US 12,126,871 B1
Interruption model
Jatin Bajaj, Santa Clara, CA (US); and Clare Elizabeth Veladanda, Sunnyvale, CA (US)
Assigned to AMAZON TECHNOLOGIES, INC., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on Oct. 3, 2019, as Appl. No. 16/592,506.
Int. Cl. H04N 21/47 (2011.01); G10L 15/22 (2006.01); H04N 21/43 (2011.01); H04N 21/431 (2011.01); H04N 21/472 (2011.01)
CPC H04N 21/47 (2013.01) [G10L 15/22 (2013.01); H04N 21/4302 (2013.01); H04N 21/4316 (2013.01); H04N 21/47217 (2013.01); G10L 2015/223 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A method comprising:
receiving, from a speech processing-enabled device, first metadata indicating that existing content being output by the speech processing-enabled device comprises a video with synchronized audio;
receiving incoming content for output by the speech processing-enabled device while the speech processing-enabled device is outputting the existing content;
receiving second metadata indicating that the incoming content comprises a scheduled notification that is classified by the second metadata as visually dominant content;
determining a plurality of decisions using at least the first metadata and the second metadata, the plurality of decisions comprising:
determining, from the second metadata, that the incoming content comprises a visual component and an audio component;
determining, from the first metadata and the second metadata, that the existing content is of a different type from the incoming content;
determining, from the first metadata, that the existing content comprises video;
determining, from the second metadata, that the incoming content is classified as visually dominant;
determining, from the second metadata, that the incoming content is scheduled;
determining to display the incoming content on a first portion of a display of the speech processing-enabled device; and
determining to continue video playback of the existing content on at least a second portion of the display of the speech processing-enabled device; and
sending a first command to the speech processing-enabled device effective to cause the speech processing-enabled device to display the incoming content on the first portion of the display and continue video playback of the existing content on at least the second portion of the display.