US 12,405,998 B2
Systems and methods for generating personalized playlists
Colin Patrick Fahy, Brooklyn, NY (US); Leila Catherine Siddique, New York, NY (US); Christopher Ciollaro, Boston, MA (US); Matthew Budelman, Providence, RI (US); Mark VanMiddlesworth, Cambridge, MA (US); and Stanislav Chekalin, Brooklyn, NY (US)
Assigned to Spotify AB, Stockholm (SE)
Filed by Spotify AB, Stockholm (SE)
Filed on Oct. 21, 2022, as Appl. No. 18/048,766.
Prior Publication US 2024/0134904 A1, Apr. 25, 2024
Prior Publication US 2024/0232255 A9, Jul. 11, 2024
Int. Cl. G06F 16/638 (2019.01); G06F 16/635 (2019.01); G06F 16/65 (2019.01); G06F 16/683 (2019.01)
CPC G06F 16/639 (2019.01) [G06F 16/635 (2019.01); G06F 16/65 (2019.01); G06F 16/685 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method of generating personalized playlists, the method comprising:
obtaining information about recent media items presented to a user, the information including data about a respective time of day and day of week each media item was presented to the user;
grouping the recent media items into clusters based on time of day and day of week;
generating a recommendation vector using a weighted average of the clusters, wherein the clusters include two or more of: a time-of-day cluster, a day-of-week cluster, a day-and-time cluster, or a real-time cluster;
generating a playlist for the user by identifying a plurality of media items using the recommendation vector; and
causing the playlist to be presented to the user.