Unlock instant, AI-driven research and patent intelligence for your innovation.

Dialogue text classification method and electronic equipment

A classification method and text technology, applied in the field of artificial intelligence, can solve problems such as low efficiency and heavy workload, and achieve the effect of improving accuracy and classification efficiency

Pending Publication Date: 2021-06-25
CHINA MOBILE GROUP SICHUAN +1
View PDF8 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, related technologies usually rely on customer service personnel to manually classify a large number of dialogue texts, which has the problems of heavy workload and low efficiency.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Dialogue text classification method and electronic equipment
  • Dialogue text classification method and electronic equipment
  • Dialogue text classification method and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 200

[0067] Embodiment 200 introduces a training process of a type of prototype network. In fact, the above steps can be repeated to train a plurality of different types of prototype networks through different types of sample dialogue texts.

[0068] The dialog text classification method provided by the embodiment of this specification can achieve the same or equivalent technical effect as that of embodiment 100, and to avoid repetition, the description will not be repeated here.

[0069] In order to describe in detail the classification methods of dialogue texts provided by the above-mentioned embodiments of this specification, a specific embodiment will be introduced below, for example, image 3 Shown, this embodiment comprises the following steps:

[0070] S302: Obtain dialogue text.

[0071] For this step, refer to S102 of Embodiment 100.

[0072] S304: Character vectorization processing.

[0073] In this step, a glove algorithm may be used to split the dialogue text to form...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The embodiment of the specification discloses a dialogue text classification method and electronic equipment, which are used for improving the classification efficiency of dialogue texts. The method comprises the steps of obtaining a dialogue text; encoding the dialogue text through an encoder of a multi-level self-attention mechanism to obtain a document vector of the dialogue text; calculating vector distances between the document vectors and the plurality of prototype networks, wherein the plurality of prototype networks correspond to a plurality of categories, and the plurality of prototype networks are obtained by training based on sample dialogue texts of which the categories are determined; and determining the category of the dialogue text based on the calculated vector distance and the categories of the plurality of prototype networks.

Description

technical field [0001] This document relates to the field of artificial intelligence technology, in particular to a method for classifying dialogue text and electronic equipment. Background technique [0002] Service providers can quickly obtain users' opinions and suggestions through customer service channels. Customer service channels are of great significance for service providers to understand the quality of services provided in real time and to improve some services in a targeted manner. [0003] The service provider can obtain the dialogue text between the customer service personnel and the user through the customer service channel. By classifying the dialogue text, the key information of the dialogue text can be quickly determined, such as the type of question, the problem scene, etc., which can greatly improve the The service quality of the service provider. [0004] However, in related technologies, customer service personnel are usually relied on to manually clas...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/332G06F16/35G06F40/211G06F40/30
CPCG06F16/3329G06F16/35
Inventor 李丹苟浩淞杨兵伍雄
Owner CHINA MOBILE GROUP SICHUAN