Temporal semantic fusion association determining sub-system based on multimodal emotion recognition system

An emotion recognition and subsystem technology, applied in the field of time sequence semantic fusion correlation judgment subsystem, can solve the problem of not synthesizing human expressions, spoken words, posture, voice, intonation and physiological characteristics, so as to improve emotion analysis and improve ease of use. The effect of reduced performance, environmental and hardware requirements

Active Publication Date: 2018-11-13
南京云思创智信息科技有限公司
View PDF3 Cites 74 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, it does not integrate people's facial expressions, spoken words, body posture, voice intonation and physiological characteristics, etc.

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
  • Temporal semantic fusion association determining sub-system based on multimodal emotion recognition system
  • Temporal semantic fusion association determining sub-system based on multimodal emotion recognition system
  • Temporal semantic fusion association determining sub-system based on multimodal emotion recognition system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0061] The invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0062] Because the production of any emotion is accompanied by certain changes in the body, such as facial expressions, muscle tension, and visceral activities. Using these signal changes to directly perform emotion recognition is the so-called basic recognition method, also known as a single-modal emotion recognition method. The current main methods include facial images, language, text, gestures and physiological signals. The present invention proposes to integrate, correspond and reason the understanding of emotions by computers in each of the following single modes to obtain a more complete and accurate emotion recognition method and system.

[0063] The emotion recognition system based on multimodal that present embodiment proposes, its system is made up of following several parts ( figure 1 It is a schematic diagram of a multimodal emo...

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 temporal semantic fusion association determining sub-system based on a multimodal emotion recognition system. The sub-system comprises a data collection device and an outputdevice and is characterized by further comprising an emotion analysis software system, wherein the emotion analysis software system performs comprehensive analysis and deduction on data obtained by the data collection device and finally outputs a result to the output device, and the emotion analysis software system comprises a time sequence-based semantic fusion association determining sub-system.The system makes a breakthrough of five single modes of emotion recognition, uses a deep neural network to encode, deeply associate and comprehend multiple single modes of information and then determines comprehensively, thereby greatly improving the accuracy and being suitable for most common inquiry interaction scenes.

Description

technical field [0001] The present invention relates to the technical field of emotion recognition, in particular, it relates to the timing of multimodal emotion recognition systems based on machine learning, deep learning, computer vision, natural language processing, speech recognition, human action recognition, non-contact physiological detection, etc. Semantic Fusion Association Judgment Subsystem. Background technique [0002] Emotion recognition is a technology for judging people's emotional changes. It mainly collects people's external expressions and behavior changes to infer people's psychological state. In modern society, emotion recognition technology is widely used in the development of smart devices, sales guide robots, health management, advertising and marketing, etc. Emotion is a state that integrates people's feelings, thoughts, and behaviors. It includes people's psychological responses to external or self-stimuli, as well as the physiological responses th...

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): G06K9/00G06K9/62G06F17/27G10L25/30G10L25/63
CPCG10L25/30G10L25/63G06F40/30G06V40/70G06F18/25
Inventor 俞旸凌志辉
Owner 南京云思创智信息科技有限公司
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