Spotify Ab

Christopher James Ciollaro

Paul B Lamere

Matthew Budelman

Adam Latour Piel

Stanislav Chekalin

Colin Patrick Fahy

Peter Martin Deglopper

James Faulkner Kirk

Mark VanMiddlesworth

Chang Min Jeon

Leila Catherine Siddique

The various implementations described herein include methods and devices for generating personalized playlists. In one aspect, a method includes 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. The method further includes grouping the recent media items into clusters based on time of day and day of week; and generating a recommendation vector using a weighted average of the clusters. The method also includes generating a playlist for the user by identifying a plurality of media items using the recommendation vector; and presenting the playlist to the user.

Systems and methods for generating personalized playlists

A server system receives a request to generate a playlist. The playlist includes a sequence of media items. The server system receives a plurality of constraints that define disqualification criteria for excluding media items from a respective slot in the sequence of media items. The plurality of constraints for the respective slot in the sequence of media items includes at least one constraint that is based on already-populated slots in the sequence of media items. The server system generates the playlist by sequentially populating each respective slot in the sequence of media items, including selecting, for the respective slot, a respective media item that meets the plurality of constraints for the respective slot in the sequence of media items. The server system provides the playlist to a user of the media providing service.

Systems and methods for sequencing a playlist of media items

Growing community of inventors

Boston, MA, United States of America

Christopher James Ciollaro