@article{ART003259688},
author={MyounJae Lee},
title={Design and Implementation of a Real-Time Player Classification System in Game Environments Using Unity and Transformer Model},
journal={Journal of Internet of Things and Convergence},
issn={2466-0078},
year={2025},
volume={11},
number={5},
pages={14}
TY - JOUR
AU - MyounJae Lee
TI - Design and Implementation of a Real-Time Player Classification System in Game Environments Using Unity and Transformer Model
JO - Journal of Internet of Things and Convergence
PY - 2025
VL - 11
IS - 5
PB - The Korea Internet of Things Society
SP - 14
EP -
SN - 2466-0078
AB - In traditional game environments, real-time player classification primarily relies on rule-based or conventional machine learning techniques, typically processed on servers in a non-real-time manner, which limits immediate responsiveness. These methods lack adaptability to evolving player behavior and are limited in understanding context based on player action sequences, resulting in low classification accuracy. This study proposes a method for real-time player classification in game environments using a Transformer model based on the Hugging Face framework within the Unity engine. The proposed system adopts a three-tier architecture composed of a Unity client, a Flask server, and the Hugging Face Inference API. Unity preprocesses player data and sends it to the Flask server, which queries the Transformer model and returns the result to the client. The study also outlines considerations for clients, developers, and game companies when implementing such a system. Through real-time player classification, the proposed approach enables various in-game applications such as personalized gameplay, dynamic difficulty adjustment, and abnormal behavior detection. In particular, by presenting an AI system structure applicable to Unity-based game environments, this research contributes to enhancing practical applicability in the gaming industry.
KW - Game player;player Classification;Game AI Enginge;Unity Engine;Hugging Face Model
DO -
UR -
ER -
MyounJae Lee. (2025). Design and Implementation of a Real-Time Player Classification System in Game Environments Using Unity and Transformer Model. Journal of Internet of Things and Convergence, 11(5), 14.
MyounJae Lee. 2025, "Design and Implementation of a Real-Time Player Classification System in Game Environments Using Unity and Transformer Model", Journal of Internet of Things and Convergence, vol.11, no.5 14.
MyounJae Lee "Design and Implementation of a Real-Time Player Classification System in Game Environments Using Unity and Transformer Model" Journal of Internet of Things and Convergence 11.5 14 (2025) : 14.
MyounJae Lee. Design and Implementation of a Real-Time Player Classification System in Game Environments Using Unity and Transformer Model. 2025; 11(5), 14.
MyounJae Lee. "Design and Implementation of a Real-Time Player Classification System in Game Environments Using Unity and Transformer Model" Journal of Internet of Things and Convergence 11, no.5 (2025) : 14.
MyounJae Lee. Design and Implementation of a Real-Time Player Classification System in Game Environments Using Unity and Transformer Model. Journal of Internet of Things and Convergence, 11(5), 14.
MyounJae Lee. Design and Implementation of a Real-Time Player Classification System in Game Environments Using Unity and Transformer Model. Journal of Internet of Things and Convergence. 2025; 11(5) 14.
MyounJae Lee. Design and Implementation of a Real-Time Player Classification System in Game Environments Using Unity and Transformer Model. 2025; 11(5), 14.
MyounJae Lee. "Design and Implementation of a Real-Time Player Classification System in Game Environments Using Unity and Transformer Model" Journal of Internet of Things and Convergence 11, no.5 (2025) : 14.
