Hung Quoc Bui

20090307162, Dec 10, 2009

Jun 1, 2009

12/476020

Hung Bui - Mountain View CA, US
Steven Eker - East Palo Alto CA, US
Daniel Elenius - San Mateo CA, US
Melinda Gervasio - Mountain View CA, US
Thomas J. Lee - San Francisco CA, US
Mei Marker - Santa Clara CA, US
David Morley - Camberwell, AU
Janet Murdock - Mountain View CA, US
Karen Myers - Menlo Park CA, US
Bart Peintner - Palo Alto CA, US
Shahin Saadati - Santa Clara CA, US
Eric Yeh - Alameda CA, US
Neil Yorke-Smith - Mountain View CA, US

G06F 15/18
G06F 9/46
G06N 5/02

706 12, 718100, 706 54

The present invention relates to a method and apparatus for assisting with automated task management. In one embodiment, an apparatus for assisting a user in the execution of a task, where the task includes one or more workflows required to accomplish a goal defined by the user, includes a task learner for creating new workflows from user demonstrations, a workflow tracker for identifying and tracking the progress of a current workflow executing on a machine used by the user, a task assistance processor coupled to the workflow tracker, for generating a suggestion based on the progress of the current workflow, and a task executor coupled to the task assistance processor, for manipulating an application on the machine used by the user to carry out the suggestion.

20140052680, Feb 20, 2014

Aug 14, 2012

13/585003

Kenneth C. Nitz - Redwood City CA, US
Patrick D. Lincoln - Woodside CA, US
Karen L. Myers - Menlo Park CA, US
Hung H. Bui - Mountain View CA, US
Rukman Senanayake - San Jose CA, US
Grit Denker - Palo Alto CA, US
William S. Mark - San Mateo CA, US
Norman D. Winarsky - Palo Alto CA, US
Steven S. Weiner - Merion Station PA, US

G06N 5/02

706 46

A device, method and system for automatically inferring a mobile user's current context includes applying a user activity knowledge base to real-time inputs and stored user-specific information to determine a current situation. Automated reasoning is used to infer a user-specific context of the current situation. Automated candidate actions may be generated and performed in accordance with the current situation and user-specific context.

20140052681, Feb 20, 2014

Aug 14, 2012

13/585008

Kenneth C. Nitz - Redwood City CA, US
Patrick D. Lincoln - Woodside CA, US
Karen L. Myers - Menlo Park CA, US
Hung H. Bui - Mountain View CA, US
Rukman Senanayake - San Jose CA, US
Grit Denker - Palo Alto CA, US
William S. Mark - San Mateo CA, US
Norman D. Winarsky - Palo Alto CA, US
Steven S. Weiner - Merion Station PA, US

G06N 5/02

706 46

A device, method and system for automatically inferring a mobile user's current context includes applying a user activity knowledge base to real-time inputs and stored user-specific information to determine a current situation. Automated reasoning is used to infer a user-specific context of the current situation. Automated candidate actions may be generated and performed in accordance with the current situation and user-specific context.

20210050014, Feb 18, 2021

Nov 2, 2020

17/086805

- San Jose CA, US
Trung Bui - San Jose CA, US
Hung Bui - Sunnyvale CA, US

G10L 15/22
G10L 15/16
G06N 3/10
G06N 3/04
G10L 15/30

The present disclosure relates to systems, methods, and non-transitory computer readable media for generating dialogue responses based on received utterances utilizing an independent gate context-dependent additive recurrent neural network. For example, the disclosed systems can utilize a neural network model to generate a dialogue history vector based on received utterances and can use the dialogue history vector to generate a dialogue response. The independent gate context-dependent additive recurrent neural network can remove local context to reduce computation complexity and allow for gates at all time steps to be computed in parallel. The independent gate context-dependent additive recurrent neural network maintains the sequential nature of a recurrent neural network using the hidden vector output.

20200320329, Oct 8, 2020

Jun 18, 2020

16/904881

- SAN JOSE CA, US
Hung Hai Bui - Sunnyvale CA, US
Shawn Alan Gaither - Raleigh NC, US
Walter Wei-Tuh Chang - San Jose CA, US
Michael Frank Kraley - Lexington MA, US
Pranjal Daga - West Lafayette IN, US

G06K 9/34
G06K 9/00
G06K 9/72
G06Q 10/10
G06Q 10/06
G06F 40/10

The present invention is directed towards providing automated workflows for the identification of a reading order from text segments extracted from a document. Ordering the text segments is based on trained natural language models. In some embodiments, the workflows are enabled to perform a method for identifying a sequence associated with a portable document. The methods includes iteratively generating a probabilistic language model, receiving the portable document, and selectively extracting features (such as but not limited to text segments) from the document. The method may generate pairs of features (or feature pair from the extracted features). The method may further generate a score for each of the pairs based on the probabilistic language model and determine an order to features based on the scores. The method may provide the extracted features in the determined order.

20200090651, Mar 19, 2020

Sep 17, 2018

16/133190

- San Jose CA, US
Trung Bui - San Jose CA, US
Hung Bui - Sunnyvale CA, US

G10L 15/22
G10L 15/16
G10L 15/30
G06N 3/04
G06N 3/10

The present disclosure relates to systems, methods, and non-transitory computer readable media for generating dialogue responses based on received utterances utilizing an independent gate context-dependent additive recurrent neural network. For example, the disclosed systems can utilize a neural network model to generate a dialogue history vector based on received utterances and can use the dialogue history vector to generate a dialogue response. The independent gate context-dependent additive recurrent neural network can remove local context to reduce computation complexity and allow for gates at all time steps to be computed in parallel. The independent gate context-dependent additive recurrent neural network maintains the sequential nature of a recurrent neural network using the hidden vector output.

20190324606, Oct 24, 2019

Apr 19, 2018

15/957706

- San Jose CA, US
Zheng Wen - Fremont CA, US
Hung Bui - Sunnyvale CA, US
Tong Yu - San Mateo CA, US

G06F 3/0483
G06N 99/00
H04L 29/08
G06F 17/21

Systems and methods for customizing an interactive experience based on topics determined from an online topic model. In an example, a segmentation application executing on a computing device accesses past user interaction vectors that represent interaction data from an electronic content delivery system. The segmentation application accesses a segmentation model having parameters. The segmentation application updates the parameters by performing tensor decomposition on a tensor built from the past user interaction vectors and calculating updating values of the parameters from the tensor decomposition. The segmentation application performs a segmentation of user devices by applying the segmentation model with the updated parameters to the present user interaction vector. The segmentation assigns the user device to the user segment. The segmentation application transmits data describing the segmentation to the electronic content delivery system.

20190325068, Oct 24, 2019

Apr 19, 2018

15/957556

- San Jose CA, US
Trung Bui - San Jose CA, US
Sheng Li - San Jose CA, US
Quan Hung Tran - Melbourne, AU
Hung Bui - Sunnyvale CA, US

G06F 17/30
G06N 3/08
G06Q 30/06

The present disclosure relates to systems, methods, and non-transitory computer readable media for generating digital responses to digital queries by utilizing a classification model and query-specific analysis models. For example, the disclosed systems can train a classification model to generate query classifications corresponding to product queries, conversational queries, and/or recommendation/purchase queries. Moreover, the disclosed systems can apply the classification model to select pertinent models for particular queries. For example, upon classifying a product query, disclosed systems can utilize a neural ranking model (trained based on a set of training product specifications and training queries) to generate relevance scores for product specifications associated with a digital query. The disclosed systems can further compare generated relevance scores to select a product specification and generate a digital response that includes the pertinent product specification to provide for display to a client device.