ML-Driven Extension to Predict Visually Impaired Spectrum

Patent metadata

Field	Value
Publication number	US-2025087112-A1
Application number	US-202318244485-A
Country	US
Kind code	A1
Filing date	Sep 11, 2023
Priority date	Sep 11, 2023
Publication date	Mar 13, 2025
Grant date	—

Abstract

Methods, systems, and apparatuses are described herein for an extension that predicts a user's Visually Impaired Spectrum (VIS) score then adjusts a browser accessibility setting accordingly. Further, the method may monitor the user's interaction with the accessibility settings and update the user's predicted VIS score. An extension may train a machine learning model to predict a user's VIS score, then generate a VIS score employing the user's personal information as input. Further, the extension may retrieve, from a database, one or more accessibility settings associated with a VIS score. The extension may adjust one or more browser accessibility settings according to the VIS score.

First claim

What is claimed is:

1 . A method comprising:
training, by a server and based on browser interaction data, a first machine learning model to predict a visually impaired spectrum score; generating, by an extension implementing the first trained machine learning model, a first visually impaired spectrum score associated with a first user; adjusting, by the extension and based on the first visually impaired spectrum score, one or more accessibility settings of a browser executing the extension; receiving, by a second trained machine learning model, feedback from the first user regarding an adjustment to the one or more accessibility settings; adjusting, by the extension and based on the feedback from the first user, at least one accessibility setting of the one or more accessibility settings; storing the at least one adjusted accessibility setting; and causing, by the browser and using the at least one adjusted accessibility setting, presentation of a readable document on the browser.

2 . The method of claim 1 , wherein the second trained machine learning model comprises one or more speech recognition models.

3 . The method of claim 1 , further comprising automatically performing, based on detecting the first user interacting with the readable document, auto-scrolling of the readable document based on the one or more adjusted accessibility settings.

4 . The method of claim 1 , further comprising automatically performing, based on detecting the first user interacting with the readable document, text-to-speech conversion of the readable document based on the one or more adjusted accessibility settings.

5 . The method of claim 1 , wherein the generating the first visually impaired spectrum score comprises:
receiving, by the extension, past user interactions indicating at least one of a preferred auto-scrolling speed for the first user or a preferred text-to-speech conversion rate for the first user; and generating, based on the past user interactions, the first visually impaired spectrum score.

6 . The method of claim 1 , further comprising:
determining, by the server and based on the first visually impaired spectrum score, one or more additional accessibility settings associated with the first visually impaired spectrum score; and adjusting, by the extension, the one or more additional accessibility settings of the browser.

7 . The method of claim 6 , wherein the one or more additional accessibility settings comprises one or more of:
a font size; a font color; a font selection; a font spacing; a background color; a foreground color; a background pattern; a foreground pattern; a document lighting characteristic; a spotlight illumination characteristic; a magnification level; an animation characteristic; a transparency percentage; or a tactile feedback setting.

8 . The method of claim 6 , further comprising:
receiving additional feedback from the first user regarding the adjustment to the one or more additional accessibility settings; storing, based on the additional feedback, the one or more adjusted additional accessibility settings; and causing, by the extension and based on the additional feedback, presentation of the readable document on the browser using the one or more adjusted additional accessibility settings.

9 . The method of claim 8 , further comprising:
causing, by the server based on the additional feedback and the first visually impaired spectrum score, a notification to be displayed to the first user reflecting a change in the first visually impaired spectrum score.

10 . The method of claim 6 , further comprising: automatically performing, based on detecting the first user interacting with the readable document, the one or more adjusted additional accessibility settings.

11 . A computing device comprising:
one or more processors; and memory storing instructions that, when executed by the one or more processors, cause the computing device to:
train, based on browser interaction data, a first machine learning model to predict a visually impaired spectrum score;
generate, by an extension implementing the first trained machine learning model, a first visually impaired spectrum score associated with a first user;
adjust, by the extension and based on the first visually impaired spectrum score, one or more accessibility settings of a browser executing the extension;
receive, by a second trained machine learning model, feedback from the first user regarding an adjustment to the one or more accessibility settings;
adjust, by the extension and based on feedback from the first user, at least one accessibility setting of the one or more accessibility settings;
store the at least one adjusted accessibility setting; and
cause, by the browser and using the at least one adjusted accessibility setting, presentation of a webpage on the browser.

12 . The computing device of claim 11 , wherein the one or more accessibility settings comprise one or more of:
a font size; a font color; a font selection; a font spacing; a background color; a foreground color; a background pattern; a foreground pattern; a document lighting characteristic; a spotlight illumination characteristic; a magnification level; an animation characteristic; a transparency percentage; a tactile feedback setting; an auto-scrolling speed of the browser; or a text-to-speech conversion rate of the browser.

13 . The computing device of claim 11 , wherein the instructions, when executed by the one or more processors, cause the computing device to:
automatically perform, based on detecting the first user interacting with a readable document on the webpage, auto-scrolling of the readable document based on the one or more adjusted accessibility settings.

14 . The computing device of claim 11 , wherein the instructions, when executed by the one or more processors, cause the computing device to:
automatically perform, based on detecting the first user interacting with a readable document on the webpage, text-to-speech conversion of the readable document based on the one or more adjusted accessibility settings.

15 . The computing device of claim 11 , wherein the instructions, when executed by the one or more processors comprises cause the computing device to:
receive, by the extension, past user interactions indicating at least one of a preferred auto-scrolling speed for the first user or a preferred text-to-speech conversion rate for the first user; and generate, based on the past user interactions, the first visually impaired spectrum score.

16 . The computing device of claim 11 , wherein the instructions, when executed by the one or more processors comprises cause the computing device to:
determine, based on the first visually impaired spectrum score, one or more additional accessibility settings associated with the first visually impaired spectrum score; and prompt, based on determining one or more reading aids, the first user to enable the one or more reading aids.

17 . The computing device of claim 11 , wherein the feedback comprises one or more of:
verbal user feedback; or a response to a displayed prompt.

18 . One or more non-transitory computer-readable media storing instructions that, when executed by one or more processors, cause a computing device to:
train, based on browser interaction data, a first machine learning model to predict a visually impaired spectrum score; generate, by an extension implementing the first trained machine learning model, a first

Assignees

• Capital One Services Llc

Inventors

• Morales Tania Cruz
• Lowe Kevin
• Sillero Sonia Sierra

Classifications

• G10L15/22

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title

• G06F3/0485

  Scrolling or panning · CPC title

• G06F3/04847

  Interaction techniques to control parameter settings, e.g. interaction with sliders or dials · CPC title

• G09B21/006

  using audible presentation of the information · CPC title

• G09B21/008 Primary

  using visual presentation of the information for the partially sighted · CPC title