Data sharing method, computer equipment applying same and readable storage medium

Abstract

The invention discloses a data sharing method, computer equipment applying the same and a readable storage medium, and belongs to the technical field of data information security. According to the method, a blockchain technology and a federated learning technology are combined, a data security sharing model based on the blockchain and federated learning is constructed, and a data sharing basic process is designed; a working node selection algorithm based on a block chain and node working quality is designed by taking reliable federated learning as a target; a consensus method of a block chainis modified, an excitation mechanism consensus algorithm based on model training quality is designed, and the purposes of encouraging excellent work nodes to work, simplifying the consensus process and reducing the consensus cost are achieved. The differential privacy algorithm suitable for federated learning is selected by taking balance data security and model practicability as targets. According to the invention, the problem of privacy leakage in a data sharing process can be solved; the blockchain technology is combined into data sharing, so that the security and credibility of data are guaranteed; meanwhile, the efficiency of federated learning tasks is improved.

Description

technical field [0001] The invention relates to a data sharing method, computer equipment and a readable storage medium using the same, and belongs to the technical field of data information security. Background technique [0002] With the popularization of smart devices in social life, such as smart factories, smart cities, and smart homes, users' privacy is becoming more and more transparent. In order to strengthen the protection of users' personal information, realize data cooperation and sharing between platforms in these individual domains, and avoid the common disadvantages of high cost, high delay, and low efficiency in centralized platforms, it is necessary to design a safe and reliable data sharing mechanism. [0003] Existing technical solution 1: Patent No. 201910720373.9 "A hybrid federated learning method and architecture" patent, the present invention discloses a hybrid federated learning method and architecture, which is suitable for federated learning model ...

AI Technical Summary

Problems solved by technology

[0009] In view of the defects of the existing technology, the purpose of the present invention is to provide a method that can solve the problem of privacy leakage in the process of data sharing; combine blockchain technology into data sharing to ensure the security and credibility of data; use federated learning to ensure In data sharing, the user's original data is not disseminated, but only model parameters are disseminated to protect user privacy; at the same time, it solves the problem of selecting working nodes that meet the set rules in the federated learning process; further, differential privacy protection and design Consensus incentive mechanism to encourage the active participation of each working node; by solving the above problems to ensure the security of user privacy information in the process of data sharing, and at the same time will improve the efficiency of federated learning task data sharing methods and the computer equipment and readable storage media for which it is applied

Images