EXTRACTING DATA FROM DOCUMENTS USING PROXIMITY OF LABELS AND DATA AND FONT ATTRIBUTES

Patent №

US 9,508,043

Granted

2016-11-29

Filed 2016

Owner

INTERNATIONAL BUSINESS MACHINES CORPORATION

AI components

1

nlp

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

15016982

A method for identifying information in a document may include analyzing the document for a text block containing a structure element, wherein said structure element is a position, font attribute, or text character; applying a rule based analysis on the text block to identify an adjacent label and field containing a value; and identifying said label and said value as a label and value pair in the document.

Natural languageG06F 16/93G06F 40/109G06F 40/131G06F 40/174G06F 40/177

AI classification

Natural language1.00
AI hardware0.32
Knowledge representation0.14
Machine learning0.01
Vision0.00
Speech0.00
Evolutionary computation0.00
Planning0.00

Ownership

INTERNATIONAL BUSINESS MACHINES CORPORATION

assignment · 376830791

Assignors

SCHLACHTER, MICHAEL JOSEPH, SINANOVIC, ELVIR

On an employer assignment, the assignors are typically the inventors.

From the same owner

© 2026 NYSGPT2525 LLC