臺灣博碩士論文加值系統

在電子商務環境中，商家在傳送情資時(Message)，內容多數以文字方式呈現，其傳送方式也從原來的網際網路逐漸改以行動方式傳送，因此，帶給商家及消費者莫大的效益，例如，商家可以節省成本，而消費者可隨時、隨地接收行動情資(Mobile Message)，但也因為如此方便，行動情資在不斷的發送下，可能會過於氾濫且無法符合使用者興趣或需求。此外，同樣商品卻有著不同名稱的問題亦可能造成情資推薦不準確。
有鑑於此，本研究提出一個以本體論技術來建構個人化行動情資之推薦機制(PMR)。本研究以本體論(Ontology)技術建置行動情資本體論範本及使用者相關資料，然而為了分析不同的本體論資料間是否相似，因此本研究提出本體論比對技術(Ontology Matching)在項目間進行差異性比對，不過由於在比對過程中本體論結構上的議題仍須探討與解決，因此本研究設計三種不同的本體論結構相似性比對方法進行比對及效能評估，這三種比對方法分別為廣度優先比對(Breadth-First-Matching, BFM)、深度優先比對(Depth-First-Matching, DFM)及節點索引比對(Node-Index-Matching, NIM)。在比對過程中，效能評估主要以比對時所產生的比對次數(MT)為主要評估數據，在本研究提出的三種比對方法實驗結果發現，以節點索引比對方法(NIM)並結合排除空節點(NE)及比對後位置的比對(AIM)的效能最佳，因此較適用於行動環境之情資推薦。
依據上述結果，本研究運用節點索引比對(NIM)方法進行後續之行動情資推薦、效能評估及可推薦清單之實驗。推薦及效能的評估主要是以協同過濾推播模式(CFPM)進行實驗，即依據目標使用者找尋相似之群組使用者，由比對(match)來源端使用者的可推薦清單，產出可推薦清單後再加以推薦，藉此建構並完成個人化行動情資推薦。

It’s observed that the message delivering and product recommendation have moved from Internet to mobile device. Indeed, the customer is highly beneficial because the customer can receive mobile message anytime and anywhere. However, the unsoliciting messages and the synonym terms could cause problems for applying mobile-message recommendation.

To handle these problems, this paper purposes a Personalized Mobile-Message Recommendation (PMR) system. The PMR system applies ontology to construct the user preference profile and the message template which contains the product or service information. To analyze the similarity between ontologies, the ontology-structure matching is studied because it can effectively search the portion of similar or dissimilar among ontology structures and, therefore, the matching process is faster. To speed up the ontology-structure matching performance, this paper proposes three methods for ontology-structure matching and these three methods are (1) Breadth-First-Matching (BFM), (2) Depth-First-Matching (DFM), and (3) Node-Indexing-Matching (NIM). During the matching process, the Match Total (MT), Match Error (ME), and Match Success (MS) are recorded and the performance is evaluated by using MT, ME, and MS. The experimental results show that the proposed methods are practical for mobile message recommendation. Among these three methods, the Node-Index-Matching (NIM) spends the least node-comparing count and it processes faster which will be promising for mobile message recommendation.

For the recommendation part, similar users are clustered into a group based on the ontology tree of target user. The NIM is used for matching and comparing the ontologies. The recommendation is generated from the leaf-node of similar users’ ontology. The recommendation results are evaluated using precision, recall, F1 and the overall coverage. The outcome shows that the proposed PMR system is applicable for the personalized mobile-message recommendation.

摘 要 I
Abstract III
誌謝 IV
目 錄 VI
表 目 錄 IX
圖 目 錄 X
第壹章 緒論 1
1.1導論 1
1.2研究目的 5
1.3研究範圍 6
1.4論文架構 6
第貳章 文獻探討 8
2.1本體論(Ontology) 9
2.1.1本體論定義 9
2.1.2本體論應用 11
2.1.2.1本體論比對(Ontology Matching) 11
2.1.2.2本體論整合(Ontology Integration) 14
2.1.2.3本體論合併(Ontology Merging) 15
2.1.2.4本體論校正(Ontology Alignment) 16
2.1.3本體論其它運用 16
2.1.4本體論在推薦系統的應用 17
2.2本體論比對(Ontology Matching) 19
2.2.1結構性相似比對(Structure Similarity Matching) 19
2.2.2語意性相似比對(Linguistic Similarity Matching) 22
2.2.3本體論案例式比對(Ontology Instance-based Matching) 24
2.2.4本體論比對工具 27
2.2.5本體論比對策略 28
2.3推薦系統(Recommendation Systems, RSs) 29
2.3.1推薦機制 30
2.3.1.1內容導向式推薦(Content-based Filtering, CB) 30
2.3.1.2協同過濾式推薦(Collaborative Filtering, CF) 31
2.3.1.3 混合式推薦系統(Hybrid) 34
2.3.2推薦系統應用 35
2.4行動情資(Mobile Message) 38
2.5點對點環境(Peer-to-Peer Environment, P2P) 43
2.6效能評估(Performance Evaluation) 45
第參章 研究方法 48
3.1 PMR系統架構 48
3.1.1使用階層(Use Layer) 49
3.1.2模組作業階層(Module Operation Layer) 50
3.1.3儲存體階層(Repository Layer) 51
3.2使用者輪廓本體論模組(User Profile Ontology Module, UPOM) 51
3.3情資本體論模組(Message Ontology Module, MOM) 54
3.3.1本體論架構定義 56
3.3.2本體論維護作業 58
3.3.2.1新增本體論節點 58
3.3.2.2刪除情資類別 61
3.4本體論比對及推薦模組(Ontology Matching and Recommendation Module, OMRM) 64
3.4.1內容導向式詢播模型(CBPM) 65
3.4.2協同過濾式推送模型(CFPM) 68
3.4.3本體論比對模組 71
3.4.4.1廣度優先比對(Breadth-First-Matching, BFM) 72
3.4.4.2深度優先比對(Depth-First-Matching, DFM) 74
3.4.4.3節點索引比對(Node-Index-Matching, NIM) 80
3.4.4本體論比對效能及推薦效能評估 84
第肆章 實驗結果 86
4.1實驗資料 86
4.2實驗工具 88
4.3實驗流程 90
4.4比對效能評估 91
4.4.1內容導向式詢播模型(CBPM)實驗評估 95
4.4.1.1CBPM比對效能總結 100
4.4.2協同過濾式推送模型(CFPM)實驗評估 101
4.4.2.1CFPM比對效能總結 109
4.4.3比對效能總結 110
4.5推薦及效能評估 111
4.5.1推薦及效能評估總結 116
4.6產生可推薦清單 117
4.6.1多數相似門檻值(MST) 118
4.7實驗結論 121
第伍章 結論及未來研究 122
5.1未來研究 124
參考文獻 125
附錄1：情資範例本體論 133
附錄2：以User 1為例之使用者輪廓 144

表 目 錄
表1、本體論運用在推薦系統比較表 18
表2、本體論比對工具比較表 27
表3、本體論比對功用差異比較表 28
表4、使用者評比表(本研究假定) 32
表5、改善推薦效能比較表 35
表6、推薦系統特性比較表 36
表7、行動推薦差異對照表 37
表8、行動定位服務應用類型(資料來源：[2]) 39
表9、M-Honeypot測試統計結果(資料來源：[4]) 42
表10、效能評估變數表 47
表11、觸發程式(Trigger)語法變數說明表 53
表12、本實驗使用工具說明表 88
表13、各階層User節點數統計表 91
表14、CBPM及CFPM比對方法一覽表 94
表15、推薦及效能評估使用者一覽表 112
表16、以User 1為例之使用者相似群組一覽表 113
表17、以User 1為例之推薦及效能評估一覽表 114
表18、以User 1為例之比對效能評估一覽表 115
表19、以User 61為例之相似的使用者群組 116
表20、CBPM可推薦之多數相似門檻值(MST)評估表 118
表21、CBPM-MST User 5可推薦清單 119
表22、以User 1為例之相似使用者群組(例舉) 120
表23、以User 1為例之相似使用者群組可推薦清單一覽表 120

圖 目 錄
圖1、研究架構圖 7
圖2、本體論示意圖 10
圖3、全域本體論及區域本體論間比對圖 12
圖4、區域本體論比對圖 13
圖5、本體論整合示意圖 15
圖6、本體論合併示意圖 15
圖7、RDF組成圖 20
圖8、結構相似比對範例 21
圖9、案例比對概念圖(資料來源：[32]) 25
圖10、計算範例(資料來源：[32]) 26
圖11、本體論循序式比對概念圖 28
圖12、本體論平行式比對概念圖 29
圖13、推薦流程概念圖 30
圖14、GPS手機出貨量預測圖(資料來源：Berg Insight[12]) 38
圖15、行動電話使用成長圖(資料來源：國家通訊傳播委員會，NCC) 40
圖16、電信各類服務營收比例(資料來源：國家通訊傳播委員會，NCC) 40
圖17、簡訊成長及獲益圖(資料來源：國家通訊傳播委員會，NCC) 40
圖18、各類電信使用統計表(資料來源：國家通訊傳播委員會，NCC) 41
圖19、以資訊流為主的推播模式 43
圖20、P2P環境架構圖(資料來源：[40]) 45
圖21、效能評估關係圖(資料來源：[19]) 45
圖22、Overall效能評估概念示意圖(資料來源：[19]) 46
圖23、個人化行動情資推薦(PMR)架構圖 49
圖24、使用者輪廓本體論模組(UPOM)流程圖 52
圖25、使用者Ui的使用者輪廓本體論(例舉) 54
圖26、情資本體論模組(MOM)流程圖 55
圖27、情資範例本體論(例舉) 56
圖28、本體論結構組成圖(例舉) 57
圖29、新增節點示意圖 61
圖30、刪除節點示意圖 64
圖31、內容導向式詢播模型(CBPM)架構圖 66
圖32、使用者Ui之使用者輪廓本體論結構圖 67
圖33、情資範例本體論結構圖 67
圖34、協同過濾式推送模型(CFPM)架構圖 68
圖35、使用者UserA之使用者輪廓本體論架構圖 70
圖36、使用者UserB之使用者輪廓本體論架構圖 70
圖37、使用者Ui之使用者輪廓結構更新圖 74
圖38、Protégé-3.3.1介面圖 89
圖39、MySql 介面圖 89
圖40、CBPM實驗流程圖 90
圖41、CFPM實驗流程圖 90
圖42、比對效能實驗流程圖 92
圖43、CBPM實驗流程圖 95
圖44、CBPM-BFM之比對總次數(MT)比較圖 96
圖45、CBPM-BFM之比對成功數(MS)比較圖 96
圖46、CBPM-DFM之比對總次數(MT)比較圖 97
圖47、CBPM-NIM之比對總次數(MT)比較圖 99
圖48、CBPM所有方法之平均比對總次數比較圖 100
圖49、CFPM實驗流程圖 101
圖50、CFPM-BFM以User 1為比對目的端範例之比對總次數比較圖 102
圖51、CFPM-BFM以User 3為比對目的端範例之比對總次數比較圖 102
圖52、CFPM-BFM以User 5為比對目的端範例之比對總次數比較圖 102
圖53、CFPM-BFM之平均比對總次數比較圖 103
圖54、CFPM-BFM之平均比對成功數(MS)比較圖 103
圖55、CFPM-DFM以User 1為比對目的端範例之比對總次數比較圖 104
圖56、CFPM-DFM以User 3為比對目的端範例之比對總次數比較圖 105
圖57、CFPM-DFM以User 5為比對目的端範例之比對總次數比較圖 105
圖58、CFPM-DFM之平均比對總次數比較圖 105
圖59、CFPM-DFM之平均比對成功數(MS)比較圖 106
圖60、CFPM-NIM以User 1為比對目的端範例之比對總次數比較圖 107
圖61、CFPM-NIM以User 3為比對目的端範例之比對總次數比較圖 107
圖62、CFPM-NIM以User 5為比對目的端範例之比對總次數比較圖 108
圖63、CFPM-NIM之平均比對總次數比較圖 108
圖64、CFPM-NIM之平均比對成功數(MS)比較圖 109
圖65、CFPM三種比對方法之平均比對總次數(MT)比較圖 110
圖66、CFPM三種比對方法之平均比對成功數(MS)比較圖 110
圖67、可推薦清單步驟 117

[1]馮輝文、吳明蔚(2008)，無線通訊(Introduction to wireless and mobile system, 2e)，高立圖書有限公司。
[2]楊森、楊淑慧、金微華、陳重亨(2008)，行動通訊大商機—新市場、新機會與產業預測，財信出版有限公司。
[3]陳育純(2005)，以行動用戶為主之個人化區域活動推薦系統，朝陽科技大學資訊管理系碩士論文，臺中。
[4]張翰綸(2008)，濫發電子訊息法律管制之實效性，國立高雄第一科技大學科技法律研究所碩士論文，高雄。
[5]劉雅茹(2007)，利用本體論建構群組偏好樹於產品推薦之研究，朝陽科技大學資訊管理系碩士論文，臺中。
[6]鄒孟訓(2006)，含可調整及分散式比對方法的知識本體校準系統，國立中央大學資訊工程系碩士論文，桃園。
[7]歐仁德(2006)，結合本體論與通用個人輪廓於個人化推薦之研究，朝陽科技大學資訊管理系碩士論文，臺中。
[8]魏家惠(2004)，個人化行動廣告推薦機制之研究，朝陽科技大學資訊管理系碩士論文，臺中。
[9]簡維克、林雅惠(2005)，「小心！垃圾電子訊息正侵入你的手機－以財產權及隱私權面向論立法規範垃圾簡訊之必要性」，清華科技法律與政策論叢，第二卷，第三期，第87頁。
[10]Alsayed Algergawy, Eike Schallehn, and Gunter Saake, 2008, “A sequence-based ontology matching approach,” Proceedings of the 18th European Conference on Artificial Intelligence of the Fourth International Workshop on Contexts and Ontologies, pp. 26-30.
[11]Dominik Benz, Karen Tso, and Lars Schmidt Thieme, 2007, “Supporting collaborative hierarchical classification bookmarks as an example,” Computer Networks, vol. 51, no. 16, pp. 4574-4585.
[12]Berg Insight, http://www.berginsight.com/.
[13]Yukun Bao, Hua Zou, and Jinlong Zhang, 2005, “Using PACT in an e-commerce recommendation system,” Proceedings of the 7th International Conference on Electronic Commerce (ICEC), pp. 466-470.
[14]Chris Cornelis, Jie Lu, Xuetao Guo, and Guanquang Zhang, 2007, “One-and-only item recommendation with fuzzy logic techniques,” Information Sciences, vol. 177, no. 22, pp. 4906-4921.
[15]Namyoun Choi, Il Yeol Song, and Hyoil Han, 2006, “A survey on ontology mapping,” ACM Special Interest Group on Management of Data Record (SIGMOD), vol. 35, no. 3, pp. 34-41.
[16]Silvana Castano, Alfio Ferrara, Davide Lorusso, and Stefano Montanelli, 2008, “On the ontology instance matching problem,” Proceedings of the 19th International Conference on Database and Expert Systems Application (DEXA''08), pp. 180-184.
[17]Yoon Ho Cho and Jae Kyeong Kimb, 2004, “Application of web usage mining and product taxonomy to collaborative recommendations in e-commerce,” Expert Systems with Applications, vol. 26, no. 2, pp. 233-246.
[18]Anhai Doan, Jayant Madhava, Pedro Domingos, and Alon Halevy, 2004, “Ontology matching: A machine learning approach,” Proceedings of the Springer, pp. 397-416.
[19]Hong-Hai Do, Sergey Melnik, and Erhard Rahm, 2002, “Comparison of schema matching evaluations,” Proceedings of the GI-Workshop Web Databases (German Informatics Society), pp. 221-237.
[20]Hong-Hai Do and Erhard Rahm, 2002, “COMA - A system for flexible combination of schema matching approaches,” Proceedings of the 28th VLDB Conference, Hong Kong, China.
[21]Nicola Guarino and Pierdaniele Giaretta, 1995, “Ontologies and knowledge bases, towards a terminological clarification,” Knowledge Building and Knowledge Sharing, pp. 25-32.
[22]Peter Haase, Andreas Hotho, Lars Schmidt Thieme, and York Sure, 2005, “Collaborative and usage-driven evolution of personal ontologies,” Second European Semantic Web Conference, pp. 486-499.
[23]Akm Saiful Islam and Michael Piasecki, 2008, “Ontology based web simulation system for hydrodynamic modeling,” Simulation Modeling Practice and Theory, vol. 16, no. 7, pp. 754-767.
[24]Siddharth Kaza and Hsinchun Chen, 2008, “Evaluating ontology mapping techniques - An experiment in public safety information sharing,” Decision Support Systems, vol. 45, no. 4, pp. 714-728.
[25]Duen Ren Liu and Ya Yueh Shih, 2005, “Hybrid approaches to product recommendation based on customer lifetime value and purchase preferences,” The Journal of Systems and Software, vol. 77, no. 2, pp. 181-191.
[26]Hong Joo Lee and Sung Joo Park, 2007, “MONERS: A news recommender for the mobile web,” Expert Systems with Applications, vol. 32, no. 1, pp. 143-150.
[27]Li Hua Li, Fu Ming Lee, and Shang Chi Chan, 2008, “The blog-article recommendation system(BARS),” Proceedings of the 2008 IAENG International Conference on Internet Computing and Web Services (ICWS), pp. 771-776.
[28]Qianhui Althea Liang and Herman Lam, 2008, “Web service matching by ontology instance categorization,” IEEE International Conference on Services Computing, pp. 202-209.
[29]Tong Queue Lee, Young Park, and Yong Tae Park, 2008, “A time-based approach to effective recommender systems using implicit feedback,” Expert Systems with Applications, vol. 34, no. 4, pp. 3055-3062.
[30]Chunyan Miao, Qiang Yang, Haijing Fang, and Angela Goh, 2006, “A cognitive approach for agent-based personalized recommendation,” Knowledge-based Systems, vol. 20, no. 4, pp. 397-405.
[31]Malgorzata Mochol and Elena Paslaru Bontas Simperl, 2006, “A high-level architecture of a metadata-based ontology matching framework,” Proceedings of the 17th International Conference on Database and Expert Systems Applications (DEXA''06), pp. 354-358.
[32]Sabine Massmann and Erhard Rahm, 2008, “Evaluating instance-based matching of web directories,” Proceedings of the 11th International Workshop on Web and Databases (WebDB 2008).
[33]Sergey Melnik, Hector Garcia-Molina, and Erhard Rahm, 2002, “Similarity flooding: a versatile graph matching algorithm and its application to schema matching,” Proceedings of the 18th Data Engineering International Conference (ICDE), pp. 117-128.
[34]Saverio Perugini, Marcos André Gonçalves, and Edward A. Fox, 2004, “Recommender systems research: A connection-centric survey,” Journal of Intelligent Information Systems, vol. 23, no. 2, pp. 107-143.
[35]Badrul Sarwar, George Karypis, Joseph Konstan, and John Riedl, 2000, “Analysis of recommendation algorithms for e-commerce,” Proceedings of ACM E-commerce 2000 Conference, pp. 158-167.
[36]Badrul Sarwar, George Karypis, Joseph Konstan, and John Riedl, 2000, “Application of dimensionality reduction in recommender system--A case study,” Proceedings of the ACM WebKDD 2000 Web Mining for E-Commerce Workshop.
[37]Xiaomeng Su and Jon Atle Gulla, 2005, “An information retrieval approach to ontology mapping,” Data and Knowledge Engineering, vol. 58, no. 1, pp. 47-69.
[38]Junli Wang, Zhijun Ding, and Changjun Jiang, 2006, “GAOM: Genetic algorithm based ontology matching,” Proceedings of the 2006 IEEE Asia-Pacific Conference on Services Computing (APSCC''06), pp. 617-620.
[39]Sung Shun Weng and Hui Ling Chang, 2008, “Using ontology network analysis for research document recommendation,” Expert Systems with Applications, vol. 34, no. 3, pp. 1857-1869.
[40]Bo Xie, Peng Han, Fan Yang, Rui Min Shen, Hua Jun Zeng, and Zheng Chen, 2007, “A distributed collaborative-filtering neighbor-locating algorithm,” Information Sciences, vol. 177, no. 6, pp. 1349-1363.
[41]Blanco Fernández Yolanda, J. Pazos Arias José, Gil Solla Alberto, Ramos Cabrer, Manuel López Nores Martín, García Duque Jorge, Fernández Vilas Ana, Díaz Redondo Rebeca, and Bermejo Muñoz Jesús, 2008, “A flexible semantic inference methodology to reason about user preferences in knowledge-based recommender systems,” Knowledge-based Systems, vol. 21, no. 4, pp. 305-320.
[42]Soe Tsyr Yuan and Chiahsin Cheng, 2004, “Ontology-based personalized couple clustering for heterogeneous product recommendation in mobile marketing,” Expert Systems with Applications, vol. 26, no. 4, pp. 461-476.
[43]Soe Tsyr Yuan and You Wen Tsao, 2003, “A recommendation mechanism for contextualized mobile advertising,” Expert Systems with Applications, vol. 24, no. 4, pp. 399-414.
[44]Wan Shiou Yang, Hung Chi Cheng, and Jia Ben Dia, 2008, “A location-aware recommender system for mobile shopping environments,” Expert Systems with Applications, vol. 34, no. 1, pp. 437-445.
[45]Lan Zhao and Anna Nagurney, 2007, “A network equilibrium framework for Internet advertising: Models, qualitative analysis, and algorithms,” European Journal of Operational Research, vol. 187, no. 2, pp. 456-472.
[46]Rubo Zhang, Ying Wang, and Jing Wang, 2008, “Research on ontology matching approach in semantic Web,” Proceedings of the 2008 International Conference on Internet Computing in Science and Engineering, pp. 254-257.
[47]Vincent Schickel Zuber and Boi Faltings, 2007, “Using hierarchical clustering for learning the ontologies used in recommendation systems,” Proceedings of the 13th ACM SIGKDD Special Interest Group on Knowledge Discovery and Data mining, pp. 599 - 608.
[48]Yiyang Zhang and Jianxin Jiao, 2007, “An associative classification-based recommendation system for personalization in B2C e-commerce applications,” Expert Systems with Applications, vol. 33, no. 2, pp. 357-367.