Systems and methods for detecting human presence near a transaction kiosk

Patent metadata

Field	Value
Publication number	US-12548414-B2
Application number	US-202418956603-A
Country	US
Kind code	B2
Filing date	Nov 22, 2024
Priority date	Jul 20, 2021
Publication date	Feb 10, 2026
Grant date	Feb 10, 2026

Abstract

Disclosed embodiments may include a system that may receive first level authentication data from a first user, identify a first user device associated with the first user, and determine whether a current location of the first user device is within a predetermined proximity of a first computing device. In response to the determination, the system may detect one or more objects within the predetermined proximity of the first computing device using the one or more positional sensors. The system may determine that at least one of the one or more objects is associated with a human, and in response, trigger a security measure. The system may transmit an indication of the triggered security measure to the first computing device, and may transmit instructions to the first user device configured to cause the first user device to provide an alert to the first user.

First claim

What is claimed is:

1 . A system comprising:
one or more processors; one or more positional sensors configured to communicate with the one or more processors; a memory in communication with the one or more processors and storing instructions that, when executed by the one or more processors, are configured to cause the system to:
during a first user session, confirming a presence of a first user within a proximity of a first computing device by:
determining whether a current location of a first user device associated with the first user is within the proximity of the first computing device; or
determining, using the one or more positional sensors, whether the current location of the first user is within the proximity of the first computing device;

responsive to confirming the presence of the first user within the proximity of the first computing device:
monitor within the proximity of the first computing device using the one or more positional sensors; and
responsive to detecting at least one or more objects associated with a human within the proximity of the first computing device with the one or more positional sensors, trigger a security measure comprising:
cause a display of the first computing device to at least temporarily change; and
transmit an indication of the triggered security measure to the first user device, causing the first user device to provide an alert to the first user.

2 . The system of claim 1 , wherein determining, using the one or more positional sensors, whether the current location of the first user device is within the proximity of the first computing device further comprises:
determining a first positional fingerprint associated with the first user; comparing the first positional fingerprint to a stored fingerprint associated with the first user; and matching the first positional fingerprint to the stored fingerprint beyond a first predetermined threshold.

3 . The system of claim 2 , wherein the first positional fingerprint and the stored fingerprint each comprise a data type selected from LIDAR fingerprint data, ultrasound fingerprint data, capacitive fingerprint data, resistive fingerprint data, radio-frequency (RF) fingerprint data, facial recognition fingerprint data, or combinations thereof.

4 . The system of claim 1 , wherein the memory includes instructions that, when executed by the one or more processors are configured to cause the system to:
responsive to determining that the current location of the first user device is not within the proximity of the first computing device, access stored activity data associated with the first user; determine whether current first user activity associated with the first user device matches stored activity data associated with the first user; and responsive to the current first user activity matching the stored activity data beyond a second predetermined threshold, confirm the current location of the first user device is within the proximity of the first computing device.

5 . The system of claim 1 , wherein:
detecting at least the one or more objects associated with the human further comprises, for each of the one or more objects:
determining a second positional fingerprint;
comparing the second positional fingerprint to a stored second fingerprint associated with a presence of the human, and
determining that a second object is associated with the presence of the human based on the second positional fingerprint matching the stored second fingerprint beyond a third predetermined threshold.

6 . The system of claim 5 , further comprising a trained machine learning model configured to determine the presence of the human based on comparing one or more second positional fingerprints to the stored second fingerprint.

7 . The system of claim 1 , wherein causing the display of the first computing device to at least temporarily change comprises one or more actions selected from (i) causing a display associated with the first computing device to flash, (ii) causing the display to temporarily display an empty screen, or (iii) causing the display to identify a position associated with a presence of the human within the proximity of the first computing device.

8 . The system of claim 1 , wherein the alert provided by the first user device is an audible or vibrational alert.

9 . The system of claim 1 , wherein the memory includes instructions that, when executed by the one or more processors are configured to cause the system to:
responsive to not confirming the presence of the first user within the proximity of the first computing device, terminate the first user session.

10 . A system comprising:
one or more processors; a memory in communication with the one or more processors and storing instructions that, when executed by the one or more processors, are configured to cause the system to:
during a first user session, confirm a presence of a first user within a predefined area proximate a first computing device by:
determining whether a current location of a first user device associated with the first user is within the proximity of the first computing device; or
comparing a first positional fingerprint to a stored fingerprint associated with the first user device;

responsive to confirming the presence of the first user within the predefined area proximate the first computing device:
monitor the predefined area proximate the first computing device; and
responsive to detecting at least one or more objects associated with a human within the proximity of the first computing device with the one or more positional sensors, trigger a security measure comprising:
cause a display of the first computing device to at least temporarily change; and
transmit an indication of the triggered security measure to the first user device, causing the first user device to provide an alert to the first user.

11 . The system of claim 10 , wherein the first positional fingerprint and the stored fingerprint each comprise a data type selected from LIDAR fingerprint data, ultrasound fingerprint data, capacitive fingerprint data, resistive fingerprint data, radio-frequency (RF) fingerprint data, facial recognition fingerprint data, or combinations thereof.

12 . The system of claim 10 , wherein the memory includes instructions that, when executed by the one or more processors are configured to cause the system to:
responsive to not determining that the current location of the first user device is within the predefined area proximate the first computing device, access stored activity data associated with the first user; determine whether current first user activity associated with the first user device matches stored activity data associated with the first user; and responsive to the current first user activity matching the stored activity data beyond a second predetermined threshold, confirm that the current location of the first user device is within the predefined area.

13 . The system of claim 10 , wherein detecting the one or more objects associated with the human further comprises, for each of the one or more objects:
determining a second positional fingerprint; comparing the second positional fingerprint to a stored second fingerprint associated with a presence of the human; and determining that a second object is associated with the presence of the human based on the second positional fingerprint matching the stored second fingerprint beyond a third predetermined threshold.

14 . The system of claim 13 , further comprising a trained machine learning model configured to determine the presence of the human based on c

Assignees

• Capital One Services Llc

Inventors

• Wurmfeld David Kelly

Classifications

• G06F21/32

  using biometric data, e.g. fingerprints, iris scans or voiceprints · CPC title

• G06V40/172

  Classification, e.g. identification · CPC title

• G07F19/207 Primary

  Surveillance aspects at ATMs · CPC title

• H04L63/1425

  Traffic logging, e.g. anomaly detection · CPC title

• H04L63/1475

  Passive attacks, e.g. eavesdropping or listening without modification of the traffic monitored · CPC title