Google Inc.

Amazon Technologies, Inc.

Tokyo Electron Limited

Therma-wave, Inc.

Hung The Pham

Clinton Carlisle

Fred E Stanke

Edric Tong

Elliot Burke

Michael Weber

James M Cahill

Douglas E Ruth

Ruhi Sarikaya

Rohit Prasad

Xiaohu Liu

Chenlei Guo

Xing Fan

Arpit Gupta

Abhinav Sethy

Savas Parastatidis

Shuting Tang

Dean Curtis

Pushpendre Rastogi

Nitin Ashok Jain

John Arland Nave

Mayank Kumar

Nakul Dahiwade

Arshdeep Singh

Nikhil Reddy Kortha

Techniques for determining an intent of a subsequent user input in a dialog are described. The system processes historic interaction data that is structured based on natural language understanding (NLU) hypotheses, with each NLU hypothesis being associated with one or more past user inputs received by the system, one or more sample inputs, and one or more past system responses. Based on processing of the historic interaction data and dialog data of previous turns of the dialog, the system determines candidate intents for the subsequent turn of the dialog. The system also uses context data to determine the candidate intents.

Dialog management system

Techniques for recommending a skill experience to a user after a user-system dialog session has ended are described. Upon a dialog session ending, the system uses a first machine learning model to determine potential intents to recommend to a user. The system then uses a second machine learning model to determine a particular skill and intent to recommend. The system then prompts the user to accept the recommended skill and intent. If the user accepts, the system calls the recommended skill to execute. As part of calling the skill, the system sends to the skill at least one entity provided in a natural language user input of the ended dialog session. This enables the skill to skip welcome prompts, and initiate processing to output a response based on the intent and the at least one entity of the ended dialog session.

User-system dialog expansion

Techniques for transmitting a response in a messaging application via a notification can include receiving, at a computing device having one or more processors, an electronic message via a messaging application. The technique can also include outputting, at the computing device, a notification of the electronic message via a system level notification function when the messaging application is executing in a background of the computing device. The notification can include an identifier of a sender of the electronic message, at least a portion of the electronic message, and one or more suggested responses to the electronic message. The technique can further include receiving a selection of a particular response of the one or more suggested responses via the notification, and transmitting, via the messaging application, the particular response for sending to the sender of the electronic message while the messaging application is executing in the background of the computing device.

System and method for transmitting a response in a messaging application

A power distribution board (PDB) may be mounted in a server and used to convert a main power signal to useable power by the server components. The PDB can be mounted on an interior sidewall of the server to maximize available component space of the server. The PDB can include a power transformation section and a power distribution section. The power transformation section can convert the incoming power to the useable power and the power distribution section can output the useable power to the server components. Additional PDBs can be added to the server to accommodate additional server components.

Power distribution board

Implementations relate to automatic suggested responses based on message stickers provided in a messaging application. In some implementations, a computer-implemented method to provide message suggestions in a messaging application includes detecting a first message sent by a first user device to a second user device over a communication network, programmatically analyzing the first message to determine a semantic concept associated with the first message, identifying one or more message stickers based at least in part on the semantic concept, and transmitting instructions to cause the one or more message stickers to be displayed in a user interface displayed on the second user device.

Suggested responses based on message stickers

This invention is an apparatus for imaging metrology, which in particular embodiments may be integrated with a processor station such that a metrology station is apart from but coupled to a process station. The metrology station is provided with a first imaging camera with a first field of view containing the measurement region. Alternate embodiments include a second imaging camera with a second field of view. Preferred embodiments comprise a broadband ultraviolet light source, although other embodiments may have a visible or near infrared light source of broad or narrow optical bandwidth. Embodiments including a broad bandwidth source typically include a spectrograph, or an imaging spectrograph. Particular embodiments may include curved, reflective optics or a measurement region wetted by a liquid. In a typical embodiment, the metrology station and the measurement region are configured to have 4 degrees of freedom of movement relative to each other.

Apparatus for imaging metrology

Wafer metrology apparatus and method

Growing community of inventors

San Jose, CA, United States of America

Hung The Pham