Miroslav Bojic from San Francisco, CA

Resumes

Miroslav Bojic

view source

Us Patents

Suggesting Actions Based On Machine Learning
view source
US Patent:

20210208908, Jul 8, 2021
Filed:

Mar 4, 2021
Appl. No.:

17/192860
Inventors:

- Mountain View CA, US
Carl Magnus Borg - San Francisco CA, US
Miroslav Bojic - San Francisco CA, US
Henry Owen Newton-Dunn - Mountain View CA, US
Jacob M. Klinker - Mountain View CA, US
Mindy Pereira - Santa Clara CA, US
Devin Mancuso - San Francisco CA, US
Daniel June Hyung Park - Sunnyvale CA, US
Lily Sin - San Francisco CA, US
Assignee:

Google LLC - Mountain View CA
International Classification:

G06F 9/451
G06N 5/04
G06N 20/00
G06Q 10/10
Abstract:

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
view source
US Patent:

20210004247, Jan 7, 2021
Filed:

Sep 21, 2020
Appl. No.:

17/027255
Inventors:

- Mountain View CA, US
Carl Magnus Borg - San Francisco CA, US
Miroslav Bojic - San Francisco CA, US
Henry Owen Newton-Dunn - Mountain View CA, US
Jacob M. Klinker - Mountain View CA, US
Mindy Pereira - Santa Clara CA, US
Devin Mancuso - San Francisco CA, US
Daniel June Hyung Park - Sunnyvale CA, US
Lily Sin - San Francisco CA, US
Assignee:

Google LLC - Mountain View CA
International Classification:

G06F 9/451
G06N 5/04
G06N 20/00
G06Q 10/10
Abstract:

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.

Task-Related Sorting, Application Discovery, And Unified Bookmarking For Application Managers
view source
US Patent:

20200364099, Nov 19, 2020
Filed:

Aug 5, 2020
Appl. No.:

16/985935
Inventors:

- Mountain View CA, US
Carl Magnus Borg - San Francisco CA, US
Miroslav Bojic - San Francisco CA, US
Henry Owen Newton-Dunn - Mountain View CA, US
Jacob M. Klinker - Mountain View CA, US
Mindy Pereira - Santa Clara CA, US
Devin Mancuso - San Francisco CA, US
Daniel June Hyung Park - Sunnyvale CA, US
Lily Sin - San Francisco CA, US
Assignee:

Google LLC - Mountain View CA
International Classification:

G06F 9/54
G06Q 10/10
G06F 8/61
G06F 8/65
G06F 9/48
Abstract:

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.

Suggesting Actions Based On Machine Learning
view source
US Patent:

20190188013, Jun 20, 2019
Filed:

May 8, 2018
Appl. No.:

15/974284
Inventors:

- Mountain View CA, US
Carl Magnus Borg - San Francisco CA, US
Miroslav Bojic - San Francisco CA, US
Henry Owen Newton-Dunn - Mountain View CA, US
Jacob M. Klinker - Mountain View CA, US
Mindy Pereira - Santa Clara CA, US
Devin Mancuso - San Francisco CA, US
Daniel June Hyung Park - Sunnyvale CA, US
Lily Sin - San Francisco CA, US
Assignee:

Google LLC - Mountain View CA
International Classification:

G06F 9/451
G06N 99/00
G06N 5/04
Abstract:

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.

Task-Related Sorting, Application Discovery, And Unified Bookmarking For Application Managers
view source
US Patent:

20190188059, Jun 20, 2019
Filed:

Aug 24, 2018
Appl. No.:

16/112400
Inventors:

- Mountain View CA, US
Carl Magnus Borg - San Francisco CA, US
Miroslav Bojic - San Francisco CA, US
Henry Owen Newton-Dunn - Mountain View CA, US
Jacob M. Klinker - Mountain View CA, US
Mindy Pereira - Santa Clara CA, US
Devin Mancuso - San Francisco CA, US
Daniel June Hyung Park - Sunnyvale CA, US
Lily Sin - San Francisco CA, US
Assignee:

Google LLC - Mountain View CA
International Classification:

G06F 9/54
G06F 8/65
G06F 8/61
G06F 9/48
Abstract:

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.

Refined Search With Machine Learning
view source
US Patent:

20190188322, Jun 20, 2019
Filed:

Jun 13, 2018
Appl. No.:

16/008021
Inventors:

- Mountain View CA, US
Carl Magnus Borg - San Francisco CA, US
Miroslav Bojic - San Francisco CA, US
Henry Owen Newton-Dunn - Mountain View CA, US
Jacob M. Klinker - Mountain View CA, US
Mindy Pereira - Santa Clara CA, US
Devin Mancuso - San Francisco CA, US
Daniel June Hyung Park - Sunnyvale CA, US
Lily Sin - San Francisco CA, US
Assignee:

Google LLC - Mountain View CA
International Classification:

G06F 17/30
G06N 99/00
Abstract:

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.

Transitioning Between Graphical Interface Element Modalities Based On Common Data Sets And Characteristic Of User Input
view source
US Patent:

20190050115, Feb 14, 2019
Filed:

Aug 11, 2017
Appl. No.:

15/675092
Inventors:

- Mountain View CA, US
Mindy Pereira - Santa Clara CA, US
Carl Magnus Borg - San Francisco CA, US
Henry Owen Newton-Dunn - Mountain View CA, US
Lily Sin - San Fransisco CA, US
Glen Murphy - Palo Alto CA, US
Miroslav Bojic - San Francisco CA, US
International Classification:

G06F 3/0482
G06F 3/0488
G06F 3/041
Abstract:

In general, techniques are described for enabling a computing device to expand an element associated with an application in order to show different sets of actions associated with the application. The computing device displays a graphical user interface including an interface element associated with the application. The computing device receives an indication of user input. The computing device determines a characteristic of the user input and whether the characteristic is a first characteristic or a second characteristic. The computing device, responsive to determining that the characteristic of the user input is the first characteristic, outputs, for display, a first set of sub-elements or, responsive to determining that the characteristic of the user input is the second characteristic, outputs, for display, a second set of sub-elements. Each sub-element in the first and second sets of sub-elements is associated with unique actions associated with the application.