METHOD OF TEXT GENERATION BASED ON MACHINE LEARNING Russian patent published in 2024 - IPC G06N3/02 G06F40/00 

Abstract RU 2821835 C1

FIELD: information technology.

SUBSTANCE: invention relates to a method for text generation based on machine learning. Method includes creating expounders designed to recognize the semantic content of individual text fragments of the analyzed document included in the digital content, each of which can initiate the involvement of other expounders to ensure the best accuracy, use of several separate models of neural networks, each of which is trained on its individual data set, to recognize a separate text element, combining the required set of neural models into a conveyor contained in the expander, to solve the recognition task, the expander forming several possible versions of the recognized individual text elements, wherein if the expounder does not contain a neural network for recognizing any text element, then creates a request to create a new neural network with other training data obtained from another expounder, to which, in case of its addition to the pipeline, the execution of the recognition request is delegated, the selection of the most suitable version from the recognized individual text elements, which satisfies the given criteria, formation of a new text document based on the selected recognized text elements, taking into account a given template, which sets the design style, wherein the stage of combining the required set of neural models into the pipeline is carried out by parameterizing existing expounders with new neural networks and training data sets for formation by expander of several solutions for each task of recognition of separate text elements, where solutions are required neural networks and training data sets, wherein expander in real time performing dynamic combination of new neural networks and training data sets and subsequent solutions of problems of recognition of text documents or their fragments in parallel streams in a multithreaded environment.

EFFECT: high speed of generating a target text document owing to implementation of a multithreaded parallel computing environment.

1 cl, 6 dwg, 2 tbl

Similar patents RU2821835C1

Title Year Author Number
METHOD FOR RECOGNITION OF TEXT IN IMAGES OF DOCUMENTS 2021
  • Gordeev Dmitrij Vladimirovich
  • Kondratev Kirill Andreevich
  • Ostrovskij Konstantin Igorevich
RU2768544C1
DETECTING TEXT FIELDS USING NEURAL NETWORKS 2018
  • Zuev, Konstantin Alekseevich
  • Senkevich, Oleg Evgenyevich
  • Golubev, Sergei Vladimirovich
RU2699687C1
IDENTIFICATION OF FIELDS AND TABLES IN DOCUMENTS USING NEURAL NETWORKS USING GLOBAL DOCUMENT CONTEXT 2019
  • Stanislav Semenov
RU2723293C1
METHOD AND SYSTEM FOR SEARCHING GRAPHIC IMAGES 2022
  • Shulga Sergej Aleksandrovich
RU2807639C1
DETECTING SECTIONS OF TABLES IN DOCUMENTS BY NEURAL NETWORKS USING GLOBAL DOCUMENT CONTEXT 2019
  • Stanislav Semenov
RU2721189C1
METHOD FOR GENERATING MATHEMATICAL MODELS OF A PATIENT USING ARTIFICIAL INTELLIGENCE TECHNIQUES 2017
  • Drokin Ivan Sergeevich
  • Bukhvalov Oleg Leonidovich
  • Sorokin Sergej Yurevich
RU2720363C2
IMAGE RECOGNITION SYSTEM: BEORG SMART VISION 2020
  • Zuev Georgij Alekseevich
  • Kolosov Anton Aleksandrovich
RU2777354C2
METHOD FOR CONTROLLING A DIALOGUE AND NATURAL LANGUAGE RECOGNITION SYSTEM IN A PLATFORM OF VIRTUAL ASSISTANTS 2020
  • Ashmanov Stanislav Igorevich
  • Sukhachev Pavel Sergeevich
  • Zorkij Fedor Kirillovich
RU2759090C1
MACHINE TRAINING 2005
  • Uill'Jams Dehvid R.
  • Khill Dzheffri
RU2391791C2
RECOGNITION OF EVENTS ON PHOTOGRAPHS WITH AUTOMATIC SELECTION OF ALBUMS 2020
  • Savchenko Andrey Vladimirovich
RU2742602C1

RU 2 821 835 C1

Authors

Aleksandrova Margarita Vladimirovna

Golovnin Oleg Konstantinovich

Golovnina Anastasiia Aleksandrovna

Ivashchenko Anton Vladimirovich

Krivosheev Arkadii Vladimirovich

Krupin Daniil Nikolaevich

Sitnikov Pavel Vladimirovich

Surnin Oleg Leonidovich

Dates

2024-06-26Published

2023-07-18Filed