Federal learning model training method and device, and electronic equipment

Abstract

The invention provides a federal learning model training method and device, and electronic equipment. The training method comprises the steps of acquiring enterprise portraits and feature information of multiple enterprises on a data providing end; based on the enterprise portrait and the feature information, cooperating with other data providers to perform federated training of the model so as to obtain model intermediate results of respective local learning models; sending the model intermediate result to a third-party platform to be summarized, and receiving a global model intermediate result sent by the third-party platform; and based on the global model intermediate result, adjusting model parameters of the local learning model to continue federated training of the model to generate a target federated learning model which is used for predicting the credit investigation state of the enterprise. Therefore, according to the method, federated learning can be applied to acquisition of the enterprise credit investigation state, federated training of the model is carried out through enterprise portraits and feature information of multiple data providing ends, and the accuracy of the obtained target federated learning model is better.

Description

technical field [0001] The present application relates to the technical field of deep learning, and in particular to a training method, device, electronic device and storage medium of a federated learning model. Background technique [0002] At present, when an enterprise wants to apply for a loan, financial institutions or government agencies often need to evaluate the credit status of the enterprise. If the credit status is good, the capital risk of allowing the enterprise to apply for a loan is relatively low. However, at present, it is impossible to accurately and quickly assess the credit status of enterprises, and the loan business processing process is relatively cumbersome, which is not conducive to the operation of enterprises and the precise implementation of enterprise assistance policies. Contents of the invention [0003] This application aims to solve one of the technical problems in the related art at least to a certain extent. [0004] For this reason, th...

AI Technical Summary

Problems solved by technology

However, at present, it is impossible to accurately and quickly assess the credit status of the enterprise, and the loan business process is relatively cumbersome, which is not conducive to the operation of the enterprise, and is also not conducive to the accurate implementation of the enterprise assistance policy

Images