure Data

Web recommender system can provide different users with different services.However,there are some problems existing in systems based on collaborative filtering and web usage mining,such as incomplete or incorrect information,recommendation imprecision,quality drop,etc.For more effective personalization,usage,content and structure,site data must be integrated into a hybrid recommender system. The authors present a novel web recommender system framework,which combines usage data,content data, and structure data on a web site to generate user navigational models.These models are then fed back into the system to recommend users resources.Preliminary experiments show that this system can significantly improve the quality of web site recommendation.