English  |  正體中文  |  简体中文  |  Items with full text/Total items : 90120/105277 (86%)
Visitors : 8130895      Online Users : 80
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/310904400/9609


    Title: 應用知識導向推薦技術於互動式代理人系統之研究 - 以eNovelAdvisor為例
    Authors: 洪振偉
    Contributors: 資訊學院
    資訊工程學系
    Keywords: 推薦系統
    知識導向推薦機制
    互動式代理人
    eNovelAdvisor
    recommender system,
    knowledge-based recommendation,
    interactive software agent,
    Date: 2008
    Issue Date: 2010-05-13 11:32:48 (UTC+8)
    Abstract: 推薦系統的主要概念在於能夠從大量的資料中搜尋並推薦使用者合適的解答。而推薦系統可以區分為三類:「協同式」、「內容導向」以及「知識導向」推薦系統,其中知識導向推薦系統主要用於知識性的資訊或知識性商品的推薦。知識導向推薦的特色在於引導使用者描繪出自身的需求,並且推薦系統透過知識庫幫助使用者推薦產品。為了瞭解使用者的需求,通常都會利用問卷或是對話框( Dialog )與人互動,系統必須具備推理能力將互動的回饋解釋轉換成使用者的喜好,藉由使用者的限制條件進一步計算出滿足使用者需求的答案。
    本計畫的研究目的在於應用知識導向推薦機制於劇本互動式軟體代理人系統中,並且以網路小說社群為例,實作eNovelAdvisor 軟體代理人。對於讀者而言,面對網路上大量的創意作品,往往僅能透過作品分類、線上排行以及簡單的搜尋條件讓系統列出作品清單,然而讀者面對清單也不知該如何挑選。其實讀者挑選知識性商品時,若作者能夠解說與推薦,相信能讓讀者正確地找到合適的作品。當系統初步挑選可能的小說清單後,讀者可以透過與eNovelAdvisor 進行互動,其互動模式必須包含「問卷」以及「解說」。其中,eNovelAdvisor 以問卷方式可以獲得讀者互動過程的回饋資料,而回饋資料將由eNovelAdvisor 導入Knowledge-based filtering,來再次過濾出合適的小說,當讀者挑選了適合的作品之後,可以要求eNovelAdvisor 對該作品進行解說,以便加強讀者對該作品的忠誠度。
    The concept of recommender systems is to provide advice to users about information from a large number of data. The well-known types of recommender systems are collaborative-, content-based, and knowledge-based type. The third type, knowledge-based recommender system, uses knowledge of users and items/products to perform a knowledge-based filtering technology to generating an advice. Studies have shown that knowledge-based recommender systems can be well applied on complex products such as financial services, digital products, and literatures, because users purchasing or searching these complex products need the explicit knowledge.

    This proposal is aimed to investigate how to apply knowledge-based recommendation in the interactive software agent system. Furthermore, this project will develop an eNovelAdvisor software agent for an e-Novel system. The e-Novel system contains a number of novels for the Internet readers. A reader can firstly get a list of novels with simple criteria. As the reader chooses one novel, the eNovelAdvisor will present the novel for him and list novels that fulfill certain reader’s quality requirements. Moreover, eNovelAdvisor explains solutions for the reader if he needs. The explicit interaction between eNovelAdvisor and the reader is able to help him find novels.
    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4.doc29KbMicrosoft Word577View/Open
    97洪振偉5.doc30KbMicrosoft Word422View/Open
    index.html0KbHTML159View/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