Patents by Inventor Ashish Mungi
Ashish Mungi 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: 11010545Abstract: A method for narrating a table using at least one narration template, wherein the table is extracted from a data source is provided. The method may also include performing structural analysis on the extracted table. The method may further include selecting a structural template based on the structural analysis of the extracted table. Additionally, the method may include selecting a narration template based on the selected structural template. The method may further include narrating the extracted table based on the selected narration template and displaying a narrative output of the extracted table.Type: GrantFiled: April 24, 2019Date of Patent: May 18, 2021Assignee: International Business Machines CorporationInventors: Chinnappa Guggilla, Ashish Mungi, Purushothaman K. Narayanan, Ankur S. Parikh, Krishma Singla, Bijo A. Thomas
-
Patent number: 11010546Abstract: A method for narrating a table using at least one narration template, wherein the table is extracted from a data source is provided. The method may also include performing structural analysis on the extracted table. The method may further include selecting a structural template based on the structural analysis of the extracted table. Additionally, the method may include selecting a narration template based on the selected structural template. The method may further include narrating the extracted table based on the selected narration template and displaying a narrative output of the extracted table.Type: GrantFiled: April 24, 2019Date of Patent: May 18, 2021Assignee: International Business Machines CorporationInventors: Chinnappa Guggilla, Ashish Mungi, Purushothaman K. Narayanan, Ankur S. Parikh, Krishma Singla, Bijo A. Thomas
-
Patent number: 10943064Abstract: One or more table content documents (TCDs) can be constructed for a set of tabular data or portion thereof. A set of query features corresponding to a question can be matched to one or more TCDs. A respective candidate answer can be generated for each of the one or more TCDs having a set of features matching the set of query features above a threshold. Zero or more candidate answers can be output to a user consumable data object.Type: GrantFiled: May 29, 2019Date of Patent: March 9, 2021Assignee: International Business Machines CorporationInventors: Ashish Mungi, Purushothaman K. Narayanan, Ankur Parikh
-
Patent number: 10789552Abstract: Generating distractors for text-based MCT items. An MCT item stem is received. The stem is transmitted to a QA system and a plurality of candidate answers related to the stem is received from the QA system. Incorrect answers in the plurality of candidate answers are identified. Textual features are extracted from the stem. A set of semantic criteria associated with the extracted textual features is generated. Based on the generated semantic criteria, a subset of the incorrect candidate answers is selected.Type: GrantFiled: August 7, 2019Date of Patent: September 29, 2020Assignee: International Business Machines CorporationInventors: Lalit Agarwalla, Ashish Mungi, Joy Mustafi, Ankur Parikh
-
Patent number: 10579340Abstract: Model element characteristic preservation is provided when instantiating unified modeling language elements of a unified modeling language model. Requirements management tool elements become associated with a stereotype via, for instance, user assignment of the stereotype to a requirements type of the requirements management project. A stereotype assignment is obtained for a requirements management tool element, and the stereotype is automatically applied when instantiating a UML element representative of the requirements management tool element. Nesting and traceability relationships between the requirements management tool element and other requirements management tool elements are additionally preserved.Type: GrantFiled: June 6, 2012Date of Patent: March 3, 2020Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Ahamed Jalaldeen, Ashish Mungi, Cedric Sequeira
-
Publication number: 20190362265Abstract: Generating distractors for text-based MCT items. An MCT item stem is received. The stem is transmitted to a QA system and a plurality of candidate answers related to the stem is received from the QA system. Incorrect answers in the plurality of candidate answers are identified. Textual features are extracted from the stem. A set of semantic criteria associated with the extracted textual features is generated. Based on the generated semantic criteria, a subset of the incorrect candidate answers is selected.Type: ApplicationFiled: August 7, 2019Publication date: November 28, 2019Inventors: Lalit Agarwalla, Ashish Mungi, Joy Mustafi, Ankur Parikh
-
Patent number: 10417581Abstract: Generating distractors for text-based MCT items. An MCT item stem is received. The stem is transmitted to a QA system and a plurality of candidate answers related to the stem is received from the QA system. Incorrect answers in the plurality of candidate answers are identified. Textual features are extracted from the stem. A set of semantic criteria associated with the extracted textual features is generated. Based on the generated semantic criteria, a subset of the incorrect candidate answers is selected.Type: GrantFiled: May 20, 2016Date of Patent: September 17, 2019Assignee: International Business Machines CorporationInventors: Lalit Agarwalla, Ashish Mungi, Joy Mustafi, Ankur Parikh
-
Publication number: 20190278838Abstract: One or more table content documents (TCDs) can be constructed for a set of tabular data or portion thereof. A set of query features corresponding to a question can be matched to one or more TCDs. A respective candidate answer can be generated for each of the one or more TCDs having a set of features matching the set of query features above a threshold. Zero or more candidate answers can be output to a user consumable data object.Type: ApplicationFiled: May 29, 2019Publication date: September 12, 2019Inventors: Ashish Mungi, Purushothaman K. Narayanan, Ankur Parikh
-
Patent number: 10409907Abstract: One or more table content documents (TCDs) can be constructed for a set of tabular data or portion thereof. A set of query features corresponding to a question can be matched to one or more TCDs. A respective candidate answer can be generated for each of the one or more TCDs having a set of features matching the set of query features above a threshold. Zero or more candidate answers can be output to a user consumable data object.Type: GrantFiled: June 11, 2018Date of Patent: September 10, 2019Assignee: International Business Machines CorporationInventors: Ashish Mungi, Purushothaman K. Narayanan, Ankur Parikh
-
Publication number: 20190251159Abstract: A method for narrating a table using at least one narration template, wherein the table is extracted from a data source is provided. The method may also include performing structural analysis on the extracted table. The method may further include selecting a structural template based on the structural analysis of the extracted table. Additionally, the method may include selecting a narration template based on the selected structural template. The method may further include narrating the extracted table based on the selected narration template and displaying a narrative output of the extracted table.Type: ApplicationFiled: April 24, 2019Publication date: August 15, 2019Inventors: Chinnappa Guggilla, Ashish Mungi, Purushothaman K. Narayanan, Ankur S. Parikh, KRISHMA SINGLA, Bijo A. Thomas
-
Publication number: 20190251160Abstract: A method for narrating a table using at least one narration template, wherein the table is extracted from a data source is provided. The method may also include performing structural analysis on the extracted table. The method may further include selecting a structural template based on the structural analysis of the extracted table. Additionally, the method may include selecting a narration template based on the selected structural template. The method may further include narrating the extracted table based on the selected narration template and displaying a narrative output of the extracted table.Type: ApplicationFiled: April 24, 2019Publication date: August 15, 2019Inventors: Chinnappa Guggilla, Ashish Mungi, Purushothaman K. Narayanan, Ankur S. Parikh, KRISHMA SINGLA, Bijo A. Thomas
-
Patent number: 10318626Abstract: A method for narrating a table using at least one narration template, wherein the table is extracted from a data source is provided. The method may include parsing the extracted table. The method may also include performing structural analysis on the parsed extracted table. The method may further include selecting at least one structural template based on the structural analysis of the parsed extracted table. Additionally, the method may include selecting the at least one narration template based on the at least one selected structural template. The method may also include applying the at least one selected narration template to the extracted table. The method may further include narrating the extracted table based on the applying of the at least one selected narration template to the extracted table.Type: GrantFiled: August 25, 2014Date of Patent: June 11, 2019Assignee: International Business Machines CorporationInventors: Chinnappa Guggilla, Ashish Mungi, Purushothaman K. Narayanan, Ankur S. Parikh, Krishma Singla, Bijo A. Thomas
-
Patent number: 10318625Abstract: A computer system for narrating a table using at least one narration template, wherein the table is extracted from a data source is provided. The computer system may include parsing the extracted table. The computer system may also include performing structural analysis on the parsed extracted table. The computer system may further include selecting at least one structural template based on the structural analysis of the parsed extracted table. Additionally, the computer system may include selecting the at least one narration template based on the at least one selected structural template. The computer system may also include applying the at least one selected narration template to the extracted table. The computer system may further include narrating the extracted table based on the applying of the at least one selected narration template to the extracted table.Type: GrantFiled: May 13, 2014Date of Patent: June 11, 2019Assignee: International Business Machines CorporationInventors: Chinnappa Guggilla, Ashish Mungi, Purushothaman K. Narayanan, Ankur S. Parikh, Krishma Singla, Bijo A. Thomas
-
Patent number: 10133732Abstract: A method and system for improving location specific (L) functions is provided. The method includes generating and maintaining an online L-word dictionary. Location specific attributes, settings, and preferences associated with a current location of a mobile device and a user are retrieved. An input question is received and an NLP analysis with respect to the input question is executed to extract a required value phrase. An interim question based on an extracted required value phrase is formed and an answer to the input question is determined in natural language based on a solved interim question. The answer is narrated in natural language and includes an automated interactive response from a hardware device in real time.Type: GrantFiled: March 21, 2017Date of Patent: November 20, 2018Assignee: International Business Machines CorporationInventors: Ashish Mungi, Joy Mustafi
-
Publication number: 20180293218Abstract: One or more table content documents (TCDs) can be constructed for a set of tabular data or portion thereof. A set of query features corresponding to a question can be matched to one or more TCDs. A respective candidate answer can be generated for each of the one or more TCDs having a set of features matching the set of query features above a threshold. Zero or more candidate answers can be output to a user consumable data object.Type: ApplicationFiled: June 11, 2018Publication date: October 11, 2018Inventors: Ashish Mungi, Purushothaman K. Narayanan, Ankur Parikh
-
Publication number: 20180276198Abstract: A method and system for improving location specific (L) functions is provided. The method includes generating and maintaining an online L-word dictionary. Location specific attributes, settings, and preferences associated with a current location of a mobile device and a user are retrieved. An input question is received and an NLP analysis with respect to the input question is executed to extract a required value phrase. An interim question based on an extracted required value phrase is formed and an answer to the input question is determined in natural language based on a solved interim question. The answer is narrated in natural language and includes an automated interactive response from a hardware device in real time.Type: ApplicationFiled: March 21, 2017Publication date: September 27, 2018Inventors: Ashish Mungi, Joy Mustafi
-
Patent number: 10078629Abstract: One or more table content documents (TCDs) can be constructed for a set of tabular data or portion thereof. A set of query features corresponding to a question can be matched to one or more TCDs. A respective candidate answer can be generated for each of the one or more TCDs having a set of features matching the set of query features above a threshold. Zero or more candidate answers can be output to a user consumable data object.Type: GrantFiled: October 22, 2015Date of Patent: September 18, 2018Assignee: International Business Machines CorporationInventors: Ashish Mungi, Purushothaman K. Narayanan, Ankur Parikh
-
Patent number: 9940114Abstract: An approach is provided for managing a deployment of a software package. First and second quality assurance (QA) seals are determined to match exactly one QA seal and no QA seal, respectively, in a plurality of QA seals. First details about hardware, middleware, and applications required in a first environment, which are included in the first QA seal, are determined to match second details of the first environment. Based on the first QA seal matching exactly one QA seal and the first details matching the second details, the software package is determined to be compatible with the first environment and a notification is generated authorizing the deployment of the software package to the first environment. Based on the second QA seal not matching any of the plurality of QA seals, a notification is generated indicating that the deployment of the software package to a second environment is not authorized.Type: GrantFiled: May 31, 2016Date of Patent: April 10, 2018Assignee: International Business Machines CorporationInventors: Nagesh K. Mantripragada, Ashish Mungi, Manjit S. Sodhi, Ram Viswanathan
-
Patent number: 9916303Abstract: A method providing an answer to an input question containing at least one time-sensitive word or at least one time-sensitive phrase using natural language processing (NLP) is provided. The method may include receiving the input question. The method may also include performing natural language processing (NLP) analysis on the input question to extract a required value phrase. The method may further include forming at least one mathematical equation based on the extracted required value phrase. Additionally, the method may include forming at least one interim question based on the extracted required value phrase. The method may further include solving the at least one formed mathematical equation and the at least one formed interim question. The method may also include narrating the answer to the input question in natural language based on the solved at least one interim question or the solved at least one mathematical equation.Type: GrantFiled: February 17, 2017Date of Patent: March 13, 2018Assignee: International Business Machines CorporationInventors: Ashish Mungi, Joy Mustafi
-
Patent number: 9684876Abstract: Generating distractors for text-based MCT items. An MCT item stem is received. The stem is transmitted to a QA system and a plurality of candidate answers related to the stem is received from the QA system. Incorrect answers in the plurality of candidate answers are identified. Textual features are extracted from the stem. A set of semantic criteria associated with the extracted textual features is generated. Based on the generated semantic criteria, a subset of the incorrect candidate answers is selected.Type: GrantFiled: March 30, 2015Date of Patent: June 20, 2017Assignee: International Business Machines CorporationInventors: Lalit Agarwalla, Ashish Mungi, Joy Mustafi, Ankur Parikh