Data label distribution determination method and device, computer equipment and storage medium

Abstract

The invention relates to a data label distribution determination method and device, computer equipment and a storage medium. The method comprises the steps of obtaining label ciphertext information sent by a label party device after performing homomorphic encryption processing on sample labels corresponding to a plurality of sample identifiers; obtaining initial binning information corresponding to the sample feature set, wherein the sample feature set comprises sample features corresponding to the multiple sample identifiers, and the initial binning information comprises initial binning corresponding to the sample features; obtaining initial ciphertext statistical information corresponding to each initial sub-box based on the label ciphertext information and the initial sub-box information; performing confusion processing on the initial ciphertext statistical information to obtain a target ciphertext statistical information sequence; and obtaining a target decryption statistical information sequence returned by the label side equipment after homomorphic decryption processing is carried out on the target ciphertext statistical information sequence, and carrying out restoration processing on the target decryption statistical information sequence to obtain initial label distribution information corresponding to each initial sub-box. By adopting the method, the data interaction security can be improved.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to a method, device, computer equipment and storage medium for determining data tag distribution. Background technique [0002] With the development of computer technology, the data that can be transmitted and stored on the network is increasing day by day. Different departments of different companies usually store and maintain different data. For example, department A stores the labels of samples, and department B stores the characteristics of samples. [0003] Based on business needs, different departments of different companies sometimes need to interact with each other to conduct data analysis. For example, department B can use the tag data of department A to determine the distribution of local sample tags. However, holders who store and maintain different data usually maintain their own data independently. Direct data interaction is not conducive to maintaining the...

AI Technical Summary

Problems solved by technology

However, holders who store and maintain different data usually maintain their own data independently. Direct data interaction is not conducive to maintaining the data privacy of both parties, which will lead to data leakage and pose certain security risks.

Images