Automatically modifying display presentations to programmatically accommodate for visual impairments

Patent metadata

Field	Value
Publication number	US-11482133-B2
Application number	US-202016936604-A
Country	US
Kind code	B2
Filing date	Jul 23, 2020
Priority date	Sep 4, 2019
Publication date	Oct 25, 2022
Grant date	Oct 25, 2022

Abstract

Methods, apparatus, systems, computing devices, computing entities, and/or the like for identifying one or more visual impairments of a user, mapping the visual impairments to one or more accessibility solutions, (e.g., program code entries) and dynamically modifying a display presentation based at least in part on the identified accessibility solutions.

First claim

The invention claimed is:

1. A computer-implemented method for an internet browser to dynamically modify a webpage document using one or more scripts, the method comprising:
responsive to a user initiating an internet browser, generating, by the internet browser, a request for a determined program code entry, wherein (a) the request comprises a program code identifier, (b) the program code identifier is used by a server to identify the determined program code entry corresponding to the program code identifier, (c) the determined program code entry is configured to dynamically modify a webpage document using one or more scripts;
receiving, by the internet browser, a response to the request for the determined program code entry, wherein (a) the request comprises the program code identifier, and (b) the response comprises the determined program code entry;
storing, by the internet browser, the determined program code entry;
receiving, by the internet browser, a webpage document, wherein the webpage document originates from a web server;
executing, by the internet browser and based at least in part on the determined program code entry, one or more scripts on the received webpage document to generate a modified webpage document;
providing, by the internet browser, the modified webpage document for display;
capturing, by the internet browser, a plurality of user interaction events; and
providing, by the internet browser, user interaction data for each of the interaction events to the server, wherein a server system (a) provides at least a portion of the user interaction data for each of user interaction event to one or more machine learning models responsive to a determination that the plurality of user interaction events satisfies a configurable user interaction threshold, and (b) the one or more machine learning models generate a predicted output indicative of a predicted user display setting and a confidence score for the predicted user display setting.

2. The computer-implemented method of claim 1 , wherein the server system determines whether the confidence score for the predicted user display setting satisfies a configurable prediction threshold.

3. The computer-implemented method of claim 2 , wherein the server system:
responsive to a determination that the confidence score for the predicted user display setting satisfies the configurable prediction threshold, identifies a predicted program code entry corresponding to the predicted user display setting;
associates the program code identifier with the predicted program code entry; and
provides the predicted program code entry to the internet browser.

4. A computer program product for dynamically modifying a display presentation comprising a non-transitory computer readable medium having computer program instructions stored therein, the computer program instructions when executed by a processor, cause an internet browser to:
responsive to a user initiating an internet browser, generate a request fora determined program code entry, wherein (a) the request comprises a program code identifier, (b) the program code identifier is used by a server to identify the determined program code entry corresponding to the program code identifier, (c) the determined program code entry is configured to dynamically modify a webpage document using one or more scripts;
receive a response to the request for the determined program code entry, wherein (a) the request comprises the program code identifier, and (b) the response comprises the determined program code entry;
store the determined program code entry;
receive a webpage document, wherein the webpage document originates from a web server;
execute, based at least in part on the determined program code entry, one or more scripts on the received webpage document to generate a modified webpage document;
provide the modified webpage document for display;
capture a plurality of user interaction events; and
provide user interaction data for each of the interaction events to the server, wherein a server system (a) provides at least a portion of the user interaction data for each of user interaction event to one or more machine learning models responsive to a determination that the plurality of user interaction events satisfies a configurable user interaction threshold, and (b) the one or more machine learning models generate a predicted output indicative of a predicted user display setting and a confidence score for the predicted user display setting.

5. The computer program product of claim 4 , wherein the server system determines whether the confidence score for the predicted user display setting satisfies a configurable prediction threshold.

6. The computer program product of claim 5 , wherein the server system:
responsive to a determination that the confidence score for the predicted user display setting satisfies the configurable prediction threshold, identifies a predicted program code entry corresponding to the predicted user display setting;
associates the program code identifier with the predicted program code entry; and
provides the predicted program code entry to the internet browser.

7. An apparatus storing computer program instructions when executed by a processor of the apparatus, cause an internet browser to:
responsive to a user initiating an internet browser, generate a request fora determined program code entry, wherein (a) the request comprises a program code identifier, (b) the program code identifier is used by a server to identify the determined program code entry corresponding to the program code identifier, (c) the determined program code entry is configured to dynamically modify a webpage document using one or more scripts;
receive a response to the request for the determined program code entry, wherein (a) the request comprises the program code identifier, and (b) the response comprises the determined program code entry;
store the determined program code entry;
receive a webpage document, wherein the webpage document originates from a web server;
execute, based at least in part on the determined program code entry, one or more scripts on the received webpage document to generate a modified webpage document;
provide the modified webpage document for display;
capture a plurality of user interaction events; and
provide user interaction data for each of the interaction events to the server, wherein a server system (a) provides at least a portion of the user interaction data for each of user interaction event to one or more machine learning models responsive to a determination that the plurality of user interaction events satisfies a configurable user interaction threshold, and (b) the one or more machine learning models generate a predicted output indicative of a predicted user display setting and a confidence score for the predicted user display setting.

8. The apparatus of claim 7 , wherein the server system determines whether the confidence score for the predicted user display setting satisfies a configurable prediction threshold.

9. The apparatus of claim 8 , wherein the server system:
responsive to a determination that the confidence score for the predicted user display setting satisfies the configurable prediction threshold, identifies a predicted program code entry corresponding to the predicted user display setting;
associates the program code identifier with the predicted program code entry; and
provides the predicted program code entry to the internet browser.

Assignees

• Optum Services Ireland Ltd

Inventors

• O'Reilly Sarah Noreen
• Keane Michael
• Crossan Gareth M
• Mooney Patrick G

Classifications

• G06N20/00

  Machine learning · CPC title

• G06F3/04847

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

• G09B21/008 Primary

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