Utilizing a machine learning model to perform actions based on selection of a single selection abort transaction mechanism

Patent metadata

Field	Value
Publication number	US-11775980-B2
Application number	US-202016842959-A
Country	US
Kind code	B2
Filing date	Apr 8, 2020
Priority date	May 29, 2019
Publication date	Oct 3, 2023
Grant date	Oct 3, 2023

Abstract

A device receives, from a transaction device, transaction data associated with a transaction of a user logged into the transaction device, and receives information indicating a selection of an abort transaction mechanism to cause the transaction to be canceled concurrently with the user being logged out of the transaction device. The device provides, to a user device associated with the user, a notification indicating that the transaction was canceled and that the user was logged out, and determines whether a response, indicating that the notification was received by the user and indicating a reason for utilizing the abort transaction mechanism, is received from the user device within a threshold period of time. The device provides an alert message to an emergency point of contact for the user when it is determined that the response is not received from the user device within the threshold period of time.

First claim

What is claimed is:

1. A method, comprising:
receiving, by a device and from a transaction device, transaction data associated with a transaction of a user logged into the transaction device,
the transaction data including information indicating a selection of an abort transaction mechanism that, when selected a single time, causes the transaction to be canceled and the user to be logged out of the transaction device;

receiving, by the device, the information indicating the selection of the abort transaction mechanism from the transaction device to cause the transaction to be canceled concurrently with the user being logged out of the transaction device;
transmitting, by the device, to a user device associated with the user, and based on receiving the information indicating the selection of the abort transaction mechanism, a request for response data from the user device;
determining, by the device, whether the response data is received from the user device within a threshold period of time,
the response data including information identifying a reason for utilizing the abort transaction mechanism, and
wherein determining whether the response data is received from the user device within the threshold period of time comprises:
determining whether any response data is received within the threshold period of time based on starting a timer associated with the threshold period of time;

training, by the device, a machine learning model based on historical data indicating that historical users aborted transactions associated with safety reasons;
processing, by the device and upon determining whether the response data is received from the user device within the threshold period of time, the information identifying the reason for utilizing the abort transaction mechanism, with the machine learning model, to determine one or more actions to perform; and
performing, by the device, the one or more actions.

2. The method of claim 1 , wherein performing the one or more actions comprises:
transmitting an alert message to an emergency point of contact for the user and/or to an emergency service when it is determined that the response data is not received from the user device within the threshold period of time.

3. The method of claim 1 , wherein the machine learning model includes a pattern recognition model that generates predictions for the one or more actions to perform based on the information identifying the reason for utilizing the abort transaction mechanism.

4. The method of claim 1 , further comprising:
training the machine learning model with historical abort transaction data.

5. The method of claim 1 , further comprising:
receiving camera data from a camera associated with a location of the transaction device; and
predicting the reason for utilizing the abort transaction mechanism based on the camera data.

6. A device, comprising:
one or more memories; and
one or more processors communicatively coupled to the one or more memories, configured to:
receive, from a transaction device, transaction data associated with a transaction of a user logged into the transaction device,
the transaction data including information indicating a selection of an abort transaction mechanism that, when selected a single time, causes the transaction to be canceled and the user to be logged out of the transaction device;

receive the information indicating the selection of the abort transaction mechanism from the transaction device to cause the transaction to be canceled concurrently with the user being logged out of the transaction device;
transmit to a user device associated with the user, and based on receiving the information indicating the selection of the abort transaction mechanism, a request for response data from the user device;
determine whether the response data is received from the user device within a threshold period of time,
the response data including information identifying a reason for utilizing the abort transaction mechanism, and
wherein the one or more processors, to determine whether the response data is received from the user device within the threshold period of time, are configured to:
determine whether any response data is received within the threshold period of time based on starting a timer associated with the threshold period of time;

train a model based on historical data indicating that historical users aborted transactions associated with safety reasons; and
selectively provide, based on using the model, an alert message to an emergency point of contact for the user and/or to an emergency service based on whether the response data is received from the user device within the threshold period of time,
wherein the alert message is to be provided when the response data is not received from the user device within the threshold period of time, or
wherein the alert message is not to be provided when the response data is received from the user device within the threshold period of time or when camera data indicates that the user is safe.

7. The device of claim 6 , wherein the one or more processors are further to:
process information identifying the reason for utilizing the abort transaction mechanism and information identifying reasons for utilizing the abort transaction mechanism by other users of the transaction device, with a machine learning model, to determine one or more actions to perform; and
perform the one or more actions.

8. The device of claim 7 , wherein the machine learning model includes a pattern recognition model that generates predictions for the one or more actions to perform based on the information identifying the reason for utilizing the abort transaction mechanism.

9. The device of claim 7 , wherein the one or more processors, when performing the one or more actions, are to one or more of:
send a request to a security guard to move to a location of the transaction device.

10. The device of claim 6 , wherein information identifying the reason for utilizing the abort transaction mechanism includes one of:
information indicating that the user aborted the transaction because the user felt unsafe, or
information indicating that the user aborted the transaction because the user was in a hurry.

11. The device of claim 6 , wherein the abort transaction mechanism is displayed as a button or a key on a keypad.

12. The device of claim 6 , wherein the one or more processors are further configured to:
receive camera data from a camera associated with a location of the transaction device; and
predict the reason for utilizing the abort transaction mechanism based on the camera data.

13. 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, from a transaction device, transaction data associated with a transaction of a user logged into the transaction device,
the transaction data including information indicating a selection of an abort transaction mechanism that, when selected, enables the user to cancel the transaction and log out of the transaction device at a same time;

receive the information indicating the selection of the abort transaction mechanism from the transaction device to cause the transaction to be canceled concurrently with the user being logged out of the transaction device;
provide, to a user device associated with the user and based on receiving the information indicating the selection of the abort transaction mechanism, a notification indicating that the transaction was canceled and that the user was logged out of the

Assignees

• Capital One Services Llc

Inventors

• Benkreira Abdelkadar M'Hamed
• Edwards Joshua
• Miracolo Max

Classifications

• G06N3/09

  Supervised learning · CPC title

• G06N3/0499

  Feedforward networks · CPC title

• G06Q20/407 Primary

  Cancellation of a transaction · CPC title

• G06N20/00

  Machine learning · CPC title

• G06Q20/4016

  involving fraud or risk level assessment in transaction processing · CPC title