Google Inc.

Mindy Pereira

Devin Mancuso

Golden Gopal Krishna

Daniel June Hyung Park

Henry Owen Newton-Dunn

Miroslav Bojic

Carl Magnus Borg

Jacob M Klinker

Lily Sin

Daniel Marc Gatan Shiplacoff

Mark Thomas Renouf

Ned Burns

This document describes techniques for suggesting actions based on machine learning. These techniques determine a task that a user desires to perform, and presents a user interface through which to perform the task. To determine this task, the techniques can analyze content displayed on the user device or analyze contexts of the user and user device. With this determined task, the techniques determine an action that may assist the user in performing the task. This action is further determined to be performable through analysis of functionalities of an application, which may or may not be executing or installed on the user device. With some subset of the application's functionalities determined, the techniques presents the subset of functionalities via the user interface. By so doing, the techniques enable a user to complete a task more easily, quickly, or using fewer computing resources.

Suggesting actions based on machine learning

This document describes techniques and devices for a refined search with machine learning. These techniques improve computer-aided searches through enabling selection of search criteria used in a prior search and providing a refined search result based on that selection. Furthermore, a machine-learning component of a search engine can be altered to improve future search results based on the selection and an indication of the desirability of the refined search result.

Refined search with machine learning

This document describes techniques and devices for task-related sorting, application discovery, and unified bookmarking for application managers. Through use of an application manager, multiple applications (including standalone applications, instant applications, websites, and other content) that a person can use to accomplish a single task, or multiple related tasks, are sorted into discrete groups for display in the application manager. The application manager can automatically recognize relationships between activities performed with the applications and recognize user actions with the applications that are related to the activities. Based on the relationships and user actions, the application manager can automatically determine that the activities and actions represent a task and display a task group that includes the applications that represent the task. The task groups may be visually displayed as a stack, strip, or pile of windows or thumbnails representing each application or other content the person could use for the task.

Task-related sorting, application discovery, and unified bookmarking for application managers

A computing device includes at least one processor; a display device; and at least one module. The at least one processor may be operable to store data that defines a plurality of discrete graphical elements (DGE's), wherein the plurality of DGE's includes at least one root DGE, and wherein dismissal of the root DGE causes dismissal of all of the plurality of DGE's. The at least one module may be operable to output a particular DGE of the plurality of DGE's; output, for display, the root DGE, responsive to receiving a first indication of user input of a particular input type; and ignore the second indication of user input to refrain from dismissal of the root DGE, responsive to receiving a second indication of user input of the particular input type within a threshold time duration that is initiated responsive to outputting the root DGE.

Inadvertent dismissal prevention for graphical content

Growing community of inventors

Santa Clara, CA, United States of America

Mindy Pereira