Data processing method and device and storage medium

Abstract

The invention discloses a data processing method. The method comprises the following steps: acquiring a first modulo result determined according to the rotation of first original data corresponding to other clients; determining a second modulo result according to the rotation degree of second original data corresponding to the second modulo result; determining a first target rotation corresponding to the first modulo result and a second target rotation corresponding to the second modulo result according to the first modulo result and the second modulo result; and inputting the first target rotation and the second target rotation into a preset model as input data to obtain a training result obtained after the preset model is trained based on the input data. The invention further discloses a data processing device and a storage medium. According to the method and the device, the data is converted into the corresponding rotation degree, training is carried out according to the rotation degree, desensitization processing does not need to be carried out on the data, and the problems that data loss is caused by data desensitization and the training result is inaccurate when the lost data is trained are solved.

Description

technical field [0001] The present invention relates to the technical field of information processing, and in particular, to a data processing method, device and storage medium. Background technique [0002] At present, traditional machine learning methods need to centralize all data in one place, such as a data center, and then train machine learning models. However, for some sensitive data, this centralized data-based approach will seriously infringe on user privacy and Data Security. In order to prevent the above-mentioned private data or sensitive data from being leaked, the uploaded data is usually desensitized, such as random value substitution desensitization or special character substitution desensitization. However, the uploaded data is desensitized because the data itself has Meaning, according to the traditional method of replacing desensitization with random values ​​or replacing desensitization with special characters, the data itself will be changed, so that p...

AI Technical Summary

Problems solved by technology

[0004] The main purpose of the present invention is to provide a data processing method, device and storage medium, aiming to solve the problem that desensitization of data can easily lead to data loss, and the training result after training the lost data is inaccurate.

Images