Patents by Inventor Béla Lóránt KOVÁCS

Béla Lóránt KOVÁCS 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).

  • METHODS AND SYSTEM FOR SEMANTIC SEARCH IN LARGE DATABASES
    Publication number: 20220261427
    Abstract: A computer-implemented method of performing a semantic search in a source document database containing documents that are identified by a unique document identifier, including: reading a text component of a text-containing query; generating a set of query features from the text component of the query using a predefined feature extraction model; generating a set of training features based on the plurality of query features; training a trainable classifier with the training features and a set of document features obtained from at least a portion of the source documents using a predefined feature extraction model; selecting a number of source documents for classification according to a predefined selection scheme; obtaining features of the selected documents; classifying the selected source documents into different classes of relevance by using features of the selected documents, where at least one value of relevance is associated with each selected document; ranking the classified documents in an ordered list b
    Type: Application
    Filed: March 2, 2022
    Publication date: August 18, 2022
    Inventors: Bela Lorant KOVACS, Akos Jager
  • SYSTEMS AND METHODS TO FACILITATE TEXT CONTENT SEARCH
    Publication number: 20210073303
    Abstract: A user interface system for performing searches in text-containing documents including a graphical user interface. The system may include a query window management system operable to display a query window for receiving a query text input by a user; a search result presentation system operable to display a search result window for displaying a result list of relevant documents returned by a search; a preview window management system operable to display a preview window for displaying at least part of the content of a relevant document listed in the search result window; and an activation tool operable to start a search at a search engine based on the query text, wherein the query window management system is adapted to receive a text of any length in the query window and to forward the text received in the query window to the search engine.
    Type: Application
    Filed: November 19, 2020
    Publication date: March 11, 2021
    Applicant: NEGENTROPICS Mesterséges Intelligencia Kutató és Fejlesztõ Kft
    Inventor: Béla Lóránt Kovács
  • SYSTEMS AND METHODS TO FACILITATE TEXT CONTENT SEARCH
    Publication number: 20190325070
    Abstract: A user interface system for performing searches in text-containing documents including a graphical user interface. The system may include a query window management system operable to display a query window for receiving a query text input by a user; a search result presentation system operable to display a search result window for displaying a result list of relevant documents returned by a search; a preview window management system operable to display a preview window for displaying at least part of the content of a relevant document listed in the search result window; and an activation tool operable to start a search at a search engine based on the query text, wherein the query window management system is adapted to receive a text of any length in the query window and to forward the text received in the query window to the search engine.
    Type: Application
    Filed: April 23, 2018
    Publication date: October 24, 2019
    Inventor: Béla Lóránt KOVÁCS
  • METHODS AND SYSTEM FOR SEMANTIC SEARCH IN LARGE DATABASES
    Publication number: 20190108276
    Abstract: A computer-implemented method of performing a semantic search in a source document database containing documents that are identified by a unique document identifier, including: reading a text component of a text-containing query; generating a set of query features from the text component of the query using a predefined feature extraction model; generating a set of training features based on the plurality of query features; training a trainable classifier with the training features and a set of document features obtained from at least a portion of the source documents using a predefined feature extraction model; selecting a number of source documents for classification according to a predefined selection scheme; obtaining features of the selected documents; classifying the selected source documents into different classes of relevance by using features of the selected documents, where at least one value of relevance is associated with each selected document; ranking the classified documents in an ordered list b
    Type: Application
    Filed: October 10, 2017
    Publication date: April 11, 2019
    Inventors: Béla Lóránt KOVÁCS, Ákos Jáger
  • Display screen or portion thereof with animated graphical user interface
    Patent number: D864220
    Type: Grant
    Filed: June 28, 2018
    Date of Patent: October 22, 2019
    Assignee: Negentropics Mesterséges Intelligencia Kutató´ és Fejlesztő Kft.
    Inventor: Béla Lóránt Kovács
  • Display screen or portion thereof with graphical user interface
    Patent number: D865777
    Type: Grant
    Filed: June 28, 2018
    Date of Patent: November 5, 2019
    Assignee: Negentropics Mesterséges Intelligencia Kutató  és Fejlesztõ Kft.
    Inventor: Béla Lóránt Kovács
  • Display screen or portion thereof with graphical user interface
    Patent number: D876463
    Type: Grant
    Filed: June 28, 2018
    Date of Patent: February 25, 2020
    Assignee: Negentropics Mesterséges Intelligencia Kutató és Fejlesztő Kft.
    Inventor: Béla Lóránt Kovács