• Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 1
  • 1
  • Tagged with
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • About
  • The Global ETD Search service is a free service for researchers to find electronic theses and dissertations. This service is provided by the Networked Digital Library of Theses and Dissertations.
    Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
1

多人線上戰鬥競技場遊戲之團隊成員推薦機制 / A Team Member Recommender System for Multiplayer Online Battle Arenas

周佩諄, Chou, Pei Chun Unknown Date (has links)
近幾年來遊戲軟硬體的進步以及遊玩人數的增加,虛擬世界中的使用者行為已經開始受到注目,也有研究指出人們在虛擬世界的行為會反應他們在現實世界的行為並且交互影響。現今最熱門的線上遊戲更是提供多樣化的機制讓玩家們進行合作、競爭、交流等活動,遊戲開發者也會根據不同的目的開始分析玩家的行為,希望能藉此發現遊戲中更多的可能性。 遊戲的種類繁多,遊玩機制也相當多元,目前是以MOBA這類的線上遊戲最為熱門、擁有最多的玩家基數,MOBA是基於團隊合作的對戰型遊戲,玩家可以自由選擇多種職業(或稱作角色)的其中一種並和其他4位玩家組成隊伍,而對手也是同樣由5位玩家組成的隊伍。這類遊戲最大特色是職業的組合關係以及玩家之間的合作關係。在各個遊戲論壇或電競場合中,玩家們對於找出最佳的團隊組成或遊戲技巧提高勝率的分析相當熱衷,但在學術研究領域上目前針對線上遊戲團隊還沒有太多深入的研究。 本研究的目標旨在提出一個結合資料探勘與社群網路分析的方法來分析玩家與團隊績效之間的關係,並用於團隊績效預測與團隊組成上,藉此進行隊友的推薦。首先從抓取來的資料中取出三種玩家與英雄之間的關係,考量玩家的合作關係與英雄的組合關係,藉此篩選出具有高相關度的玩家作為推薦候選人。而在團隊績效預測的部分,取出對玩家個人表現或團隊表現具有影響的特徵值,並分析勝利的玩家或團隊通常會具備什麼樣的特質,再進行團隊表現的預測模型的建置。最後再結合兩者推薦出適合此隊伍的隊友供團隊選擇。 / Multiplayer online battle arenas (MOBA) is a subgenre of strategy games and has become the most popular online game genres recently. Teams of players could fight against each other in arena environments. To find good team members when playing MOBA is a challenge. In this thesis, we proposed a team member recommender mechanism to recommend team members for MOBA. The proposed mechanism first takes the team chemistry into consideration and generates the candidates based on the cooperation history among players and associated heroes. Then the proposed win/lose prediction model is employed to predict the win rate of each candidate by considering characteristics and proficiency of players and associated heroes. The recommended team members are ranked according to the predicted win rates. The experiments show that the proposed win/lose prediction model achieves approximately 91.6% accuracy and our mechanism could recommend players who have close cooperation with query players instead of considering the win rate only. Our proposed method could help the team formation and may enhance team performance of the on-line game.

Page generated in 0.0216 seconds