US 12,394,230 B2
Systems and methods for detecting user created circular shaped indications using machine learning models
Maksim Chepel, Hartford, CT (US)
Assigned to Aetna Inc., Hartford, CT (US)
Filed by Aetna Inc., Hartford, CT (US)
Filed on Aug. 2, 2022, as Appl. No. 17/879,353.
Prior Publication US 2024/0046676 A1, Feb. 8, 2024
Int. Cl. G06V 30/14 (2022.01); G06V 30/20 (2022.01); G06V 30/412 (2022.01)
CPC G06V 30/1448 (2022.01) [G06V 30/20 (2022.01); G06V 30/412 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method for detecting circular shaped user indications, comprising:
obtaining, by a computing system, a plurality of documents, wherein at least one document, of the plurality of documents, comprises one or more circular shaped user indications, wherein each of the one or more circular shaped user indications indicates a user selection of a design or text within the associated circular shaped user indication;
determining, by the computing system, circular shaped identification information for a document, of the plurality of documents based on using a trained machine learning-artificial intelligence (ML-AI) model, wherein the circular shaped identification information indicates the user selection of the design or the text within the associated circular shaped user indication, and wherein determining the circular shaped identification information comprises:
performing a text recognition algorithm for the document to determine a plurality of extracted text for the document and a plurality of extracted coordinate points associated with the plurality of extracted text:
processing the document using the trained ML-AI model to determine a plurality of ML-AI coordinate points, wherein each subset of the plurality of ML-AI coordinate points is associated with a circular shaped user indication of the one or more circular shaped user indications within the document; and
determining the circular shaped identification information based on comparing the plurality of ML-AI coordinate points with the plurality of extracted coordinate points; and
performing, by the computing system, one or more actions based on the circular shaped identification information.