US 12,288,570 B1
Conversational AI-encoded language for video navigation
Ruthie Lyle, Durham, NC (US); Somayyeh Rahimi, Del Mar, CA (US); and Pratyush Mahapatra, Santa Clara, CA (US)
Assigned to NVIDIA CORPORATION, Santa Clara, CA (US)
Filed by NVIDIA Corporation, Santa Clara, CA (US)
Filed on Oct. 25, 2022, as Appl. No. 18/049,446.
Int. Cl. G06F 3/0482 (2013.01); G06V 10/94 (2022.01); G06V 20/40 (2022.01); G11B 27/031 (2006.01); G11B 27/34 (2006.01); G06V 40/16 (2022.01)
CPC G11B 27/34 (2013.01) [G06F 3/0482 (2013.01); G06V 10/945 (2022.01); G06V 20/41 (2022.01); G11B 27/031 (2013.01); G06V 40/174 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
receiving an encoded video file representing original video content and a transcript associated with the original video content;
storing the encoded video file in place of an original video file containing original video content;
processing the transcript using one or more machine learning models to identify a plurality of topics discussed in the transcript;
causing a presentation, via a user interface, of a list of topics corresponding to the plurality of topics;
receiving, via the user interface, a selection of a topic from the list of topics;
responsive to the selection, selecting a sequence of one or more portions of the encoded video file that are associated with the topic;
generating, based on the sequence, synthesized video data that simulates at least a portion of the original video content; and
causing presentation of the synthesized video data.