Patents by Inventor John Grothendieck
John Grothendieck has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11023676Abstract: Systems and methods for efficiently detecting and coordinating step changes, trends, cycles, and bursts affecting lexical items within data streams are provided. Data streams can be sourced from documents that can optionally be labeled with metadata. Changes can be grouped across lexical and/or metavalue vocabularies to summarize the changes that are synchronous in time. The methods described herein can be applied either retrospectively to a corpus of data or in a streaming mode.Type: GrantFiled: March 18, 2016Date of Patent: June 1, 2021Assignee: AT&T INTELLECTUAL PROPERTY I, L.P.Inventors: Jeremy Wright, Alicia Abella, John Grothendieck
-
Patent number: 10749882Abstract: Aspects are generally directed to network security systems and methods of monitoring network activity. In one example, a network security system includes and interface to receive a Hypertext Transfer Protocol (HTTP) network log that includes a matrix of data, a feature extraction component configured to extract a connectivity matrix from the HTTP network log based on a recurring pattern within the matrix of data, and a training module configured to provide deep learning architecture training data based on the connectivity matrix. The system may include a deep learning architecture configured to receive and propagate the training data through one or more layers thereof to train the one or more layers, and being configured to generate a general data representation of the HTTP network log. The system may include a behavior analytics component to detect a discordant network activity within the HTTP network log based on the general data representation.Type: GrantFiled: April 19, 2018Date of Patent: August 18, 2020Assignee: Raytheon BBN Technologies Corp.Inventors: John Grothendieck, Ilana Heintz
-
Publication number: 20190327252Abstract: Aspects are generally directed to network security systems and methods of monitoring network activity. In one example, a network security system includes and interface to receive a Hypertext Transfer Protocol (HTTP) network log that includes a matrix of data, a feature extraction component configured to extract a connectivity matrix from the HTTP network log based on a recurring pattern within the matrix of data, and a training module configured to provide deep learning architecture training data based on the connectivity matrix. The system may include a deep learning architecture configured to receive and propagate the training data through one or more layers thereof to train the one or more layers, and being configured to generate a general data representation of the HTTP network log. The system may include a behavior analytics component to detect a discordant network activity within the HTTP network log based on the general data representation.Type: ApplicationFiled: April 19, 2018Publication date: October 24, 2019Inventors: John Grothendieck, Ilana Heintz
-
Patent number: 9792905Abstract: An apparatus, a method, and a machine-readable medium are provided for characterizing differences between two language models. A group of utterances from each of a group of time domains are examined. One of a significant word change or a significant word class change within the plurality of utterances is determined. A first cluster of utterances including a word or a word class corresponding to the one of the significant word change or the significant word class change is generated from the utterances. A second cluster of utterances not including the word or the word class corresponding to the one of the significant word change or the significant word class change is generated from the utterances.Type: GrantFiled: November 14, 2014Date of Patent: October 17, 2017Assignee: Nuance Communications, Inc.Inventors: Allen Louis Gorin, John Grothendieck, Jeremy Huntley Greet Wright
-
Publication number: 20160203122Abstract: Systems and methods for efficiently detecting and coordinating step changes, trends, cycles, and bursts affecting lexical items within data streams are provided. Data streams can be sourced from documents that can optionally be labeled with metadata. Changes can be grouped across lexical and/or metavalue vocabularies to summarize the changes that are synchronous in time. The methods described herein can be applied either retrospectively to a corpus of data or in a streaming mode.Type: ApplicationFiled: March 18, 2016Publication date: July 14, 2016Inventors: JEREMY WRIGHT, ALICIA ABELLA, JOHN GROTHENDIECK
-
Patent number: 9324007Abstract: Systems and methods for efficiently detecting and coordinating step changes, trends, cycles, and bursts affecting lexical items within data streams are provided. Data streams can be sourced from documents that can optionally be labeled with metadata. Changes can be grouped across lexical and/or metavalue vocabularies to summarize the changes that are synchronous in time. The methods described herein can be applied either retrospectively to a corpus of data or in a streaming mode.Type: GrantFiled: August 30, 2012Date of Patent: April 26, 2016Assignee: AT&T INTELLECTUAL PROPERTY I, L.P.Inventors: Jeremy Wright, Allcia Abella, John Grothendieck
-
Publication number: 20150073791Abstract: An apparatus, a method, and a machine-readable medium are provided for characterizing differences between two language models. A group of utterances from each of a group of time domains are examined. One of a significant word change or a significant word class change within the plurality of utterances is determined. A first cluster of utterances including a word or a word class corresponding to the one of the significant word change or the significant word class change is generated from the utterances. A second cluster of utterances not including the word or the word class corresponding to the one of the significant word change or the significant word class change is generated from the utterances.Type: ApplicationFiled: November 14, 2014Publication date: March 12, 2015Inventors: Allen Louis GORIN, John Grothendieck, Jeremy Huntley Greet Wright
-
Patent number: 8892438Abstract: An apparatus, a method, and a machine-readable medium are provided for characterizing differences between two language models. A group of utterances from each of a group of time domains are examined. One of a significant word change or a significant word class change within the plurality of utterances is determined. A first cluster of utterances including a word or a word class corresponding to the one of the significant word change or the significant word class change is generated from the utterances. A second cluster of utterances not including the word or the word class corresponding to the one of the significant word change or the significant word class change is generated from the utterances.Type: GrantFiled: September 14, 2010Date of Patent: November 18, 2014Assignee: AT&T Intellectual Property II, L.P.Inventors: Allen Louis Gorin, John Grothendieck, Jeremy Huntley Greet Wright
-
Patent number: 8843361Abstract: A method, an apparatus, and a computer-readable medium are provided. Whether at least one significant change occurs in a use of at least one word of a group of text documents of a text corpus is determined. A display based, at least in part, on at least one change point corresponding to the at least one significant change is presented when the at least one significant change is determined to have occurred.Type: GrantFiled: November 30, 2005Date of Patent: September 23, 2014Assignee: AT&T Intellectual Property II, L.P.Inventors: Wen-Ling Hsu, John Grothendieck, Guy J. Jacobson, Jeremy Huntley Greet Wright
-
Publication number: 20120323836Abstract: Systems and methods for efficiently detecting and coordinating step changes, trends, cycles, and bursts affecting lexical items within data streams are provided. Data streams can be sourced from documents that can optionally be labeled with metadata. Changes can be grouped across lexical and/or metavalue vocabularies to summarize the changes that are synchronous in time. The methods described herein can be applied either retrospectively to a corpus of data or in a streaming mode.Type: ApplicationFiled: August 30, 2012Publication date: December 20, 2012Inventors: Jeremy Wright, Allcia Abella, John Grothendieck
-
Patent number: 8271422Abstract: Systems and methods for efficiently detecting and coordinating step changes, trends, cycles, and bursts affecting lexical items within data streams are provided. Data streams can be sourced from documents that can optionally be labeled with metadata. Changes can be grouped across lexical and/or metavalue vocabularies to summarize the changes that are synchronous in time. The methods described herein can be applied either retrospectively to a corpus of data or in a streaming mode.Type: GrantFiled: November 29, 2008Date of Patent: September 18, 2012Assignee: AT&T Intellectual Property I, LPInventors: Jeremy Wright, Alicia Abella, John Grothendieck
-
Publication number: 20110093268Abstract: An apparatus, a method, and a machine-readable medium are provided for characterizing differences between two language models. A group of utterances from each of a group of time domains are examined. One of a significant word change or a significant word class change within the plurality of utterances is determined. A first cluster of utterances including a word or a word class corresponding to the one of the significant word change or the significant word class change is generated from the utterances. A second cluster of utterances not including the word or the word class corresponding to the one of the significant word change or the significant word class change is generated from the utterances.Type: ApplicationFiled: September 14, 2010Publication date: April 21, 2011Applicant: AT&T Intellectual Property II, L.P.Inventors: Allen Louis Gorin, John Grothendieck, Jeremy Huntley Greet Wright
-
Patent number: 7805300Abstract: An apparatus, a method, and a machine-readable medium are provided for characterizing differences between two language models. A group of utterances from each of a group of time domains are examined. One of a significant word change or a significant word class change within the plurality of utterances is determined. A first cluster of utterances including a word or a word class corresponding to the one of the significant word change or the significant word class change is generated from the utterances. A second cluster of utterances not including the word or the word class corresponding to the one of the significant word change or the significant word class change is generated from the utterances.Type: GrantFiled: March 21, 2005Date of Patent: September 28, 2010Assignee: AT&T Intellectual Property II, L.P.Inventors: Allen Louis Gorin, John Grothendieck, Jeremy Huntley Greet Wright
-
Publication number: 20100138377Abstract: Systems and methods for efficiently detecting and coordinating step changes, trends, cycles, and bursts affecting lexical items within data streams are provided. Data streams can be sourced from documents that can optionally be labeled with metadata. Changes can be grouped across lexical and/or metavalue vocabularies to summarize the changes that are synchronous in time. The methods described herein can be applied either retrospectively to a corpus of data or in a streaming mode.Type: ApplicationFiled: November 29, 2008Publication date: June 3, 2010Inventors: Jeremy Wright, Alicia Abella, John Grothendieck
-
Publication number: 20060212294Abstract: An apparatus, a method, and a machine-readable medium are provided for characterizing differences between two language models. A group of utterances from each of a group of time domains are examined. One of a significant word change or a significant word class change within the plurality of utterances is determined. A first cluster of utterances including a word or a word class corresponding to the one of the significant word change or the significant word class change is generated from the utterances. A second cluster of utterances not including the word or the word class corresponding to the one of the significant word change or the significant word class change is generated from the utterances.Type: ApplicationFiled: March 21, 2005Publication date: September 21, 2006Applicant: AT&T Corp.Inventors: Allen Gorin, John Grothendieck, Jeremy Wright