Verfahren und System zur Tiefenlernbasierten Muskel-Skelett-Erkrankungsvorhersage

Details

Veröffentlichungs-Nr.

EP4756730

Anmeldetag

1. Dezember 2025

Veröffentlichung

10. Juni 2026

Rechtsraum

EP

Abstract

The present invention relates to a method and system for deep learning-based musculoskeletal disease prediction. A method for deep learning-based musculoskeletal disease prediction, according to the present invention, may comprise: receiving an image of a worker serving as a photographing target and a specific environment in which the worker is positioned; specifying, from the image, a first bounding-box corresponding to the worker and a second bounding-box corresponding to the specific environment by using a pre-trained deep learning model; extracting keypoints corresponding to a plurality of joints included in a body of the worker based on the first bounding-box; calculating angles between the plurality of joints by using the extracted keypoints and calculating a risk score on the calculated angles between the plurality of joints; specifying a risk degree for the worker based on the calculated risk score; and generating response action information according to the specified risk degree.

Anmelder

Firma

Kyungpook National University Industry-Academic Cooperation Foundation

Land

🇰🇷 Südkorea