• Journal of Korea Game Society
• /
• v.21 no.6
• /
• pp.87-96
• /
• 2021

As the industry develops, the technology used for games is also being advanced. In particular, AI technology is used to game automation and intelligence. These game player patterns are widely used in online games such as player matchmaking, generation of friendly or hostile NPCs, and balancing of game worlds. This study proposes a model generation method for game players. For model generation, attributes such as hunting, collection, movement, combat, crisis management, production, and interaction were defined, and patterns were extracted and modeled using decision tree method. To evaluate the proposed method, we used the game log of a commercial game and confirmed the meaningful results.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.25 no.5
• /
• pp.1123-1129
• /
• 2015

Macro(automatic hunting) of mobile game is a program that touch the screen by defined rules like a game bot in PC online games, and it is used by make various ways like android application or windows application program. This gives honest users deprivation and make to lose their interest. Finally they would leave the game and gradually game life would be shorten. Although many studies to prevent these problems in PC online game are conducted, applying mobile game to PC's way is difficult because mobile games are limited to use the network and device performance is different with PC. In this paper, we propose a framework for macro detection by using the touch event information. A touch event on the mobile game is a necessary control command to the game. Because macro touches the screen with the same pattern, there is a difference between normal user's behavior and macro's operation. In mobile games that casual games are mostly, Touch event is the best difference that identify normal user against macro for a short period of time. As a result of detecting macros used in real mobile game by using the proposed framework it showed 100% accuracy and 0% false positive rate.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10d
• /
• pp.319-321
• /
• 2002

본 논문에서는 대표적인 3차원 일인칭 액션 게임(first-person action game)인 Unreal Tournament 게임과 이것에 기초한 Gamebots시스템을 소개하고, 이러한 환경에서 효과적으로 동작하는 지능형 NPC인 KGBot의 설계와 구현에 대해 설명한다. KGBot는 Gamebots시스템에서 하나의 보트 클라이언트(bot client)로 동작하면서 지형이 복잡한 3차원 가상환경 안에서 적들에 대항해 아군과 연합하여 특정 목표 지점(domination point)들을 찾아 점령하는 자율 NPC이다. KGBot는 BDI기반의 범용 에이전트 구조인 UM-PRS를 제어엔진으로 채용하고 있으며, 복잡한 행위들을 효과적으로 구현하기 위해 계충화된 지식베이스를 가지고 있다. 본 논문에서는 특히 제한적인 센서정보와 이동점(waypoint)에 기초하여 자신이 놓여진 월드의 전체지도를 작성하고 임의의 목적지까지 효율적인 이동경로를 계획할 수 있는 KGBot의 행위의 구현과 실험에 대해 설명한다.