English  |  正體中文  |  简体中文  |  Post-Print筆數 : 20 |  Items with full text/Total items : 90058/119991 (75%)
Visitors : 24100185      Online Users : 2258
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version
    政大機構典藏 > 商學院 > 資訊管理學系 > 期刊論文 >  Item 140.119/68327
    Please use this identifier to cite or link to this item: http://nccur.lib.nccu.edu.tw/handle/140.119/68327

    Title: 多樣需求與資源環境中之智慧型e化服務決策研究-以垃圾桶模式為基礎
    Authors: 苑守慈;呂知穎
    Contributors: 資管系
    Keywords: e化服務;垃圾桶模式;智慧型代理人;增強式學習
    e-Services;garbage can model;intelligent agent;reinforcement learning
    Date: 2008-07
    Issue Date: 2014-08-06 14:01:11 (UTC+8)
    Abstract: 為因應人類生理或心理上的需求,而產生了形形色色之服務。隨著高科技不斷地發展,人類的未來生活,將會是充滿e化服務的生活環境。在此環境中,並非所有人均能了解各應用服務,更不知該選擇何服務才能滿足自身之多重需求。本論文設計一決策機制,當人們有多重需求時,能考慮有形及無形資源之有效利用,並考量不同個體之使用偏好及興趣,提供適合個人的e化服務決策建議。本論文之應用環境,符合垃圾桶模式中的無政府狀態之三大特性,然而原垃圾桶決策方式卻不適用於個人。因此,本論文之主體為一智慧代理人,將以垃圾桶模式的決策原理做為基礎,並對其加以修改,分為二階段的決策過程。在第一階段,將使用一考量資源使用效率之task-chosen演算法,並搭配增強式學習中之AH-learning演算法;在第二階段,則是使用BDI代理人的架構。本研究所提出之提供e化服務建議的決策機制,預期將促使應用服務能不斷地創新及進步,並使資源獲得更有效之利用,使得人類擁有高品質的生活環境。
    There are manifold services to fulfill people's physical and mental needs. Through the continual development of high technique, people will live in the environment surrounding e-services in the future. In this environment, it is hard for everyone to understand all e-services and choose a service to fulfill his/her multiple needs. Therefore, the paper presents a decision mechanism which provides a suitable e-service strategy for people when they have the multiple needs, considering the uses of resources (tangible and intangible) and different preferences and interests for different people. This paper's application environment satisfies the three general properties of an organized anarchy of "Garbage Can Model". This paper extends the model to accommodate its application to individuals in terms of an intelligent agent. The intelligent agent uses a two-phase decision process. The first phase is a task-chosen algorithm considering resource utility and AH-learning in the context of reinforcement learning. The second phase then exerts the BDI reasoning. This paper presents a decision strategy providing e-service tactics (that can use resources effectively) and enabling people to enjoy high quality life.
    Relation: 資訊管理學報, 15(3), 49-82
    Data Type: article
    Appears in Collections:[資訊管理學系] 期刊論文

    Files in This Item:

    File Description SizeFormat
    4982.pdf4426KbAdobe PDF561View/Open

    All items in 政大典藏 are protected by copyright, with all rights reserved.

    社群 sharing

    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback