Training method, classification method, terminal and storage medium

By using a text classification model training method, text vectors are generated using text encoding and context encoding networks, and a fusion loss function is constructed by combining a multi-classification network. This solves the problem of recognition difficulty caused by the large number of intent categories in medical consultation systems, and improves the accuracy of intent recognition and diagnostic efficiency.

CN116795983BActive Publication Date: 2026-01-02PING AN TECH (SHENZHEN) CO LTD
2 Cites 0 Cited by

Patent Information

Application Number
CN202310717469.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-06-16
Publication Date
2026-01-02
Estimated Expiration
2043-06-16

AI Technical Summary

Technical Problem

The large number of intent categories in existing medical consultation systems makes identification difficult, and general multi-classification methods cannot effectively uncover the inherent relationships between intents, affecting the identification effect, resulting in question-and-answer redundancy and low diagnostic efficiency.

Method used

A text classification model training method is adopted, which generates text vectors through a text encoding network and a context encoding network, and uses the first and second classification networks for classification. A fusion loss function is constructed for iterative updates to improve the accuracy of intent recognition.

Benefits of technology

It improved the accuracy of intent text classification in the medical consultation system, reduced redundant question-and-answer rounds, and improved the diagnostic efficiency and service quality of the consultation system.

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

Abstract

The embodiment of the application relates to the technical field of digital medical treatment, and specifically provides a text classification model training method, a classification method, a terminal and a storage medium. The method comprises the following steps: inputting a training sample into a text coding network to obtain a first text vector corresponding to the training sample; inputting the first text vector into a context coding network to obtain a second text vector corresponding to the first text vector; inputting the second text vector into a first classification network and a second classification network respectively to obtain a first category probability distribution of the training sample classified by the first classification network and a second category probability distribution of the training sample classified by the second classification network, constructing a first loss function according to the first category probability distribution and constructing a second loss function according to the second category probability distribution, and determining a fusion loss function according to the first loss function and the second loss function; and iteratively updating a text classification model based on the training sample and the fusion loss function to obtain a target text classification model.
Need to check novelty before this filing date? Find Prior Art