US 11,989,810 B2
Interactive system application for digital humans
Abhijit Z. Bendale, Campbell, CA (US); Pranav K. Mistry, Saratoga, CA (US); Bola Yoo, Seoul (KR); Kijeong Kwon, Seoul (KR); Simon Gibbs, San Jose, CA (US); Anil Unnikrishnan, Los Gatos, CA (US); and Link Huang, Mountain View, CA (US)
Assigned to SAMSUNG ELECTRONICS CO., LTD., Gyeonggi-do (KR)
Filed by SAMSUNG ELECTRONICS CO., LTD., Gyeonggi-do (KR)
Filed on Jan. 7, 2022, as Appl. No. 17/571,106.
Claims priority of provisional application 63/135,855, filed on Jan. 11, 2021.
Claims priority of provisional application 63/135,516, filed on Jan. 8, 2021.
Claims priority of provisional application 63/135,526, filed on Jan. 8, 2021.
Claims priority of provisional application 63/135,505, filed on Jan. 8, 2021.
Prior Publication US 2022/0222880 A1, Jul. 14, 2022
Int. Cl. G06T 13/00 (2011.01); G06F 3/01 (2006.01); G06F 3/147 (2006.01); G06F 3/16 (2006.01); G06T 13/40 (2011.01); G06V 40/16 (2022.01); G06V 40/20 (2022.01); G09F 13/04 (2006.01); G10L 13/02 (2013.01); G10L 15/06 (2013.01); G10L 15/16 (2006.01); G10L 15/22 (2006.01); G10L 25/63 (2013.01); H05B 47/12 (2020.01); H05B 47/125 (2020.01)
CPC G06T 13/00 (2013.01) [G06F 3/011 (2013.01); G06F 3/147 (2013.01); G06F 3/16 (2013.01); G06T 13/40 (2013.01); G06V 40/174 (2022.01); G06V 40/20 (2022.01); G09F 13/049 (2021.05); G10L 13/02 (2013.01); G10L 15/063 (2013.01); G10L 15/16 (2013.01); G10L 15/22 (2013.01); G10L 25/63 (2013.01); H05B 47/12 (2020.01); H05B 47/125 (2020.01); G06F 3/012 (2013.01); G06F 3/017 (2013.01); G06F 2203/011 (2013.01); G10L 2015/0638 (2013.01); G10L 2015/227 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
determining, with an interactive system, a contextual response to a user input;
generating, with the interactive system, a digital human; and
conveying, with the digital human, the contextual response to the user in real time, wherein the digital human is configured to convey the contextual response with a predetermined behavior corresponding to the contextual response;
wherein the predetermined behavior includes a sequence of keypoints corresponding to visual representations of the digital human and to image frames, wherein at least one keypoint of the sequence of keypoints anchors the predetermined behavior with a portion of audio of the contextual response, and wherein the predetermined behavior includes an eye movement of the digital human.