US 12,236,539 B2
Contextual positioning in virtual space
Martin G. Keen, Cary, NC (US); Jeremy R. Fox, Georgetown, TX (US); Alexander Reznicek, Troy, NY (US); and Bahman Hekmatshoartabari, White Plains, NY (US)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by International Business Machines Corporation, Armonk, NY (US)
Filed on Jun. 20, 2022, as Appl. No. 17/807,784.
Prior Publication US 2023/0410435 A1, Dec. 21, 2023
Int. Cl. G06T 19/00 (2011.01); G06F 3/01 (2006.01); G10L 15/22 (2006.01)
CPC G06T 19/006 (2013.01) [G06F 3/011 (2013.01); G10L 15/22 (2013.01); G10L 2015/223 (2013.01)] 25 Claims
OG exemplary drawing
 
1. A method, comprising:
obtaining virtual session data in real time from a virtual session in a virtual space, wherein the virtual session data comprises natural language utterances of users participating in the virtual session;
identifying a positional utterance in the natural language utterances;
generating a positional insight for the positional utterance, wherein the positional insight indicates an ideal location within the virtual space for an avatar representing a user from the users;
determining that the positional insight has a confidence score above a threshold score;
in response to the determining, selecting the positional insight;
in response to the selecting, generating a best-practices recommendation based on the positional insight;
in response to the best-practices recommendation, comparing a location of the avatar with the ideal location; and
based on the comparing, automatically modifying a positional rendering of the avatar.