Federation learning development method, device and equipment and storage medium

Abstract

The invention relates to the field of financial science and technology, and discloses a federation learning development method, device and equipment and a storage medium, and the method comprises thesteps: determining a plurality of participants in an industrial development demand if the industrial development demand is detected, and determining a first evaluation model and a preset evaluation condition according to the industrial development demand, wherein different industrial development requirements correspond to different first evaluation models and different preset evaluation conditions; generating a random number of each participant according to the plurality of participants, and performing fusion evaluation processing on the first evaluation model based on the local data of each participant and the random number to obtain a fusion evaluation value; and according to the preset evaluation condition and the fusion evaluation value, performing federated learning training on the first evaluation model to obtain a second evaluation model. According to the method, the development process of the transverse federated learning algorithm is simplified, the algorithm development workload is reduced, and the algorithm development efficiency is improved.

Description

technical field [0001] The present invention relates to the technical field of financial technology, in particular to a federated learning development method, device, equipment and storage medium. Background technique [0002] With the development of computer technology, more and more technologies (big data, distributed, blockchain, artificial intelligence, etc.) The industry's security and real-time requirements also put forward higher requirements for technology. [0003] Developing a horizontal federated learning algorithm that can be applied to the actual production environment requires a lot of development resources, and the development of different algorithms also requires a lot of development costs. Each algorithm has its own corresponding development process, which makes developers need to carry out separate development for each algorithm. Custom development, its development process is cumbersome and complicated, and each development process cannot be applied to oth...

AI Technical Summary

Problems solved by technology

[0003] Developing a horizontal federated learning algorithm that can be applied to the actual production environment requires a lot of development resources, and the development of different algorithms also requires a lot of development costs. Each algorithm has its own corresponding development process, which makes developers need to carry out separate development for each algorithm. Custom development, its development process is cumbersome and complicated, and each development process cannot be applied to other development processes. The lack of scalability and flexibility makes the development process too cumbersome and lengthy, greatly increasing the workload of algorithm development and reducing the efficiency of algorithm development

Images