Data Integrity Assessment Method Based on Data Dependence

摘要

Data integrity assessment measures the integrity of the data set to provide the basis for the selection, optimization and evaluation of relevant algorithms. This paper proposes that the integrity can be evaluated on the processed data set after using data dependence, and the result is sufficient to express the true integrity of the data set. This paper also puts forward the data integrity evaluation index based on data dependence, and gives the index definition, evaluation method and practical application, realizing evaluating the integrity of the overall data set from multiple dimensions. Finally, the applicability of large-scale data of the evaluation method and the accuracy of the method for evaluating attribute value integrity are verified by experiments.