基于动态时间的个性化推荐模型

在推荐系统中，往往会存在数据的非实时性、稀疏性和冷启动性等问题，文中通过引入遗忘曲线来跟踪用户对资源偏好程度随时间变化情况，利用提出一种改进的K-Means聚类算法对用户集进行聚类，根据改进的个性化推荐算法对用户进行推荐，建立了一种基于动态时间的个性化推荐模型. 通过实验验证，文中提出的个性化推荐模型能够获取准确的用户偏好信息，并缓解冷启动问题，降低算法计算的时间空间复杂度，提高个性化推荐算法的推荐质量.

Personalized Recommendation Model Based on Dynamic Time

In the recommendation systems, it often exists some problems of non-real-time data, sparse data and cold start. First, the paper uses forgetting curve to track the changed of user’s interests with time, and then puts forward an improved K-Means clustering algorithm to cluster users, and finally uses the improved personalized recommendation algorithm. A model of personalized recommendation based on dynamic time is built. The experimental results show that the proposed personalized recommendation model can get more accurate recommendation performance and alleviate the cold start problem. It also can reduce the computing time and space complexity, and improve the quality of the recommendation of personalized recommendation algorithm.