Systems and methods for accounts payable-based batch processing

Patent metadata

Field	Value
Publication number	US-12106281-B1
Application number	US-202318094055-A
Country	US
Kind code	B1
Filing date	Jan 6, 2023
Priority date	Apr 14, 2021
Publication date	Oct 1, 2024
Grant date	Oct 1, 2024

Abstract

Systems and methods for receiving an enterprise resource dataset associated with the first entity, the enterprise resource dataset including an invoice data for the first entity, the invoice data including a first data entry including first value and a first maturity date and a second data entry including a second value and second maturity date, determining a predicted future account balance, determining based on the predicted future account balance, the first value, the second value, the first maturity date, the second maturity date, one or more financing options including a first finance option associated with the first data entry included in the invoice data, generating, a user interface display configured to be displayed within the enterprise application, the user interface display including the first finance option a selection of the first finance option, and initiating a first transfer to a second entity associated with the first data entry.

First claim

What is claimed:

1. A computer system comprising:
an application programming interface (API) gateway managing a API calls and responses between a plurality of APIs of the computer system and one or more external sources; and
a processing circuit comprising one or more processors communicably coupled to memory, the memory configured to store instructions that, when executed by the one or more processors, cause the one or more processors to:
train, during a training phase, a machine-learning model to output scores corresponding to financing recommendations regarding invoice data, the machine-learning model trained using a training set including a plurality of data entries for invoices from a first data source and account data for a plurality of accounts from a second data source;
deploy the machine-learning model responsive to outputs from the machine-learning model satisfying one or more criteria during the training phase;
receive, via the API gateway, a first API call for a first API managed by the API gateway, the first API call including information corresponding to authentication of an enterprise application executing on a second server, the enterprise application being authenticated for accessing information via the API gateway based on the information corresponding to the authentication, the enterprise application linked to a common account holder of an account of the second data source, the enterprise application corresponding to the first data source;
establish, responsive to receiving the first API call and authentication of the information, a connection between the computer system and the enterprise application;
receive, from the enterprise application of the first data source, an enterprise resource dataset associated with the common account holder, the enterprise resource dataset including invoice data for the common account holder, the invoice data including a first data entry including first value and a first maturity date and a second data entry including a second value and second maturity date;
receive, from the second data source managed by the computer system, accounting data corresponding to the common account holder;
determine a predicted future account balance at a first date based on a current account balance associated with the first entity from the accounting data, and the first value, the second value, the first maturity date, and the second maturity date included in the invoice data;
determine, by applying the predicted future account balance, the first value, the second value, the first maturity date, the second maturity date as an input to the machine-learning model, one or more financing options including a first finance option associated with the first data entry included in the invoice data, based on a score corresponding to the one or more financing options output by the machine-learning model;
generate a user interface display configured to be displayed within the enterprise application, the user interface display including the first finance option;
receive, via the API gateway, from the enterprise application, a second API call to a second API managed by the API gateway, the second API call indicating a selection of the first finance option;
in response to receiving the selection of the first finance option, initiating a first transfer to a second entity associated with the first data entry, the first transfer being initiated on the first maturity date and corresponding with the first value; and
receive, via the API gateway, from the enterprise application, a third API call to a third API managed by the API gateway, the third API call indicating a second transfer from a first entity account associated with the first entity on a second date subsequent to the first date.

2. The computer system of claim 1 , wherein the instructions further cause the one or more processors to:
receive, via the API gateway, from the enterprise application associated with the common account holder, a fourth API call to the third API, the fourth API call indicating a request for a third value to be transferred to a second entity account associated with the second entity at a third date prior to the first maturity date and the second maturity date; and
determine a value reduction based on the request for the third value, wherein the third value is determined based on the first value and the value reduction.

3. The computer system of claim 2 , wherein the value reduction is determined based on the predicted future account balance, at least one of the first value or the second value, and at least one of the first maturity date or the second maturity date.

4. The computer system of claim 3 , wherein the instructions further cause the one or more processors to provide a notification to a second enterprise application associated with the second entity in response to receiving the selection of the first finance option, the second entity being associated with the first data entry.

5. The computer system of claim 4 , wherein the notification indicates payment to the second entity at the third date.

6. The computer system of claim 1 , wherein the first transfer is equal to the first value.

7. The computer system of claim 1 , wherein the second transfer is greater than the first transfer.

8. The computer system of claim 1 , wherein the first maturity date is different from the second maturity date.

9. A computer implemented method, comprising:
training, by a computer system, during a training phase, a machine-learning model to output scores corresponding to financing recommendations regarding invoice data, the machine-learning model trained using a training set including a plurality of data entries for invoices from a first data source and account data for a plurality of accounts from a second data source;
deploying, by the computer system, the machine-learning model responsive to outputs from the machine-learning model satisfying one or more criteria during the training phase;
receiving, by an application programming interface (API) gateway of the computer system, a first API call for a first API managed by the API gateway, the first API call including information corresponding to authentication of an enterprise application, the enterprise application being authenticated for accessing information via the API gateway of the computer system based on the information, the computer system corresponding to the second data source and the enterprise application corresponding to the first data source;
establishing, responsive to receiving the first API call and authentication of the information, a connection between the computer system and the enterprise application;
receiving, by the computer system, from the enterprise application of the first data source associated with a first entity, an enterprise resource dataset associated with the first entity, the enterprise resource dataset including invoice data for the first entity, the invoice data including a first data entry including first value and a first maturity date and a second data entry including a second value and second maturity date;
receiving, by the computer system from the second data source, accounting data corresponding to the first entity;
determining, by the computer system, a predicted future account balance at a first date based on a current account balance associated with the first entity from the accounting data, and the first value, the second value, the first maturity date, and the second maturity date included in the invoice data;
determining, by the computer system, by applying the predicted future account balance, the first value, the second value, the first maturity date, the second maturity date as an input to the machine-learning model, one or more fina

Assignees

• Wells Fargo Bank Na

Inventors

• Kurani Ashish B
• Noe James C
• Haider Imran
• Fehrenbach Frank
• Ragothaman Guruprasadh
• Strader Matthew C
• Munuswamy Palani
• Subramanian Chandra
• Atala George
• Morris Mattie L
• More Braden
• Worth Loftlon
• Coles Nathan B

Classifications

• G06N20/00

  Machine learning · CPC title

• G06Q20/102 Primary

  Bill distribution or payments · CPC title

• G06Q20/227 Primary

  characterised in that multiple accounts are available, e.g. to the payer · CPC title

• G06Q40/06

  Asset management; Financial planning or analysis · CPC title

• G06Q40/02

  Banking, e.g. interest calculation or account maintenance (credit or loans G06Q40/03) · CPC title