Detecting reliability using augmented reality

Patent metadata

Field	Value
Publication number	US-12573222-B2
Application number	US-202217932110-A
Country	US
Kind code	B2
Filing date	Sep 14, 2022
Priority date	Sep 14, 2022
Publication date	Mar 10, 2026
Grant date	Mar 10, 2026

Abstract

In some implementations, an augmented reality (AR) device may receive first images representing a webpage, an email, a product, or a store associated with a first entity. The AR device may detect, within the first images, a logo, a font, and/or a color. The AR device may apply a model, trained on a set of guidelines associated with the first entity, to the logo, the font, and/or the color. Accordingly, the AR device may receive, from the model, a first score associated with the webpage, the email, the product, or the store. The AR device may transmit an alert based on the first score. In some implementations, the AR device may further receive second images and apply the model to receive a second score associated with the webpage, the email, the product, or the store. Accordingly, the AR device may transmit an additional alert based on the second score.

First claim

What is claimed is:

1 . A system for using augmented reality to detect reliability, the system comprising:
one or more memories; and one or more processors, communicatively coupled to the one or more memories, configured to:
receive, at an augmented reality (AR) device, one or more first images representing a webpage or an email associated with a first entity;
detect, within the one or more first images, at least one logo;
apply a model, trained on a set of guidelines associated with the first entity, to the at least one logo as shown in the one or more first images;
receive, from the model, a first score associated with the webpage or the email;
receive, at the AR device, one or more second images further representing the webpage or the email;
detect, within the one or more second images, the at least one logo;
apply the model to the at least one logo as shown in the one or more second images;
receive, from the model, a second score associated with the webpage or the email; and
transmit, to the AR device, an alert based on the second score failing to satisfy a reliability threshold.

2 . The system of claim 1 ,
wherein the model is further trained on a set of images of products associated with the first entity.

3 . The system of claim 1 ,
wherein the one or more processors are further configured to:
receive, from the model, an indication that the webpage or the email is likely associated with a second entity.

4 . The system of claim 1 ,
wherein the one or more processors are further configured to:
detect, within the one or more first images, at least one first color, wherein the first score is further based on the at least one first color; and
detect, within the one or more second images, at least one second color, wherein the second score is further based on the at least one second color.

5 . The system of claim 1 ,
wherein the one or more processors are further configured to:
detect, within the one or more first images, at least one first font, wherein the first score is further based on the at least one first font; and
detect, within the one or more second images, at least one second font, wherein the second score is further based on the at least one second font.

6 . The system of claim 1 ,
wherein the one or more processors are further configured to:
detect, within the one or more first images, a first placement and a first size associated with the at least one logo, wherein the first score is further based on the first placement and the first size.

7 . A method of using augmented reality to detect reliability, comprising:
receiving, at an augmented reality (AR) device, one or more first images representing a webpage or an email associated with a first entity; detecting, within the one or more first images, at least one logo; detecting, within the one or more first images, at least one font; detecting, within the one or more first images, at least one color; applying a model, trained on a set of guidelines associated with the first entity, to the at least one logo, the at least one font, and the at least one color; receiving, from the model, a first score associated with the webpage or the email; receiving, at the AR device, one or more second images further representing the webpage or the email; detecting, within the one or more second images, at least one of a new logo, a new font, or a new color; applying the model to the new logo, the new font, or the new color; receiving, from the model, a second score associated with the webpage or the email; and transmitting, to the AR device, an alert based on the second score failing to satisfy a reliability threshold.

8 . The method of claim 7 , further comprising:
detecting, within the one or more first images, at least one spacing associated with the at least one logo,
wherein the model is applied to the spacing.

9 . The method of claim 7 , further comprising:
detecting, within the one or more first images, one or more white space measurements associated with text,
wherein the model is applied to the one or more white space measurements.

10 . The method of claim 7 , further comprising:
detecting, within the one or more first images, text; and transcribing the text using optical character recognition,
wherein the model is applied to words within the text.

11 . The method of claim 10 , further comprising:
applying sentiment analysis to the text to determine a tone associated with the text,
wherein the model is applied to the tone.

12 . The method of claim 7 , further comprising:
detecting, within the one or more first images, a uniform resource locator (URL),
wherein the model is applied to the URL.

13 . The method of claim 7 , further comprising:
transmitting, to the AR device, an update based on the second score.

14 . A non-transitory computer-readable medium storing a set of instructions for using augmented reality to detect reliability, 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, at an augmented reality (AR) device, one or more first images representing a webpage or an email associated with a first entity;
detect, within the one or more first images, at least one logo;
detect, within the one or more first images, at least one font;
detect, within the one or more first images, at least one color;
apply a model, trained on a set of guidelines associated with the first entity, to the at least one logo, the at least one font, and the at least one color;
receive, from the model, a first score associated with the webpage or the email;
receive, at the AR device, one or more second images representing the webpage or the email;
detect, within the one or more second images, at least one of a new logo, a new font, or a new color;
apply the model to the new logo, the new font, or the new color;
receive, from the model, a second score associated with the webpage or the email; and
transmit, to the AR device, an alert based on the second score failing to satisfy a reliability threshold.

15 . The non-transitory computer-readable medium of claim 14 ,
wherein the one or more instructions, when executed by the one or more processors, further cause the device to:
detect, within the one or more first images, one or more white space measurements associated with text,
wherein the model is applied to the one or more white space measurements.

16 . The non-transitory computer-readable medium of claim 14 ,
wherein the one or more instructions, when executed by the one or more processors, further cause the device to:
detect, within the one or more first images, text; and
transcribe the text using optical character recognition,
wherein the model is applied to words within the text.

17 . The non-transitory computer-readable medium of claim 16 ,
wherein the one or more instructions, when executed by the one or more processors, further cause the device to:
apply sentiment analysis to the text to determine a tone associated with the text,
wherein the model is applied to the tone.

18 . The non-transitory computer-readable medium of claim 14 ,
wherein the one or more instructions, when executed by the one or more processors, further cause the device to:
detect, within the one or more first images, an email address,
wherein the model is applied to the email address.

19 . The non-transitory computer-readable medium of claim 14 ,
wherei

Assignees

• Capital One Services Llc

Inventors

• Tessler Leeyat Bracha
• Mays Robert
• Maiman Tyler
• Byrd Juwan

Classifications

• G06V30/244

  using graphical properties, e.g. alphabet type or font · CPC title

• G06V10/56

  relating to colour · CPC title

• G06V2201/09

  Recognition of logos · CPC title

• G06V30/19093 Primary

  Proximity measures, i.e. similarity or distance measures · CPC title

• G06V20/62 Primary

  Text, e.g. of license plates, overlay texts or captions on TV images · CPC title