# US 2022/0028011 A1 · Utilizing machine learning models to automatically perform actions that maintain a plan for an event

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2022/0028011 A1
- Document ID: US20220028011A1
- Status: Published application
- Kind: A1
- Application number: 17/449,865
- Filed: 2021-10-04
- Published: 2022-01-27
- Earliest claimed: 2019-02-20
- Assignees: Capital One Services, LLC
- Applicants: Capital One Services, LLC
- Inventors: Ljubica CHATMAN; Michael MOSSOBA; Abdelkadar M'Hamed BENKREIRA; Joshua EDWARDS; Tyler MAIMAN
- Web page: https://patentgrep.com/patent/US20220028011A1

## CPC

- G06Q 40/12: Accounting
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## 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.

## Claims

### Claim at position 1

1-20. (canceled)

### Claim 21

A method, comprising:
processing, by a device and with a machine learning model, plan information, identifying an item associated with a plan, and transaction information, identifying one or more transactions, to identify a first transaction, of the one or more transactions, as being related to the plan;
determining, by the device and based on the first transaction, that a threshold preference, associated with the item, is satisfied;
processing, by the device and based on determining that the threshold preference is satisfied, item information associated with the item, the plan information, and the transaction information to determine one or more recommendations for the plan; and
automatically performing, by the device and based on the one or more recommendations for the plan, one or more actions for the plan.

### Claim 22 (depends on 21)

The method of claim 21, further comprising:
receiving user input associated with at least one of the plan information or the transaction information,
wherein processing the plan information and the transaction information is based on receiving the user input associated with the at least one of the plan information or the transaction information.

### Claim 23 (depends on 21)

The method of claim 21, further comprising:
identifying, based on identifying the first transaction as being related to the plan, the first transaction as being related to the item,
wherein determining that the threshold preference is satisfied is based on identifying the first transaction as being related to the item.

### Claim 24 (depends on 21)

The method of claim 21, further comprising:
processing, with an initial machine learning model, the plan information to identify one or more initial recommendations associated with the item,
wherein processing, with the machine learning model, the plan information to identify the first transaction is based on processing, with the initial machine learning model, to identify the one or more initial recommendations associated with the item.

### Claim 25 (depends on 24)

The method of claim 24, wherein the one or more initial recommendations associated with the item includes at least one:
a recommended item that is the item,
a recommended priority of the item, or
a recommended preference of the item.

### Claim 26 (depends on 21)

The method of claim 21, wherein processing the item information, the plan information, and the transaction information to determine the one or more recommendations for the plan comprises:
comparing, based on determining that the threshold preference is satisfied and using the machine learning model, a priority, associated with the item, to a priority associated with one or more other items associated with the plan; and
determining, based on comparing the priority, associated with the item, to the priority associated with one or more other items, the one or more recommendations for the plan.

### Claim 27 (depends on 21)

The method of claim 21, wherein processing the item information, the plan information, and the transaction information to determine the one or more recommendations for the plan comprises:
comparing, based on determining that the threshold preference is satisfied and using the machine learning model, a preference, associated with the item, to a preference associated with one or more other items associated with the plan; and
determining, based on comparing the preference, associated with the item, to the preference associated with one or more other items, the one or more recommendation for the plan.

### Claim 28 (depends on 21)

The method of claim 21, wherein the one or more recommendations relate to a different item of the plan.

### Claim 29 (depends on 21)

The method of claim 21, further comprising:
providing information indicating the one or more recommendations to a user device associated with a user associated with the plan.

### Claim 30 (depends on 21)

The method of claim 21, wherein automatically performing the one or more actions includes one or more of:
increasing an amount allotted to the item;
preventing future transactions associated with the item;
requiring third-party approval of the future transactions associated with the item;
providing directions to recommended merchants providing products and/or services associated with the item;
allocating an amount from another account to the item; or
adjusting the item for a future time period.

### Claim 31

A device, comprising:
one or more memories; and
one or more processors, coupled to the one or more memories, configured to:
process, by a device and with a machine learning model, plan information, identifying an item associated with a plan, and transaction information, identifying one or more transactions, to identify a first transaction, of the one or more transactions, as being related to the plan;
identify, based on identifying the first transaction as being related to the plan, the first transaction as being related to the item,
determine, based on identifying the first transaction, that a threshold preference, associated with the item, is satisfied;
process, based on determining that the threshold preference is satisfied, item information associated with the item, the plan information, and the transaction information to determine one or more recommendations for the plan; and
automatically perform, based on the one or more recommendations for the plan, one or more actions for the plan.

### Claim 32 (depends on 35)

The device of claim 35, wherein the one or more processors are further configured to:
receive user input associated with at least one of the plan information or the transaction information,
wherein processing the plan information and the transaction information is based on receiving the user input associated with the at least one of the plan information or the transaction information.

### Claim 33 (depends on 31)

The device of claim 31, wherein the one or more processors are further configured to:
process, with an initial machine learning model, the plan information to identify one or more recommendations associated with the item,
wherein processing, with the machine learning model, the plan information to identify the first transaction is based on processing, with the initial machine learning model, to identify the one or more recommendations associated with the item.

### Claim 34 (depends on 31)

The device of claim 31, wherein the one or more processors, to process the item information, the plan information, and the transaction information to determine the one or more recommendations for the plan, are configured to:
compare, based on determining that the threshold preference is satisfied and using the machine learning model, a priority, associated with the item, to a priority associated with one or more other items associated with the plan, or
compare, based on determining that the threshold preference is satisfied and using the machine learning model, a preference, associated with the item, to a preference associated with the one or more other items, and
determine, based on comparing the priority associated with the item to the priority associated with the one or more other items or based on comparing the preference associated with the item to the preference associated with one or more other items, the one or more recommendations for the plan.

### Claim 35

A non-transitory computer-readable medium storing a set of instructions, the set of instructions comprising:
one or more instructions that, when executed by one or more processors of a device, cause the device to:
receive, by the device, user input associated with plan information, identifying an item associated with a plan, and transaction information identifying one or more transactions;
process, by the device and with a machine learning model, the plan information and the transaction information to identify a first transaction, of the one or more transactions, as being related to the plan;
determine, based on identifying the first transaction, that a threshold preference, associated with the item, is satisfied;
process, based on determining that the threshold preference is satisfied, item information associated with the item, the plan information, and the transaction information to determine one or more recommendations for the plan; and
automatically perform, based on the one or more recommendations for the plan, one or more actions for the plan.

### Claim 36 (depends on 35)

The non-transitory computer-readable medium of claim 35, wherein the one or more instructions further cause the device to:
identify, based on identifying the first transaction as being related to the plan, the first transaction as being related to the item,
wherein determining that the threshold preference is satisfied is based on identifying the first transaction as being related to the item.

### Claim 37 (depends on 35)

The non-transitory computer-readable medium of claim 35, wherein the one or more instructions further cause the device to:
process, with an initial machine learning model, the plan information to identify one or more initial recommendations associated with the item,
wherein processing, with the machine learning model, the plan information to identify the first transaction is based on processing, with the initial machine learning model, to identify the one or more initial recommendations associated with the item.

### Claim 38 (depends on 35)

The non-transitory computer-readable medium of claim 35, wherein the one or more instructions, that cause the device to process the item information, the plan information, and the transaction information, cause the device to:
compare, based on determining that the threshold preference is satisfied and using the machine learning model, a priority, associated with the item, to a priority associated with one or more other items associated with the plan, or
compare, based on determining that the threshold preference is satisfied and using the machine learning model, a preference, associated with the item, to a preference associated with the one or more other items, and
determine, based on comparing the priority associated with the item to the priority associated with the one or more other items or based on comparing the preference associated with the item to the preference associated with one or more other items, the one or more recommendations for the plan.

### Claim 39 (depends on 35)

The non-transitory computer-readable medium of claim 35, wherein the one or more recommendations associated with the item includes at least one:
a recommended item that is the item,
a recommended priority of the item, or
a recommended preference of the item.

### Claim 40 (depends on 35)

The non-transitory computer-readable medium of claim 35, wherein the one or more instructions, that cause the device to automatically perform the one or more actions, cause the device to:
allot an amount of the plan to the item from another item of the plan,
increase an amount allotted to the item,
prevent future transactions associated with the item,
require third-party approval of the future transactions associated with the item,
provide directions to recommended merchants providing products and/or services associated with the item,
allocate an amount from another account to the item, or
adjust the item for a future time period.
