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

Dialogue response method and device

A text and intent technology, applied in special data processing applications, natural language data processing, instruments, etc., can solve the problems of failure of dialogue response and low accuracy of intent recognition, and achieve the effect of improving accuracy and reducing failure rate.

Inactive Publication Date: 2020-03-17
HUAWEI TECH CO LTD
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The embodiment of the present application provides a dialogue response method and device, which can solve the problem of failure of dialogue response due to low accuracy of intention recognition in the process of man-machine dialogue

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 response method and device
  • Dialogue response method and device
  • Dialogue response method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] In man-machine dialogue for the purpose of task-driven, terminal devices often need to recognize the user's intention from the natural language input by the user when responding to the dialogue, so as to drive the corresponding task, so as to achieve the goal that the user wants to achieve. At present, the more common recognition method is to use neural network, clustering algorithm, classification algorithm, rule system and other algorithms to train a recognition model based on a large amount of text corpus, and then use the recognition model to recognize the user's intention. However, due to the limitation of the corpus, the recognition model can cover only limited linguistic phenomena, and cannot perform intent error correction or accurately identify multiple intents.

[0025] For example, the user's dialogue text is "check the weather in city 1, oh no, the weather in city 2", and the user's real intention is "check the weather in city 2". However, based on the exist...

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 dialogue response method and device, and relates to the field of terminal artificial intelligence (AI), in particular to the field of voice recognition. The method comprises the steps of obtaining a to-be-recognized dialogue text; converting the dialogue text into a predicate formula according to a preset predicate logic rule, wherein the predicate formula is used for describing semantics of the dialogue text; determining at least one intention described in the dialogue text according to the predicate formula; and executing a dialogue operation indicated by the at least one intention.

Description

technical field [0001] The present application relates to the field of terminal artificial intelligence (AI), specifically related to the field of speech recognition, and relates to a dialogue response method and device. Background technique [0002] Human-machine dialogue refers to the process of dialogue between humans and machines through human language (ie, natural language), and is an important research direction in the field of AI. Task-based multi-turn dialogue is a human-computer dialogue for the purpose of realizing task-driven. In the process of responding to the dialogue, the terminal device recognizes the user's intention in natural language (that is, the goal that the user wants the machine to achieve, such as querying the weather, playing music, booking tickets, etc.), to drive the corresponding tasks, so as to realize the user's desired goals achieved. [0003] At present, when terminal devices respond to dialogues, they often use identification methods such...

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
IPC IPC(8): G06F16/332G06F40/284G06F40/30
CPCG06F16/3329
Inventor 刘璐朱越张宝峰
Owner HUAWEI TECH CO LTD
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