基于不确定理论的不确定性数据Top-k查询计算  

Top-k Query Calculation of Uncertain Data Based on Uncertainty Theory

作　　者：郭长友[1,2] 郑雪峰[1] 高秀莲[2] 

机构地区：[1]北京科技大学计算机与通信工程学院,北京100083 [2]德州学院,德州253000

出　　处：《计算机科学》2016年第3期225-230,共6页Computer Science

基　　金：国家自然科学基金(61163025;61370063);北京市重点实验室2012年度阶梯计划项目(Z121101002812005)资助

摘　　要：在不确定性数据集中,基于参数化排名函数的Top-k查询研究近年来备受关注。给出了一种新的解决方法,该方法将不确定性数据集中的元组建模为不确定网络,将有序元组的Top-k查询等价转化为相应样本图中边的不确定测度关系,并对样本图依据所包含边的排序位置进行分类,从而将不确定性数据中基于参数化排名函数的Top-k查询等价转换为依Top-k值不同的有限查询。本算法避免了计算所有元组在样本图中的排名不确定测度值,提高了不确定图的Top-k查询计算效率。理论分析和实验结果表明,提出的Top-k查询算法能够从非确定角度解决不确定性数据的Top-k查询计算问题。The Top-k query in the uncertain data set based on parametric ranking function has been focused in recent years.This paper gave out a new solution.The tuples of uncertain data set is modeled as uncertain network,Top-k query of the orderly tuples is transformed equivalently into uncertain measure relations of edges in corresponding sample figures,and the sample figures are classified according the ranking position of edge contained in them.So the Top-k query in the uncertain data set based on parametric ranking function is transformed equivalently into different limited query with different Top-k value.The proposed algorithm avoids calculating the ranking uncertain measure values of all tuples in the sample figures,and improves the computation efficiency of Top-k query in uncertain figure.Theoretical analysis and experimental results show that the proposed Top-k query algorithm can solve Top-k query calculation of uncertain data from the uncertainty perspective.

关 键 词：不确定网络 不确定测度 样本图指数 TOP-K查询 

分 类 号：TP309.5[自动化与计算机技术—计算机系统结构]