US 12,032,620 B2
Identifying media content
Tristan Jehan, Brooklyn, NY (US); and Nicola Montecchio, New York, NY (US)
Assigned to Spotify AB, Stockholm (SE)
Filed by Spotify AB, Stockholm (SE)
Filed on Mar. 22, 2021, as Appl. No. 17/208,703.
Application 17/208,703 is a continuation of application No. 15/617,884, filed on Jun. 8, 2017, granted, now 10,984,035.
Claims priority of provisional application 62/347,642, filed on Jun. 9, 2016.
Prior Publication US 2021/0303612 A1, Sep. 30, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 16/435 (2019.01); G06N 20/00 (2019.01); G06F 16/9535 (2019.01); G06F 16/2457 (2019.01); G06Q 30/02 (2023.01); G06F 16/9538 (2019.01); G06F 16/63 (2019.01)
CPC G06F 16/435 (2019.01) [G06F 16/24578 (2019.01); G06F 16/63 (2019.01); G06F 16/9535 (2019.01); G06F 16/9538 (2019.01); G06N 20/00 (2019.01); G06Q 30/02 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A media-delivery system comprising:
a processing device;
a media data store for storing a plurality of media content items; and
a non-transitory computer-readable medium storing instructions executable by the processing device to cause the media-delivery system to:
automatically identify media content items from the plurality of media content items for use as potential training examples, to present for evaluation regarding an indirect quality, by processing descriptive data associated with the plurality of media content items to identify keywords associated with the indirect quality;
send messages to present the identified media content items including a first media content item and a second media content item;
receive indirect quality scores relating to the indirect quality wherein to receive the indirect quality scores includes to receive comparative assessment inputs identifying which of the first media content item and the second media content item has more of the indirect quality;
combine the indirect quality scores to generate combined indirect quality scores regarding the indirect quality for the identified media content items, and
select training examples from the identified media content items based on the combined indirect quality scores.