US 11,673,044 B1
Contextual recommendations in media streaming
Michael Glenn Minton, Redmond, WA (US); and Ken Llewellyn Demarest, Austin, TX (US)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on May 31, 2017, as Appl. No. 15/610,405.
Int. Cl. A63F 13/335 (2014.01); H04N 21/478 (2011.01); H04N 21/45 (2011.01); H04N 21/466 (2011.01); H04N 21/84 (2011.01); A63F 13/79 (2014.01)
CPC A63F 13/335 (2014.09) [A63F 13/79 (2014.09); H04N 21/4532 (2013.01); H04N 21/4668 (2013.01); H04N 21/4781 (2013.01); H04N 21/84 (2013.01); A63F 2300/5546 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system for providing media stream contextual recommendations comprising:
a gaming service computing device including one or more processors and memory, the gaming service computing device generating one or more gaming media streams corresponding to interaction by a first user with the gaming service computing device, the one or more gaming media streams including video content;
a contextual recommendation service computing device including one or more processors and memory, wherein the contextual recommendation service computing device is configured to:
obtain a request from a second user for a gaming media broadcast,
wherein the request includes a user identifier associated with the second user and a gaming identifier associated with the first user;
obtain personalization information based on the user identifier associated with the second user, wherein the personalization information includes at least one of social network information and historical information;
obtain a gaming media stream corresponding to the gaming identifier, the obtained gaming media stream including video content depicting a plurality of items;
process the video content in the gaming media stream to identify one or more items visually depicted in the gaming media stream;
responsive to identifying the one or more items visually depicted in the gaming media stream and without user input, obtain a set of recommendations based on the identified one or more items visually depicted in the gaming media stream;
filter the set of recommendations based at least in part on the personalization information to generate a final set of recommendations;
generate the gaming media broadcast based on the gaming media stream, the gaming media broadcast including one or more item recommendations from the final set of recommendations; and
provide the gaming media broadcast to the second user.