标签推荐Top-N列表优化算法  

TOP-N LIST OPTIMIZATION ALGORITHM FOR TAG RECOMMENDATION

作　　者：朱小兵 丁明玉 肖玉 Zhu Xiaobin;Ding Mingyu;Xiao Yu(Information Center,Sailun Group Co.,Ltd.,Qingdao 266400,Shandong,China)

机构地区：[1]赛轮集团股份有限公司信息中心,山东青岛266400

出　　处：《计算机应用与软件》2022年第11期281-287,共7页Computer Applications and Software

摘　　要：针对标签推荐算法推荐列表长度常为固定值,进而导致推荐精度下降的问题,提出一种优化标签推荐算法Top-N推荐列表长度的算法。该算法对Top-N推荐列表进行重排序;再对排序以后的Top-N标签推荐列表进行列表长度的优化,进而计算出最优的标签推荐列表长度。在多个真实数据集之上进行了多次对比实验,结果表明,标签Top-N推荐列表优化算法具有较好的推荐性能。Aiming at the problem that the recommended list length of the tag recommendation algorithm is often fixed,which leads to the decrease of the recommendation accuracy,an algorithm is proposed to optimize the recommended list length of the tag recommendation algorithm Top-N.This algorithm reordered the recommended list of the Top-N.Then optimized the length of the Top-N tag recommendation list after sorting,and then calculated the optimal tag recommendation list length.A number of comparison experiments were conducted on several real data sets.The results show that the proposed algorithm has good recommendation performance.

关 键 词：标签推荐 Top-N列表 标签推荐系统 列表优化 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]