Human-computer interaction method, device and medium based on neural network

A technology of human-computer interaction and neural network, applied in the field of human-computer interaction method, device and medium based on neural network, can solve problems such as unclear logic, large meaning difference, empty dialogue content, etc., and achieve the effect of improving chat experience

Active Publication Date: 2020-11-24
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the actual dialogue process, the user input has similar meanings but great differences in literal expressions, and similar literal expressions but great differences in meanings, etc., resulting in corpus-based retrieval methods or generation methods generally having empty dialogue content, unclear logic, and irrelevant answers, etc. question

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
  • Human-computer interaction method, device and medium based on neural network
  • Human-computer interaction method, device and medium based on neural network
  • Human-computer interaction method, device and medium based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] In the present disclosure, unless otherwise stated, using the terms "first", "second", etc. to describe various elements is not intended to limit the positional relationship, temporal relationship or importance relationship of these elements, and such terms are only used for Distinguishes one element from another. In some examples, the first element and the second element may refer to the same instance of the element, and in some cases, they may also refer to different instances based on contextual description.

[0018] The terminology used in describing the various described examples in this disclosure is for the purpose of describing particular examples only and is not intended to be limiting. Unless the context clearly indicates otherwise, if the number of elements is not specifically limited, there may be one or more elements. In addition, the term "and / or" used in the present disclosure covers any one and all possible combinations of the listed items.

[0019] 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 present disclosure provides a neural network-based human-computer interaction method, device and medium, which relate to the technical field of artificial intelligence, specifically the technical fields of natural language processing and knowledge graph. The method includes: providing user input as a first input to the neural network system; providing the user input to a dialog control system different from the neural network system; processing the user input by the dialog control system based on information related to the user input ; providing the processing result of the dialog control system as a second input to the neural network system; and generating a reply to the user input based on the first input and the second input by the neural network system.

Description

technical field [0001] The present disclosure relates to the technical field of artificial intelligence, specifically to the technical field of natural language processing and knowledge graph, and in particular to a neural network-based human-computer interaction method, device and medium. Background technique [0002] The goal of the open domain dialogue system is to make the machine use natural language as the medium of information transmission like a human being. The machine meets people's daily interaction needs by answering questions, executing commands, chatting, etc. There are no restrictions on the topic and content of chatting. [0003] At present, open-domain dialogue systems mainly use corpus-based retrieval methods or generation methods. Among them, the corpus stores the language materials that have actually appeared in the actual use of the language. In the actual dialogue process, the user input has similar meanings but great differences in literal expressions...

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): G06F16/332G06F40/30G06N3/08
CPCG06F16/3329G06F40/30G06N3/08G06F16/3344G06F16/328G06F40/35G06F40/247G06N5/041G06N3/042G06N3/045G06N3/008G06N3/063G06N5/02G06N3/02H04L51/02G06F18/29G06F18/2113
Inventor 吴华王海峰刘占一
Owner BEIJING BAIDU NETCOM SCI & TECH 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