Grace C Cheng

US Patent:

20200125050, Apr 23, 2020

Filed:

Oct 21, 2019

Appl. No.:

16/658757

Inventors:

- Dublin, IE
Mary Elizabeth Hamilton - San Mateo CA, US
Grace T. Cheng - Mountain View CA, US
Michael E. Simanek - Chicago IL, US
Amir M. Khan - Frisco TX, US
Joseph Pollock - Piedmont CA, US
Fadi Mahmoud - Sausalito CA, US
Michael Baroody - San Francisco CA, US

International Classification:

G05B 19/042
G06F 9/451

Abstract:

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for initiating actions based on sequences of events. In one aspect, a process includes receiving, from each of multiple devices, data specifying an event detected by the device. The events are compared to configured scenarios that each specify a sequence of trigger events and an action to be initiated in response to detecting the sequence of trigger events. A determination is made that the events match a first scenario of the scenarios. In response to determining that the events detected by the multiple devices match the first scenario, a first action specified by the first scenario is initiated. A determination is made that a combination of one or more of the events detected by the multiple devices and the first action matches a second scenario. In response, a second action specified by the second scenario is initiated.

US Patent:

20200118323, Apr 16, 2020

Filed:

Dec 3, 2019

Appl. No.:

16/701969

Inventors:

- Dublin, IE
Robert Dooley - Dublin CA, US
Grace T. Cheng - Mountain View CA, US
Sunny Webb - San Francisco CA, US
Mary Elizabeth Hamilton - San Mateo CA, US

International Classification:

G06T 13/20
G06K 9/00
G06T 15/20
G06K 9/62
G06T 19/20

Abstract:

Implementations are directed to methods, systems, apparatus, and computer programs for generation of a three-dimensional (3D) animation by receiving a user input defining a two-dimensional (2D) representation of a plurality of elements, processing, by the one or more processors, the 2D representation to classify the plurality of elements in symbolic elements and action elements, generating, by the one or more processors, based on the symbolic elements, the action elements, and a set of rules a 3D animation corresponding to the 2D representation, and transmitting, by the one or more processors, the 3D animation to an extended reality device for display.

US Patent:

20190087733, Mar 21, 2019

Filed:

Sep 21, 2017

Appl. No.:

15/711752

Inventors:

- Dublin, IE
Grace T. Cheng - Mountain View CA, US
Alex M. Kass - Palo Alto CA, US

International Classification:

G06N 5/04
G06Q 10/08
G06N 3/02
G06N 99/00

Abstract:

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for a predictive analytics system that provides a mechanism to change the design or implementations of a product manufactured in a supply chain are disclosed. In one aspect, a method includes the actions of receiving training data that includes private information for a node in a supply chain network and information regarding previous decisions related to product change requests for a product manufactured through the supply chain network; training, using the training data, a predictive model configured to render decisions for requests to change a part used in manufacturing the product; receiving a request to change a given part; applying the predictive model to the request to change the given part; determining a decision approving or denying the request; and transmitting the decision to the requesting node.

US Patent:

20190026931, Jan 24, 2019

Filed:

Jul 17, 2018

Appl. No.:

16/037660

Inventors:

- Dublin, IE
Robert Dooley - Dublin CA, US
Grace T. Cheng - Mountain View CA, US
Sunny Webb - San Francisco CA, US
Mary Elizabeth Hamilton - San Mateo CA, US

International Classification:

G06T 13/20
G06T 19/20
G06T 15/20
G06K 9/62

Abstract:

Implementations are directed to methods, systems, apparatus, and computer programs for generation of a three-dimensional (3D) animation by receiving a user input defining a two-dimensional (2D) representation of a plurality of elements, processing, by the one or more processors, the 2D representation to classify the plurality of elements in symbolic elements and action elements, generating, by the one or more processors, based on the symbolic elements, the action elements, and a set of rules a 3D animation corresponding to the 2D representation, and transmitting, by the one or more processors, the 3D animation to an extended reality device for display.

US Patent:

20180307311, Oct 25, 2018

Filed:

Apr 19, 2018

Appl. No.:

15/956816

Inventors:

- Dublin, IE
Matthew Thomas Short - San Jose CA, US
Manish Mehta - Milpitas CA, US
Robert Dooley - Dublin CA, US
Grace T. Cheng - Sunnyvale CA, US
Alpana Dubey - San Jose CA, US

International Classification:

G06F 3/01
G06T 3/40

Abstract:

Methods, systems, and apparatus for performing virtual reality simulations using virtual reality systems. In some aspects a method includes the actions of logging user actions in a virtual reality system, wherein the user actions include one or more of (i) a path traveled by user in the virtual reality system, or (ii) user interactions with objects in the virtual reality system; aggregating logged action over a first user and a second user; and deriving modifications to the virtual reality system based at least in part on the aggregated logged actions. The modifications to the VR system can include modifying at least one of (i) appearance of objects shown in the VR system, (ii) floor plan of the VR system, and (iii) location of objects shown in the VR system.

US Patent:

20180308379, Oct 25, 2018

Filed:

Apr 18, 2018

Appl. No.:

15/956491

Inventors:

- Dublin, IE
Robert Dooley - Dublin CA, US
Matthew Thomas Short - San Jose CA, US
Grace T. Cheng - Sunnyvale CA, US

International Classification:

G09B 9/052
G06T 19/00
G09B 5/02

Abstract:

Methods and systems for creating digital representations of real world objects that are connected back to real world objects, creating a digital double. In some aspects a method includes the actions of receiving sensor data from a real world object; receiving data representing a digital version of the real world object; and performing a virtual reality simulation displaying (i) a representation of at least some of the sensor data, and (ii) the digital version of the real world object. Performing a virtual reality simulation using (i) the sensor data, and (ii) the data representing the digital version of the real world object can include overlaying a visual representation of the sensor data on a visual representation of the digital version of the real world object. The method can further include determining one or more modifications to the real world object based on the performed virtual reality simulation.