用户兴趣模型是个性化推荐技术的基础与核心,针对现有用户兴趣模型在模型建立阶段用户兴趣评价的不足,提出了一种基于混合行为评价兴趣度值的方法。突出了用户阅读时间的特殊性,在用户阅读时间异常的情况下利用其他浏览行为来量化用户兴趣度,并结合用户的浏览内容提出了用户兴趣模型的表示和更新机制,从而建立用户兴趣模型。实验验证了兴趣度度量方法的有效性,将测试结果与 K-means 聚类模型进行比较,证明该模型的推荐准确度有明显提高。%User interest model is the basic and core component in personalized recommendation.Aiming at the deficiency of the evaluation of the user’s interest when building user interest model,this paper brought out a quantification method of inte-rest rate based on hybrid behaviors,which highlighted the specificity of page browsing time and evaluated interest rate based on other browsing behaviors in the case of abnormal page browsing time,and combined with the contents the user had browsed to present the representation and update mechanism for user interest model.Then this paper proposed the user interest model . The experimental results show that this model can recommend personalized information with a higher rate of accuracy compared with the model based on K-means clustering.
展开▼