US 12,231,745 B1
Automated video summary generation using textual quotes
Deep Dubey, Bellevue, WA (US); Sushanta Das, Kirkland, WA (US); Kenneth Benoit, Ravensdale, WA (US); Anup Gandotra, Shoreline, WA (US); Adam Fluckey, Shoreline, WA (US); and Nikhil Kajale, Sammamish, WA (US)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on Jan. 23, 2019, as Appl. No. 16/255,344.
Int. Cl. H04N 21/8549 (2011.01); G11B 27/031 (2006.01); G11B 27/22 (2006.01); H04N 21/482 (2011.01); H04N 21/845 (2011.01)
CPC H04N 21/8549 (2013.01) [G11B 27/031 (2013.01); G11B 27/22 (2013.01); H04N 21/4828 (2013.01); H04N 21/8456 (2013.01)] 14 Claims
OG exemplary drawing
 
1. A system comprising:
memory configured to store computer-executable instructions; and
at least one computer processor configured to access the memory and execute the computer-executable instructions to:
determine first text representing a phrase spoken in unidentified video content;
determine that the first text is present in first subtitle data of first video content;
determine an amount of the first text present in the first subtitle data;
determine a first score for the first video content based at least in part on the amount of the first text present in the first subtitle data;
determine second subtitle data of second video content;
determine an amount of the first text present in the second subtitle data;
determine a second score for the second video content based at least in part on the amount of the first text present in the second subtitle data;
determine that the first score is greater than the second score;
determine a first timestamp and a second timestamp associated with the first text in the first subtitle data;
determine a first video segment of the first video content corresponding to the first timestamp and the second timestamp;
generate a video summary for the first video content, the video summary comprising the first video segment;
determine that the first video segment is present in a second video summary for the first video content; and
reorder an arrangement of video segments of the second video summary to present the first video segment in a first position of the arrangement.