异构物联网中关联数据一致性规则挖掘模型

Mining Model of Association Data Consistency Rules in Heterogeneous Internet of Things

数据一致性规则属于数据质量管理的核心规则。因此,以高效、准确挖掘为目的,研究了面向异构物联网,构建了一种关联数据一致性规则挖掘模型。先通过多维数据聚类去除异构物联网中的重复数据,以此来减少后续关联数据一致性规则挖掘过程的耗时;基于内容相关的条件函数依赖关系建立挖掘模型,并将清理后数据导入中,对其中的一致性规则展开挖掘。经仿真测试可知,针对3种不同数据量的异构物联网数据,上述模型对在挖掘其一致性规则时的效率与准确性均较高,挖掘耗时最大值仅为1.27s,规则挖掘结果与实际规则数量一致,充分证明了上述模型的高效性。

For mining the association data in heterogeneous Internet of things efficiently and accurately,a consistency rule mining model of association data based on Internet of things was studied.Multidimensional data clustering was applied to delete duplicate data in heterogeneous Internet of things,in order to reduce the time-consuming process of subsequent association data consistency rule mining.Through the dependency of content related conditional function,the mining model was founded.The cleaned data waswere imported into the model,and the consistency rules were mined.According to the simulation test,the above model has high efficiency and accuracy in mining its consistency rules for three heterogeneous Internet of Things data with different data volumes.The maximum mining time is only 1.27s.The rule mining results are consistent with the actual number of rules,which fully proves the efficiency of the above model.The simulation results show that the model has high efficiency(low time consumption,1.27s)and accuracy,and the rule mining results accord with the actual number of rules,which shows that the model is efficient.