Narendra K Gupta

US Patent:

7152029, Dec 19, 2006

Filed:

May 31, 2002

Appl. No.:

10/160461

Inventors:

Hiyan Alshawi - Madison NJ, US
Giuseppe DiFabbrizio - Summit NJ, US
Narendra K. Gupta - Dayton NJ, US
Mazin G. Rahim - Matawan NJ, US
Robert E. Schapire - Maplewood NJ, US
Yoram Singer - Murray Hill NJ, US

Assignee:

AT&T Corp. - New York NY

International Classification:

G06F 17/20

US Classification:

704 1

Abstract:

A system for understanding entries, such as speech, develops a classifier by employing prior knowledge with which a given corpus of training entries is enlarged threefold. A rule is created for each of the labels employed in the classifyier, and the created rules are applied to the given corpus to create a corpus of attachments by appending a weight of ηp(x), or 1−ηp(x), to labels of entries that meet, or fail to meet, respectively, conditions of the labels' rules, and to also create a corpus of non-attachments by appending a weight of 1−ηp(x), or ηp(x), to labels of entries that meet, or fail to meet conditions of the labels' rules.

US Patent:

7328146, Feb 5, 2008

Filed:

Jul 11, 2006

Appl. No.:

11/484120

Inventors:

Hiyan Alshawi - Madison NJ, US
Giuseppe DiFabrizzio - Summit NJ, US
Narendra K. Gupta - Dayton NJ, US
Mazin G. Rahim - Matawan NJ, US
Robert E. Schapire - Maplewood NJ, US
Yoram Singer - Murray Hill NJ, US

Assignee:

AT&T Corp. - New York NY

International Classification:

G06F 17/20

US Classification:

704 1, 704 9, 706 25

Abstract:

A system for understanding entries, such as speech, develops a classifier by employing prior knowledge with which a given corpus of training entries is enlarged threefold. A rule is created for each of the labels employed in the classifier, and the created rules are applied to the given corpus to create a corpus of attachments by appending a weight of ηp(x), or 1−ηp(x), to labels of entries that meet, or fail to meet, respectively, conditions of the labels' rules, and to also create a corpus of non-attachments by appending a weight of 1−ηp(x), or ηp(x), to labels of entries that meet, or fail to meet conditions of the labels' rules.

US Patent:

7630917, Dec 8, 2009

Filed:

Apr 14, 2006

Appl. No.:

11/279802

Inventors:

Srinivas Bangalore - Morristown NJ, US
Giuseppe Di Fabbrizio - Florham Park NJ, US
Narendra Kumar Gupta - Dayton NJ, US

Assignee:

AT&T Intellectual Property II, L.P. - New York NY

International Classification:

G06F 17/30
G06Q 10/00

US Classification:

705 10, 705 1, 705 4

Abstract:

A method, processing device, and machine-readable medium are provided. Costs of states of a state space are calculated. Each state represent one or more available product attributes having zero or more decided attribute values. The calculating is based, at least in part, on training data associated with previously requested and offered products. determining a next state such that one or more products are available and a sum of values, including a cost of a next state and a cost of a perturbation of one of the one or more requested product attribute values to reach the next state is a minimum value. A value for a product attribute is mapped according to the minimum sum of values and product attribute values of available products.

US Patent:

7746990, Jun 29, 2010

Filed:

Oct 12, 2005

Appl. No.:

11/248625

Inventors:

Giuseppe Di Fabbrizio - Florham Park NJ, US
Narendra K. Gupta - Dayton NJ, US

Assignee:

AT&T Corp. - New York NY

International Classification:

H04M 15/00

US Classification:

37911413, 379 8817

Abstract:

A system and method to provide content and call attributes for a destination phone number using a click-to-dial connection includes accepting a query, retrieving links to a document, and searching through cached data using the query to identify relevant or destination number information. If no match is found, the method continues with accessing the document identified by the link for identifying relevant number information and creating a click-to-dial icon to link to the relevant numbers included in the relevant phone number information identified by the query. Next, a popup box for content relevant to the click-to-dial icon and a click feature on the popup box are created to retrieve call destination attributes for viewing by a user. Further, computer instructions create at least one communication connection between two communication devices after viewing call destination attributes.

US Patent:

7869998, Jan 11, 2011

Filed:

Dec 19, 2002

Appl. No.:

10/325295

Inventors:

Giuseppe Di Fabbrizio - Summit NJ, US
Dawn L Dutton - West Long Branch NJ, US
Narendra K. Gupta - Dayton NJ, US
Barbara B. Hollister - Mountainside NJ, US
Mazin G Rahim - Matawan NJ, US
Giuseppe Riccardi - Hoboken NJ, US
Robert Elias Schapire - Maplewood NJ, US
Juergen Schroeter - New Providence NJ, US

Assignee:

AT&T Intellectual Property II, L.P. - New York NY

International Classification:

G10L 15/04

US Classification:

704251, 704 1, 704 9, 704231, 704257, 704270

Abstract:

A voice-enabled help desk service is disclosed. The service comprises an automatic speech recognition module for recognizing speech from a user, a spoken language understanding module for understanding the output from the automatic speech recognition module, a dialog management module for generating a response to speech from the user, a natural voices text-to-speech synthesis module for synthesizing speech to generate the response to the user, and a frequently asked questions module. The frequently asked questions module handles frequently asked questions from the user by changing voices and providing predetermined prompts to answer the frequently asked question.

US Patent:

7937301, May 3, 2011

Filed:

Dec 7, 2009

Appl. No.:

12/632347

Inventors:

Srinivas Bangalore - Morristown NJ, US
Giuseppe Di Fabbrizio - Florham Park NJ, US
Narendra Kumar Gupta - Dayton NJ, US

Assignee:

AT&T Intellectual Property II, L.P. - Atlanta GA

International Classification:

G07B 17/00
G06F 17/30
G06Q 10/00

US Classification:

705 30, 705 10, 705 4

Abstract:

A method, processing device, and machine-readable medium are provided. Costs of states of a state space are calculated. Each state represent one or more available product attributes having zero or more decided attribute values. The calculating is based, at least in part, on training data associated with previously requested and offered products. Determining a next state such that one or more products are available and a sum of values, including a cost of a next state and a cost of a perturbation of one of the one or more requested product attribute values to reach the next state is a minimum value. A value for a product attribute is mapped according to the minimum sum of values and product attribute values of available products.

US Patent:

8051134, Nov 1, 2011

Filed:

Dec 21, 2005

Appl. No.:

11/312475

Inventors:

Lee Begeja - Gillette NJ, US
Narendra K Gupta - Dayton NJ, US
Benjamin J Stern - Morris Township NJ, US

Assignee:

AT&T Intellectual Property II, L.P. - Atlanta GA

International Classification:

G06F 15/16

US Classification:

709206

Abstract:

Systems, methods, and programs, for evaluating audio messages store a model that may include language patterns, audio patterns, and/or metafeatures that indicate a likelihood that the audio message is a spam message or a non-spam message and compare the content of the input audio message with the model. Based on the comparison, the systems, methods, and programs identify the input audio message as a spam message or a non-spam message.

US Patent:

8082151, Dec 20, 2011

Filed:

Sep 18, 2007

Appl. No.:

11/857036

Inventors:

Srinivas Bangalore - Morristown NJ, US
Mazin Gilbert - Warren NJ, US
Narendra Gupta - Dayton NJ, US

Assignee:

AT&T Intellectual Property I, LP - Atlanta GA

International Classification:

G10L 15/00

US Classification:

704251, 704257, 709223

Abstract:

In accordance with one aspect of the present invention, an automated method of and system for generating a response to a text-based natural language message is disclosed. The method includes identifying a sentence in the text-based natural language message. Also, identifying an input clause in the sentence. Further, comparing the input clause to a previously received clause, where the previously received clause is correlated with a previously generated response message. Additionally, generating an output response message based on the previously generated response message. The system includes means for performing the method steps.