	US 12,743,902 B2
	Multi-modal document type classification systems and methods
Ozan Eren Bilgen, New York, NY (US); Alperen Sahin, Istanbul (TR); Mustafa Batuhan Ceylan, Balikesir (TR); Begum Yalcin, Amsterdam (NL); Can Korkut, Ankara (TR); Hasan Huseyin Kacmaz, Munich (DE); Ihsan Soydemir, Munich (DE); Bryan Contreras Herrera, New York, NY (US); Mizane Johnson-Bowman, Voorhees Township, NJ (US); and Gulsah Dengiz, Bursa (TR)
Assigned to Base64.ai, Inc., New York, NY (US)
Filed by Base64.ai, Inc., New York, NY (US)
Filed on Apr. 26, 2023, as Appl. No. 18/307,682.
Prior Publication US 2024/0362944 A1, Oct. 31, 2024
Int. Cl. G06V 30/413 (2022.01); G06V 30/18 (2022.01); G06V 30/19 (2022.01); G06V 30/42 (2022.01)

CPC G06V 30/413 (2022.01) [G06V 30/18 (2022.01); G06V 30/19147 (2022.01); G06V 30/42 (2022.01)]

20 Claims

1. A method of using an artificial intelligence (AI) system to classify documents, the method comprising the steps of:

receiving, at a platform server running the AI system, a file comprising a document;

conducting optical character recognition (OCR) on the document to extract text content of the document;

identifying a document candidate based on the text content, wherein the document candidate has an expected document shape;

detecting a shape of the document in the file;

classifying the document at least in part by determining whether the shape of the document matches the expected document shape; and

upon determining that the shape of the document matches the expected shape, verifying that the document candidate is correctly classified.