《计算机应用研究》|Application Research of Computers

基于综合赋权的包推荐查询松弛方法

Query relaxation approach for package recommendation based on synthetic weighting

免费全文下载 (已被下载 次)  
获取PDF全文
作者 张东伟,王曦杨
机构 南京邮电大学 计算机学院,南京 210003
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2018)03-0835-04
DOI 10.3969/j.issn.1001-3695.2018.03.040
摘要 针对包推荐系统的推荐结果用户满意度较低的问题,提出一种基于综合赋权的包推荐查询松弛方法。该方法引入改进的熵权法,综合考虑用户的主观意图和客观情况,计算属性权重;根据初始查询返回结果情况,计算松弛阈值;并利用不同属性值域大小情况下数据相似性不同的原理以及隶属度方法,确定数值型属性相似性,计算松弛区间。实验结果表明,所提出方法的权重评估结果合理;在多个不同类型的查询条件下,所提方法在未增加额外时间开销基础上,相较于QRRR方法效用提升更加明显,验证了该方法的有效性。
关键词 包推荐;熵权法;查询松弛;属性权重;综合赋权
基金项目
本文URL http://www.arocmag.com/article/01-2018-03-040.html
英文标题 Query relaxation approach for package recommendation based on synthetic weighting
作者英文名 Zhang Dongwei, Wang Xiyang
机构英文名 CollegeofComputer,NanjingUniversityofPosts&Telecommunications,Nanjing210003,China
英文摘要 In order to improve the customer satisfaction in package recommendation system, this paper proposed a query relaxation approach based on synthetic weighting for package recommendation. The approach introduced an improved entropy weight method for computing attribute weights, which considered both user’s subjective intention and objective conditions. To determine degree of relaxation, it computed relaxation threshold according to the result of initial query. And to ensure the rationality of the relaxation degree, the approach calculated relaxation interval by using two principles, different data similarity in different value domain and membership degree method. Experimental results show that the weight evaluation results of the proposed approach is reasonable. Compared with QRRR method, the proposed approach’s utility improvement is increased more obviously, which verifies the effectiveness of the proposed method.
英文关键词 package recommendation; entropy weight method; query relaxation; attribute weight; synthetic weighting
参考文献 查看稿件参考文献
  [1] Lappas T, Liu Kun, Terzi E. Finding a team of experts in social networks[C] //Proc of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York:ACM Press, 2009:467-476.
[2] Liu Qi, Chen Enhong, Xiong Hui, et al. A cocktail approach for travel package recommendation[J] . IEEE Trans on Knowledge and Data Engineering, 2014, 26(2):278-293.
[3] Parameswaran A, Venetis P, Garcia-Molina H. Recommendation systems with complex constraints:a course recommendation perspective[J] . ACM Trans on Information Systems, 2011, 29(4):1-13.
[4] Brucato M, Ramakrishna R, Abouzied A, et al. PackageBuilder:from tuples to packages[J] . Proceedings of the VLDB Endowment, 2014, 7(13):1593-1596.
[5] Kantere V. Approximate queries on big heterogeneous data[C] //Proc of IEEE International Congress on Big Data. 2015:712-715.
[6] Muslea I, Lee T J. Online query relaxation via Bayesian causal structures discovery[C] //Proc of the 20th National Conference on Artificial Intelligence. 2005:831-836.
[7] Nambiar U, Kambhampati S. Answering imprecise queries over autonomous Web databases[C] //Proc of the 22nd International Confe-rence on Data Engineering. Washington DC:IEEE Computer Society, 2006:45.
[8] Nambiar U, Kambhampati S. Mining approximate functional depen-dencies and concept similarities to answer imprecise queries[C] //Proc of the 7th International Workshop on the Web and Databases:Colocated with ACM SIGMOD/PODS. New York:ACM Press, 2004:73-78.
[9] 申德荣, 马也, 聂铁铮, 等. 一种应用于 Deep Web 数据集成系统中的查询松弛策略[J] . 计算机研究与发展, 2010, 47(1):88-95.
[10] Deng Ting, Fan Wenfei, Geerts F. On the complexity of package recommendation problems[J] . SIAM Journal on Computing, 2013, 42(5):1940-1986.
[11] Brucato M, Abouzied A, Meliou A. Improving package recommendations through query relaxation[C] //Proc of the 1st International Workshop on Bringing the Value of Big Data to Users. New York:ACM Press, 2014:13.
[12] 孟祥福, 严丽, 马宗民, 等. 基于语义相似度的数据库自适应查询松弛方法[J] . 计算机学报, 2011, 34(5):812-824.
[13] Shan Jing, Shen Derong, Nie Tiezheng, et al. An effective and high-quality query relaxation solution on the Deep Web[C] //Proc of the 12th International Asia-Pacific Conference on Web. Washington DC:IEEE Computer Society, 2010:68-74.
[14] Mottin D, Marascu A, Roy S B, et al. IQR:an interactive query relaxation system for the empty-answer problem[C] //Proc of ACM SIGMOD International Conference on Management of Data. New York:ACM Press, 2014:1095-1098.
[15] Mottin D, Marascu A, Roy S B, et al. A probabilistic optimization framework for the empty-answer problem[J] . Proceedings of the VLDB Endowment, 2013, 6(14):1762-1773.
[16] Vasilyeva E, Thiele M, Mocan A, et al. Relaxation of subgraph queries delivering empty results[C] //Proc of the 27th International Conference on Scientific and Statistical Database Management. New York:ACM Press, 2015.
[17] 欧阳森, 石怡理. 改进熵权法及其在电能质量评估中的应用[J] . 电力系统自动化, 2013, 37(21):156-159.
收稿日期 2016/11/8
修回日期 2016/12/15
页码 835-838,843
中图分类号 TP301.6
文献标志码 A