Granted Patent B2

US 12,423,761 · App. 18/069,223 · Granted Sep 23, 2025

Inventors: 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); Niklas Patrick Pechan (Wellington, NZ)

Assignee: Xero Limited

G06Q40/12G06F40/279G06F40/284G06F40/30G06N20/00

Abstract

Claims (56)

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.

2. The computer-implemented method of claim 1 , further comprising:

determining, using the numerical representation generation model, a numerical representation of the accounting entity specified first attributes, the numerical representation generation model having been trained on the corpus generated from historical transaction records.

3. The computer-implemented method of claim 1 , wherein the accounting entity specified first attributes comprises accounting system predefined first attributes.

4. The computer-implemented method of claim 1 , further comprising:

sending, to a computing device, the determined at least one first transaction attribute for presentation on a user interface of a reconciliation application.

5. The computer-implemented method of claim 4 , further comprising:

receiving, from the computing device, approval of an approved first transaction attribute of the determined at least one first transaction attributes; and

generating a reconciliation record associated with the transaction, the reconciliation record comprising the candidate financial record and the approved first transaction attribute.

6. The computer-implemented method of claim 1 , further comprising:

determining a confidence score associated with each of the determined at least one first transaction attribute; and

generating a reconciliation record associated with the transaction, the reconciliation record comprising the candidate financial record and the determined at least first transaction attributes having associated confidence scores than meet the confidence threshold.

7. The computer-implemented method of claim 1 , wherein determining the numerical representation of the candidate financial record comprises determining an average of the numerical representations of each token of a set of tokens.

8. The computer-implemented method of claim 1 , wherein the corpus for training the numerical representation generation model was generated using a combination of historical financial records and entity information associated with the respective historical financial records, and wherein the method further comprises:

determining the accounting entity associated with the candidate financial record; and

determining one or more entity attributes from an accounting entity record associated with the first accounting entity;

wherein generating a set of tokens further comprises tokenizing each of the one or more entity attributes.

9. The computer-implemented method of claim 8 , wherein the one or more entity attributes comprise any one or more of: entity type; entity industry; and entity country.

10. The computer-implemented method of claim 1 , wherein determining the numerical representation of accounting entity specified first attribute comprises determining an average of the numerical representations of each token of the set of tokens.

11. The computer-implemented method of claim 1 , wherein the candidate financial record comprises financial data including any one or more of: payee data;

transaction reference; and transaction notes.

12. The computer-implemented method of claim 1 , wherein the at least one first transaction attribute comprises an identifier of the second entity.

13. The computer-implemented method of claim 1 , wherein the neural network comprises a feedforward neural network.

14. The computer-implemented method of claim 1 , wherein the at least one first transaction attribute is an identifier of the second entity and the transaction attribute prediction model comprises an entity prediction model to predict the second entity associated with the transaction.

15. The computer-implemented method of claim 1 , wherein the plurality of accounting entity specified first attributes comprises accounting entity defined first attributes.

16. An accounting system comprising:

one or more processors; and

memory comprising computer executable instructions, which when executed by the one or more processors, cause the system to:

determine a candidate financial record associated with a transaction between a first accounting entity and a second entity;

determine, using a numerical representation generation model, a numerical representation of the candidate financial record, the numerical representation generation model having been trained on a corpus generated from historical transaction records;

provide, to a transaction attribute prediction model, 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;

provide, to the transaction attribute prediction model, numerical representations of each of a plurality of accounting entity specified first attributes, wherein the accounting entity specified first transaction attributes are accounting entity specified account code identifiers;

determine, 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

use, 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 account 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.

17. A computer-readable storage medium storing instructions that, when executed by a computer, cause the computer to perform operations including:

determining a candidate financial record associated with a transaction between a first accounting entity and a second entity;

determining, using a numerical representation generation model, 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, to a transaction attribute prediction model, 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, to the transaction attribute prediction model, numerical representations of each of a plurality of accounting entity specified first 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, 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 account 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.

Assignments (1)

Priority Claims (1)

Continuity (5)

References Cited (89)