Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Compositional pipeline for generating synthetic training data for machine learning models to extract line items from OCR text

Compositional pipeline for generating synthetic training data for machine learning models to extract line items from OCR text

US Patent 11798301 · Granted Oct 24, 2023

Estimated economic value: $68,125,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Computationally efficient artifact tagging for document management2025
Entity extraction with encoder decoder machine learning model2025
Method for serving parameter efficient NLP models through adaptive architectures2025
Methods and systems for generating mobile enabled extraction models2025
Text feature guided visual based document classifier2024
Image-based document search using machine learning2024
Model based document image enhancement2024
Methods and systems for generating mobile enabled extraction models2024
Systems and methods for training an information extraction transformer model arc2024
System and method for spatial encoding and feature generators for enhancing info2023
Image-based document search using machine learning2023
Generalizable key-value set extraction from documents using machine learning mod2023