Peng Kelly K Zhang

US Patent:

20130204715, Aug 8, 2013

Filed:

Feb 8, 2012

Appl. No.:

13/369281

Inventors:

Peng ZHANG - Los Angeles CA, US

International Classification:

G06Q 30/02
G06F 17/30

US Classification:

705 1473

Abstract:

Systems and methods of identifying ad elements of web pages via a computer network are provided. A script configured to identify an ad slot on a web page can be obtained by at least one data processing system having an ad slot evaluation module. The script can be executed to obtain advertisement parameters of the ad slot and web page parameters of the ad slot and generate a unique identifier of the ad slot. The generated unique identifier is associated with a URL identifier of the web page. The data processing system evaluates at least one database to determine one of a presence and an absence of the historical ad slot data. The data processing system provides content for display in the ad slot of the web page based at least in part on a result of the evaluation of the database.

US Patent:

20140019262, Jan 16, 2014

Filed:

Jul 11, 2012

Appl. No.:

13/546978

Inventors:

Paul Schelte Albert Reitsma - Marina del Rey CA, US
Peng Zhang - Los Angeles CA, US

Assignee:

GOOGLE INC. - Mountain View CA

International Classification:

G06F 15/16
G06Q 30/02

US Classification:

705 1471, 709217, 705 1473

Abstract:

Methods, systems, and apparatus, including computer programs encoded on a computer-readable storage medium, and including a method for predicting visibility of web pages. The method comprises identifying web pages that include slots for presenting content. The method further comprises, for each slot, creating a fingerprint based on a URL associated with the page and structural information associated with the slot's location on the page, determining a likelihood of the slot being visible when the web page is initially presented, the likelihood in the form of a predictive model, and saving the fingerprint and predictive model in a data structure. The method further comprises receiving a request for content from a web page, creating fingerprints associated with the web page, and comparing the fingerprints to fingerprints in the data structure. When a matching fingerprint is located, prediction data is used that is associated with a matching fingerprint for the web page.

US Patent:

20200202058, Jun 25, 2020

Filed:

Dec 20, 2019

Appl. No.:

16/723091

Inventors:

- Los Angeles CA, US
Peng Zhang - Los Angeles CA, US
Jingsheng Jason Cong - Los Angeles CA, US

International Classification:

G06F 30/27
G06F 30/34
G06F 9/50
G06F 9/54
G06N 20/10

Abstract:

Systems and methods for designing an information processing system are described. In one embodiment, a design space is partitioned into a plurality of independent partitions based on a defined set of rules. A unique processing core is assigned to each partition. A plurality of starting points is generated for each partition, where each starting point is associated with a machine learning algorithm. The starting points for each partition may include a performance driven seed and an area-driven seed. A set of feasible designs associated with the information processing system are determined.

US Patent:

20170236524, Aug 17, 2017

Filed:

May 2, 2017

Appl. No.:

15/584839

Inventors:

- Mountain View CA, US
Farnaz Azmoodeh - Marina Del Rey CA, US
Eric Wood - Los Angeles CA, US
Congxing Cai - Los Angeles CA, US
Paul Schelte Albert Reitsma - Marina Del Rey CA, US
Glenn Wilson - Playa Vista CA, US
Peng Zhang - Los Angeles CA, US
Troy Louis Walker - Santa Monica CA, US
Gaurav Bhaya - Mountain View CA, US
Robert Stets - Mountain View CA, US

Assignee:

Google Inc. - Mountain View CA

International Classification:

G10L 19/16
H04N 21/439
G06K 9/00
G06Q 30/02
G06F 17/22
G06F 3/16
G06K 9/62

Abstract:

Systems and methods to determine the status of transmitted audio packets. The audio packets can include digital components that are presented by a client computing device. Based on presentation variables and determinations of presentation status, the system can generate a predictive model that can be used to dynamically determines presentation values of audio packets prior to their transmission to a client computing device.

US Patent:

20160335664, Nov 17, 2016

Filed:

Apr 5, 2016

Appl. No.:

15/091323

Inventors:

- Mountain View CA, US
Farnaz Azmoodeh - Marina Del Rey CA, US
Eric Wood - Los Angeles CA, US
Congxing Cai - Los Angeles CA, US
Paul Schelte Albert Reitsma - Marina Del Rey CA, US
Glenn Wilson - Playa Vista CA, US
Peng Zhang - Los Angeles CA, US
Troy Louis Walker - Santa Monica CA, US

International Classification:

G06Q 30/02
G06K 9/00
G06K 9/62
G06F 17/22

Abstract:

Systems and methods to determine image pixel status on a hardware display are provided. The systems and methods can determine a status of a uniquely identifiable measurement pixel of a first content item displayed on a display of a client device. The status can indicate that the measurement pixel is present in a viewable region of the display. The systems and methods can receive viewability variables from the client device. The viewability variables can include information regarding physical and electrical characteristics of the display, and can include information regarding data displayed on the display. The systems and methods can generate a view probability predictive model based on statuses and viewability variables determined from other client devices that previously displayed content items having measurement pixels.

US Patent:

20150269615, Sep 24, 2015

Filed:

Jun 9, 2015

Appl. No.:

14/734644

Inventors:

- Mountain View CA, US
Peng Zhang - Los Angeles CA, US

International Classification:

G06Q 30/02
G06N 5/02

Abstract:

Methods, systems, and apparatus, including computer programs encoded on a computer-readable storage medium, and including a method for predicting visibility of web pages. The method comprises identifying web pages that include slots for presenting content. The method further comprises, for each slot, creating a fingerprint based on a URL associated with the page and structural information associated with the slot's location on the page, determining a likelihood of the slot being visible when the web page is initially presented, the likelihood in the form of a predictive model, and saving the fingerprint and predictive model in a data structure. The method further comprises receiving a request for content from a web page, creating fingerprints associated with the web page, and comparing the fingerprints to fingerprints in the data structure. When a matching fingerprint is located, prediction data is used that is associated with a matching fingerprint for the web page.

US Patent:

20150206199, Jul 23, 2015

Filed:

Apr 18, 2014

Appl. No.:

14/256775

Inventors:

- Mountain View CA, US
Peng Zhang - Los Angeles CA, US

Assignee:

Google Inc. - Mountain View CA

International Classification:

G06Q 30/02

Abstract:

Systems and methods of identifying ad elements of web pages via a computer network are provided. A script configured to identify an ad slot on a web page can be obtained by at least one data processing system having an ad slot evaluation module. The script can be executed to obtain advertisement parameters of the ad slot and web page parameters of the ad slot and generate a unique identifier of the ad slot. The generated unique identifier is associated with a URL identifier of the web page. The data processing system evaluates at least one database to determine one of a presence and an absence of the historical ad slot data. The data processing system provides content for display in the ad slot of the web page based at least in part on a result of the evaluation of the database.

US Patent:

20140372205, Dec 18, 2014

Filed:

Jun 12, 2013

Appl. No.:

13/916407

Inventors:

- Mountain View CA, US
Farnaz Azmoodeh - Marina Del Rey CA, US
Eric Wood - Los Angeles CA, US
Congxing Cai - Los Angeles CA, US
Paul Schelte Albert Reitsma - Marina Del Rey CA, US
Glenn Wilson - Playa Vista CA, US
Peng Zhang - Los Angeles CA, US
Troy Louis Walker - Santa Monica CA, US

Assignee:

Google Inc. - Mountain View CA

International Classification:

G06Q 30/02

US Classification:

705 1445

Abstract:

A system may select and serve content items based on a view probability. The view probability may be determined using a view probability predictive model and one or more current viewability variables. Based on the determined view probability output by the view probability predictive model, a content item may be selected and served. A script may be included with or otherwise associated with the data output to effect presentation of the selected content item. The script outputs data indicative of whether the served content item is viewed on a display of a device. The script may output data indicating that the served content item is viewed when at least a predetermined percentage of the pixels of the served content item are within a viewable region for a period of time. A served content item may be determined to not have been viewed if a predetermined period of time elapses.