DATA AGGREGATION METHOD FOR MULTIPLE DATA SETS

摘要

A data aggregation method for multiple data sets, comprising: respectively extracting a feature value corresponding to a common behavior property of each behavior record in a first data set and a second data set to form a set of a first feature values and a set of a second feature values (S10); comparing the set of the first feature values with the set of the second feature values to determine a first correspondence between each behavior record in the first data set and each behavior record in the second data set (S11); based on the first correspondence, determining a second correspondence between each behavior subject in the first data set and each behavior subject in the second data set (S12). The method can accurately realize data aggregation between data sets with no common unique identifier and can be carried out simply and reliably so as to facilitate popularization and application in the industry.