Looja R Tuladhar

US Patent:

20080222130, Sep 11, 2008

Filed:

Mar 5, 2007

Appl. No.:

11/682233

Inventors:

Kavel Patel - Sunnyvale CA, US
Christopher Sanger - Glendale CA, US
Josh Meyers - Hollywood CA, US
Looja Tuladhar - Pasadena CA, US

Assignee:

YAHOO! INC. - Sunnyvale CA

International Classification:

G06F 17/30

US Classification:

707 5

Abstract:

In an embodiment of the present invention, keywords may be dynamically optimized. This may include techniques for reducing the number of keywords assigned to a particular web page (and selecting which keywords to eliminate). This may also include techniques for reordering keywords, introducing new keywords, and/or changing the attributes of keywords (e.g., size, font, color, spacing, etc.) assigned to a particular web page. Any of these techniques may be dynamically implemented by basing the optimization on one or more metrics and data collected from user interactions with the webpage.

US Patent:

20100082421, Apr 1, 2010

Filed:

Sep 30, 2008

Appl. No.:

12/241815

Inventors:

Looja Tuladhar - Sunnyvale CA, US
Manish Satyapal Gupta - Bangalore Karnataka, IN

Assignee:

YAHOO! INC. - Sunnyvale CA

International Classification:

G06Q 30/00
G06Q 40/00
G06Q 20/00
G06Q 90/00

US Classification:

705 1441, 705 40, 705400, 705 1

Abstract:

A computer implemented method comprises analyzing a plurality of attributes of a sample of online documents using a boosted decision tree and generating a model from it. The model is used to predict a click through rate (CTR) of an additional online document based on the analyzing. The predicted CTR is output to a display device, storage medium or network.

US Patent:

20100169316, Jul 1, 2010

Filed:

Dec 30, 2008

Appl. No.:

12/346832

Inventors:

Gaurav GEHLOT - Bangalore, IN
Manish Satyapal GUPTA - Mumbai, IN
Anand Vishwanath SUVARNKAR - Bangalore, IN
Bhupesh GOEL - Faridabad, IN
Looja TULADHAR - Sunnyvale CA, US

Assignee:

Yahoo! Inc. - Sunnyvale CA

International Classification:

G06F 17/30

US Classification:

707736, 707E17014, 707E17017, 707758

Abstract:

Search Query Concept Based Recommendations. A method includes electronically receiving, in a computer system, a title as an input. One or more subsets of the title are generated. A list of key phrases associated with the title is obtained. Further, one or more key phrases from the list corresponding to the one or more subsets is electronically identified. Contents are selected based on the one or more key phrases identified. The contents can be ranked. The contents are then provided to the user.

US Patent:

20230029333, Jan 26, 2023

Filed:

Jul 20, 2021

Appl. No.:

17/380076

Inventors:

- Dulles VA, US
Daryl LOW - San Jose CA, US
Sanika SHIRWADKAR - Milpitas CA, US
Xiaoyan YIN - Fairfax Station VA, US
Nils SCHIMMELMANN - Mountain View CA, US
Looja TULADHAR - Sunnyvale CA, US

International Classification:

H04L 29/08

Abstract:

The disclosed systems and methods provide a novel framework that provides on-device functionality to user devices for localized content ranking, modification and rendering. The disclosed systems and methods provide functionality for on-device personalization in a real-time, secure and network anonymous manner. Rather than exposing a user's data to the network for content tailoring, the disclosed framework performs the ranking and content manipulation locally on the user's device. The disclosed framework enables locally (on-device) built, updated and hosted user profiles to be used to tailor received content for display on a user device. This ensures the integrity of the personalization while maintaining security for the user's personalized data and activities.