Structured-neural-network-based dialogue method and system, equipment and storage medium

A neural network and structured technology, applied in speech analysis, instrumentation, semantic analysis, etc., can solve problems such as low training efficiency and achieve efficient training

Active Publication Date: 2018-12-07
AISPEECH CO LTD
View PDF9 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, the training efficiency is low, that is, a large amount of dialogue interaction data training is required to make the performance of the model reach a relatively good level

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
  • Structured-neural-network-based dialogue method and system, equipment and storage medium
  • Structured-neural-network-based dialogue method and system, equipment and storage medium
  • Structured-neural-network-based dialogue method and system, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention. It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

[0024] It should also be noted that in this article, relational terms such as first and second etc. are only used to distinguish one entity or operation from another entity or ope...

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 discloses a structured-neural-network-based dialogue method and system, equipment and a storage medium. The method comprises: decomposing a received confidence dialog state into a plurality of sub-dialog states; transforming the plurality of sub-dialog states into a plurality of corresponding sub-dialog state vectors by a plurality of network nodes; for each of the network nodes, determining output values of all network nodes according to the plurality of sub-dialog state vectors; and according to the output value of each of the network nodes, determining a dialog action corresponding to the confidence dialog state. According to the invention, with the structured neural network, the obtained neural network dialogue strategy can be trained more efficiently; and training is carried out by using a few of dialogue interaction data to obtain a model with the performance reaching the high level.

Description

[0001] The present invention claims the priority of the Chinese patent application submitted to the Chinese Patent Office on April 25, 2018, with the application number 201810378993.4, and the title of the invention is "Adaptive Method for Dialogue Strategies Based on Deep Reinforcement Learning", the entire contents of which are incorporated by reference in this application. technical field [0002] The present invention relates to the technical field of artificial intelligence, in particular to a dialogue method, system, device and storage medium based on a structured neural network. Background technique [0003] A task-oriented spoken dialogue system (Spoken Dialogue System, SDS) is a system that can continuously interact with a human to complete a predefined task, for example, find a restaurant or book a flight. Dialog management (DM) is the core of SDS. It has two tasks: one is to track the dialog state, and the other is to decide how to reply to the user according to ...

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): G10L15/22G10L15/16G10L15/06
CPCG06F40/30G10L15/063G10L15/16G10L15/22
Inventor 俞凯陈露
Owner AISPEECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap