Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Training method, dialogue method, device and storage medium for dialogue generation model

A technology for generating models and training methods, applied in biological neural network models, neural learning methods, instruments, etc., can solve the problem of difficult to generate innovative sentences or expand to new dialogue fields, template or rule design is time-consuming and laborious, High cost and other issues, to achieve the effect of improving fast convergence ability, improving user experience, and sufficient training

Active Publication Date: 2021-09-21
SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This type of method mainly relies on carefully designed manual templates or rules, which makes it difficult for the model to generate innovative sentences or expand to new dialogue fields, and the design of templates or rules is time-consuming, laborious, and costly

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
  • Training method, dialogue method, device and storage medium for dialogue generation model
  • Training method, dialogue method, device and storage medium for dialogue generation model
  • Training method, dialogue method, device and storage medium for dialogue generation model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

[0031] The terms "first", "second", etc. in the present application are used to distinguish different objects, not to describe a specific order or structure. Furthermore, the terms "comprising" and "having", and any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units is not limited to the listed steps or units, but optionally also inclu...

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 application relates to the technical field of dialog systems, and discloses a dialog generation model training method, dialog method, device and storage medium. The training method includes: constructing a dialogue generation model and at least one auxiliary model; wherein, the parameters of the dialogue generation model and the auxiliary model are different; inputting training samples into the dialogue generation model for training, obtaining the first matching loss, and inputting the training samples Training in at least one auxiliary dialogue model to obtain at least one auxiliary matching loss; using the first matching loss and at least one auxiliary matching loss to update the parameters of the dialogue generation model to obtain the final dialogue generation model. Through the above method, the accuracy of replying to the user's utterance can be improved, the replied information can better match the user's utterance, and the user experience can be improved.

Description

technical field [0001] The present application relates to the technical field of dialog systems, in particular to a dialog generation model training method, dialog method, device and storage medium. Background technique [0002] Currently, there are many models and methods in task-based dialogue systems. There are three common types of solutions: template or rule-based methods, and neural network-based sequence-to-sequence model methods. [0003] The method based on templates or rules is to manually pre-establish a series of templates or rules for dialogue responses. When a user enters a dialogue message, the system selects an appropriate template or rule to combine with the dialogue message according to the characteristics of the dialogue message (such as emotional state). and generate the final reply. This type of method mainly relies on carefully designed manual templates or rules, which makes it difficult for the model to generate innovative sentences or expand to new ...

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 Patents(China)
IPC IPC(8): G06F16/332G06N3/08G06N3/04
CPCG06F16/3329G06N3/08G06N3/045
Inventor 秦博文杨敏李成明姜青山
Owner SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com