當學術研究者遇見線上遊戲
39 likes37,912 views
此文件探討學術研究者在線上遊戲領域的研究，特別是自動化遊戲機器人檢測及其對遊戲經濟與平衡的影響。研究著重於檢測機器人行為的方法，例如利用流量分析和玩家動態路徑，並考察不同技術的準確性和有效性。文件還提到玩家的滿意度和退訂預測的相關研究，以提升遊戲體驗和維持收入。
當學術研究者遇見線上遊戲
- 2. 陳昇瑋 / 當學術研究者遇見線上遊戲 2 US$ 42 billion US$ 35 billion US$ 63 billion Video games Movie Music US$ 27 billion Book http://vgsales.wikia.com/wiki/Video_game_industry Entertainment Market Size (worldwide) No. 1 No. 2 No. 3 No. 4
- 3. 陳昇瑋 / 當學術研究者遇見線上遊戲 3
- 4. 陳昇瑋 / 當學術研究者遇見線上遊戲 7 Game Research: My Own Reasons As A PC Gamer … As A Programmer … As A Researcher …
- 5. As A PC Gamer (1) 198 8 1989 199 0 199 1
- 6. As A PC Gamer (2) 199 0 199 2 199 3 199 8
- 7. 陳昇瑋 / 當學術研究者遇見線上遊戲 10
- 8. As A Programmer (1) 10 歲寫 football game with ROM BASIC 國中寫對打遊戲 with dBASE & Pascal 高中寫 RPG with C & Assembly RichardGarriott 1980
- 9. My Role Model in 1990
- 10. As A Programmer (2) 1999 – 2002 資策會教育訓練課程 (C/C++, Winsock Programming, Delphi, C++Builder) 夾帶遊戲設計課程 1999 – 2001《遊戲設計大師》專欄作家 2000 出版《Delphi 深度歷險》 2002 出版《C++Builder 深度歷險》
- 11. 陳昇瑋 / 當學術研究者遇見線上遊戲 16 As A Researcher A killer application 35% Internet users & larger business than movie & music An emerging field E.g., IEEE Transactions on AI and CI in Games since Sep 2008 Asia-based researchers have some niches Large user base (50%) Lots of local game companies It’s fun!
- 12. 陳昇瑋 / 當學術研究者遇見線上遊戲 19 SecurityTopics Game Bot Detection
- 13. 陳昇瑋 / 當學術研究者遇見線上遊戲 20 Game Bots Game bots: automated AI programs that can perform certain tasks in place of gamers Popular in MMORPG and FPS games MMORPGs (Role Playing Games) accumulate rewards in 24 hours a day break the balance of power and economies in game FPS games (First-Person Shooting Games) a) improve aiming accuracy only b) fully automated achieve high ranking without proficient skills and efforts
- 14. 陳昇瑋 / 當學術研究者遇見線上遊戲 21 Bot Detection Detecting whether a character is controlled by a bot is difficult since a bot obeys the game rules perfectly No general detection methods are available today State of practice is identifying via human intelligence Detect by “bots may show regular patterns or peculiar behavior” Confirm by “bots cannot talk like humans” Labor-intensive and may annoy innocent players
- 15. 陳昇瑋 / 當學術研究者遇見線上遊戲 22 CAPTCHA in a Japanese Online Game (CompletelyAutomated PublicTuring test to tell Computers and Humans Apart)
- 16. 陳昇瑋 / 當學術研究者遇見線上遊戲 23 Our Goal of Bot Detection Solutions Passive detection No intrusion in players’ gaming experience No client software support is required Generalizable schemes (for other games and other game genres)
- 17. 陳昇瑋 / 當學術研究者遇見線上遊戲 24 Our Solution I: Traffic Analysis Game client Game server Traffic stream Q: Whether a bot is controlling a game client given the traffic stream it generates? A: Yes or No
- 18. 陳昇瑋 / 當學術研究者遇見線上遊戲 25 Case Study: Ragnarok Online (Figure courtesy of www.Ragnarok.co.kr)
- 19. 陳昇瑋 / 當學術研究者遇見線上遊戲 26 DreamRO -- A screen shot World Map View scope Character Status
- 20. 陳昇瑋 / 當學術研究者遇見線上遊戲 27 Trace Collection Category Tr# ID Avg. Period Avg. Pkt rate Network Human players 8 A, B, C, D 2.6 hr 1.0 / 3.2 pkt/s ADSL, Cable Modem, Campus Network Bots 11 K (Kore) R (DreamRO) 17 hr 1.0 / 2.2 pkt/s 207 hours, 3.8 million packets were traced in total Heterogeneity in player skills and network conditions Category participants Client pkt rate Avg. RTT Avg. Loss rate Human players 2 rookies 2 experts 0.8 ~ 1.2 pkt/s 45 ~ 192 ms 0.01% ~ 1.73% Bots 2 bots 0.5 ~ 1.7 pkt/s 33 ~ 97 ms 0.004% ~ 0.2%
- 21. 陳昇瑋 / 當學術研究者遇見線上遊戲 28 Command Timing Client response time (response time): time difference between the client packet departure time and the most recent server packet arrival time We expect the following patterns: A large number of small response times (bots respond server packets immediately) Regularity in response times Observation bots often issue their commands based on arrivals of server packets, which carry the latest status of the character and environment State UpdateCommandAfter certain time t
- 22. 陳昇瑋 / 當學術研究者遇見線上遊戲 29 CDF of Client Response Times Kore: Zigzag pattern (multiples of a certain value) DreamRO: > 50% response times are very small
- 23. 陳昇瑋 / 當學術研究者遇見線上遊戲 30 Histograms of Response Times 1 ms multiple peaks 1 ms multiple peaks
- 24. 31 Periodograms of Histograms of Response times Player 1 Player 2
- 25. 陳昇瑋 / 當學術研究者遇見線上遊戲 32 Examining the Trend of Traffic Burstiness
- 26. 陳昇瑋 / 當學術研究者遇見線上遊戲 36 An Integrated Classifier Conservative approach (10000 packets): false positive rate ≈ 0% and 90% correct rate Progressive approach (2000 packets): false negative rate < 1% and 95% correct rate
- 27. 陳昇瑋 / 當學術研究者遇見線上遊戲 37 Robustness against Counter Attacks Adding random delays to the release time of client commands Command timing scheme will be ineffective Schemes based on traffic burstiness and human reaction to network conditions are robust Adding random delay to command timing will not eliminate the regularity unless the added delay is longer than the updating interval by orders of magnitude or heavy-tailed However, adding such long delays will make the bots incompetent as this will slowdown the character’s speed by orders of magnitude
- 28. 陳昇瑋 / 當學術研究者遇見線上遊戲 38 The IDC of the original packet arrival process and that of intentionally-delayed versions
- 29. 陳昇瑋 / 當學術研究者遇見線上遊戲 39 Our Solution II: Movement Trajectory Based on the avatar’s movement trajectory in game Applicable for all genres of games where players control the avatar’s movement directly Avatar’s trajectory is high-dimensional (both in time and spatial domain)
- 30. 陳昇瑋 / 當學術研究者遇見線上遊戲 40 The Rationale behind Our Scheme The trajectory of the avatar controlled by a human player is hard to simulate for two reasons: Complex context information: Players control the movement of avatars based on their knowledge, experience, intuition, and a great deal of environmental information in game. Human behavior is not always logical and optimal How to model and simulate realistic movements (for game agents) is still an open question in the AI field.
- 31. 陳昇瑋 / 當學術研究者遇見線上遊戲 41 Bot Detection: A Decision Problem Q: Whether a bot is controlling a game client given the movement trajectory of the avatar? A: Yes / No?
- 32. 陳昇瑋 / 當學術研究者遇見線上遊戲 42 User Movement Trails
- 33. 陳昇瑋 / 當學術研究者遇見線上遊戲 43 3D Path Visualization Tool
- 34. 陳昇瑋 / 當學術研究者遇見線上遊戲 44 Case Study: Quake 2
- 35. 陳昇瑋 / 當學術研究者遇見線上遊戲 45 Data Collection Human traces downloaded from fan sites including GotFrag Quake, Planet Quake, Demo Squad, and Revilla Quake Site Bot traces collected on our own Quake server CR BOT 1.14 Eraser Bot 1.01 ICE Bot 1.0 Totally 143.8 hours of traces were collected
- 36. 陳昇瑋 / 當學術研究者遇見線上遊戲 46 Data Representation (X,Y)(X,Y)t (X,Y) (X,Y)
- 37. 陳昇瑋 / 當學術研究者遇見線上遊戲 47 Aggregate View of Trails (Human & 3 Bots) Human CR Bot Eraser ICE Bot
- 38. 陳昇瑋 / 當學術研究者遇見線上遊戲 48 Trails of Human Players
- 39. 陳昇瑋 / 當學術研究者遇見線上遊戲 49 Trails of Eraser Bot
- 40. 陳昇瑋 / 當學術研究者遇見線上遊戲 50 Trails of ICE Bot
- 41. 陳昇瑋 / 當學術研究者遇見線上遊戲 51 Movement Trail Analysis Activity mean/sd of ON/OFF periods Pace speed/offset in each time period teleportation frequency Path linger frequency/length smoothness detourness Turn frequency of mild turn, U-turn, …
- 42. 陳昇瑋 / 當學術研究者遇見線上遊戲 52 Bot Detection Performance
- 43. 陳昇瑋 / 當學術研究者遇見線上遊戲 53 Step 1. Pace Vector Construction For each trace sn , we compute the pace (distance) in successive two seconds by We then compute the distribution (histogram) of paces with a fixed bin size by where B is the number of bins in the distribution.
- 44. 陳昇瑋 / 當學術研究者遇見線上遊戲 54 Pace Vector: An Example B is set to 200 (dimensions) in this work
- 45. 陳昇瑋 / 當學術研究者遇見線上遊戲 55 Step 2. Dimension Reduction with Isomap We adopt Isomap for nonlinear dimension reduction for Better classifiaction accuracy Lower computation overhead in classification Isomap Assume data points lie on a manifold 1. Construct the neighborhood graph by kNN (k-nearest neighbor) 2. Compute the shortest geodesic path for each pair of points 3. Reconstruct data by MDS (multidimensional scaling) A mathematical space in which every point has a neighborhood which resembles Euclidean space, but in which the global structure may be more complicated. (Wikipedia)
- 46. 陳昇瑋 / 當學術研究者遇見線上遊戲 56 A Graphic Representation of Isomap
- 47. 陳昇瑋 / 當學術研究者遇見線上遊戲 58 PCA (Linear) vs. Isomap (Nonlinear)
- 48. 陳昇瑋 / 當學術研究者遇見線上遊戲 59 Five Methods for Comparison Method Data Input kNN Original 200-dimension PaceVectors Linear SVM Nonlinear SVM Isomap + kNN Isomap-reduced Pace VectorsIsomap + Nonlinear SVM
- 49. 陳昇瑋 / 當學術研究者遇見線上遊戲 60 Evaluation Results Error Rate False Positive Rate False Negative Rate
- 50. 陳昇瑋 / 當學術研究者遇見線上遊戲 62 Evaluation Results Error Rate False Postive Rate False Negative Rate
- 51. 陳昇瑋 / 當學術研究者遇見線上遊戲 63 User BehaviorTopics Game-PlayTime Prediction
- 52. 陳昇瑋 / 當學術研究者遇見線上遊戲 64 Unsubscription Prediction Game improvement Players’ unsubscription low satisfaction Surveys can be conducted to determine the causes of player dissatisfaction and improve the game accordingly More likely to receive useful comments before players quit Prevent VIP players’ quitting (maintain revenue) For “item mall” model, users’ contribution (of revenue) is heavy-tailed Losing VIP players may significantly harm the revenue Network/system planning and diagnosis By predicting “which” players tend to leave the game investigating is there any problem regarding network resource planning, network congestion, or server arrangement
- 53. 陳昇瑋 / 當學術研究者遇見線上遊戲 65 Unsubscription Prediction: Our Proposal Rationale: players’ satisfaction / enthusiasm / addiction to a game is embedded in her game play history Quit in 30 days? Quit Stay Login history Jan Feb Mar Apr May Jun July Aug Sep Oct Nov Dec 2007 Subscription time
- 54. 陳昇瑋 / 當學術研究者遇見線上遊戲 66
- 55. 陳昇瑋 / 當學術研究者遇見線上遊戲 67 World of Warcraft The most popular MMOG for now
- 56. 陳昇瑋 / 當學術研究者遇見線上遊戲 68 Data Collection Methodology Create a game character Use the command ‘who’ The command asks the game server to reply with a list of players who are currently online Write a specialized data-collection program (using C#, VBScript, and Lua)
- 57. 陳昇瑋 / 當學術研究者遇見線上遊戲 70 Trace Summary
- 58. 陳昇瑋 / 當學術研究者遇見線上遊戲 71 福克斯大神之謎？？ (1) ref. http://forum.gamebase.com.tw/content.jsp?no=4715&cno=47150002&sno=75201947 ref. http://www.wings-of-narnia.com/viewtopic.php?t=3012 網友A：不知道在聖光之願部落的玩家有沒有發現到，在新手村薩滿訓練師的後 面，永遠都會站著一個叫「福克斯大神」的獵人玩家！在半年前我到聖光定居時 我在新手村見到他，到現在他仍然還是留守在那個地方……不會暫離, 而且可以觀 察他= =" 這種事該回報給GM嗎？創新手看到他的時候都覺得好恐佈啊囧 網友B：me too 看到的一瞬間 突然起雞皮疙瘩..... 網友C："已離去"玩家的怨念(怨魂@@)嗎? 還是在悲傷愛情故事裡,癡等所愛的另一人? ^^^^^^^^QQ 網友D：哈 線在好多人在看噢 旁邊為了一大群人@@ 觀光景點呀XD
- 59. 陳昇瑋 / 當學術研究者遇見線上遊戲 72 福克斯大神之謎？？ (2) 網友E：我剛剛也有去看了一下 開了一個ID叫做“聽說有鬼”的獸人戰士 坐在他 面前的桶子一直望著他~ 忽然! <暫離>福克斯大神 他蹲下了...隔一分鐘..消失=ˇ=" .. .. 現在我心裡也是毛毛的.. 網友F：好猛鬼啊!!!!!!大神的力量好可怕啊,一堆信眾死在他之前！！！！！！ 網友G：我上次有開過去看，還遇到了兩位同好，看的時候真的蠻不可思議的... 可以列入魔獸10大世界奇觀吧!
- 60. 陳昇瑋 / 當學術研究者遇見線上遊戲 73 福克斯大神與祂的信眾們 -_-
- 61. 陳昇瑋 / 當學術研究者遇見線上遊戲 74
- 62. 陳昇瑋 / 當學術研究者遇見線上遊戲 75
- 63. 陳昇瑋 / 當學術研究者遇見線上遊戲 76 Questionnaire 37% 19% 16% 12% 4% 4%3%2%2%1% WoW 天堂 RO 楓之谷 石器時代 LUNA 神州 其他 洛汗 萬王之王 # samples: 1,747
- 64. 陳昇瑋 / 當學術研究者遇見線上遊戲 77 Reasons for User Unsubscription
- 65. 陳昇瑋 / 當學術研究者遇見線上遊戲 78 Trend of Game Playing Time 37% 28% 20% 9% 6% 沒有特定趨勢，依當時情 況而定 越玩越短， 登入的天數也 越來越少 沒有明顯變化 到後期反而玩得比較多 隨著月份不同而周期性變 化
- 66. 陳昇瑋 / 當學術研究者遇見線上遊戲 79 Logisitic Regression Model for Unsubscription Prediction Significant features (out of > 20 features) Avg. session time Daily session count Variation of the login hour (when the player starts playing a game each day) Variation of daily play time (number of hours) A naive logistic regression model achieves approximately 75% prediction accuracy
- 67. 陳昇瑋 / 當學術研究者遇見線上遊戲 80 Unsubscription Prediction Result
- 68. 陳昇瑋 / 當學術研究者遇見線上遊戲 NetworkingTopics How gamers are aware of service quality? User Perception Measurement
- 69. 陳昇瑋 / 當學術研究者遇見線上遊戲 82 How Gamers are Aware of Service Quality? Real-time interactive online games are generally considered QoS- sensitive Gamers are always complaining about high “ping-times” or network lags Online gaming is increasingly popular despite the best-effort Internet Q1: Are game players really sensitive to network quality as they claim? Q2: If so, how do they react to poor network quality?
- 70. 陳昇瑋 / 當學術研究者遇見線上遊戲 83 Our Conjecture Poor Network Quality Unstable Game Play Less Fun Shorter Game PlayTime strongly associated Verified with real-life game traces
- 71. 陳昇瑋 / 當學術研究者遇見線上遊戲 84 神州 Online ShenZhouOnline A commercial MMORPG in Taiwan Thousands of players online at anytime TCP-based client-server architecture
- 72. 陳昇瑋 / 當學術研究者遇見線上遊戲 85 Trace Collection (20 hours and 1,356 million packets) Session # Avg.Time Top 20% Bottom 20% 15,140 100 min > 8 hours < 40 min
- 73. 陳昇瑋 / 當學術研究者遇見線上遊戲 86 Round-Trip Times vs. Session Time y-axis is logarithemic
- 74. 陳昇瑋 / 當學術研究者遇見線上遊戲 87 Delay Jitter vs. Session Time (std. dev. of the round-trip times)
- 75. 陳昇瑋 / 當學術研究者遇見線上遊戲 88 Hypothesis Testing -- Effect of Loss Rate Null Hypothesis: All the survival curves are equivalent Log-rank test: P < 1e-20 We have > 99.999% confidence claiming loss rates are correlated with game playing times high loss low loss med loss TheCCDF of game session times
- 76. 陳昇瑋 / 當學術研究者遇見線上遊戲 89 Regression Modeling Linear regression is not adequate Violating the assumptions (normal errors, equal variance, …) The Cox regression model provides a good fit Log-hazard function is proportional to the weighted sum of factors Hazard function (conditional failure rate) The instantaneous rate of quitting a game for a player (session) where each session has factors Z (RTT=x, jitter=y, …)
- 77. 陳昇瑋 / 當學術研究者遇見線上遊戲 90 Final Model & Interpretation Interpretation A: RTT = 200 ms B: RTT = 100 ms, other factors same as A Hazard ratio between A and B: exp((log(0.2) – log(0.1)) × 1.27) ≈ 2.4 A will more likely leave a game (2.4 times probability) than B at any moment Variable Coef Std. Err. Signif. log(RTT) 1.27 0.04 < 1e-20 log(jitter) 0.68 0.03 < 1e-20 log(closs) 0.12 0.01 < 1e-20 log(sloss) 0.09 0.01 7e-13
- 78. 陳昇瑋 / 當學術研究者遇見線上遊戲 91 How good does the model fit?
- 79. 陳昇瑋 / 當學術研究者遇見線上遊戲 92 Relative Influence of QoS Factors Latency = 20% Client packet loss = 20% Delay jitter = 45% Server packet loss = 15%
- 80. 陳昇瑋 / 當學術研究者遇見線上遊戲 93 An Index for ShenZhou Online Features derived from real-life game sessions accessible and computable in real time implications: delay jitter is more intolerable than delay RTT: jitter: closs: sloss: round-trip times level of network congestion loss rate of client packets loss rate of server packets
- 81. 陳昇瑋 / 當學術研究者遇見線上遊戲 94 App #1: Evaluation of Alternative Designs Suppose now we have two designs (e.g., protocols) One leads to lower delay but high jitter: 100 ms, 120 ms, 100 ms, 120 ms, 100 ms, 120 ms, 100 ms, 120 ms, … One leads to higher delay but lower jitter: 150 ms, 150 ms, 150 ms, 150 ms, 150 ms, 150 ms, 150 ms, 150 ms, … Which one design shall we choose? time network latency 150 ms
- 82. 陳昇瑋 / 當學術研究者遇見線上遊戲 95 App #2: Overlay Path Selection Internet path delay jitter loss rate score 100 ms (G) 50 ms (P) 5% (P) 3.84 150 ms (A) 20 ms (G) 1% (A) 6.33 200 ms (P) 30 ms (A) 1% (A) 5.43
- 83. 陳昇瑋 / 當學術研究者遇見線上遊戲 96 Player Departure Behavior Analysis Player departure rate is decreasing by time Golden time is the first 10 minutes: the longer gamers play, the more external factors would affect their decisions to stay or leave allocating more resources to players just entered
- 87. 陳昇瑋 / 當學術研究者遇見線上遊戲 100
- 90. 陳昇瑋 / 當學術研究者遇見線上遊戲 資料分析團隊該通常做些什麼？ 玩家層面 DAU, WAU, MAU 上線時間 平均花費 商品層面 每個商品的交易量 每個商品隨著時間交易量 演進 玩家 vs. 商品 玩家對於特定商品的偏好 玩家屬性 (性別、年紀、 等級、職業、是否 VIP)、 購買期間與商品的關係 行銷作法 使用推薦系統來做個人化 推薦商品給玩家 103 X
- 92. 陳昇瑋 / 當學術研究者遇見線上遊戲 以資料分析幫助設計虛擬商品 量化影響虛擬商品銷售好壞的要素 主觀要素 影像訊號要素 提供可以讓設計師參考的設計指引 建構一套系統化的方法，為運行在不同區域, 國家的 遊戲，提供調整虛擬商品設計的準則
- 95. 陳昇瑋 / 當學術研究者遇見線上遊戲 Feature Engineering 108 A feature is a piece of information that might be useful for prediction. Any attribute could be a feature, as long as it is useful to the model. "…some machine learning projects succeed and some fail. What makes the difference? Easily the most important factor is the features used.“ —Pedro Domingos, "A Few UsefulThings to Know about Machine Learning”
- 97. 陳昇瑋 / 當學術研究者遇見線上遊戲 Netflix Taggers 聘請專人依照 SOP (36 pages) 觀賞並標註影片 555 個標籤，76,897 種組合 (2014年一月) 以標籤為基礎建立影片推薦系統
- 98. 陳昇瑋 / 當學術研究者遇見線上遊戲 Netflix Micro-genres for Videos
- 100. 陳昇瑋 / 當學術研究者遇見線上遊戲 113
- 101. 陳昇瑋 / 當學術研究者遇見線上遊戲 女角衣服的風格標籤 俏皮 暗紅 撩人 溫婉 魔女 和風 裸露 辣妹 可愛 火焰 管家 華麗 東洋 誘惑 媚惑 學生 蓬裙 火辣 性感 淘氣 萌萌 制服 彩衣 艷麗 冷豔 惡魔 女傭 夢幻 狂野 神聖 女僕 飄逸 野性 青春 古典 甜美 日式 迷你裙
- 104. 陳昇瑋 / 當學術研究者遇見線上遊戲 虛擬商品銷售指標 (SI) 比較不同時期發售之裝備的銷售優劣 去除發售時間之影響 (1) 去除銷售期間之影響 (2) 去除玩家購買力影響 (3) 每個裝備的銷售指標 SI (Sale Index) 定義為 銷售數量 normalized by (1), (2), and (3)
- 105. 風格 標籤 與SI 之相 關係 數
- 106. 陳昇瑋 / 當學術研究者遇見線上遊戲 彩衣：0.667 誘惑：0.143 俏皮：0.048 火辣：0 冷豔：0.548 夢幻：0.161 俏皮：0.065 裸露：0 SI：0.0621 SI：0.0013
- 107. 陳昇瑋 / 當學術研究者遇見線上遊戲 以風格標籤預測女裝 SI 高低 真實值 總數 高 低 預 測 值 高 19 2 21 低 2 14 16 總數 21 16 準確度：89.2% 靈敏度：90.5% 特異度：90.5% AUC：0.890
- 109. 陳昇瑋 / 當學術研究者遇見線上遊戲 以影像訊號分辨女裝 SI 高低 真實值 總數 高 低 預 測 值 高 16 2 18 低 5 19 24 總數 21 21 準確度：83.3% 靈敏度：88.9% 特異度：76.2% AUC：0.833 略低於風格標籤
- 111. 陳昇瑋 / 當學術研究者遇見線上遊戲 當然，這只是個開始… 開發虛擬商品設計指引 與遊戲企劃與美術人員共同開發更具體的風格標籤 與影像訊號與實務上商品設計之間的關係 分析不同玩家族群對於商品外觀之偏好 男玩家買女裝 vs. 女玩家買女裝 大戶 vs. 偶而購物玩家 跨文化比較 廣告的拍攝