US 11,861,692 B2
Automated hybrid pipeline for customer identification
Auguste Byiringiro, Singapore (SG); Jiatai Qiang, Singapore (SG); Atreya Biswas, Singapore (SG); and Sean Saito, Singapore (SG)
Assigned to SAP SE, Walldorf (DE)
Filed by SAP SE, Walldorf (DE)
Filed on Jun. 4, 2019, as Appl. No. 16/430,674.
Prior Publication US 2020/0387963 A1, Dec. 10, 2020
Int. Cl. G06Q 40/02 (2023.01); G06N 3/08 (2023.01); G06Q 40/12 (2023.01); G06N 3/045 (2023.01); G06F 16/22 (2019.01)
CPC G06Q 40/02 (2013.01) [G06N 3/045 (2023.01); G06N 3/08 (2013.01); G06Q 40/12 (2013.12); G06F 16/2282 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for determining customer identifiers (IDs) from bank statements provided as computer-readable electronic documents, the method being executed by one or more processors and comprising:
receiving a first bank statement at a hybrid pipeline comprising a set of lookup tables and a deep learning (DL) model that can each be used to determine customer IDs from bank statements;
providing a first key based on data associated with the first bank statement, the first key comprising a hash value determined for a concatenation of the data; and
determining that the first key is included in a first lookup table of the set of lookup tables, and in response:
identifying a first set of customer IDs from the first lookup table, the customer lookup table mapping hash values to customer IDs, the first set of customer IDs comprising one or more customer IDs, and
outputting the first set of customer IDs to computer-executable software that matches the first bank statement to one or more electronic documents at least partially based on the first set of customer IDs.