Patent №
US 11,763,087
Granted
2023-09-19
Filed 2022
Owner
APPLICA SP. Z O.O.
Lab
—
AI components
6
ml · nlp · vision · speech · kr · hardware
Assignment
Recorded
Dataset
AIPD
2023_r1 edition
Application
17651311
Disclosed herein is a system and method for Natural Language Processing (NLP) of real world documents. The system and method combine various models not previously combined and overcome the challenges of this combination. Models include an encoder-decoder model, a spatial model, and a multi-modal model.
Machine learningNatural languageVisionSpeechKnowledge representationAI hardwareG06F 40/295G06V 10/454G06F 18/24133G06F 40/106G06F 40/30G06N 3/0455G06N 3/0464G06N 3/08+5 more
AI classification
Natural language1.00
Speech1.00
Machine learning1.00
Vision1.00
Knowledge representation1.00
AI hardware1.00
Evolutionary computation0.00
Planning0.00
Ownership
APPLICA SP. Z O.O.
assignment · 591420680
Assignors
BORCHMANN, LUKASZ KONRAD, JURKIEWICZ, DAWID ANDRZEJ, DWOJAK, TOMASZ, PIETRUSZKA, MICHAL WALDEMAR, PALKA, GABRIELA KLAUDIA
On an employer assignment, the assignors are typically the inventors.
From the same owner
NATURAL LANGUAGE PROCESSING TEXT-IMAGE-LAYOUT TRANSFORMERUS 12,346,658 · 2025ITERATIVE TRAINING FOR MULTI-MODAL DATA IN NATURAL LANGUAGE PROCESSINGUS 12,169,692 · 2024ITERATIVE TRAINING FOR TEXT-IMAGE-LAYOUT DATA IN NATURAL LANGUAGE PROCESSINGUS 11,934,786 · 2024ITERATIVE TRAINING FOR TEXT-IMAGE-LAYOUT TRANSFORMERUS 11,620,451 · 2023ITERATIVE TRAINING FOR TEXT-IMAGE-LAYOUT TRANSFORMERUS 11,455,468 · 2022