US 12,192,595 B2
Automatically processing content streams for insertion points
Varun Ram, Portland, OR (US); Ki Myung Han, Happy Valley, OR (US); Meera Jindal, Portland, OR (US); Viriya Ratanasangpunth, Portland, OR (US); and Chris Price, Portland, OR (US)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on Oct. 17, 2023, as Appl. No. 18/488,390.
Application 18/488,390 is a continuation of application No. 17/583,011, filed on Jan. 24, 2022, granted, now 11,825,176.
Application 17/583,011 is a continuation of application No. 16/121,514, filed on Sep. 4, 2018, granted, now 11,234,059, issued on Jan. 25, 2022.
Prior Publication US 2024/0048820 A1, Feb. 8, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. H04N 21/84 (2011.01); H04N 21/231 (2011.01); H04N 21/236 (2011.01); H04N 21/239 (2011.01); H04N 21/845 (2011.01)
CPC H04N 21/8455 (2013.01) [H04N 21/23106 (2013.01); H04N 21/23614 (2013.01); H04N 21/2393 (2013.01); H04N 21/8456 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system to transmit content comprising:
one or more computing devices associated with a video packaging and origination service, wherein the video packaging and origination service is configured to:
encode received content into a set of encoded content segments, the received content including markers that correspond to manually determined insertion points for insertion of supplemental content;
receive content requests from a user device;
determine video and audio attributes of sequential segments of the encoded content segments;
characterize one or more segments of the sequential segments as indicative of a transition based on differences between the determined video and audio attributes of the sequential segments, wherein the transitions are indicative of locations in the set of encoded content for insertion of supplemental content;
dynamically determine insertion points for insertion of the supplemental content in the set of encoded content segments based on the transitions;
form a set of insertion points for the insertion of the supplemental content, wherein the set of insertion points includes at least one dynamically determined insertion point and at least one manually determined insertion point;
render the encoded content segments;
identify a subset of a plurality of detectable objects based on processing the set of encoded content segments using a machine-learning algorithm to detect specific objects within the set of encoded content segments, the identified objects associated with the supplemental content; and
prioritize, in the set of insertion points, the insertions points that can be matched with the identified objects associated with the supplemental content over the insertion points that do not match with the identified objects associated with the supplemental content.