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

Context-based emotional dialogue method and system and storage medium

A contextual and emotional technology, applied in the direction of neural learning methods, text database query, character and pattern recognition, etc., can solve the problem of not considering the topic and emotion of the dialogue context, and achieve the effect of good emotional changes

Pending Publication Date: 2020-11-17
HEFEI UNIV OF TECH
View PDF1 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the deficiencies of the prior art, the present invention provides a method, system and storage medium based on contextual emotional dialogue, which solves the problem that the existing emotional dialogue is to give a reply to a certain sentence without considering the theme and emotion of the dialogue context technical problem

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
  • Context-based emotional dialogue method and system and storage medium
  • Context-based emotional dialogue method and system and storage medium
  • Context-based emotional dialogue method and system and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0046] Such as figure 1 As shown, the embodiment of the present invention provides a method for context-based emotional dialogue, including:

[0047] Get the dialog context dataset;

[0048] Extracting the theme category and the emotion category of the dialogue context data set, obtaining the theme keyword probability and the emotion keyword probability of the dialogue context data set;

[0049] According to the subject category and subject keyword probability prediction in reply, the emotion keyword in reply according to described emotion category and emotion keyword probability prediction;

[0050] Generate a preliminary reply according to the predicted subject keywords and emotional keywords;

[0051] Obtaining the weight of the preliminary reply according to the preliminary reply;

[0052] According to the preliminary replies and weights, a final reply is obtained.

[0053] The beneficial effects of the embodiments of the present invention include: the emotional dialog...

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 context-based emotional dialogue method and system and a storage medium, and relates to the technical field of emotional dialogues. According to the embodiment of the invention, the method comprises the steps: firstly obtaining a dialogue context data set, extracting a theme category and an emotion category in the dialogue context data set, obtaining a theme keyword probability and an emotion keyword probability, predicting theme keywords and emotion keywords in replies, and generating preliminary replies according to the predicted theme keywords and emotion keywords;and then obtaining a weight value of the preliminary reply, and obtaining a final reply according to the preliminary reply and the weight. Therefore, according to the embodiment of the invention, thedialogue context is fully utilized, the reply generated by the machine is closer to the theme, the emotional change of the context is better judged, and the extension of the dialogue theme is mastered.

Description

technical field [0001] The invention relates to the technical field of emotional dialogue, in particular to a method, system and storage medium for emotional dialogue based on context. Background technique [0002] The human-computer dialogue system is a hot issue in current research, and its main goal is to realize the machine's understanding of natural language and complete emotional dialogue like people. [0003] At present, there are artificial intelligence systems that can automatically generate dialogues and complete simple communication with people. For example, the invention with the application number CN110032636A "A Method for Asynchronous Generation of Emotional Dialogue Based on Reinforcement Learning", the basic idea of ​​automatically generating replies is to select an agent, set x in the agent to represent the sentence input from the external environment, and y to represent the agent For the answer given by the input x, and then given a question, use the enco...

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): G06F16/33G06F16/332G06F16/35G06F40/289G06K9/62G06N3/04G06N3/08
CPCG06F16/3329G06F16/3344G06F16/35G06F40/289G06N3/049G06N3/08G06N3/047G06N3/045G06F18/2415G06F18/241
Inventor 孙晓丁兵兵汪萌
Owner HEFEI UNIV OF 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