Model training method and device, text classification method, computer equipment and medium

Abstract

The invention relates to the field of artificial intelligence and model construction, and by uploading model parameters of a local classification model and a local classification result to a federatedlearning server for joint learning, the security of text data in a model training process can be improved. The invention relates to a text classification model training method and device, a text classification method, computer equipment and a medium, and the training method comprises the steps: obtaining a text training set, and carrying out text classification training on a local classificationmodel according to the text training set; encrypting the model parameters of the trained local classification model and the local classification result, and uploading the encrypted model parameters and local classification result to a federated learning server for joint learning to obtain learning parameters; and receiving the learning parameters sent by the federated learning server, updating thetrained local classification model according to the learning parameters, and taking the updated local classification model as a trained text classification model. In addition, the invention also relates to a blockchain technology, and the text training set can be stored in the blockchain.

Description

technical field [0001] The present application relates to the field of artificial intelligence, and in particular to a text classification model training method, text classification method, device, computer equipment and media. Background technique [0002] With the rapid development of the Internet and the advent of the era of big data, text mining technologies such as text classification are applied in more and more fields. Existing text classification technologies generally realize the classification processing of a large amount of semi-structured and unstructured text data through a trained text classification model. In the process of training the text classification model, a large amount of text data from different clients needs to be used. In actual business scenarios, user privacy is involved in a lot of text data, but the existing text classification models cannot achieve data isolation and avoid data leakage, and cannot guarantee the security of text data. [0003...

AI Technical Summary

Problems solved by technology

In actual business scenarios, user privacy is involved in many text data, but the existing text classification model cannot achieve data isolation and avoid data leakage, and cannot guarantee the security of text data

Images