Google Inc.

Adam Coimbra

Ilya Firman

Ulas Kirazci

Nikhil Rao

Ian Baker

Gaurav Bhaya

Abraham Lee

Thushan Amarasiriwardena

Carey Radebaugh

Bradley M Abrams

Wei Dong

Anshul Mohan Gupta

Hao Wu

Jay Akkad

Quazi Hussain

Prithvi Balaram

Gabriel Taubman

Cliff Kuang

Marcin M Nowak-Przygodzki

Keun Soo Yim

Sunny Goyal

Joseph Lange

James Stout

Mugurel Ionut Andreica

Thomas Weedon Hume

Abhanshu Sharma

Svetoslav Ganov

Gökhan Bakir

Mikhail Reutov

Radu Voroneanu

Jindong Chen

Mugurel-Ionut Andreica

Jacek Szmigiel

Andre Elisseeff

Dana Ritter

Robert Berry

Michael Oh

Diana Avram

Kyle Pedersen

Adam Cohen

Sneha Ashok

Alice Liang

Yudong Sun

Xiao Gao

Kalyana Ram Desineni

Saurabh Kumar

Mehdi Alizadeh

Sanjana Patel

Mubaraq Mishra

Vidhya Bhat

Reed Enger

Vishwath Mohan

Yunfan Jin

Gilles Baechler

Kyunghoon Lee

Deepak Goyal

Anton Berezin

Secure digital assistant integration with web pages is provided. The system receives an intent manifest data structure that maps actions of a digital assistant with link templates of an electronic resource developed by a third-party developer device. The system validates the electronic resource based on the intent manifest data structure. The system receives, from a data exchange component of an iframe of the electronic resource loaded by a client computing device, an identifier of the client computing device. The system receives a foreground state of the electronic resource from an onsite state sharing API. The system selects a data value for a parameter based on the foreground state and the intent manifest data structure. The system provides the data value. An authorization component generates an authorization prompt, receives input, and transmits the data value to an onsite intent execution API of the electronic resource to execute an action.

Secure digital assistant integration in web pages

The present disclosure is directed to automating user interactions in an application. In particular, the computing device can determine, based on the input data, an intent associated with performing an action on the computing device. Additionally, the computing device can invoke, using an application-level assistant component configured to provide an application-level interface on the computing device, execution of an application. Moreover, the computing device can transmit, to a system-level assistant component configured to provide a system-level interface with the computing device, instructions to interface with an actionable component of the application. The instructions can be transmitted using a trusted intermediary component configured to facilitate an interface between the system-level assistant component and the application-level assistant component. Furthermore, the computing device can engage, using the system-level assistant component, the actionable component of the application to perform the action.

Human-in-the-loop voice automation system

Indexing application actions for voice-based execution is provided. An indexer of a device receives, from an application executed by the device, an indication of an action and a deep link corresponding to the action declared by the application via an application programming interface. The indexer accesses an index stored in the memory of the device that is accessible to a plurality of applications. The indexer inputs, into a location in the index, the action and the deep link with a cryptographic token that prevents access to the deep link by unauthorized applications. A digital assistant of the device receives a voice query detected by a microphone and parses the voice query to determine the action. The digital assistant identifies in the index the deep link corresponding to the action. The digital assistant invokes, with the cryptographic token, the deep link to cause the application to perform the action.

Indexing application actions for voice-based execution

Implementations relate to determining a rendering type for an application that is executing automatically. Based on user interactions with an application that is associated with specified input from the user while the user is interacting with the application, a confidence metric is generated for each specified input and a rendering type is determined based on the confidence metrics. Subsequently, when the user requests that a sequence of actions be performed, the application will be displayed according to the rendering type.

Automatically executing application routines with user inputs

Techniques are described herein for multi-modal interaction between users, automated assistants, and other computing services. In various implementations, a user may engage with the automated assistant in order to further engage with a third party computing service. In some implementations, the user may advance through dialog state machines associated with third party computing service using both verbal input modalities and input modalities other than verbal modalities, such as visual/tactile modalities.

Multi-modal interaction between users, automated assistants, and other computing services

Interface and mode selection for digital action execution is provided. For example, a system loads a script library embedded in an electronic resource. The system determines a historic level of engagement between a client computing device and one or more digital assistants. The system selects, based on a first property of the client computing device and the historic level of engagement, a type of digital interface. The system generates, based on the type of digital interface, a digital interface with the call-to-action. The system determines, responsive to an instruction to execute the call-to-action, a mode of execution. The system selects a digital assistant and a second client device to execute the call-to-action. The system transmits the call-to-action to the second client device for execution.

Interface and mode selection for digital action execution

Implementations set forth herein relate to an automated assistant that can interact with applications that may not have been pre-configured for interfacing with the automated assistant. The automated assistant can identify content of an application interface of the application to determine synonymous terms that a user may speak when commanding the automated assistant to perform certain tasks. Speech processing operations employed by the automated assistant can be biased towards these synonymous terms when the user is accessing an application interface of the application. In some implementations, the synonymous terms can be identified in a responsive language of the automated assistant when the content of the application interface is being rendered in a different language. This can allow the automated assistant to operate as an interface between the user and certain applications that may not be rendering content in a native language of the user.

Automated assistant control of non-assistant applications via identification of synonymous term and/or speech processing biasing

Dynamic interfacing with applications is provided. For example, a system receives a first input audio signal. The system processes, via a natural language processing technique, the first input audio signal to identify an application. The system activates the application for execution on the client computing device. The application declares a function the application is configured to perform. The system modifies the natural language processing technique responsive to the function declared by the application. The system receives a second input audio signal. The system processes, via the modified natural language processing technique, the second input audio signal to detect one or more parameters. The system determines that the one or more parameters are compatible for input into an input field of the application. The system generates an action data structure for the application. The system inputs the action data structure into the application, which executes the action data structure.

Interfacing with applications via dynamically updating natural language processing

The present disclosure is generally directed to the generation of voice-activated data flows in interconnected network. The voice-activated data flows can include input audio signals that include a request and are detected at a client device. The client device can transmit the input audio signal to a data processing system, where the input audio signal can be parsed and passed to the data processing system of a service provider to fulfill the request in the input audio signal. The present solution is configured to conserve network resources by reducing the number of network transmissions needed to fulfill a request.

Activation of remote devices in a networked system

Growing community of inventors

Mountain View, CA, United States of America

Adam Coimbra