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

Method and device for generating reply sentences based on keywords

A technology for replying sentences and keywords, applied in instruments, text database query, calculation, etc., can solve problems such as poor user experience, ignorance, and the inability of man-machine dialogue to continue.

Active Publication Date: 2021-01-05
MOBVOI INFORMATION TECH CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In the process of realizing the present invention, the inventor found that there are the following technical problems in the prior art, because, when training the Seq2Seq model, the maximum likelihood method is usually used for training, therefore, it will lead to reply sentences with higher frequency It is easier to be generated, so that the man-machine dialogue system has a high probability of generating general reply sentences such as "don't know" and "okay", which will cause the man-machine dialogue to be unable to continue, making end users poor user experience

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
  • Method and device for generating reply sentences based on keywords
  • Method and device for generating reply sentences based on keywords
  • Method and device for generating reply sentences based on keywords

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0077] Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the drawings, it should be understood that the invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

[0078] Embodiments of the present invention provide a method for generating reply sentences based on keywords, such as figure 1 As shown, the method includes:

[0079] 101. Acquire a question sentence input by a user, and generate multiple word vectors corresponding to the question sentence.

[0080] Wherein, the question sentence input by the user may be, but not limited to: the question sentence entered by the user through the keyboard on th...

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 invention discloses a method and a device for generating a reply sentence based on a keyword, which relates to the technical field of natural language processing and improves thecontent richness of the reply sentence generated by a man-machine conversation system. A main technical scheme of that embodiment of the invention is as follow: a question sentence input by a user isobtained, and a plurality of word vectors corresponding to the question sentence are generated; an encoder is used to encode a plurality of the word vectors to generate a hidden layer state vector corresponding to the question statement; a word vector of a keyword corresponding to the question statement is determined; a word vector of the keyword and the hidden layer state vector are decoded using a decoder to generate a reply statement corresponding to the question statement. The embodiment of the invention is mainly applied to a man-machine conversation system to generate a reply statement.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of natural language processing, and in particular to a method and device for generating reply sentences based on keywords. Background technique [0002] With the continuous development of artificial intelligence technology, the human-computer dialogue system developed based on the Seq2Seq (Sequence to Sequence, sequence to sequence) model has gradually attracted people's attention. Among them, the Seq2Seq model is composed of an encoder and a decoder. When the human-computer dialogue system receives the question sentence input by the end user, the human-computer dialogue system first uses the encoder to encode the question sentence into a state vector, and then uses the decoder to compare the The state vector is decoded to generate a reply statement. [0003] In the process of realizing the present invention, the inventor found that the following technical problems existed in the prior...

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): G06F16/332G06F16/33
Inventor 姚丽丽
Owner MOBVOI INFORMATION 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