# US 2026/0099529 A1 · Computerized method and system for dynamic engine prompt generation

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0099529 A1
- Document ID: US20260099529A1
- Status: Published application
- Kind: A1
- Application number: 19/232,966
- Filed: 2025-06-10
- Published: 2026-04-09
- Earliest claimed: 2024-02-09
- Assignees: Highlight US Inc.
- Applicants: Highlight US Inc.
- Inventors: Wilhelmus de Witte; Karthick Jeyapal; Umut Yildrim; Haris M. Butt
- Web page: https://patentgrep.com/patent/US20260099529A1

## CPC

- G06F 16/3347: {using vector based model}
- G06F 16/335: Filtering based on additional data, e.g. user or group profiles (filtering in web context G06F16/9535, G06F16/9536)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

The method and system improves upon standard user interaction by supplementing user interfacing and computer operations based on dynamic analysis of content including detecting a user capture a portion of the output via further user input from one of the plurality of input devices, a visual focus on the portion of the output. The method and system includes electronically processing the user capture to determine a content within the portion of the output within the visual focus and dynamically generate a secondary display element visible to the user as part of the output, the secondary display element including a user interface display for receiving additional user input including at least one input command. The method and system includes accessing at least one artificial intelligence processing system for performing a processing operation in response to the at least one input command and generating an updated output for the user.

## Claims

### Claim 1

A computerized method for supplementing user interfacing and computer operations based on dynamic analysis of content, the method comprising:
processing a plurality of user inputs via at least one of a plurality of input devices and generating an output to the user based on the user input commands;
detecting a user capture of a portion of the output via further user input from one of the plurality of input devices, where the user capture generates an output display of a visual focus on the portion of the output;
electronically processing the user capture to determine a content within the portion of the output within the visual focus;
dynamically generating a secondary display element visible to the user as part of the output, the secondary display element including a user interface display for receiving additional user input including at least one input command;
in response to the additional user input, accessing at least one artificial intelligence processing system for performing a processing operation in response to the at least one input command; and
generating an updated output for the user including an output of a result of the processing operations as performed by the artificial intelligence processing system in response to the at least one input command.

### Claim 2 (depends on 1)

The method of claim 1 wherein the user capture of the at least a portion of the output includes a user input command via at least one the plurality of input devices to highlight at least a portion of text within the portion of the output display.

### Claim 3 (depends on 2)

The method of claim 2 further comprising:
performing content recognition of the text within the portion to determine a contextual input; and
performing the processing operation on the contextual input.

### Claim 4 (depends on 3)

The method of claim 3, wherein the performing the processing operation includes generating a structured document therefrom.

### Claim 5 (depends on 3)

The method of claim 3, further comprising:
accessing at least one preference database associated with the user; and
acquiring a plurality of user preferences, wherein performing the processing operation includes generating personalized content based on the contextual input and the user preferences.

### Claim 6 (depends on 1)

The method of claim 1, wherein the generating the updated output including inputting the output of the result of the processing operations into a first software application.

### Claim 7 (depends on 1)

The method of claim 1, wherein the user capture includes creating a visual outline around or encompassing at least one visual element.

### Claim 8 (depends on 7)

The method of claim 7 further comprising:
performing content recognition of the visual element to determine a contextual input; and
performing the processing operation on the contextual input.

### Claim 9 (depends on 8)

The method of claim 8, wherein the performing of the content recognition includes performing content recognition on at least a portion of text within the visual element.

### Claim 10 (depends on 7)

The method of claim 7 wherein the visual element is at least one of: an image, a graph, and a graphic.

### Claim 11

A computerized method for supplementing user interfacing and computer operations based on dynamic analysis of content, the method comprising:
executing a first software application;
processing a plurality of user inputs to the first software application via at least one of a plurality of input devices and generating an output within the first software application to the user based on the user input commands;
detecting a user capture of a portion of the output from the first application via further user input from one of the plurality of input devices, where the user capture generates an output display of a visual focus on the portion of the output;
electronically processing the user capture to determine a content within the portion of the output within the visual focus;
dynamically generating a secondary display element visible to the user as part of the output, the secondary display element including a user interface display for receiving additional user input including at least one input command;
in response to the additional user input, accessing at least one artificial intelligence processing system for performing a processing operation in response to the at least one input command; and
generating an updated output for the user including an output of a result of the processing operations as performed by the artificial intelligence processing system in response to the at least one input command including generating a new output display for the user in a second application.

### Claim 12 (depends on 11)

The method of claim 11 wherein the user capture of the at least a portion of the output includes a user input command via at least one the plurality of input devices to highlight at least a portion of text within the portion of the output display.

### Claim 13 (depends on 12)

The method of claim 12 further comprising:
performing content recognition of the text within the portion to determine a contextual input; and
performing the processing operation on the contextual input.

### Claim 14 (depends on 13)

The method of claim 13, wherein the performing the processing operation includes generating a structured document therefrom.

### Claim 15 (depends on 13)

The method of claim 13, further comprising:
accessing at least one preference database associated with the user; and
acquiring a plurality of user preferences, wherein performing the processing operation includes generating personalized content based on the contextual input and the user preferences.

### Claim 16 (depends on 11)

The method of claim 11, wherein the user capture includes creating a visual outline around or encompassing at least one visual element.

### Claim 17 (depends on 16)

The method of claim 16 wherein the visual element is at least one of: an image, a graph, and a graphic.

### Claim 18

A computerized method for supplementing user interfacing and computer operations based on dynamic analysis of content, the method comprising:
executing a first software application;
processing a plurality of user inputs to the first software application via at least one of a plurality of input devices and generating an output within the first software application to the user based on the user input commands;
detecting a user capture of a portion of the output from the first application via further user input from one of the plurality of input devices, where the user capture generates an output display of a visual focus on the portion of the output;
electronically processing the user capture to determine a content within the portion of the output within the visual focus;
dynamically generating a secondary display element visible to the user as part of the output, the secondary display element including a user interface display for receiving additional user input including at least one input command;
performing content recognition of the text within the portion to determine a contextual input;
performing the processing operation on the contextual input;
accessing at least one preference database associated with the user;
acquiring a plurality of user preferences, wherein performing the processing operation includes generating personalized content based on the contextual input and the user preferences;
in response to the additional user input, accessing at least one artificial intelligence processing system for performing a processing operation in response to the at least one input command; and
generating an updated output for the user including an output of a result of the processing operations as performed by the artificial intelligence processing system in response to the at least one input command including generating a new output display for the user in at least one of: the first application and a second application.

### Claim 19 (depends on 18)

The method of claim 18 wherein the user capture of the at least a portion of the output includes a user input command via at least one the plurality of input devices to highlight at least a portion of text within the portion of the output display.

### Claim 20 (depends on 18)

The method of claim 18, wherein the user capture includes creating a visual outline around or encompassing at least one visual element and the visual element is at least one of: an image, a graph, and a graphic.
