Patents by Inventor Krishna Mahajan

Krishna Mahajan 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: 11687796
    Abstract: An approach is provided that receives a document and a document type of the document. The document type identifies a document category to which the received document belongs. A set of linguistic metrics are retrieved that correspond to the document type. A quality of the received document is automatically determined based on a set of linguistic features found in the document as compared to the retrieved set of linguistic metrics. The document is then ingested into a corpus that is utilized by a question-answering (QA) system. The ingestion of the document is based on the determined quality.
    Type: Grant
    Filed: April 17, 2019
    Date of Patent: June 27, 2023
    Assignee: International Business Machines Corporation
    Inventors: Brien H. Muschett, Andrew R. Freed, Roberto Delima, David Contreras, Krishna Mahajan
  • Patent number: 11593561
    Abstract: A phrase that includes a trigger word that modifies a meaning within the phrase is received. The trigger word is identified. The words of the phrase that are modified by the trigger word are identified by analyzing features of the phrase that link the trigger word to other words. The phrase is interpreted by modifying the second subset of words according to the modification of the trigger word.
    Type: Grant
    Filed: September 11, 2019
    Date of Patent: February 28, 2023
    Assignee: International Business Machines Corporation
    Inventors: David Contreras, Krishna Mahajan, Roberto Delima, Kandhan Sekar, Corville O. Allen, Chris Mwarabu
  • Patent number: 11295080
    Abstract: A method, system, and computer program product include providing a list of triggers, training the natural language processor with the list of triggers, providing to the natural language processor a text including one trigger, selecting nodes in the text to create an original potential span, predicting whether the original potential span includes another trigger, and adjusting, in response to predicting that the original potential span includes another trigger, the original potential span to exclude the another trigger to create a new potential span.
    Type: Grant
    Filed: June 4, 2019
    Date of Patent: April 5, 2022
    Assignee: International Business Machines Corporation
    Inventors: Corville O. Allen, Roberto Delima, David Contreras, Krishna Mahajan
  • Patent number: 11113469
    Abstract: A phrase may be received that includes a plurality of tokens in a natural language format. A plurality of levels relating to dependencies between tokens of the plurality of tokens within the phrase is determined. A matrix structure is generated for the phrase. The matrix structure utilizes a plurality of rows and a plurality of columns to store data of the phrase. The plurality of rows and the plurality of columns each indicate one of an order of tokens of the plurality of tokens or levels of the plurality of levels.
    Type: Grant
    Filed: March 27, 2019
    Date of Patent: September 7, 2021
    Assignee: International Business Machines Corporation
    Inventors: Corville O. Allen, Roberto Delima, Chris Mwarabu, David Contreras, Kandhan Sekar, Krishna Mahajan
  • Patent number: 11017171
    Abstract: A method, computer system, and a computer program product for relevancy-based document quality assessment is provided. The present invention may include computing a document quality score based on at least one container relevancy score determined based on at least one domain link to a domain knowledge base.
    Type: Grant
    Filed: June 6, 2019
    Date of Patent: May 25, 2021
    Assignee: International Business Machines Corporation
    Inventors: Roberto Delima, Andrew R. Freed, Brien Muschett, Krishna Mahajan, David Contreras
  • Publication number: 20210030418
    Abstract: An everter device to facilitate preparation of ends of arterial segments for end-to-end microvascular anastomosis. The device includes structure that provides sufficient support to prevent unwanted buckling of arterial tissue. The everter device offsets the tendency of the arterial tissue wall to recover its natural shape and fall off securement posts or pins of a coupler ring. The structure may be in the form of an intraluminal catheter balloon. Alternately, the structure may be in the form of a plunger. Alternately, the structure may be in the form of a radially expanding member provided on a shaft. The device further has a contoured surface on an everter end to evert a free end of arterial tissue over a coupler ring, and to cause the posts or pins of the coupler ring to pierce through the everted arterial tissue. The everter end is provided with one or more openings therein, such as a circumferential slot, to receive the posts or pins of the coupler ring.
    Type: Application
    Filed: October 20, 2020
    Publication date: February 4, 2021
    Inventors: Jeffrey Stephen Plott, Paul S. Cederna, Kirsten Boelkins, Jeffrey H. Kozlow, Jonathan William Zwier, Krishna Mahajan, Kelsey L. Luibrand, Martin Sisolak, Sebastian Kwon, Aaron S. Farberg, Adeyiza Momoh, Albert J. Shih
  • Publication number: 20200387571
    Abstract: A method, computer system, and a computer program product for relevancy-based document quality assessment is provided. The present invention may include computing a document quality score based on at least one container relevancy score determined based on at least one domain link to a domain knowledge base.
    Type: Application
    Filed: June 6, 2019
    Publication date: December 10, 2020
    Inventors: Roberto Delima, Andrew R. Freed, Brien Muschett, Krishna Mahajan, David Contreras
  • Publication number: 20200387572
    Abstract: A method, system, and computer program product include providing a list of triggers, training the natural language processor with the list of triggers, providing to the natural language processor a text including one trigger, selecting nodes in the text to create an original potential span, predicting whether the original potential span includes another trigger, and adjusting, in response to predicting that the original potential span includes another trigger, the original potential span to exclude the another trigger to create a new potential span.
    Type: Application
    Filed: June 4, 2019
    Publication date: December 10, 2020
    Inventors: Corville O. Allen, Roberto Delima, David Contreras, Krishna Mahajan
  • Patent number: 10842493
    Abstract: An everter device to facilitate preparation of ends of arterial segments for end-to-end microvascular anastomosis. The device includes structure that provides sufficient support to prevent unwanted buckling of arterial tissue. The everter device offsets the tendency of the arterial tissue wall to recover its natural shape and fall off securement posts or pins of a coupler ring. The structure may be in the form of an intraluminal catheter balloon. Alternately, the structure may be in the form of a plunger. Alternately, the structure may be in the form of a radially expanding member provided on a shaft. The device further has a contoured surface on an everter end to evert a free end of arterial tissue over a coupler ring, and to cause the posts or pins of the coupler ring to pierce through the everted arterial tissue. The everter end is provided with one or more openings therein, such as a circumferential slot, to receive the posts or pins of the coupler ring.
    Type: Grant
    Filed: September 2, 2016
    Date of Patent: November 24, 2020
    Assignee: THE REGENTS OF THE UNIVERSITY OF MICHIGAN
    Inventors: Jeffrey Stephen Plott, Paul S. Cederna, Kirsten Boelkins, Jeffrey H. Kozlow, Jonathan William Zwier, Krishna Mahajan, Kelsey L. Luibrand, Martin Sisolak, Sebastian Kwon, Aaron S. Farberg, Adeyiza Momoh, Albert J. Shih
  • Publication number: 20200334546
    Abstract: An approach is provided that receives a document and a document type of the document. The document type identifies a document category to which the received document belongs. A set of linguistic metrics are retrieved that correspond to the document type. A quality of the received document is automatically determined based on a set of linguistic features found in the document as compared to the retrieved set of linguistic metrics. The document is then ingested into a corpus that is utilized by a question-answering (QA) system. The ingestion of the document is based on the determined quality.
    Type: Application
    Filed: April 17, 2019
    Publication date: October 22, 2020
    Inventors: Brien H. Muschett, Andrew R. Freed, Roberto Delima, David Contreras, Krishna Mahajan
  • Publication number: 20200311197
    Abstract: A phrase may be received that includes a plurality of tokens in a natural language format. A plurality of levels relating to dependencies between tokens of the plurality of tokens within the phrase is determined. A matrix structure is generated for the phrase. The matrix structure utilizes a plurality of rows and a plurality of columns to store data of the phrase. The plurality of rows and the plurality of columns each indicate one of an order of tokens of the plurality of tokens or levels of the plurality of levels.
    Type: Application
    Filed: March 27, 2019
    Publication date: October 1, 2020
    Inventors: Corville O. Allen, Roberto Delima, Chris Mwarabu, David Contreras, Kandhan Sekar, Krishna Mahajan
  • Publication number: 20200302332
    Abstract: A computer-implemented method, system and computer program product for generating a client-specific document quality model, by: analyzing data using existing quality heuristics to identify new, unexpected or problem patterns in the data; forming the quality heuristics into one or more clusters for each container level of the data; exploring each of the clusters to identify sources of the patterns; and developing new quality heuristics based on the sources of the patterns, wherein the new quality heuristics are used to generate the client-specific document quality model.
    Type: Application
    Filed: March 20, 2019
    Publication date: September 24, 2020
    Inventors: David Contreras, Krishna Mahajan, Roberto Delima, Andrew R. Freed, Brien Muschett
  • Publication number: 20200175116
    Abstract: A phrase that includes a trigger word that modifies a meaning within the phrase is received. The trigger word is identified. The words of the phrase that are modified by the trigger word are identified by analyzing features of the phrase that link the trigger word to other words. The phrase is interpreted by modifying the second subset of words according to the modification of the trigger word.
    Type: Application
    Filed: September 11, 2019
    Publication date: June 4, 2020
    Inventors: David Contreras, Krishna Mahajan, Roberto Delima, Kandhan Sekar, Corville O. Allen, Chris Mwarabu
  • Publication number: 20180271529
    Abstract: An everter device to facilitate preparation of ends of arterial segments for end-to-end microvascular anastomosis. The device includes structure that provides sufficient support to prevent unwanted buckling of arterial tissue. The everter device offsets the tendency of the arterial tissue wall to recover its natural shape and fall off securement posts or pins of a coupler ring. The structure may be in the form of an intraluminal catheter balloon. Alternately, the structure may be in the form of a plunger. Alternately, the structure may be in the form of a radially expanding member provided on a shaft. The device further has a contoured surface on an everter end to evert a free end of arterial tissue over a coupler ring, and to cause the posts or pins of the coupler ring to pierce through the everted arterial tissue. The everter end is provided with one or more openings therein, such as a circumferential slot, to receive the posts or pins of the coupler ring.
    Type: Application
    Filed: September 2, 2016
    Publication date: September 27, 2018
    Inventors: Jeffrey Stephen Plott, Paul S. Cederma, Kirsten Boelkins, Jeffrey H. Kozlow, Jonathan William Zwier, Krishna Mahajan, Kelsey L. Luibrand, Martin Sisolak, Sebastian Kwon, Aaron S. Farberg, Adeyiza Momoh, Albert J. Shih