Google Inc.

Thomas L Dean

Johnny C Chen

Sudeep Gandhe

Gabriel Schine

Qiangfeng Peter Lau

Oriol Vinyals

Larry Paul Heck

Brian Strope

Howard Scott Roy

Shalini Ghosh

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for handing off a user conversation between computer-implemented agents. One of the methods includes receiving, by a computer-implemented agent specific to a user device, a digital representation of speech encoding an utterance, determining, by the computer-implemented agent, that the utterance specifies a requirement to establish a communication with another computer-implemented agent, and establishing, by the computer-implemented agent, a communication between the other computer-implemented agent and the user device.

Conversational agent response determined using a sentiment

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining other users that will attend an event with a user. One of the methods includes receiving, by a computer-implemented agent for a device, input from a user identifying an event, determining constraints for other users that will be invited to attend the event, determining one or more other users who meet the constraints, identifying, for each of the other users, other computer-implemented agents, each of the other agents for respective other devices, sending, to each of the other agents, a request to determine whether the respective other user of the other agent is interested in attending the event, receiving, from a first subset of the other agents, a response that indicates that the respective other user is interested in attending the event, and facilitating communication between the user and the respective other users.

Event scheduling

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing word sequences using neural networks. One of the methods includes receiving a first sequence of words arranged according to a first order; and for each word in the first sequence, beginning with a first word in the first order: determining a topic vector that is associated with the word; generating a combined input from the word and the topic vector, and processing the combined input through one or more sequence modeling layers to generate a sequence modeling output for the word; and processing one or more of the sequence modeling outputs through an output layer to generate a neural network output for the first sequence of words.

Topic-based sequence modeling neural networks

Conversational agent response determined using a sentiment or user profile data

Conversational agent with a particular style of expression

Conversational agent with a particular spoken style of speech

Growing community of inventors

Los Altos Hills, CA, United States of America

Thomas L Dean