Patents by Inventor Naveen Sundar Govindarajulu
Naveen Sundar Govindarajulu 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).
-
Publication number: 20230368321Abstract: A system, method and program product for implementing an artificially intelligent emergency response system to generate a plan for an emergency event in response to received event information from one or more input devices. A process includes: translating the received event information into a logically controlled natural language; selecting a meta-model that conforms to the emergency event; generating a hypergraph model from the meta-model, wherein the hypergraph model includes details from the received event information; generating a goal based on the received event information; generating and outputting a plan to an output device based on the hypergraph model, the goal, and semantic information.Type: ApplicationFiled: May 10, 2023Publication date: November 16, 2023Inventors: Alexander Bringsjord, Selmer Bringsjord, Paul Spadaro, Naveen Sundar Govindarajulu
-
Patent number: 11526779Abstract: An artificial intelligence (AI) logic problem platform. A disclosed system includes a first AI module having: a problem generator for automatically generating unique reasoning problems; and a solution analyzer for automatically analyzing a logic solution submitted in response to an automatically generated reasoning problem; and a second AI module includes a user interface for allowing a user to create the logic solution and output a solution file.Type: GrantFiled: February 11, 2019Date of Patent: December 13, 2022Assignee: Motalen LLCInventors: Selmer Bringsjord, Alexander Bringsjord, Naveen Sundar Govindarajulu
-
Patent number: 11379732Abstract: A system, method and program product for countering fraud using artificial intelligence. A system is disclosed that includes: a system for formalizing real world semantic information pertaining to a domain that includes rules and processes expressed as formulae, semantic models of known fraud schemes, and knowledge bases of domain participants represented using cognitive calculi; and a scheme generation system for generating a plurality of fraud schemes within the domain using the semantic information, wherein each fraud scheme: comprises a plan expressed using cognitive calculi; includes at least one domain participant; achieves an illicit result that breaks at least one rule of the domain; is provable to be outside the purview of relevant observers; and is not a known fraud scheme.Type: GrantFiled: March 30, 2018Date of Patent: July 5, 2022Assignee: DEEP DETECTION LLCInventors: Selmer Bringsjord, Alexander Bringsjord, Joseph Johnson, Naveen Sundar Govindarajulu
-
Patent number: 10997370Abstract: Systems and methods for domain classification in natural language processing based on domains are disclosed. The method includes generating a trigram corpus for the purpose of classification based on a trigram analysis of a domain model containing a hierarchical ontology and semantic construction that maps patterns of semantic tokens to syntactic patterns. An input string is parsed within each domain, tokenized in each domain. The resulting trigrams for the input text in each domain are looked up in the corresponding trigram corpus to determine the relevancy of each domain to the input text. The input string is thus classified based on the relevancy determination. The systems and methods avoids having to rely on existing annotated domain corpora for classification and allows for fast regeneration of the classifier when domain models are under frequent update and development.Type: GrantFiled: November 5, 2018Date of Patent: May 4, 2021Assignee: Verizon Media Inc.Inventors: Jonathan R. Scally, Nicholas L. Cassimatis, Richard Caneba, Naveen Sundar Govindarajulu
-
Patent number: 10579727Abstract: A system and method for processing a natural language input. The natural language input is initially processed through a strict parser, which results in an initial parse. The initial parse is evaluated to determine if it exceeds a completeness threshold. If the initial parse does not pass the completeness threshold, any open slots are filled using type based slot filling. The final parse is then output for further processing by another system, such as a search engine.Type: GrantFiled: April 30, 2019Date of Patent: March 3, 2020Assignee: Oath Inc.Inventors: Naveen Sundar Govindarajulu, Nicholas L. Cassimatis, Jonathan R. Scally
-
Publication number: 20190258711Abstract: A system and method for processing a natural language input. The natural language input is initially processed through a strict parser, which results in an initial parse. The initial parse is evaluated to determine if it exceeds a completeness threshold. If the initial parse does not pass the completeness threshold, any open slots are filled using type based slot filling. The final parse is then output for further processing by another system, such as a search engine.Type: ApplicationFiled: April 30, 2019Publication date: August 22, 2019Inventors: Naveen Sundar Govindarajulu, Nicholas L. Cassimatis, Jonathan R. Scally
-
Publication number: 20190251454Abstract: An artificial intelligence (AI) logic problem platform. A disclosed system includes a first AI module having: a problem generator for automatically generating unique reasoning problems; and a solution analyzer for automatically analyzing a logic solution submitted in response to an automatically generated reasoning problem; and a second AI module includes a user interface for allowing a user to create the logic solution and output a solution file.Type: ApplicationFiled: February 11, 2019Publication date: August 15, 2019Inventors: Selmer Bringsjord, Alexander Bringsjord, Naveen Sundar Govindarajulu
-
Patent number: 10275443Abstract: A system and method for processing a natural language input. The natural language input is initially processed through a strict parser, which results in an initial parse. The initial parse is evaluated to determine if it exceeds a completeness threshold. If the initial parse does not pass the completeness threshold, any open slots are filled using type based slot filling. The final parse is then output for further processing by another system, such as a search engine.Type: GrantFiled: August 6, 2018Date of Patent: April 30, 2019Assignee: Oath Inc.Inventors: Naveen Sundar Govindarajulu, Nicholas L. Cassimatis, Jonathan R. Scally
-
Publication number: 20190073357Abstract: Systems and methods for domain classification in natural language processing based on domains are disclosed. The method includes generating a trigram corpus for the purpose of classification based on a trigram analysis of a domain model containing a hierarchical ontology and semantic construction that maps patterns of semantic tokens to syntactic patterns. An input string is parsed within each domain, tokenized in each domain. The resulting trigrams for the input text in each domain are looked up in the corresponding trigram corpus to determine the relevancy of each domain to the input text. The input string is thus classified based on the relevancy determination. The systems and methods avoids having to rely on existing annotated domain corpora for classification and allows for fast regeneration of the classifier when domain models are under frequent update and development.Type: ApplicationFiled: November 5, 2018Publication date: March 7, 2019Inventors: Jonathan R. Scally, Nicholas L. Cassimatis, Richard Caneba, Naveen Sundar Govindarajulu
-
Publication number: 20180349344Abstract: A system and method for processing a natural language input. The natural language input is initially processed through a strict parser, which results in an initial parse. The initial parse is evaluated to determine if it exceeds a completeness threshold. If the initial parse does not pass the completeness threshold, any open slots are filled using type based slot filling. The final parse is then output for further processing by another system, such as a search engine.Type: ApplicationFiled: August 6, 2018Publication date: December 6, 2018Inventors: Naveen Sundar Govindarajulu, Nicholas L. Cassimatis, Jonathan R. Scally
-
Patent number: 10120861Abstract: Systems and methods for domain classification in natural language processing based on domains are disclosed. The method includes generating a trigram corpus for the purpose of classification based on a trigram analysis of a domain model containing a hierarchical ontology and semantic construction that maps patterns of semantic tokens to syntactic patterns. An input string is parsed within each domain, tokenized in each domain. The resulting trigrams for the input text in each domain are looked up in the corresponding trigram corpus to determine the relevancy of each domain to the input text. The input string is thus classified based on the relevancy determination. The systems and methods avoids having to rely on existing annotated domain corpora for classification and allows for fast regeneration of the classifier when domain models are under frequent update and development.Type: GrantFiled: August 17, 2016Date of Patent: November 6, 2018Assignee: OATH INC.Inventors: Jonathan R. Scally, Nicholas L. Cassimatis, Richard Caneba, Naveen Sundar Govindarajulu
-
Patent number: 10042840Abstract: A system and method for processing a natural language input. The natural language input is initially processed through a strict parser, which results in an initial parse. The initial parse is evaluated to determine if it exceeds a completeness threshold. If the initial parse does not pass the completeness threshold, any open slots are filled using type based slot filling. The final parse is then output for further processing by another system, such as a search engine.Type: GrantFiled: August 4, 2016Date of Patent: August 7, 2018Assignee: OATH INC.Inventors: Naveen Sundar Govindarajulu, Nicholas L. Cassimatis, Jonathan R. Scally
-
Publication number: 20180052823Abstract: Systems and methods for domain classification in natural language processing based on domains are disclosed. The method includes generating a trigram corpus for the purpose of classification based on a trigram analysis of a domain model containing a hierarchical ontology and semantic construction that maps patterns of semantic tokens to syntactic patterns. An input string is parsed within each domain, tokenized in each domain. The resulting trigrams for the input text in each domain are looked up in the corresponding trigram corpus to determine the relevancy of each domain to the input text. The input string is thus classified based on the relevancy determination. The systems and methods avoids having to rely on existing annotated domain corpora for classification and allows for fast regeneration of the classifier when domain models are under frequent update and development.Type: ApplicationFiled: August 17, 2016Publication date: February 22, 2018Applicant: Yahoo Holdings, Inc.Inventors: Jonathan R. Scally, Nicholas L. Cassimatis, Richard Caneba, Naveen Sundar Govindarajulu
-
Publication number: 20180039614Abstract: A system and method for processing a natural language input. The natural language input is initially processed through a strict parser, which results in an initial parse. The initial parse is evaluated to determine if it exceeds a completeness threshold. If the initial parse does not pass the completeness threshold, any open slots are filled using type based slot filling. The final parse is then output for further processing by another system, such as a search engine.Type: ApplicationFiled: August 4, 2016Publication date: February 8, 2018Inventors: Naveen Sundar Govindarajulu, Nicholas L. Cassimatis, Jonathan R. Scally
-
Patent number: 8700911Abstract: An authentication system comprises a sensor for detecting a fingerprint and a doodle drawn by the user. The fingerprint, or other biometric information, is distorted in accordance with the doodle to provide distorted biometric information that is referred to as a doodleprint. The user can use different doodles on different systems, and if the doodleprint is compromised, can change the doodle to create a different doodleprint.Type: GrantFiled: February 13, 2008Date of Patent: April 15, 2014Assignee: Hewlett-Packard Development Company, L.P.Inventors: Sriganesh Madhvanath, Naveen Sundar Govindarajulu
-
Patent number: 8214767Abstract: The present application discloses a method for generating a shortcut for launching computer program functionality on a computer. The method comprises the steps of monitoring a sequence of user actions resulting in the launch of the functionality; determining a launch frequency of the functionality; determining a complexity rating for the launch; comparing the launch frequency and the complexity rating with a predefined criterion; and generating the shortcut for activating the functionality if the predefined criterion is met. The present application further discloses a computer program product implementing the above method and a computer comprising such a computer program.Type: GrantFiled: January 9, 2009Date of Patent: July 3, 2012Assignee: Hewlett-Packard Development Company, L.P.Inventors: Muralikrishna Sridhar, Dinesh Mandalapu, Naveen Sundar Govindarajulu, Sriganesh Madhvanath
-
Publication number: 20090183124Abstract: The present application discloses a method for generating a shortcut for launching computer program functionality on a computer. The method comprises the steps of monitoring a sequence of user actions resulting in the launch of the functionality; determining a launch frequency of the functionality; determining a complexity rating for the launch; comparing the launch frequency and the complexity rating with a predefined criterion; and generating the shortcut for activating the functionality if the predefined criterion is met. The present application further discloses a computer program product implementing the above method and a computer comprising such a computer program.Type: ApplicationFiled: January 9, 2009Publication date: July 16, 2009Inventors: Muralikrishna SRIDHAR, Dinesh Mandalapu, Naveen Sundar Govindarajulu, Sriganesh Madhvanath
-
Publication number: 20090138725Abstract: An authentication system comprises a sensor for detecting a fingerprint and a doodle drawn by the user. The fingerprint, or other biometric information, is distorted in accordance with the doodle to provide distorted biometric information that is referred to as a doodleprint. The user can use different doodles on different systems, and if the doodleprint is compromised, can change the doodle to create a different doodleprint.Type: ApplicationFiled: February 13, 2008Publication date: May 28, 2009Inventors: Sriganesh MADHVANATH, Naveen Sundar Govindarajulu