US 12,293,601 B2
Classifying documents based on machine learning
Lev Sigal, Karmiel (IL); Anna Fishbein, Hadera (IL); Anton Ioffe, Netanya (IL); and Iryna Butselan, Netanya (IL)
Assigned to SAP SE, Walldorf (DE)
Filed by SAP SE, Walldorf (DE)
Filed on Aug. 26, 2022, as Appl. No. 17/897,022.
Prior Publication US 2024/0071121 A1, Feb. 29, 2024
Int. Cl. G06V 30/418 (2022.01); G06V 30/19 (2022.01); G06V 30/413 (2022.01)
CPC G06V 30/418 (2022.01) [G06V 30/19147 (2022.01); G06V 30/413 (2022.01)] 17 Claims
OG exemplary drawing
 
1. A non-transitory machine-readable medium storing a program executable by at least one processing unit of a device, the program comprising sets of instructions for an expense management system, the sets of instructions comprising:
receiving an image of a document associated with acknowledging payment for a line item in a set of line items for an expense report, the document comprising a set of text;
providing the set of text to a machine learning model configured to determine, based on the set of text, a plurality of probabilities for a plurality of defined types of documents, wherein the plurality of defined types of documents includes a credit card statement type of document, and a missing receipt affidavit type of document;
based on the plurality of probabilities for the plurality of defined types of documents, determining a type of the document from the plurality of defined types of documents; and
storing the determination of the type of the document along with the expense report.