US 12,423,761 B2
Transaction data processing systems and methods
Delia Rusu, Wellington (NZ); Hayden Jeune, Wellington (NZ); Rebecca Dridan, Wellington (NZ); Soon-Ee Cheah, Wellington (NZ); Brett Calcott, Wellington (NZ); Zhimin Wang, Wellington (NZ); Quentin-Gabriel Thurier, Wellington (NZ); Fubiao Qin, Wellington (NZ); and Niklas Patrick Pechan, Wellington (NZ)
Assigned to Xero Limited, (NZ)
Filed by Xero Limited, Wellington (NZ)
Filed on Dec. 20, 2022, as Appl. No. 18/069,223.
Application 18/069,223 is a continuation of application No. 17/749,135, filed on May 20, 2022, granted, now 11,610,271.
Application 17/749,135 is a continuation of application No. 17/693,300, filed on Mar. 11, 2022.
Application 17/693,300 is a continuation of application No. PCT/NZ2021/050151, filed on Aug. 25, 2021.
Application 17/749,135 is a continuation of application No. PCT/NZ2021/050151, filed on Aug. 25, 2021.
Claims priority of application No. 2020904805 (AU), filed on Dec. 23, 2020.
Prior Publication US 2023/0123072 A1, Apr. 20, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 40/12 (2023.01); G06F 40/279 (2020.01); G06F 40/284 (2020.01); G06F 40/30 (2020.01); G06N 20/00 (2019.01)
CPC G06Q 40/12 (2013.12) [G06F 40/279 (2020.01); G06F 40/284 (2020.01); G06F 40/30 (2020.01); G06N 20/00 (2019.01)] 17 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
determining, by an accounting system comprising memory, and one or more processors configured to execute instructions stored in memory, a candidate financial record associated with a transaction between a first accounting entity and a second accounting entity;
determining, by a numerical representation generation model of the accounting system, a numerical representation of the candidate financial record, the numerical representation generation model having been trained on a corpus generated from historical transaction records;
providing, by the numerical representation generation model and to a transaction attribute prediction model of the accounting system, the numerical representation of the candidate financial record, the transaction attribute prediction model having been trained using a dataset of previously reconciled financial records, each associated with a respective first transaction attribute, wherein the first transaction attributes are account code identifiers, and wherein the transaction attribute prediction model comprises an account code prediction model to determine an account code associated with the transaction;
providing, by the numerical representation generation model and to the transaction attribute prediction model, numerical representations of each of a plurality of accounting entity specified first transaction attributes, wherein the accounting entity specified first transaction attributes are accounting entity specified account code identifiers;
determining, by the transaction attribute prediction model, at least one first transaction attribute associated with the candidate financial record by determining the first transaction attribute associated with the candidate financial record as being one of the plurality of accounting entity specified first attributes, wherein the at least one first transaction attribute comprises an account code identifier; and
using, by the accounting system, the at least one first transaction attribute to: (i) reconcile the candidate financial record with a respective accounting record of the accounting system; or (ii) create a new accounting record in the accounting system;
wherein the account code prediction model comprises a neural network trained to:
determine a confidence score associated with the candidate financial record and each one of a plurality of account code identifiers associated with the first accounting entity; and
determine the at least one first transaction attribute as the account code identifiers having the highest confidence score.