Patents by Inventor Ashish Sureka
Ashish Sureka 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: 8752001Abstract: A system and method for developing a rule-based named entity extraction system is provided. The method includes analyzing requirements of business users. The method further includes designing the rule-based named entity extraction system based on the requirement analysis. Further, the method includes implementing the design of rule-based named entity extraction system using one or more GUI-based tools. Thereafter, regression testing of the rule-based named entity extraction system is conducted. Finally, rule-based named entity extraction system is deployed.Type: GrantFiled: May 21, 2010Date of Patent: June 10, 2014Assignee: Infosys LimitedInventors: Ashish Sureka, Pranav Prabhakar Mirajkar, Kishore Varma Indukuri
-
Publication number: 20130275753Abstract: A system and method for verifying credentials are provided. The system includes a credential verification server (102) and a plurality of credential verification local servers (104). The system (100) is configured to receive a request from credential seeker (CS) to verify credentials of a credential owner (CO). The request is forwarded to an appropriate credential verification local server (104) among the plurality of credential verification local servers (104). Thereafter, the credential owner (CO) is notified about the request. Further, instruction is received from the credential owner (CO), wherein the instruction comprises at least one of, denying permission, granting permission to verify credential information as requested by the credential seeker (CS) and granting permission to verify credential information after modifying scope of access to information. Subsequently, access is provided to the credential seeker (CS) to verify credentials based on the instruction received by the credential owner (CO).Type: ApplicationFiled: June 10, 2012Publication date: October 17, 2013Applicant: INDRAPRASHTA INSTITUTE OF INFORMATION TECHNOLOGYInventors: Denzil Correa, Ashish Sureka
-
Patent number: 8489530Abstract: A system, method and computer program product for the root cause analysis of the failure of a manufactured product is disclosed. The present invention includes the development of a knowledge model, based on information obtained from historical warranty claim forms and various manufacturing data sources. The invention also includes processing text information in a free-form text that is obtained from warranty claim forms by using text-tagging and annotation techniques. Thereafter, the knowledge model is converted to a Bayesian network. The present invention provides a user interface to select parameters and corresponding instances from current warranty claim forms. The selected parameters and corresponding instances are used as input evidence for the Bayesian network. The present invention facilitates the process of drawing inferences for root cause analysis of the failure of manufactured products and corresponding probabilities.Type: GrantFiled: December 3, 2008Date of Patent: July 16, 2013Assignee: Infosys LimitedInventors: Sudripto De, Srinivas Narasimhamurthy, Ashish Sureka, Satyabrata Pradhan
-
Patent number: 8468155Abstract: Various techniques can be used to implement a collaborative filtering-based recommendation engine. For example, different similarity measures can be used for different users. Different similarity measures can be used for a particular user across time. A superior similarity measure can be found for a user. User-defined similarity measures can be supported.Type: GrantFiled: June 19, 2007Date of Patent: June 18, 2013Assignee: Infosys LimitedInventor: Ashish Sureka
-
Publication number: 20110093293Abstract: The invention provides a method and clinical data mining system for enabling a user to derive knowledge from data corresponding to a plurality of electronic health records stored in a repository. One or more data elements are provided as an input. The data elements may include textual reports, images, and one or more criteria specified by the user. Information is extracted from one or more images associated with one or more electronic health records stored in the repository, based on the data elements. Further, information is extracted from one or more textual reports and structured data associated with the one or more electronic health records. Thereafter, one or more reports are generated based on the extracted information to enable the user to analyze the information. Subsequently, the user may derive knowledge from the data based on the analysis.Type: ApplicationFiled: June 14, 2010Publication date: April 21, 2011Applicant: INFOSYS TECHNOLOGIES LIMITEDInventors: Harikrishna Rai G. N., Ashish Sureka, Sivaram V. Thangam, Pranav Prabhakar Mirajkar, K. Sai Deepak
-
Publication number: 20110010685Abstract: A system and method for developing a rule-based named entity extraction system is provided. The method includes analyzing requirements of business users. The method further includes designing the rule-based named entity extraction system based on the requirement analysis. Further, the method includes implementing the design of rule-based named entity extraction system using one or more GUI-based tools. Thereafter, regression testing of the rule-based named entity extraction system is conducted. Finally, rule-based named entity extraction system is deployed.Type: ApplicationFiled: May 21, 2010Publication date: January 13, 2011Applicant: INFOSYS TECHNOLOGIES LIMITEDInventors: Ashish SUREKA, Pranav Prabhakar MIRAJKAR, Kishore Varma INDUKURI
-
Patent number: 7801836Abstract: A predictive data mining model can be selected based on how well the model meets an objective function. In certain implementations genetic algorithms can be used to search a space of predictive data mining model building parameters to determine an optimal predictive data mining model based on a score function corresponding to, for example, the accuracy of the selected predictive data mining model.Type: GrantFiled: September 26, 2007Date of Patent: September 21, 2010Assignee: Infosys Technologies Ltd.Inventor: Ashish Sureka
-
Patent number: 7743068Abstract: A computerized method, system and program product for generating a data mining model. A user can provide objectives for the model and sample data to train, validate, and test the model. A rules system can automatically select a set of algorithms based on the objectives and/or sample data. A plurality of datasets can also be created from the sample data. Using the datasets, the set of algorithms can be optimized for the particular data on which it is intended to be used. The data mining model can then be generated from the optimized set of algorithms.Type: GrantFiled: October 25, 2007Date of Patent: June 22, 2010Assignee: International Business Machines CorporationInventors: Feng-wei Chen Russell, Ameet M. Kini, John A. Medicke, Jr., Betsy M. Plunket, Ashish Sureka
-
Patent number: 7739297Abstract: A computerized method, system and program product for generating a data mining model. A user can provide objectives for the model and sample data to train, validate, and test the model. A rules system can automatically select a set of algorithms based on the objectives and/or sample data. A plurality of datasets can also be created from the sample data. Using the datasets, the set of algorithms can be optimized for the particular data on which it is intended to be used. The data mining model can then be generated from the optimized set of algorithms.Type: GrantFiled: October 25, 2007Date of Patent: June 15, 2010Assignee: International Business Machines CorporationInventors: Feng-wei Chen Russell, Ameet M. Kini, John A. Medicke, Jr., Betsy M. Plunket, Ashish Sureka
-
Patent number: 7734645Abstract: A computerized method, system and program product for generating a data mining model. A user can provide objectives for the model and sample data to train, validate, and test the model. A rules system can automatically select a set of algorithms based on the objectives and/or sample data. A plurality of datasets can also be created from the sample data. Using the datasets, the set of algorithms can be optimized for the particular data on which it is intended to be used. The data mining model can then be generated from the optimized set of algorithms.Type: GrantFiled: October 25, 2007Date of Patent: June 8, 2010Assignee: International Business Machines CorporationInventors: Feng-wei Chen Russell, Ameet M. Kini, John A. Medicke, Jr., Betsy M. Plunket, Ashish Sureka
-
Publication number: 20090150325Abstract: A system, method and computer program product for the root cause analysis of the failure of a manufactured product is disclosed. The present invention includes the development of a knowledge model, based on information obtained from historical warranty claim forms and various manufacturing data sources. The invention also includes processing text information in a free-form text that is obtained from warranty claim forms by using text-tagging and annotation techniques. Thereafter, the knowledge model is converted to a Bayesian network. The present invention provides a user interface to select parameters and corresponding instances from current warranty claim forms. The selected parameters and corresponding instances are used as input evidence for the Bayesian network. The present invention facilitates the process of drawing inferences for root cause analysis of the failure of manufactured products and corresponding probabilities.Type: ApplicationFiled: December 3, 2008Publication date: June 11, 2009Applicant: Infosys Technologies Ltd.Inventors: Sudripto De, Srinivas Narasimhamurthy, Ashish Sureka, Satyabrata Pradhan
-
Publication number: 20090144276Abstract: Under the present invention, a data exploration system, a customized model system and an existing model system are provided. The data exploration system analyzes user data to identify statistical information such as data distribution, data relationships, data outliners and invalid or missing data values. The customized model center iteratively generates customized data mining models in parallel based on permutations of the user data, user-provided business parameters and/or a set of model generation algorithms. The existing model system provides users with a library of existing data mining models, assembled based on the business parameters, from which they can choose one or more. In any event, any customized or existing data mining models selected can be run against the user data in parallel.Type: ApplicationFiled: January 5, 2009Publication date: June 4, 2009Inventors: Feng-wei Chen Russell, Ameet M. Kini, Marcelo Cunha Loureiro, John A. Medicke, JR., Betsy M. Plunket, Ashish Sureka
-
Patent number: 7523106Abstract: Under the present invention, a data exploration system, a customized model system and an existing model system are provided. The data exploration system analyzes user data to identify statistical information such as data distribution, data relationships, data outliners and invalid or missing data values. The customized model center iteratively generates customized data mining models in parallel based on permutations of the user data, user-provided business parameters and/or a set of model generation algorithms. The existing model system provides users with a library of existing data mining models, assembled based on the business parameters, from which they can choose one or more. In any event, any customized or existing data mining models selected can be run against the user data in parallel.Type: GrantFiled: November 24, 2003Date of Patent: April 21, 2009Assignee: International Business Machines CoporationInventors: Feng-wei Chen Russell, Ameet M. Kini, Marcelo Cunha Loureiro, John A. Medicke, Jr., Betsy M. Plunket, Ashish Sureka
-
Publication number: 20080077544Abstract: A predictive data mining model can be selected based on how well the model meets an objective function. In certain implementations genetic algorithms can be used to search a space of predictive data mining model building parameters to determine an optimal predictive data mining model based on a score function corresponding to, for example, the accuracy of the selected predictive data mining model.Type: ApplicationFiled: September 26, 2007Publication date: March 27, 2008Applicant: Infosys Technologies Ltd.Inventor: Ashish Sureka
-
Patent number: 7349919Abstract: A computerized method, system and program product for generating a data mining model. A user can provide objectives for the model and sample data to train, validate, and test the model. A rules system can automatically select a set of algorithms based on the objectives and/or sample data. A plurality of datasets can also be created from the sample data. Using the datasets, the set of algorithms can be optimized for the particular data on which it is intended to be used. The data mining model can then be generated from the optimized set of algorithms.Type: GrantFiled: November 21, 2003Date of Patent: March 25, 2008Assignee: International Business Machines CorporationInventors: Feng-wei Chen Russell, Ameet M. Kini, John A. Medicke, Jr., Betsy M. Plunket, Ashish Sureka
-
Publication number: 20080046402Abstract: A computerized method, system and program product for generating a data mining model. A user can provide objectives for the model and sample data to train, validate, and test the model. A rules system can automatically select a set of algorithms based on the objectives and/or sample data. A plurality of datasets can also be created from the sample data. Using the datasets, the set of algorithms can be optimized for the particular data on which it is intended to be used. The data mining model can then be generated from the optimized set of algorithms.Type: ApplicationFiled: October 25, 2007Publication date: February 21, 2008Inventors: Feng-wei Russell, Ameet Kini, John Medicke, Betsy Plunket, Ashish Sureka
-
Publication number: 20080046452Abstract: A computerized method, system and program product for generating a data mining model. A user can provide objectives for the model and sample data to train, validate, and test the model. A rules system can automatically select a set of algorithms based on the objectives and/or sample data. A plurality of datasets can also be created from the sample data. Using the datasets, the set of algorithms can be optimized for the particular data on which it is intended to be used. The data mining model can then be generated from the optimized set of algorithms.Type: ApplicationFiled: October 25, 2007Publication date: February 21, 2008Inventors: Feng-wei Russell, Ameet Kini, John Medicke, Betsy Plunket, Ashish Sureka
-
Publication number: 20080046426Abstract: A computerized method, system and program product for generating a data mining model. A user can provide objectives for the model and sample data to train, validate, and test the model. A rules system can automatically select a set of algorithms based on the objectives and/or sample data. A plurality of datasets can also be created from the sample data. Using the datasets, the set of algorithms can be optimized for the particular data on which it is intended to be used. The data mining model can then be generated from the optimized set of algorithms.Type: ApplicationFiled: October 25, 2007Publication date: February 21, 2008Inventors: Feng-wei Russell, Ameet Kini, John Medicke, Betsy Plunket, Ashish Sureka
-
Publication number: 20080010258Abstract: Various techniques can be used to implement a collaborative filtering-based recommendation engine. For example, different similarity measures can be used for different users. Different similarity measures can be used for a particular user across time. A superior similarity measure can be found for a user. User-defined similarity measures can be supported.Type: ApplicationFiled: June 19, 2007Publication date: January 10, 2008Applicant: Infosys Technologies Ltd.Inventor: Ashish Sureka
-
Publication number: 20050114360Abstract: Under the present invention, a data exploration system, a customized model system and an existing model system are provided. The data exploration system analyzes user data to identify statistical information such as data distribution, data relationships, data outliners and invalid or missing data values. The customized model center iteratively generates customized data mining models in parallel based on permutations of the user data, user-provided business parameters and/or a set of model generation algorithms. The existing model system provides users with a library of existing data mining models, assembled based on the business parameters, from which they can choose one or more. In any event, any customized or existing data mining models selected can be run against the user data in parallel.Type: ApplicationFiled: November 24, 2003Publication date: May 26, 2005Applicant: International Business Machines CorporationInventors: Feng-Wei Russell, Ameet Kini, Marcelo Loureiro, John Medicke, Betsy Plunket, Ashish Sureka