Classification model training method, text classification method, medium, equipment and product

By combining the text classification model of the large language model and the activation function layer, using prompt text and statistical features for training, the problem of the inability to classify long text in the existing technology is solved, and efficient long text classification and output controllability are achieved.

CN119046691BActive Publication Date: 2025-03-25BEIJING VOLCANO ENGINE TECH CO LTD
1 Cites 0 Cited by

Patent Information

Application Number
CN202411525748.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-10-29
Publication Date
2025-03-25
Estimated Expiration
2044-10-29

AI Technical Summary

Technical Problem

Due to structural limitations, the existing text classification model cannot be applied to long text classification, and the output content of the large language model is uncontrollable, which affects the classification effect.

Method used

The text classification model including a large language model and activation function layer is adopted. The model is trained by using prompt text and text samples as input, and the pre-trained corpus and prompt word tuning is used, and feature fusion is combined with statistical features to improve the classification ability and output controllability of the model.

Benefits of technology

It realizes effective classification of long texts, captures the context characteristics of long distances, improves the classification effect, and ensures the stability and reliability of the model through controllable input and output.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

A classification model training method, a text classification method, a medium, a device and a product. The text classification model includes a first model and an activation function layer. The first model is a pre-trained large language model. The training method includes: obtaining a training sample set and a prompt text, wherein the training samples in the training sample set include text samples and classification labels corresponding to the text samples; the text classification model is trained by taking the prompt text and the text sample as inputs of the first model, taking the first embedding vector matrix of the first generated word output by the first model as input of the activation function layer, and taking the classification label corresponding to the text sample as the target output of the activation function layer. In this way, the classification of long texts can be supported and the classification effect of long texts can be improved. Taking the first embedding vector matrix of the first generated word output by the first model as input of the activation function layer can ensure the controllability of the output content of the text classification model and further improve the classification ability of the model.
Need to check novelty before this filing date? Find Prior Art