Apple Inc.

Eric Circlaeys

Kevin Bessiere

Benedikt M Hirmer

Killian Huyghe

Zachary H Smith

Sabrine Rekik

Guillaume Vergnaud

Kevin Aujoulet

Patrick H Kelly

Alan C Dye

Stephen Olivier Lemay

Gary Ian Butcher

Henrique Dias Penha

Cyrus Daniel Irani

Brendan John Langoulant

Justin S Titi

Britt S Miura

Paulo Michaelo Lopez

Simon Bovet

Daniel E Gobera Rubalcava

Marcos Regis Vescovi

Gavin B Thomson

Tony F Kinnis

Baskaran Subramaniam

James Alan Queen

Paul M Bombach

Christopher I Wilson

Christopher G Wilson

Vignesh Jagadeesh

Christopher John Moulios

Krishna M Behara

Sowmya Gopalan

Daniel Cartoon

Betim Deva

Matthias Mauch

Nathaniel B Chapman

Michael S Smochko

Shanni A Weilert

Christopher C Foster

Kalu Onuka Kalu

Bruno J Conejo

Elliot C Liskin

Cristina N Smith

Alexa Rockwell

Samantha E Fierro

Alexandre N Lopoukhine

Rohan Chandra

Lee A Morgan

Michael Chatzidakis

Omid Javidbakht

Rehan Rishi

Mayank Yadav

Brian J Rogosky

Alfredo Ramos-Alvarez

Bruno Di Giorgi

Jeremy P Bogle

Hao Yang

Neil C Foley

Menelaos D Kokolios

Lewis Kaneshiro

Jorge A Herrera Soto

James E Hewitt

Casey W Baker

Alexis H Durocher

Joy Hsu

Kartheekeya D Kasibatta

Trevor M Slaton

Devices, methods, and non-transitory program storage devices (NPSDs) are disclosed herein to provide for the privacy-respectful learning of iconic scenes and places, wherein the learning is based on information received from one or more client devices in response to one or more collection criteria specified as part of one or more collection operations launched by a server device. In some embodiments, differential privacy techniques (such as the submission of predetermined amounts of noise-injecting, e.g., randomly-generated, data in conjunction with actual data) are employed by the client devices, such that any insights learned by the server device only relate to 'hot spots,' “themes,” or other scenes, objects, and/or topics that are highly popular and captured in the digital assets (DAs) of many users, ensuring there is no way for the server device to learn or glean any insights related to particular users of individual client devices participating in the collection operations.

Learning iconic scenes and places with privacy

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

In some implementations, a computing device may create a semantic mapping that includes identified features that appear in a particular percentage of assets in a subset of assets of a media library. Also, the computing device may analyze assets of the media library using the semantic mapping to generate semantic scores, which may be used to determine a first tier of assets from the media library that rate highest for semantic score out of all assets. The computing device may present at least one of the first tier assets prominently in a user interface when viewing assets of the media library.

Behavioral curation of media assets

The present disclosure generally relates to retrieving and displaying contextually-relevant media content. In some embodiments, a device receives a request to display contextually-relevant media and, in response, displays a representation of a collection of media items relevant to a context of the device. In some embodiments, a device displays a visual media item of a sequence of items and, in response to receiving a swipe gesture, displays a detail user interface comprising related content for the media item. In some embodiments, a device, while displaying a first detail user interface, displays an affordance corresponding to a plurality of individuals identified as having attended a first event, that when selected, causes display of visual media corresponding to a plurality of events attended by the individuals. In some embodiments, a device, in response to user input, obtains an automatically-generated collection of visual media and displays a corresponding affordance.

User interfaces for retrieving contextually relevant media content

Embodiments of the present disclosure present devices, methods, and computer readable medium for disambiguating clustered location identifiers. A location identifier can be the name of a business or establishment. Digital assets contain a plurality of metadata that can be used to identify the location or establishment at which digital assets were captured. Techniques can use various types contextual information based on a category of the digital asset for disambiguation. Automatically labelling the digital assets assists a user in organizing and sharing the digital assets with friends and family. Users can search for digital assets by the name of the location where the digital assets were captured.

Techniques for disambiguating clustered location identifiers

Systems, methods, and computer-readable media for defining a collection of media content items of a media library for a relevant interest are provided.

Defining a collection of media content items for a relevant interest

Systems, methods, and computer-readable media for determining at least one valid mood for a collection of media content items of a media library are provided.

Mood determination of a collection of media content items

In some implementations, a computing device may generate a day view, month views, and year view that show cards specific to each view. The cards include images, videos, and/or other assets from a media library that reflect a corresponding time frame of the card on which the assets are displayed. A selected view is presented in a graphical user interface (GUI) for interaction with a user of the media library. Upon selection of an asset displayed to the GUI, the view is switched to show more assets from a time frame similar to the selected asset while maintaining a focus on the selected asset.

Curated media library

Embodiments of the present disclosure present devices, methods, and computer readable medium for presenting a user interface that allows a user to quickly and easily filter and search a digital asset collection. The disclosed techniques allow for rapid recall of desired digital assets, linking assets into logical collections, and an overall improved user experience. The zero keyword/contextual keyword feature presents multimedia content icons and searchable keywords to allow a user to search the digital asset collection simply by tapping on one of these keywords. The top auto completion feature auto-completes suggestions in the search field based on various heuristics to ensure the method produces diverse and relevant results. The next keyword suggestion feature predicts a next search term based on learned properties about the digital asset collection.

Digital asset search user interface

A memory management system which can effectively determine whether, when, and to what extent, to modify a graph database based on changes in a paired relational database storing various data like media assets, such as photos and videos. The media assets are associated with data objects, such as moments, events, and people. The memory management system also includes one or more knowledge graph metadata networks (or more simply 'knowledge graphs'). The knowledge graph(s) store information which is related to the data stored by the relational databases. The memory management system detects changes in the data and data objects stored by the relational database(s). The memory management system can translate detected changes into modification instructions for the knowledge graph. The memory management system can also determine that it is unnecessary to modify the knowledge graph due to a detected change.

Smart updates from historical database changes

Embodiments are disclosed for face syncing in a distributed computing environment. In an embodiment, a method comprises: obtaining, by a processor, media assets that include faces of individuals; detecting, by the processor of a mobile device, the faces on the media assets; generating, by the processor, faceprints for the detected faces; clustering, by the processor, the faceprints into clusters; generating, by the processor, a face crop image for each cluster; and sending, by the processor, the face crop images to a network-based, distributed syncing service.

Face syncing in distributed computing environment

Systems, methods, and computer-readable media for reducing a number of unverified persons detected in media content are provided.

Reduction of unverified entity identities in a media library

In some implementations, a computing device can generate personalized music selections to associate with any collections of visual media (e.g., photos and videos) stored on the computing device. A user may prefer particular genres of music and listen to some genres more frequently than others. The computing device can create measures of the user's genre preferences and use these measures to select music that is preferred by the user and music that may be significant or relevant to the particular collection of visual media. The computing device may also determine music that was being played when and where the visual media were being created. The computing device may store the visual media and music items in association with each other. The computing device may generate composite media items that combine the visual media and music items. When the visual media are viewed, the selected music item is also played.

Music selections for personal media compositions

Growing community of inventors

Los Gatos, CA, United States of America

Eric Circlaeys