Utilizing machine learning models to automatically perform actions that maintain a plan for an event

Patent metadata

Field	Value
Publication number	US-11138674-B2
Application number	US-201916523087-A
Country	US
Kind code	B2
Filing date	Jul 26, 2019
Priority date	Feb 20, 2019
Publication date	Oct 5, 2021
Grant date	Oct 5, 2021

Abstract

A device receives, from a user device, plan information that identifies a plan for an event and includes information identifying an account associated with the plan, plan items of the plan, and priorities and preferences associated with the plan items, where the user device is associated with a user of the account and the plan. The device receives transaction information identifying transactions associated with the account, and processes the plan information and the transaction information, with a first model, to identify transactions related to the plan. The device processes information associated with the particular plan item, the plan information, and the transaction information, with a second model, to determine recommendations for the plan, where the information associated with the particular plan item includes information identifying a priority and a preference associated with the particular plan item. The device provides information indicating the recommendations to the user device.

First claim

What is claimed is:

1. A method, comprising:
receiving, by a device, plan information identifying a plan for an event and a plan item of the plan;
receiving, by the device, transaction information identifying transactions,
the transactions including an expenditure related to a purchase;

processing, by the device, the plan information and the transaction information to identify one or more transactions, of the transactions, related to the plan;
determining, by the device, that a threshold preference for the plan item of the plan is satisfied based on a first transaction of the one or more transactions related to the plan,
wherein the threshold preference is associated with a budget associated with the plan item;

processing, by the device and based on determining that the threshold preference is satisfied, information associated with the plan item, the plan information, and the transaction information, with a machine learning model, to determine one or more recommendations for the plan; and
automatically performing, by the device, one or more actions based on the one or more recommendations for the plan.

2. The method of claim 1 , wherein the threshold preference is satisfied when the first transaction exceeds the budget associated with the plan item.

3. The method of claim 1 , wherein the threshold preference is set to less than the budget associated with the plan item.

4. The method of claim 1 , wherein automatically performing the one or more actions includes one or more of:
allotting an amount of the plan to the plan item from another plan item of the plan;
increasing an amount allotted to the plan item;
preventing future transactions associated with the plan item;
requiring third-party approval of the future transactions associated with the plan item;
providing directions to recommended merchants providing products and/or services associated with the plan item;
allocating an amount from another account to the plan item; or
adjusting the plan item for a future time period.

5. The method of claim 1 , further comprising:
providing information indicating the one or more recommendations to a user device associated with a user of the plan.

6. The method of claim 1 , wherein:
the machine learning model includes one or more of:
a Markov model,
a Bayesian model, or
a Bayesian-Markov decision model.

7. The method of claim 1 , wherein the transactions are related to the event, and wherein the transaction information includes information associated with additional transactions not related to the event.

8. The method of claim 1 , wherein the information associated with the plan item includes information identifying:
a priority associated with the plan item, and
a preference associated with the plan item.

9. A device, comprising:
a memory; and
one or more processors to:
receive plan information identifying a plan for an event, event and a plan item of the plan,
receive transaction information identifying transactions,
the transactions including an expenditure related to a purchase;

process the plan information and the transaction information to identify one or more transactions, of the transactions, related to the plan;
determine that a threshold preference for the plan item of the plan is satisfied based on a first transaction of the one or more transactions related to the plan;
wherein the threshold preference is associated with a budget associated with the plan item;

process, based on determining that the threshold preference is satisfied, information associated with the plan item, the plan information, and the transaction information, with a machine learning model, to determine one or more recommendations for the plan; and
automatically perform one or more actions based on the one or more recommendations for the plan.

10. The device of claim 9 , wherein the threshold preference is satisfied when the first transaction exceeds the budget associated with the plan item.

11. The device of claim 9 , wherein the threshold preference is set to less than the budget associated with the plan item.

12. The device of claim 9 , wherein the one or more actions include one or more of:
allot an amount of the plan to the plan item from another plan item of the plan;
increase an amount allotted to the plan item;
prevent future transactions associated with the plan item;
require third-party approval of the future transactions associated with the plan item;
provide directions to recommended merchants providing products and/or services associated with the plan item;
allocate an amount from another account to the plan item; or
adjust the plan item for a future time period.

13. The device of claim 9 , wherein the one or more processors are further to:
provide information indicating the one or more recommendations to a user device associated with a user of the plan.

14. The device of claim 9 , wherein:
the machine learning model includes one or more of:
a Markov model,
a Bayesian model, or
a Bayesian-Markov decision model.

15. The device of claim 9 , wherein the transactions are related to the event, and wherein the transaction information includes information associated with additional transactions not related to the event.

16. The device of claim 9 , wherein the information associated with the plan item includes information identifying:
a priority associated with the plan item, and
a preference associated with the plan item.

17. A non-transitory computer-readable medium storing instructions, the instructions comprising:
one or more instructions that, when executed by one or more processors, cause the one or more processors to:
receive plan information identifying a plan for an event and a plan item of the plan,
receive transaction information identifying transactions,
the transactions including an expenditure related to a purchase;

process the plan information and the transaction information to identify one or more transactions, of the transactions, related to the plan;
determine that a threshold preference for the plan item of the plan is satisfied based on a first transaction of the one or more transactions related to the plan;
wherein the threshold preference is associated with a budget associated with the plan item;

process, based on determining that the threshold preference is satisfied, information associated with the plan item, the plan information, and the transaction information, with a machine learning model, to determine one or more recommendations for the plan; and
automatically perform one or more actions based on the one or more recommendations for the plan.

18. The non-transitory computer-readable medium of claim 17 , wherein the threshold preference is satisfied when the first transaction exceeds the budget associated with the plan item.

19. The non-transitory computer-readable medium of claim 17 , wherein the threshold preference is set to less than the budget associated with the plan item.

20. The non-transitory computer-readable medium of claim 17 , wherein the one or more actions include one or more of:
allot an amount of the plan to the plan item from another plan item of the plan;
increase an amount allotted to the plan item;
prevent future transactions associated with the plan item;
require third-party approval of the future transactions associated with the plan item;
provide directions to recommended merchants providing products and/or services associated with the plan item;
allocate an amount from another accou

Assignees

• Capital One Services Llc

Inventors

• Chatman Ljubica
• Mossoba Michael
• Benkreira Abdelkadar M'Hamed
• Edwards Joshua
• Maiman Tyler

Classifications

• G06Q40/12 Primary

  Accounting · CPC title