logo

For the Inventor, By the Inventor

The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Patent No.:

US 12743670 B1

PDFFull Text
Date of Patent:
Sep. 22, 2026

Filed:

Dec. 21, 2022

Extracting features from screen images for task mining

Applicant:

Uipath, Inc., New York, NY (US);

Inventor:

Gregory Allen Barello, Seattle, WA (US);

Assignee:

UiPath, Inc., New York, NY (US);

Attorney:

Chiesa Shahinian & Giantomasi PC

Primary Examiner:

Vu Le

Assistant Examiner:

Matthew James Bodnark

Int. Cl.
CPC ...
G06Q 10/0631 (2023.01); G06T 3/4046 (2024.01); G06T 9/00 (2006.01); G06V 10/44 (2022.01); G06V 10/74 (2022.01); G06V 10/762 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 30/18 (2022.01); G06V 30/412 (2022.01);
U.S. Cl.
CPC ...
G06Q 10/06316 (2013.01); G06T 3/4046 (2013.01); G06T 9/002 (2013.01); G06V 10/44 (2022.01); G06V 10/761 (2022.01); G06V 10/762 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 30/18 (2022.01); G06V 30/412 (2022.01);
Abstract

Systems and methods for extracting features from screen images for performing a task mining task are provided. A screen image depicting a user interface of a computing system is received. The screen image is preprocessed to generate a preprocessed screen image and processing results. Image features are extracted from the preprocessed screen image using a first machine learning based network. Text features and control element features are extracted from the processing results using a second machine learning based network. The text features and the control element features are encoded using a third machine learning based network to generate representative features of the screen image. A task is performed on the screen image based on one or more of the image features, the text features, the control element features, or the representative features. Results of the task are output.

Find Patent Forward Citations

Barello, Gregory. (2026). Extracting features from screen images for task mining (U.S. Patent No. 12743670). U.S. Patent and Trademark Office. https://idiyas.com/patent/badge/12743670

Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile

Loading…