US 12,266,218 B2
Method and system for extracting information from a document
Vrajesh Ricky Amin, Livingston, NJ (US); Ashish Singla, Harrison, NJ (US); Samantha Zucker, Hoboken, NJ (US); Dana Marie Niblack, Shoreline, WA (US); Stephen Musacchia, Glen Cove, NY (US); Lawrence Fata, Brick, NJ (US); Albert Naclerio, Bedford, NY (US); Hozefa Shabbir Zariwala, Ridgewood, NJ (US); Anirudh Hegde, Bangalore (IN); Yasser Thamby, Carrollton, TX (US); and Saquib Ahmad, Bengaluru (IN)
Assigned to JPMORGAN CHASE BANK, N.A., New York, NY (US)
Filed by JPMorgan Chase Bank, N.A., New York, NY (US)
Filed on Aug. 31, 2021, as Appl. No. 17/446,522.
Claims priority of application No. 202111027338 (IN), filed on Jun. 18, 2021.
Prior Publication US 2022/0405499 A1, Dec. 22, 2022
Int. Cl. G06V 40/30 (2022.01); G06N 20/00 (2019.01); G06V 30/414 (2022.01); H04N 1/00 (2006.01)
CPC G06V 40/394 (2022.01) [G06N 20/00 (2019.01); G06V 30/414 (2022.01); H04N 1/00331 (2013.01); H04N 1/00334 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A method for extracting information from a document, the method with a memory storing instructions being implemented by at least one processor, the method comprising:
receiving, by the at least one processor, a first document;
extracting, by the at least one processor, first data from the first document;
assigning, by the at least one processor, the first document to a first category from among a predetermined plurality of categories based on a result of the extracting the first data from the first document;
generating, by the at least one processor, a first structured output by formatting the extracted first data based on the first category;
performing a signature matching function with respect to the first document by comparing the first structured output with a second document that includes a signature of a predetermined person; and
determining, based on a result of the performing of the signature matching function, a discrepancy between the first structured output and the signature of the predetermined person,
wherein the first data includes an indication of a resolution of the document based on an amount of dots per inch of the document, and wherein the first data includes at least one of whether at least a portion of the document is handwritten, whether at least a portion of the document is typed, whether initials are detected on the document, a type of character set of the document, a language present in the document, whether the document is in a digital format, whether the document is scanned by a scanner, and whether the document includes at least one table.