Patents by Inventor Dmitry Levinson

Dmitry Levinson 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).

  • Self-service classification system
    Patent number: 10990897
    Abstract: Systems, technologies and techniques for generating a customized classification model are disclosed. The system and technologies, such as THOMSON REUTERS SELF-SERVICE CLASSIFICATION™, employ part machine learning and part an user interactive approach to generate a customized classification model. The system combines a novel approach for text classification using a smaller initial set of data to initiate training, with a unique workflow and user interaction for customization.
    Type: Grant
    Filed: April 4, 2017
    Date of Patent: April 27, 2021
    Inventors: Hila Zarosim, Oren Hazai, Ofri Rom, Ehud Azikri, Lior Weintraub, Yael Lindman, Enav Weinreb, Savva Khalaman, Yossi Ben-Shlomo, Dmitry Levinson, Evyatar Sharabi, Alexandra Rabinovich Goldshlager, Shai Hertz
  • Apparatuses, methods and systems for adjusting tagging in a computing environment
    Patent number: 10891421
    Abstract: The present disclosure is directed to methods, systems and programs for adjusting tagging of files. An illustrative method includes receiving a request to upload at least one document from a user via processor, assigning a first metadata tag via processor to at least one word contained within the at least one document, wherein the first metadata tag identifies the at least one word as an alias for a first unique entity, delivering the at least one document to the user including the first metadata tag via processor, receiving feedback via processor from the user relating to the assignment of the first metadata tag to the at least one word, determining at least one potential adjustment for the assignment of the first metadata tag via processor, sending information to the user proposing the at least one potential adjustment via processor, and receiving confirmation information from the user concerning the potential adjustment.
    Type: Grant
    Filed: December 18, 2017
    Date of Patent: January 12, 2021
    Assignee: Refinitiv US Organization LLC
    Inventors: Enav Weinreb, Rani Shlivinski, Shai Hertz, Shai Taub, Yaniv Ben-Meir, Chen Weiss, Dmitry Levinson, Danel Kotev, Lior Gelernter, Saar Miron
  • APPARATUSES, METHODS AND SYSTEMS FOR ADJUSTING TAGGING IN A COMPUTING ENVIRONMENT
    Publication number: 20190361960
    Abstract: The present disclosure is directed to methods, systems and programs for adjusting tagging of files. An illustrative method includes receiving a request to upload at least one document from a user via processor, assigning a first metadata tag via processor to at least one word contained within the at least one document, wherein the first metadata tag identifies the at least one word as an alias for a first unique entity, delivering the at least one document to the user including the first metadata tag via processor, receiving feedback via processor from the user relating to the assignment of the first metadata tag to the at least one word, determining at least one potential adjustment for the assignment of the first metadata tag via processor, sending information to the user proposing the at least one potential adjustment via processor, and receiving confirmation information from the user concerning the potential adjustment.
    Type: Application
    Filed: December 18, 2017
    Publication date: November 28, 2019
    Inventors: Enav Weinreb, Rani Shlivinski, Shai Hertz, Shai Taub, Yaniv Ben-Meir, Chen Weiss, Dmitry Levinson, Danel Kotev, Lior Gelernter, Saar Miron
  • APPARATUSES, METHODS AND SYSTEMS FOR ADJUSTING TAGGING IN A COMPUTING ENVIRONMENT
    Publication number: 20190188247
    Abstract: The present disclosure is directed to methods, systems and programs for adjusting tagging of files. An illustrative method includes receiving a request to upload at least one document from a user via processor, assigning a first metadata tag via processor to at least one word contained within the at least one document, wherein the first metadata tag identifies the at least one word as an alias for a first unique entity, delivering the at least one document to the user including the first metadata tag via processor, receiving feedback via processor from the user relating to the assignment of the first metadata tag to the at least one word, determining at least one potential adjustment for the assignment of the first metadata tag via processor, sending information to the user proposing the at least one potential adjustment via processor, and receiving confirmation information from the user concerning the potential adjustment.
    Type: Application
    Filed: December 18, 2017
    Publication date: June 20, 2019
    Inventors: Enav Weinreb, Rani Shlivinski, Shai Hertz, Shai Taub, Yaniv Ben-Meir, Chen Weiss, Dmitry Levinson, Danel Kotev, Lior Gelernter, Saar Miron
  • Self-Service Classification System
    Publication number: 20170286869
    Abstract: Systems, technologies and techniques for generating a customized classification model are disclosed. The system and technologies, such as THOMSON REUTERS SELF-SERVICE CLASSIFICATION™, employ part machine learning and part an user interactive approach to generate a customized classification model. The system combines a novel approach for text classification using a smaller initial set of data to initiate training, with a unique workflow and user interaction for customization.
    Type: Application
    Filed: April 4, 2017
    Publication date: October 5, 2017
    Inventors: Hila Zarosim, Oren Hazai, Ofri Rom, Ehud Azikri, Lior Weintraub, Yael Lindman, Enav Weinreb, Savva Khalaman, Yossi Ben-Shlomo, Dmitry Levinson, Evyatar Sharabi, Alexandra Rabinovich Goldshlager, Shai Hertz