Method, apparatus and system for performing machine learning by employing to-be-exchanged data

Abstract

The invention provides a method, apparatus and system for performing machine learning by employing to-be-exchanged data. The apparatus comprises a primary encryption data reception unit configured toreceive first primary encryption result data from a first data provider and receive second primary encryption result data from a second data provider; a primary encryption data transmission unit configured to transmit the first primary encryption result data to the second data provider and transmit the second primary encryption result data to the first data provider; a secondary encryption data reception unit configured to receive second secondary encryption result data from the first data provider and receive first secondary encryption result data from the second data provider; and a machinelearning execution unit configured to obtain a machine learning sample and perform machine learning based on the machine learning sample. According to the apparatus, machine learning can be performedby safely and reliably employing external data.

Description

technical field [0001] Exemplary embodiments of the present invention generally relate to the field of machine learning for artificial intelligence, and in particular, relate to a method, device and system for performing machine learning using data to be exchanged. Background technique [0002] With the development of technologies such as big data, cloud computing and artificial intelligence, machine learning is widely used to mine useful information hidden in massive data. [0003] In order to apply machine learning, it is usually necessary to learn a model function consisting of features and its parameters from a given training data set. When new data arrives, this model can be applied to the new data. In order to better learn or apply the model, data from various aspects are often required to participate in the process of the model, such as training, testing or estimation, and these data can be purchased from corresponding data providers or obtained in other ways. For ex...

AI Technical Summary

Problems solved by technology

However, it should be noted that during the exchange of the above-mentioned encrypted data, it is easy to leak the user's private information or other information that is not suitable for disclosure due to the collusion between a third party and a certain data provider, and the exchanged data It is easy to be reused or sold without authorization, and it is difficult to technically guarantee the legal use of data

F

Images