Google Inc.

Balint Miklos

Phillip Neal Sharp

Prabhakar Raghavan

Tobias Kaufmann

Ijeoma Emeagwali

Karol Piotr Kurach

Thompson Alexander Ivor Gawley

László Lukács

Gregory Sean Corrado

Bogdan Prisacari

Julia Proskurnia

Ivo Krka

Matthew Nirvan Sharifi

Victor Carbune

Luis Garcia Pueyo

Luv Kothari

Marc-Allen Cartright

Itamar Gilad

Jacopo Sannazzaro Natta

Domenico Carbotta

Felix Weissenberger

Jae Seo

Ray Chen

Kevin Fu

Fo Lee

Mucun Lu

Neha Garg

Barbara Poblocka

Matthew Miao

Thomas Qian

Jason Briggs Cornwell

Kevin Courtney Smilak

Andrew Ward Moedinger

Jeroen Daniël Jillissen

Jonathan Aroner

Jung-won Shin

Marina Ganea

Victor Anchidin

Katie Hart

Stella Schieffer

Brian Strope

Deepak Jindal

Timothy Youngjin Sohn

Harshit Kharbanda

Christopher Kelley

Andrew M Dai

Louis Wang

Belinda Zeng

Peter Junteng Liu

Yun-hsuan Sung

Jessica Lee

Paul Roland Lambert

Jacqueline Amy Tsay

Matthew Vincent Dierker

Thijs Van As

Severin Heiniger

Viviana Caso Corella

Pendar Yousefi

Neil Smith

Dounia Berrada

Kai Yu

Liam MacDermed

Sundeep Vaddadi

Noah Constant

Jan Van De Kerkhof

Amr Abdelfattah

László Lukacs

Alexandru Damian

Bjarke Ebert

Heeyoung Lee

Bryan Kenneth Rea

A multimodal search system is described. The system can receive image data captured by a camera of a user device. Additionally, the system can receive audio data associated with the image data. The audio data can be captured by a microphone of the user device. Moreover, the system can process the image data to generate visual features. Furthermore, the system can process the audio data to generate a plurality of words. The system can generate a plurality of search terms based on the plurality of words and the visual features. Subsequently, the system can determine one or more search results associated with the plurality of search terms and provide the one or more search results as an output.

Visual and audio multimodal searching system

Methods and apparatus related to determining reply content for a reply to an electronic communication. Some implementations are directed generally toward analyzing a corpus of electronic communications to determine relationships between one or more original message features of 'original' messages of electronic communications and reply content that is included in “reply” messages of those electronic communications. Some implementations are directed generally toward providing reply text to include in a reply to a communication based on determined relationships between one or more message features of the communication and the reply text.

Determining reply content for a reply to an electronic communication

Methods and apparatus related to determining non-textual reply content for a reply to an electronic communication and providing the non-textual reply content for inclusion in the reply. Some of those implementations are directed to determining, based on an electronic communication sent to a user, one or more electronic documents that are responsive to the electronic communication, and providing one or more of those electronic documents for inclusion in a reply by the user to the electronic communication. For example, the electronic documents may be automatically attached to the reply and/or link(s) to the electronic documents automatically provided in the reply.

Methods and apparatus for determining non-textual reply content for inclusion in a reply to an electronic communication

An example method includes receiving, by a computing system, an identification of a recipient of an electronic message being composed from a message account associated with a user; predicting, by the computing system and based on text contained in previous electronic messages sent from the message account, text for a body of the electronic message; and outputting, for display, the predicted text for optional selection and insertion into the body of the electronic message.

Recipient based text prediction for electronic messaging

Implementations set forth herein relate to an automated assistant that can control a camera according to one or more conditions specified by a user. A condition can be satisfied when, for example, the automated assistant detects a particular environment feature is apparent. In this way, the user can rely on the automated assistant to identify and capture certain moments without necessarily requiring the user to constantly monitor a viewing window of the camera. In some implementations, a condition for the automated assistant to capture media data can be based on application data and/or other contextual data that is associated with the automated assistant. For instance, a relationship between content in a camera viewing window and other content of an application interface can be a condition upon which the automated assistant captures certain media data using a camera.

Conditional camera control via automated assistant commands

Methods and apparatus related to determining reply content for a reply to an electronic communication. Some implementations are directed generally toward analyzing a corpus of electronic communications to determine relationships between one or more original message features of 'original' messages of electronic communications and reply content that is included in 'reply' messages of those electronic communications. Some implementations are directed generally toward providing reply text to include in a reply to a communication based on determined relationships between one or more message features of the communication and the reply text.

A system may use a machine-learned model to determine whether to classify a sequence of one or more words within a first document that is being edited as a candidate hyperlink based at least in part on context associated with the first document. In response to classifying the sequence of one or more words as the candidate hyperlink, the system may use the machine-learned model and based at least in part on the sequence of one or more words and the context to determine one or more candidate document to be hyperlinked from the sequence of one or more words. In response to receiving an indication of a second document being selected out of the one or more candidate documents, the system may modify the first document to associate the sequence of one or more words with a hyperlink to the second document.

Automatic hyperlinking of documents

Methods, apparatus, systems, and computer-readable media are provided for generating and applying outgoing communication templates. In various implementations a corpus of outgoing communications sent by a user may be grouped into a plurality of clusters based on one or more attributes of a context of the user. One or more segments of each outgoing communication of a particular cluster may be classified as fixed in response to a determination that a count of occurrences of the one or more segments across the particular cluster satisfies a criterion. One or more remaining segments of each communication of the particular cluster may or may not be classified as transient. Based on sequences of classified segments associated with each communication of the particular cluster, an outgoing communication template may be generated to automatically populate at least a portion of a draft outgoing communication being prepared by the user.

Generating and applying outgoing communication templates

Systems and methods for classifying messages are provided. Each message in a plurality of messages is classified, thereby independently identifying a message category in a set of message categories for each respective message in the plurality. The plurality of messages is delivered to a plurality of recipients with a designation of the message category of each respective message in the first plurality of messages. A plurality of recipient initiated message interaction events for messages in the first plurality of messages over a predetermined period of time is collected from the plurality of recipients. A message categorization dataset is then constructed from (i) the first plurality of messages, (ii) the designation of the message category of each respective message in the subset of the first plurality of messages, and (iii) the plurality of recipient initiated message interaction events. This message categorization dataset is used to train or evaluate a message classifier.

Systems and methods for generating a message topic training dataset from user interactions in message clients

Methods and apparatus related to determining reply content for a reply to an electronic communication and providing the reply content for inclusion in the reply. Some of those implementations are directed to determining, based on an electronic communication that includes an event and is sent to a user, reply content that is tailored to the electronic communication and tailored to schedule data of the user that is temporally related to the event, and providing the reply content for inclusion in a reply by the user to the electronic communication. For example, the reply content may be automatically included in the reply and/or suggested for inclusion in the reply.

Methods and apparatus for determining, based on features of an electronic communication and schedule data of a user, reply content for inclusion in a reply by the user to the electronic communication

Growing community of inventors

Zurich, Switzerland

Balint Miklos