Google Inc.

Googel Inc.

Lars Fabian Krüger

Johan Granström

Matthew John Leske

Peter Tore Fredrik Solenberg

Matthew Nirvan Sharifi

Dominik Roblek

Salih Burak Gokturk

Andrew Swerdlow

Dan Fredinburg

Michael W Brandt

Owen Daniel Otto

Travis Harrison Kroll Green

Annie Chen

Umesh Shankar

Tomer Amarilio

Jonathan McPhie

Tilke Mary Judd

Brandon Kyle Trew

Kyle Garner Harrison

Mor Miller

Sara Lee Su

Hristo Stefanov Stefanov

Gregory Dardyk

Peter Klein

Mark Russell Thomas

Christoph Urs Oehler

Paul Joyce

Giora Unger

Marlo James McGriff, Ii

Istvan Hernadvolgyi

Etienne DeGuine

Si-Wai Yan Lai

Eric Tholome

Matthias Zenger

Vinsensius Berlian Vega Satriardhi Naryanto

Burak Emir

Florin Oswald

Kate Emma Whelan

Robert Moritz Buessow

Thomas Kotzmann

Jose Javier Zuniga, Jr

Johan Georg Granström

Max Michiel Loubser

Joseph Adam Taylor

Alison Michelle Huml

Bao Lam

Geva Rechav

Lauren A Schmidt

A system and method for identifying unauthorized uploaded content that has been uploaded before a validated live reference stream has been ingested is disclosed herein. The live reference stream is compared against the indexed uploaded content repeatedly as the live reference stream is received. The matching process is done once per a time period until a match meeting a minimum match duration threshold is identified. The match is then determined to be unauthorized, and a claim is issued against the unauthorized uploaded content. The time period can be based on a utility based analysis that factors the computational costs of repeated matching versus the diminishing value of the live reference stream as time progresses.

Claiming delayed live reference streams

A system and method for identifying unauthorized uploaded content that has been uploaded before a stream has been ingested is disclosed herein. The stream is compared against the indexed uploaded content repeatedly as the stream is received. The matching process is done once per a time period until a match meeting a minimum match duration threshold is identified. The match is then determined to be unauthorized, and a claim is issued against the unauthorized uploaded content. The time period can be based on a utility based analysis that factors the computational costs of repeated matching versus the diminishing value of the stream as time progresses.

Flagging portions of a content stream that match indexed content

Systems and methods described herein relate to detecting the existence of unauthorized content in multiuser composite media stream. In particular, multiuser composite media streams can be examined and to determine if these composite streams include unauthorized content such as copyrighted content or nudity, violence, language violations where desired. The multiuser composite media stream can be partitioned into sections associated with broadcasting users and the portions can be analyzed independently. A notification can be provided to, e.g., the broadcasting user responsible for the unauthorized content in response to detection of the unauthorized content.

Detection of unauthorized content in live multiuser composite streams

Matching delayed live reference streams with user uploaded streams

A method includes gathering a plurality of instances of online activity associated with a user, analyzing the plurality of instances of online activity to determine a characteristic that is likely to correspond to a profile attribute of the user and generating a profile enrichment suggestion for the user based on the determined characteristic.

Identity crowd-sourced curation

Systems and methods for hierarchically partitioning a data set including a plurality of offerings are described. A system receives a data set including a plurality of offerings characterized by one or more offering attributes. The system identifies one or more candidate offering attributes associated with the offerings according to which the offerings are to be partitioned. The system assigns a partition hierarchy level to each of the candidate offering attributes that indicates a hierarchy of the offering attribute relative to other candidate offering attributes. The system determines, for each of the candidate offering attributes, a plurality of attribute values according to which the offerings are to be partitioned. The system partitions the plurality of offerings across a plurality of partition groups according to a hierarchical decision tree structure based on the partition hierarchy levels of the candidate offering attributes and the identified attribute values of each of the candidate offering attributes.

Methods and systems for hierarchically partitioning a data set including a plurality of offerings

Systems and methods for music recognition and/or tag history synchronization are described. The system includes, for example, a first device, a second device and a server. The first device is configured to record music from a surrounding environment. The first device wirelessly sends the recorded music to the server for identification. The server is configured to identify the recorded music and to generate a tag corresponding to the identified music. The first tag history is updated to include the tag which includes information corresponding to the identified music. The first device and the second device are registered with the server as part of a particular user account. The server is configured to synchronize a second tag history stored in the second device with the updated first tag history.

System and method for synchronizing tag history

Growing community of inventors

Zurich, Switzerland

Lars Fabian Krüger