MULTI-MODAL EMOTION RECOGNITION DEVICE, METHOD AND STORAGE MEDIUM USING ARTIFICIAL INTELLIGENCE

Title:

MULTI-MODAL EMOTION RECOGNITION DEVICE, METHOD AND STORAGE MEDIUM USING ARTIFICIAL INTELLIGENCE

Document Type and Number:

WIPO Patent Application WO/2019/103484

Kind Code:

A1

Abstract:

Embodiments of the present invention relate to a multi-modal emotion recognition device, method and storage medium using artificial intelligence. The multi-modal emotion recognition device using artificial intelligence of the present disclosure comprises: a data input unit for receiving user image data and voice data; a data preprocessing unit including a voice preprocessing unit for generating voice feature data from the voice data and an image preprocessing unit for generating one or more pieces of facial feature data from the image data; a preliminary inferring unit for generating situation judgment data on whether or not a user's situation changes according to a temporal order on the basis of the image data; and a main inferring unit for generating at least one sub-feature map on the basis of the voice feature data or the facial feature data, and for inferring the emotional state of the user on the basis of the sub-feature map and the situation judgment data.

More Like This:

JP2693300	IMAGE FORMING DEVICE HAVING SELF-RECOVERING SYSTEM
WO/2022/212579	DISTRIBUTED DECOMPOSITION OF STRING-AUTOMATED REASONING USING PREDICATES
JPH05313940	MODEL BASE INFERRING SYSTEM FOR DIAGNOSING NETWORK FAILURE

Inventors:

YOO DAE HUN (KR)
LEE YOUNG BOK (KR)

Application Number:

PCT/KR2018/014439

Publication Date:

May 31, 2019

Filing Date:

November 22, 2018

Export Citation:

Click for automatic bibliography generation Help

Assignee:

GENESIS LAB INC (KR)

International Classes:

G06N5/04; G06N3/08; G06N99/00; G06V10/764; G10L15/02

Foreign References:

KR20030046444A	2003-06-12
JP2015075908A	2015-04-20
KR20130022434A	2013-03-07
KR20130009123A	2013-01-23
KR20100001928A	2010-01-06

Other References: