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

Emotion recognition method based on long short-term memory neural network combined with autoencoder

A long-short-term memory and neural network technology, applied in neural learning methods, biological neural network models, instruments, etc., to achieve the effect of judging the short time

Active Publication Date: 2019-05-03
杭州语忆科技有限公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to propose a method capable of recognizing complex emotions in language in view of the insufficient judgment of existing artificial intelligence technology on multi-dimensional complex emotions

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
  • Emotion recognition method based on long short-term memory neural network combined with autoencoder
  • Emotion recognition method based on long short-term memory neural network combined with autoencoder
  • Emotion recognition method based on long short-term memory neural network combined with autoencoder

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0038] When using the present invention for emotion recognition, the specific recognition process:

[0039] 1), the text information or the text information converted from the language will first be word-embedded through the model.

[0040] 2), the data after word embedding will obtain positive and negative neutral emotional labels and corresponding probability P through the obtained model + , P - and P * .

[0041] 3), the data after word embedding and its corresponding probability P + or P - or P * Feature engineering, that is, feature reorganization, will be performed through the autocompiler neural network.

[0042] 4), the reorganized data is combined with P again + or P - or P * And according to the obtained emotional label is input into the corresponding emotional model to obtain the probability P corresponding to the relevant emotion e The superscript e here stands for a specific emotion.

[0043] 5) For a certain emotion e, its final recognition probability...

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 an emotion recognition method based on a long-term and short-term memory neural network and by combination with an autocoder. Various kinds of complex human emotions, such as pleasant, shy and angry emotions, are recognized through voice and characters; by changing a single monitoring type training mechanism of a conventional depth learning neural network, and by introducing a multi-monitoring type neural network layer and multi-step type model training, original data is subjected to multiple times of recombination effectively; and implicit memory relations in grammar are fully excavated so as to effectively recognize various complex emotions in the Chinese language. By adoption of the emotion recognition method, complex emotions in the Chinese language can be accurately detected, so that important analysis basis is provided for formulating of a marketing strategy and a man-machine voice interaction system.

Description

technical field [0001] The invention relates to the field of artificial intelligence recognition, and is a method for realizing emotion recognition through a deep learning neural network. It can be used in precision marketing industry, social network, customer service quality management and human-computer interaction fields. Background technique [0002] Since the birth of artificial intelligence technology and the robot industry, humans have been working hard to change the core algorithms of artificial intelligence and external hardware, making artificial intelligence systems or hardware more intelligent and humane. Human beings have taken a huge step on the road of intelligence. Through traditional machine learning algorithms and current mainstream deep learning algorithms, humans have been able to basically realize machine intelligence through artificial intelligence algorithms. Google's latest AlphaGo intelligent system has been able to compete with the world's top Go p...

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): G06F17/27G06N3/08
CPCG06F40/30G06N3/08
Inventor 程凯徐骥
Owner 杭州语忆科技有限公司
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