数据质量量化评价研究与实现

Research and implementation of quantitative evaluation of data quality

近年来,随着科学技术的飞速发展,信息化、数字化社会正在形成.伴随而来的是数据质量问题越来越凸显.本文在分析了当前数据质量评价标准的基础上,确定以GB/T 25000.24为基础构建数据质量评价模型,并对指标权重进行研究.相比使用单个权重计算方法,本文综合Delphi法、层次分析法和基于信息熵的熵权系数法计算综合权重,使得权重进一步客观.针对当层次分析法的判断矩阵经计算不满足一致性时,重新构造判断矩阵成本高的问题,文章引入了诱导矩阵修正法来修正判断矩阵以尽可能避免重新构造判断矩阵.最后本文开发了相应的数据质量评价系统,有效地提高了数据质量评价工作的质量和效率.

In recent years,with the rapid development of science and technology,informationization and digital features of the society have attracted more and more attention.Simultaneously,the data quality issues are becoming more and more prominent.Based on the analysis of current data quality evaluation standards,this paper determines the data quality evaluation model based on GB/T 25000.24 and studies the index weights.Compared with the single weight calculation method,the Delphi method,the analytic hierarchy process and the entropy weight coefficient method based on information entropy are integratedly used to calculate the comprehensive weight,which makes the weight more objective.Aiming at the problem that the judgment matrix of the analytic hierarchy process does not satisfy the consistency and the cost of reconstructing the judgment matrix is expensive,the paper introduces the induction matrix correction method to modify the judgment matrix to avoid reconstructing the judgment matrix as much as possible.Furtherly,the paper develops a corresponding data quality evaluation system,which effectively improves the quality and efficiency of data quality evaluation.