Deepak Ravichandran

Address:

150 Granada Dr, Mountain View, CA 94043

VIN:

JTDKN3DU6A0012051

Make:

TOYOTA

Model:

PRIUS

Year:

2010

US Patent:

8572096, Oct 29, 2013

Filed:

Nov 16, 2011

Appl. No.:

13/297544

Inventors:

Rohan Seth - San Francisco CA, US
Shumeet Baluja - Leesburg VA, US
Dandapani Sivakumar - Cupertino CA, US
Deepak Ravichandran - Mountain View CA, US

Assignee:

Google Inc. - Mountain View CA

International Classification:

G06F 17/30

US Classification:

707748, 707E17084, 707737

Abstract:

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting keywords for resources. In one aspect, a method includes identifying a particular online resource that includes non-text content. Co-visitation data are obtained for the particular resource. The co-visitation data specify one or more co-requested online resources for the particular online resource. Each of the co-requested online resources were requested by a user device within a threshold period of the request for the particular online resource by the user device. Keywords are identified for each of the co-requested online resources, and can include keywords that were selected based on text content of the co-requested online resource. One or more of the identified keywords are selected as keywords for the particular resource.

US Patent:

8527526, Sep 3, 2013

Filed:

May 2, 2012

Appl. No.:

13/462130

Inventors:

Jia Liu - Sunnyvale CA, US
Yijian Bai - San Ramon CA, US
Deepak Ravichandran - Mountain View CA, US
Shankar Ponnekanti - Mountain View CA, US

Assignee:

Google Inc. - Mountain View CA

International Classification:

G06F 7/00

US Classification:

707751

Abstract:

A computerized method, system for, and computer-readable medium operable to select a list of network user identifiers. A processing circuit receives a list of network user identifiers represented by long-term history data indicative of web pages visited prior to a first time and short-term history data indicative of web pages visited after the first time and prior to a second time. Long-term interest categories, corresponding weight values for each long-term interest category, short-term interest categories and corresponding weight values for each short-term interest category are identified. A model comprising the long-term and short-term interest categories is generated based on the weight values of the long-term and short-term interest categories using either arithmetic or harmonic progression. The processing circuit receives a list of candidate network user identifiers and generates a list of similar network user identifiers based on the model.

US Patent:

20220253557, Aug 11, 2022

Filed:

Apr 16, 2020

Appl. No.:

17/627033

Inventors:

- Mountain View CA, US
Zhenyu Liu - San Jose CA, US
Josh Karlin - Mountain View CA, US
Deepak Ravichandran - Los Altos CA, US
Nitish John Korula - New York NY, US
Yijian Bai - San Ramon CA, US
Jason Hsueh - Palo Alto CA, US
Gang Wang - Jersey City NJ, US

International Classification:

G06F 21/62
G06N 20/00
H04L 67/53
H04L 67/50

Abstract:

The present disclosure provides systems and methods for client-side anonymized content selections. The method includes collecting a plurality of identifications of content selection lists, each content selection list associated with the first device and at least one other device. The method includes selecting a first subset of the content selection lists, responsive to a total number of unique device associated with a plurality of content selection lists of the first subset exceeding a threshold. The method includes transmitting a request for an item of content, the request comprising identifications of the content selection lists of the selected first subset. The method includes receiving a first item of content selected by the content server based on the content selection lists of the selected first subset.

US Patent:

20210034782, Feb 4, 2021

Filed:

Jul 29, 2019

Appl. No.:

16/524792

Inventors:

- Mountain View CA, US
Vic Liu - Mountain View CA, US
Josh Karlin - Mountain View CA, US
Gang Wang - Mountain View CA, US
Nitish Korula - Mountain View CA, US
Yijian Bai - San Ramon CA, US
Jason Hsueh - Menlo Park CA, US
Deepak Ravichandran - Mountain View CA, US

Assignee:

GOOGLE LLC - Mountain View CA

International Classification:

G06F 21/62
H04L 29/08
G06N 20/00

Abstract:

The present disclosure provides systems and methods for client-side anonymized content selections. The method includes collecting a plurality of identifications of content selection lists, each content selection list associated with the first device and at least one other device. The method includes selecting a first subset of the content selection lists, responsive to a total number of unique device associated with a plurality of content selection lists of the first subset exceeding a threshold. The method includes transmitting a request for an item of content, the request comprising identifications of the content selection lists of the selected first subset. The method includes receiving a first item of content selected by the content server based on the content selection lists of the selected first subset.

US Patent:

20160321692, Nov 3, 2016

Filed:

May 24, 2016

Appl. No.:

15/163463

Inventors:

- Mountain View CA, US
Yijian Bai - San Ramon CA, US
Deepak Ravichandran - Mountain View CA, US
Shankar R. Ponnekanti - Mountain View CA, US

International Classification:

G06Q 30/02
H04L 29/08

Abstract:

A system including a memory device storing instructions and servers that interact with the memory device and execute the instructions that cause the servers to perform operations including obtaining, using electronic cookies stored at client devices or pixel tags that are embedded in online resources, online activity performed at client devices; generating an online activity model using the online activity and the attributes of the users associated with the set of online activity, wherein the online activity model identifies different users as being likely to perform an activity in the online activity based on a similarity between the attributes of the users and attributes of the different users; determining, based on an application of the online activity model to the attributes, additional user identifiers of users that are likely to perform a same online activity by client devices as users corresponding to the user identifiers received from the third party.

US Patent:

20150242906, Aug 27, 2015

Filed:

May 2, 2012

Appl. No.:

13/462425

Inventors:

Jia Liu - Sunnyvale CA, US
Yijian Bai - San Ramon CA, US
Deepak Ravichandran - Mountain View CA, US
Shankar Ponnekanti - Mountain View CA, US

International Classification:

G06Q 30/02

Abstract:

A computerized method, system for, and computer-readable medium operable to take a first set of network user identifiers and generate a set of recommended network user identifiers based on the first set and advertiser bid data. A processing circuit receives the first set and advertiser bid data for the first set and stores the first set and advertiser bid data for the first set in a memory. The advertiser bid data includes a price offered by the advertiser for the advertiser's content to be shown to a network user identifier in the first set. The processing circuit receives advertiser bid data for a second set. The processing circuit generates a user similarity parameter based on the advertiser bid data for the first set and the advertiser bid data for the second set. The processing circuit generates the set of recommended network user identifiers based on the user similarity parameter.