Federal learning-based distributed language relationship identification method, system and device

Abstract

The invention belongs to the field of data identification, particularly relates to a distributed language relationship identification method, system and device based on federated learning, and aims tosolve the problem that a plurality of participants are difficult to perform joint modeling on the basis of not sharing data. The method comprises the steps that each local platform obtains to-be-recognized data and local training data with labels, a local classifier model is trained according to the local training data, the trained classifier models are integrated into a global classifier model,the local classifier model is initialized through the global classifier model, and to-be-identified data is identified by using the initialized local classification model to obtain a language relationship prediction result. According to the method, the local platform is combined with other platforms to perform data use and machine learning modeling on the basis of not sharing data, so that the training collaboration of the natural language recognition model is improved, the problem of data islands is solved, and the total amount and requirements of training data required for training the modelby each platform are reduced.

Description

technical field [0001] The invention belongs to the field of data identification, and in particular relates to a distributed language relationship identification method, system and device based on federated learning. Background technique [0002] In real life, most enterprises have the problem of small amount of data and poor data quality, which is not enough to support the realization of artificial intelligence technology; at the same time, domestic and foreign environments are gradually strengthening data protection, so data is free under the premise of security and compliance. Flow has become the general trend; from the perspective of users and enterprises, the data owned by commercial companies often has huge potential value. Two companies and even departments between companies must consider the exchange of interests. Often these institutions will not provide their private data to other companies. Even within the same company, data often appears in the form of isolated i...

AI Technical Summary

Problems solved by technology

[0003] In order to solve the above-mentioned problems in the prior art, how to realize the joint modeling of multiple participants on the basis of not sharing data, and break the data island to realize the problem of artificial intelligence cooperation, the present invention provides a distributed language based on federated learning A method for identifying a relationship, the method comprising:

Images