Supercharge Your Innovation With Domain-Expert AI Agents!

Task type multi-round dialogue method and system based on intent gate

A dialogue system and intent technology, applied in reasoning methods, special data processing applications, instruments, etc., to achieve the effects of improving correctness, improving user experience, and accurate semantic recognition

Pending Publication Date: 2022-02-11
SHANGHAI JIAO TONG UNIV
View PDF1 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although it can support the continuous operation of tasks with multiple rounds of dialogue, it can only be applied in specific scenarios and has limitations.

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
  • Task type multi-round dialogue method and system based on intent gate

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] The present invention will be described in detail below in conjunction with specific embodiments. The following examples will help those skilled in the art to further understand the present invention, but do not limit the present invention in any form. It should be noted that those skilled in the art can make several changes and improvements without departing from the concept of the present invention. These all belong to the protection scope of the present invention.

[0051] An embodiment of the present invention provides a task-type multi-round dialog method based on intent gates. figure 1 As shown, the specific steps of the method are as follows:

[0052] Step S1: Collect corresponding user corpus according to business requirements and perform preprocessing;

[0053] Specifically, in step S1, the corpus is collected:

[0054] Collecting user corpus through the production environment, our in-vehicle voice dialogue system has been operated in the actual car. For e...

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 invention provides a task type multi-round dialogue method and system based on an intent gate and relates to the technical field of natural language processing. The method comprises steps of S1, collecting corresponding user corpora according to business demands, and carrying out preprocessing; S2, defining a corresponding intention, a word slot and an intention gate label according to the user corpus; S3, training and optimizing an intention recognition model, a word slot semantic filling model and an intention gate model; S4, reasoning the intention recognition model, the word slot semantic filling model and the intention gate model; S5, the intention of the user corpus being recognized through an intention recognition model and a word slot semantic filling model, a corresponding word slot being extracted, and if the word slot is filled up, a corresponding information source service being called through the current intention to make a reply; and if the word slot is not filled up, performing multiple rounds of tasks till all the word slots are filled up. According to the method, correctness of task type multi-round conversations can be ensured, and the user experience of man-machine conversations can be improved.

Description

technical field [0001] The present invention relates to the technical field of natural language processing, in particular to a task-type multi-round dialogue method and system based on intent gates. Background technique [0002] With the development of the Internet and artificial intelligence, intelligent voice interaction is becoming more and more widespread, and in voice interaction, the recognition of semantics and the processing of information are extremely important. In the traditional intelligent voice interaction technology, it usually only recognizes the user's single-sentence voice information, but cannot realize the transmission and fusion of semantic information. [0003] The multi-turn dialogue task is one of the most practical techniques in natural language processing, which requires the system to take into account the context information while generating fluent answer sentences. In recent years, a large number of multi-turn dialogue models based on the HRED (h...

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): G06F16/332G06F16/35G06F16/36G06N5/04
CPCG06F16/3329G06F16/35G06F16/36G06N5/04
Inventor 朱亚杰卢宏涛
Owner SHANGHAI JIAO TONG UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com