English  |  正體中文  |  简体中文  |  Items with full text/Total items : 90120/105277 (86%)
Visitors : 8143929      Online Users : 1732
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


    Please use this identifier to cite or link to this item: http://asiair.asia.edu.tw/ir/handle/310904400/9604


    Title: 應用劇本導向互動式代理人技術於 PULL機制為基礎的推薦系統之研究
    Authors: 洪振偉
    Contributors: 資訊學院
    資訊工程學系
    Keywords: 劇本導向互動式代理人
    PULL 模式推薦系統
    推薦機制
    e-Novel 推薦系統
    Scenario interactive agent,
    PULL-based recommendation system,
    e-Novel recommendation system
    recommendation mechanism
    Date: 2008
    Issue Date: 2010-05-13 11:02:14 (UTC+8)
    Abstract: 本計畫的目的在於研究如何應用「劇本導向互動式代理人」相關技術於一個PULL模式的網際網路推薦系統,並且實際開發一個網路小說推薦系統來驗證本計畫的可應用性。本計畫首先將提出一個「PULL 模式為基礎之劇本導向代理人推薦系統架構」,在此架構中將明確地規劃設計一個劇本導向多代理人系統,以及參與此系統之各個軟體代理人的角色和所負責的任務。而在此架構中,多代理人之間的互動乃是基於一個PULL 模式的推薦機制,意即客戶端將透過個人化軟體代理人向外界發佈需求,再由伺服器端的軟體代理人開啟劇本代理人,劇本代理人將執行知識專家所撰寫之劇本,依照劇本的內容代替專家,向客戶端使用者推薦相關的知識。
    本計畫也將依照此PULL 模式為基礎之劇本導向代理人推薦系統架構,實際應用於開發一個網路小說推薦系統,名為e-Novel 推薦系統。透過網際網路向廣大使用者展示本身創意的創意家日漸增加,在本計畫所開發之網路社群中,線上作家可以編輯向讀者展示並且推薦小說的劇本,再透過社群中的e-Novel 推薦系統,利用軟體代理人向已經註冊為會員之線上讀者推銷小說,在推薦的過程中劇本代理人能夠持續地獲得與讀者互動的回饋資訊,如此將作為線上作家修正劇本的依據,以達到未來更為精確的推薦。此外,讀者亦可以透過個人化代理人發佈本身的閱讀偏好,以及擁有權限可以允許或是拒絕作家的推薦。藉由e-Novel 推薦系統,讀者可以經由作家的推薦找到最符合自己愛好的作品,避免浪費過多的時間在網路上搜尋小說,而作家亦可以透過推薦系統的回饋資訊得到目前大多數讀者的喜好,而能夠找出潛在的讀者。
    This project proposal is aimed to investigate how to apply Scenario Interactive Agent in PULL-based recommendation systems. Furthermore, this project will develop an e-Novel recommendation system to demonstrate the usability of this proposal. In this proposal, the scenario interactive agent architecture of a PULL-based recommendation system is firstly proposed. In this architecture, domain experts write down their domain knowledge in proposed agent scenario statements and then software engineers can write tools to translate these scenario statements into instructions for driving interactive agent. The interactive agent then recommends clients the domain expert’s knowledge by parsing the scenario. The cooperation among agents in this architecture is based on PULL model. In the client site, a personal agent is able to publish the user’s preference. The server agent subscribes the client’s preference and then creates scenario interactive agents to interact with clients. An e-Novel recommendation system will be implemented by following the architecture proposed in this project. In this system, novel writers edit recommendation scenarios to drive software agents to interact with readers. During the interaction between the agent and the reader, the agent can promote the writer’s novel for the reader. Moreover, the reader can accept or turn down the recommendation by using his personal agent.

    In this system, a novel writer edits advertisement of his novel by using a scenario editor. A reader receives promotion when he uses personal agent to ask for advertisement information of novels. Then the e-Novel system creates interactive agent to promote advertisement of the writer for the reader. The interactive agent in this system also collects the reader’s feedbacks for the writer to refine his advertisements.
    Appears in Collections:[資訊工程學系] 科技部研究計畫

    Files in This Item:

    File Description SizeFormat
    97洪振偉1.doc21KbMicrosoft Word567View/Open
    97洪振偉2.doc23KbMicrosoft Word412View/Open
    index.html0KbHTML172View/Open


    All items in ASIAIR are protected by copyright, with all rights reserved.


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