US 12,135,743 B2
Systems and methods for detecting mismatched content
Desi Hristova, London (GB); Brian Regan, London (GB); and Nicola Montecchio, Berlin (DE)
Assigned to Spotify AB, Stockholm (SE)
Filed by Spotify AB, Stockholm (SE)
Filed on Oct. 20, 2022, as Appl. No. 18/048,383.
Prior Publication US 2024/0134907 A1, Apr. 25, 2024
Prior Publication US 2024/0232257 A9, Jul. 11, 2024
Int. Cl. G06F 16/65 (2019.01); G06F 16/64 (2019.01); G06F 16/683 (2019.01)
CPC G06F 16/65 (2019.01) [G06F 16/64 (2019.01); G06F 16/683 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
at a first electronic device associated with a media-providing service, the first electronic device having one or more processors and memory storing instructions for execution by the one or more processors:
obtaining a plurality of media items, including, for each media item in the plurality of media items, a set of attributes of the media item;
displaying, in a user interface, a plurality of representations of the plurality of media items, including a first representation for a first media item, based on metadata associated with respective media items of the plurality of media items;
providing the set of attributes for each media item of the plurality of media items to a machine learning model that is trained to determine a pairwise similarity distance between respective media items in the plurality of media items;
generating an acyclic graph of an output of the machine learning model that is trained to determine pairwise similarity distances between respective media items in the plurality of media items;
clustering nodes of the acyclic graph, each node corresponding to a media item; and
based on the clustering:
modifying metadata associated with the first media item in a first cluster; and
updating display of the user interface to exclude display of the first representation of the first media item in the user interface according to the modified metadata.