中文摘要：

协作过滤算法作为最成功的个性化推荐技术已经被应用到很多领域中．算法产生的预测值通常是一个小数，还需要判定为对应到某个评分级别的整数．传统的算法按照“四舍五入”原则产生判定值，考虑过于简单，忽略了用户的评分趋势．针对这个问题，提出了基于用户评分趋势的预测值判定算法．该算法综合考虑预测值与评分级别之间的偏离，以及用户的评分趋势，再对预测值进行判定．实验表明，改进后的协作过滤算法在推荐效果方面得到了更好的改善．

英文摘要：

Collaborative filtering is the most successful personalized recommendation technology, and is extensively used in many fields. The predict value produced by collaborative filtering algorithm is always a decimal fraction, and needs to be judged as an integer correspond to some grade. However, existing collaborative filtering algorithms round predict value and get the judgment value simply without consideration of user＇s grade trend. To solve this problem, the paper describes a judgment algorithm for predict value based on user＇s grade trend. The algorithm considers both the distance between predict value and grade value, and user＇s grade trend, and then makes the decision. Experimental results show that our proposed algorithm outperforms traditional collaborative filtering algorithm.