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

Multi-round automatic chat and conversation method and system based on deep learning

A deep learning and dialogue system technology, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve problems such as return errors, robots can't get the user's true intentions well, and answer deviations, so as to improve the quality of answers , Improve the effect of user experience

Inactive Publication Date: 2017-09-22
WUHAN TIPDM INTELLIGENT TECH
View PDF5 Cites 80 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Most of the current chatbots focus on a single round of interaction with the user, making the robot unable to obtain the real intention of the user very well, because the important information of the user's chat may be in the user's previous conversation
This single-round-based chat mechanism ignores the chat topics and scene analysis of the current user's previous rounds, so the answers returned by it will have certain deviations, and even return wrong answers

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
  • Multi-round automatic chat and conversation method and system based on deep learning
  • Multi-round automatic chat and conversation method and system based on deep learning
  • Multi-round automatic chat and conversation method and system based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0023] In a chatbot with a single-round dialogue mode, when the user inputs 1, the chatbot gives reply 1 based on user input 1, and when the user inputs 2, the chatbot gives reply 2 according to user input 2. For example, in the first round of dialogue, the user enters 1 as "what day is today", and the robot replies "Wednesday". day".

[0024] Such a single-round dialogue method is ideal in a simple chat mode of one question and one answer. However, if the user's multiple conversation topics are highly correlated, the robot cannot use a single-round dialogue to reply. , otherwise the reply will h...

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 multi-round automatic chat and conversation method and system based on deep learning. The method comprises the following steps that: on the basis of the current input processing result of a user, using a deep learning model to mine the current input intention of the user; according to the current input intention of the user, the chat theme of a previous round of conversation and the current input processing result of the user, using the deep learning model to judge whether the current input intention of the user is consistent with the chat theme of the previous round of conversation, updating entity information according to a judgment result, then, obtaining response contents according to the current input intention of the user from a preset response database, and sending the response contents to the user. The method has the beneficial effects that the contents and the context scene information of the current round of conversation and the previous round of conversation can be simultaneously considered when a chatting robot carries out continuous multi-round conversations with the user, more accurate contents can be responded to the user, and answering quality is improved.

Description

technical field [0001] The invention relates to the field of intelligent chat robots, in particular to a method and system for multi-round automatic chat dialogue based on deep learning. Background technique [0002] In recent years, with the rapid development of artificial intelligence, chatbots have also received extensive attention from academia and industry. [0003] A chatbot is a program that simulates a human conversation through natural language. [0004] At present, chatbots are mainly divided into five categories: online customer service, entertainment, education, personal assistant and intelligent question and answer. No matter what kind of robot can interact with the user to some extent. However, in the current chatbot application scenarios, users still dominate. In the continuous conversation of the user, the chat topics in the context have continuity and complementarity, and the jump between topics is also random. Most of the current chatbots focus on a sin...

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): G06F17/30G06K9/62G06K9/72
CPCG06F16/3329G06V30/274G06F18/40
Inventor 叶正金灿灿何苯李成华刘丽君
Owner WUHAN TIPDM INTELLIGENT TECH
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