國立高雄大學圖資館 |

語系: 繁體中文

說明(常見問題)

圖資館首頁

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

使用序列探勘技術建立遊戲機器人偵測系統之研究 = A Study of ...

國立高雄大學資訊管理學系碩士班

使用序列探勘技術建立遊戲機器人偵測系統之研究 = A Study of Using Sequence Mining to Construct a Game Bot Detection System

紀錄類型:	書目-語言資料,印刷品 : 單行本
並列題名:	A Study of Using Sequence Mining to Construct a Game Bot Detection System
作者:	廖又加,
其他團體作者:	國立高雄大學
出版地:	[高雄市]
出版者:	撰者;
出版年:	2015[民104]
面頁冊數:	[5], 40面圖，表 : 30公分;
標題:	線上遊戲
標題:	online game
電子資源:	http://handle.ncl.edu.tw/11296/ndltd/96509843940942154623
附註:	參考書目：面37-40
附註:	104年3月25日公開
摘要註:	遊戲產業現在是相當重要的網路產業，線上遊戲在當前擁有數量龐大的使用人口，在遊戲產業市場上有相當高的市占率。而其中線上角色扮演遊戲是最受歡迎的遊戲類型，其佔有率高達整個遊戲產業的三分之一。然而這類型的遊戲一直存在著一個影響玩家參與遊戲意願的嚴重問題，也就是俗稱外掛或掛機的遊戲機器人。遊戲機器人被視為一種作弊代理程式，作弊者可透過此程式長時間且持續的自動化執行程式去獲取一般正常玩家需投入長期經營才可取得的遊戲資源，造成了嚴重的公平性問題，使得一般正常的玩家不願意繼續投入該遊戲，進而讓遊戲公司蒙受損失。隨著遊戲機器人被氾濫地使用，如何有效的偵測出線上遊戲機器人與正常玩家的遊戲行為模式已成為當前遊戲產業重視的研究議題。本研究針對此問題，提出了一個遊戲機器人自動偵測系統。使用交互資訊以及序列探勘技術，從遊戲行為記錄中挖掘遊戲機器人以及一般玩家的遊戲行為序列特徵，最後藉由這些特徵建立偵測系統的核心模組，使系統得以自動偵測出遊戲機器人。在經過實證資料的驗證後，本研究提出的偵測方法可以達到正確率91%以及F度量值90.2%。從兩項數據可看出本研究提出的偵測方法可有效地偵測出遊戲機器人程式，相信能透過本研究的模式提供未來發展即時偵測遊戲機器人的重要基礎。 Nowadays, one of the important industries is the game industry. There is a lot population playing online game which makes online games having high market share in the computer games market. The most popular type of online game is the online role playing game that having one third of the online game market share. But there has been a serious problem that would decrease players’ intention to play which is the game bot. The game bot is considered as a cheating agent program. The cheaters could use the automatic program to get the resources that would cost normal players lots of time. It brought very serious problem which was very unfair and made not only the normal players lost the intention to play and enterprises would also lost profits. Because of the increasing of the serious cheating bot problem, to distinguish the behavior patterns between game bots and normal players has become an important research issue. We proposed an automatic cheating bot detection system against this problem. We use mutual information and sequence mining to find out both the cheating bot’s and normal players’ features of acting sequences from game logs for building the detection module. After being experimented by empirical data, the detection approach we proposed could reach the accuracy rate 91% and the F-measure 90.2%. The accuracy rate and the F-measure confirmed that the detection approach is effective. We believe this approach will be an important basis for developing immediate detection of game bots.

使用序列探勘技術建立遊戲機器人偵測系統之研究 = A Study of Using Sequence Mining to Construct a Game Bot Detection System
廖, 又加

使用序列探勘技術建立遊戲機器人偵測系統之研究 = A Study of Using Sequence Mining to Construct a Game Bot Detection System / 廖又加撰 - [高雄市] : 撰者, 2015[民104]. - [5], 40面 ; 圖，表 ; 30公分.
參考書目：面37-40104年3月25日公開.
線上遊戲online game

使用序列探勘技術建立遊戲機器人偵測系統之研究 = A Study of Using Sequence Mining to Construct a Game Bot Detection System
LDR:04246nam0a2200289 450 001 446542
005 20170214093136.0
009 446542
010 0 $b 精裝
010 0 $b 平裝
100 $a 20170214d2015 k y0chiy05 e
101 1 $a chi $d chi $d eng
102 $a tw
105 $a ak am 000yy
200 1 $a 使用序列探勘技術建立遊戲機器人偵測系統之研究 $d A Study of Using Sequence Mining to Construct a Game Bot Detection System $z eng $f 廖又加撰
210 $a [高雄市] $c 撰者 $d 2015[民104]
215 0 $a [5], 40面 $c 圖，表 $d 30公分
300 $a 參考書目：面37-40
300 $a 104年3月25日公開
314 $a 指導教授：蕭漢威博士
328 $a 碩士論文--國立高雄大學資訊管理學系碩士班
330 $a 遊戲產業現在是相當重要的網路產業，線上遊戲在當前擁有數量龐大的使用人口，在遊戲產業市場上有相當高的市占率。而其中線上角色扮演遊戲是最受歡迎的遊戲類型，其佔有率高達整個遊戲產業的三分之一。然而這類型的遊戲一直存在著一個影響玩家參與遊戲意願的嚴重問題，也就是俗稱外掛或掛機的遊戲機器人。遊戲機器人被視為一種作弊代理程式，作弊者可透過此程式長時間且持續的自動化執行程式去獲取一般正常玩家需投入長期經營才可取得的遊戲資源，造成了嚴重的公平性問題，使得一般正常的玩家不願意繼續投入該遊戲，進而讓遊戲公司蒙受損失。隨著遊戲機器人被氾濫地使用，如何有效的偵測出線上遊戲機器人與正常玩家的遊戲行為模式已成為當前遊戲產業重視的研究議題。本研究針對此問題，提出了一個遊戲機器人自動偵測系統。使用交互資訊以及序列探勘技術，從遊戲行為記錄中挖掘遊戲機器人以及一般玩家的遊戲行為序列特徵，最後藉由這些特徵建立偵測系統的核心模組，使系統得以自動偵測出遊戲機器人。在經過實證資料的驗證後，本研究提出的偵測方法可以達到正確率91%以及F度量值90.2%。從兩項數據可看出本研究提出的偵測方法可有效地偵測出遊戲機器人程式，相信能透過本研究的模式提供未來發展即時偵測遊戲機器人的重要基礎。 Nowadays, one of the important industries is the game industry. There is a lot population playing online game which makes online games having high market share in the computer games market. The most popular type of online game is the online role playing game that having one third of the online game market share. But there has been a serious problem that would decrease players’ intention to play which is the game bot. The game bot is considered as a cheating agent program. The cheaters could use the automatic program to get the resources that would cost normal players lots of time. It brought very serious problem which was very unfair and made not only the normal players lost the intention to play and enterprises would also lost profits. Because of the increasing of the serious cheating bot problem, to distinguish the behavior patterns between game bots and normal players has become an important research issue. We proposed an automatic cheating bot detection system against this problem. We use mutual information and sequence mining to find out both the cheating bot’s and normal players’ features of acting sequences from game logs for building the detection module. After being experimented by empirical data, the detection approach we proposed could reach the accuracy rate 91% and the F-measure 90.2%. The accuracy rate and the F-measure confirmed that the detection approach is effective. We believe this approach will be an important basis for developing immediate detection of game bots.
510 1 $a A Study of Using Sequence Mining to Construct a Game Bot Detection System $z eng
610 0 $a 線上遊戲 $a 遊戲機器人 $a 交互資訊 $a 序列探勘
610 1 $a online game $a game bot $a mutual information $a sequence mining
681 $a 008M/0019 $b 464105 0074 $v 2007年版
700 1 $a 廖 $b 又加 $4 撰 $3 700850
712 0 2 $a 國立高雄大學 $b 資訊管理學系碩士班 $3 353936
801 0 $a tw $b NUK $c 20150310 $g CCR
856 7 $z 電子資源 $2 http $u http://handle.ncl.edu.tw/11296/ndltd/96509843940942154623