Apple Inc.

Daniel Cartoon

Mark Hilary Levy

Arvind S Shenoy

Matthias Mauch

Thomas M Alsina

Jeffrey L Robbin

Drew Rocky Domm

Eric Circlaeys

Fredric R Vinna

Kevin Bessiere

Uli M Schöberl

Paul C Irvine

Erik Lindholm

Zachary H Smith

Patrick H Kelly

Betim Deva

Priyo Mustafi

Nathaniel B Chapman

Bruno J Conejo

Trevor M Slaton

Cristina N Smith

Alexa Rockwell

Denise L Chen

Bekir B Dundar

Brian J Rogosky

Alfredo Ramos-Alvarez

Bruno Di Giorgi

Alexis H Durocher

Jeremy P Bogle

Hao Yang

Neil C Foley

Menelaos D Kokolios

Lewis Kaneshiro

Jorge A Herrera Soto

James E Hewitt

Jan Markus Harrie Van Balen

Casey W Baker

The present technology pertains to automatically context labeling media items with relevant contexts, and further for algorithmically generating high quality playlists built around a context that are personalized to a profile of an account. This is accomplished by combining data from observed playlists, and data representing intrinsic properties of media items to predict contexts for media items.

Automatically predicting relevant contexts for media items

Generating a customized playlist may include identifying a user account for which a playlist is to be generated, where the user account is associated with a user listening history, a taste profile, and a social profile, identifying one or more friend accounts linked to the user account based on the social profile, obtaining an indication of a plurality of songs associated with one or more of the friend accounts, determining a listening history for the one or more plurality of songs based on the friend accounts, obtaining a subset of the plurality of songs based on the listening history of the plurality of songs, and generating a playlist from the subset of the plurality of songs.

Generating a customized social-driven playlist

Techniques for suggesting media assets, the technique including: requesting a set of candidate media assets for a set of user media items based on a knowledge graph metadata network describing the set of user media items; receiving metadata for the set of candidate media assets; determining one or more sets of ranked media assets based on the received metadata; and outputting the determined one or more sets of ranked media assets.

Automatic media asset suggestions for presentations of selected user media items

A content management system and/or client device can enable a user to initiate a quick play mode where a content category and content medium are selected for the user. A client device and/or a content management system can select a content medium for a user based on one or more factors, such as the content category. Certain content categories of content can be preferably delivered in certain content mediums. In some embodiments, a content management system and/or client device can select a content medium for a user based on contextual data gathered from the user. Contextual data can be data describing the user's current state and/or environment. For example, contextual data can include data such as the time of day, geographic location, etc.

Automated content medium selection

The present technology pertains to steering a playlisting service toward media items that are likely to receive positive feedback from a user operating a client device. The present technology permits a request to play media items without requiring an input context. A playlist service can begin to receive feedback on the playback of the media items and the received playback can be utilized by a steering service in response to a steering request to identify media items for playback that are likely to receive positive feedback based on the feedback received on a sequence of previously played media items.

Steering for unstructured media stations

The present technology pertains to automatically contextlabeling media items with relevant contexts, and further for algorithmically generating high quality playlists built around a context that are personalized to a profile of an account. This is accomplished by combining data from observed playlists, and data representing intrinsic properties of media items to predict contexts for media items.

User created playlists can be analyzed to create a statistical language model indicating the likelihood that a particular sequence of content attributes will be found in a playlist created by a user, as well as the likelihood of any sequence of one or more content attributes following a playlist or partial playlist created by a user. The language model can be used to generate a recommended content attribute sequence based on a partial playlist of one or more content items. A recommended content item sequence that will be pleasant to a user when added to the partial playlist can be selected based on the recommended content attribute sequence.

Content item recommendations based on content attribute sequence

Growing community of inventors

Cupertino, CA, United States of America

Daniel Cartoon