# US 2023/0054815 A1 · Systems and methods for prioritizing alerts

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

- Number: US 2023/0054815 A1
- Document ID: US20230054815A1
- Status: Published application
- Kind: A1
- Application number: 17/404,375
- Filed: 2021-08-17
- Published: 2023-02-23
- Earliest claimed: 2021-08-17
- Assignees: Capital One Services, LLC
- Applicants: Capital One Services, LLC
- Inventors: Milind Patel; Yar Savchenko; Nikitha Kondapally; Adonis Moore; Kevin Nguyen
- Web page: https://patentgrep.com/patent/US20230054815A1

## CPC

- H04L 41/0604: using filtering, e.g. reduction of information by using priority, element types, position or time
- H04L 41/0609: {based on severity or priority}
- G06N 20/00: Machine learning
- H04L 41/0631: using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis
- H04L 41/0686: Additional information in the notification, e.g. enhancement of specific meta-data
- H04L 41/069: using logs of notifications; Post-processing of notifications
- H04L 41/16: using machine learning or artificial intelligence
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Disclosed embodiments may include another system for prioritizing alerts. The alert prioritization system may include one or more processors and that may store instructions that are configured to cause the system to perform a method for prioritizing alerts. For example, the system may receive a first alert from a first application and determine, using a machine learning model, whether the first alert is similar to a previous alert. The determination may be based on the second alert satisfying a predetermined similarity threshold. When the first alert is similar to the previous alert, the system may associate a previous rating label with the first alert, the previous rating label being associated with the previous alert and transmit the first alert with the previous rating label to one or more user devices for display.

## Claims

### Claim 1

A system for prioritizing alerts, comprising:
one or more processors; and
memory in communication with the one or more processors and storing instructions that are configured to cause the system to:
receive a first alert from a first application;
transmit a first prompt to rate the first alert to one or more user devices associated with one or more users;
receive a first rating label for the first alert;
train a machine learning model to associate the first rating label with the first alert;
receive a second alert from the first application;
determine, using the machine learning model, whether the second alert is similar to the first alert based on a predetermined similarity threshold;
based on the second alert satisfying the predetermined similarity threshold:
associate the first rating label with the second alert; and
transmit the second alert with the first rating label to the one or more user devices for display; and
based on the second alert failing to satisfy the predetermined similarity threshold:
transmit the second alert to the one or more user devices with a second prompt to rate the second alert;
receive a second rating label for the second alert;
train the machine learning model to associate the second rating label with the second alert; and
transmit the second alert with the second rating label to the one or more user devices for display.

### Claim 2 (depends on 1)

The system of claim 1, wherein the first alert and the second alert relate to incident management.

### Claim 3 (depends on 1)

The system of claim 1, wherein the instructions, when executed by the one or more processors, are further configured to:
cause, based on the second alert failing to satisfy the predetermined similarity threshold, the system to associate the second alert with a new alert label; and
transmit the second alert with the new alert label and the second prompt to the one or more user devices for display.

### Claim 4 (depends on 1)

The system of claim 1, wherein the instructions, when executed by the one or more processors, are further configured to cause the system to receive an immediate action label.

### Claim 5 (depends on 4)

The system of claim 4, wherein the instructions when executed by the one or more processors are further configured to:
cause, based on the second alert satisfying the predetermined similarity threshold, the system to associate the second alert with a first rating label and the immediate action label; and
transmit the second alert with the first rating label and the immediate action label to the one or more user devices for display.

### Claim 6 (depends on 1)

The system of claim 1, wherein the instructions, when executed by the one or more processors, are further configured to cause the system to:
determine whether the first rating label satisfies a threshold rating level; and
based on the first rating label failing to satisfy the threshold rating label:
generate a message comprising standards for alerts and the first alert; and
transmit the message to the first application.

### Claim 7 (depends on 1)

The system of claim 1, wherein the instructions, when executed by the one or more processors, are further configured to cause the system to:
receive a first note associated with the first alert; and
based on the second alert satisfying the predetermined similarity threshold, associate the first note with the second alert; and
transmit the first note to the one or more user devices for display.

### Claim 8 (depends on 1)

The system of claim 1, wherein the instructions, when executed by the one or more processors, are further configured to cause the system to:
receive, from the one or more user devices, a probation label for a second application;
receive a third alert;
determine whether the third alert is from the second application; and
based on the third alert being from the second application:
associate the probation label with the third alert; and
transmit the third alert with the probation label to the one or more user devices for display.

### Claim 9 (depends on 8)

The system of claim 8, wherein the instructions, when executed by the one or more processors, are further configured to cause the system to:
based on the third alert being from the second application:
receive a third rating label from the one or more user devices; and
train the machine learning model to associate the third rating label with the third alert.

### Claim 10 (depends on 9)

The system of claim 9, wherein the instructions, when executed by the one or more processors, are further configured to cause the system to:
based on the third alert not being from the second application:
determine, using the machine learning model, whether the third alert is similar to the first alert based on the predetermined similarity threshold; and
based on the third alert satisfying the predetermined similarity threshold:
associate the first rating label with the third alert; and
transmit the third alert with the first rating label to the one or more user devices for display;
based on the third alert not satisfying the predetermined similarity threshold:
transmit the third alert to the one or more user devices with a second prompt to rate the third alert;
receive a fourth rating label for the third alert;
train the machine learning model to associate the fourth rating label with the third alert; and
transmit the third alert with the fourth rating label to the one or more user devices for display.

### Claim 11

A system for prioritizing alerts, comprising:
one or more processors; and
memory in communication with the one or more processors and storing instructions that are configured to cause the system to:
receive a first alert from a first application;
determine, using a machine learning model, whether the first alert is similar to a previous alert based on a predetermined similarity threshold;
based on the first alert satisfying the predetermined similarity threshold:
associate a previous rating label with the first alert, the previous rating label being associated with the previous alert; and
transmit the first alert with the previous rating label to one or more user devices for display; and
based on the first alert failing to satisfy the predetermined similarity threshold:
transmit the first alert with a first prompt to rate the first alert to the one or more user devices;
receive a first rating label for the first alert;
train the machine learning model to associate the first rating label with the first alert; and
transmit the first alert with the first rating label to the one or more user devices for display.

### Claim 12 (depends on 11)

The system of claim 11, wherein the first alert relates to incident management.

### Claim 13 (depends on 11)

The system of claim 11, wherein instructions, when executed by the one or more processors, are further configured to:
cause, based on the first alert failing to satisfy the predetermined similarity threshold, the system to associate the first alert with a new alert label; and
transmit the first alert with the new alert label and the first prompt to the one or more user devices for display.

### Claim 14 (depends on 11)

The system of claim 11, wherein the instructions when executed by the one or more processors are further configured to cause the system to receive an immediate action label.

### Claim 15 (depends on 14)

The system of claim 14, wherein the instructions when executed by the one or more processors are further configured to:
cause, based on the first alert satisfying the predetermined similarity threshold, the system to associate the first alert with a first rating label and the immediate action label; and
transmit the first alert with the first rating label and the immediate action label to the one or more user devices for display.

### Claim 16 (depends on 11)

The system of claim 11, wherein the instructions when executed by the one or more processors are further configured to cause the system to:
determine whether the first rating label satisfies a threshold rating level;
based on the first rating label failing to satisfy the threshold rating label:
generate a message comprising standards for alerts and the first alert; and
transmit the message to the first application.

### Claim 17 (depends on 11)

The system of claim 11, wherein the instructions when executed by the one or more processors are further configured to cause the system to:
based on the first alert satisfying the predetermined similarity threshold, associate a previous note, associated with the previous alert, with the first alert; and
transmit the previous note to the one or more user devices for display.

### Claim 18 (depends on 11)

The system of claim 11, wherein the instructions when executed by the one or more processors are further configured to cause the system to:
receive, from the one or more user devices, a probation label for a second application;
receive a second alert;
determine whether the second alert is from the second application;
based on the second alert being from the second application:
associate the probation label with the second alert;
transmit the second alert with the probation label to the one or more user devices for display;
receive a second rating label from the one or more user devices; and
train the machine learning model to associate the second rating label with the second alert.

### Claim 19

An alert prioritization system comprising:
one or more processors; and
memory in communication with the one or more processors and storing instructions that are configured to cause the system to:
receive a first alert from a first application;
determine, using a machine learning model, whether the first alert is similar to a previous alert based on a predetermined similarity threshold; and
based on the first alert satisfying the predetermined similarity threshold;
associate a previous rating label with the first alert, the previous rating label being associated with the previous alert; and
transmit the first alert with the previous rating label to one or more user devices for display.

### Claim 20 (depends on 19)

The system of claim 19, wherein the instructions when executed by the one or more processors are further configured to cause the system to:
based on the first alert failing to satisfy the predetermined similarity threshold:
transmit the first alert to the one or more user devices with a first prompt to rate the first alert;
receive a first rating label for the first alert;
train the machine learning model to associate the first rating label with the first alert; and
transmit the first alert with the first rating label to the one or more user devices for display.
