近年來，情境感知在很多應用中皆扮演著重要角色，這些情境感知應用系統可以讓其所提供的服務更貼近使用者的需求，提昇服務的價值。以本篇論文中的故宮博物院為例，參觀者不可能在有限的時間觀賞所有文物，如何根據使用者的個人屬性取得其最可能會喜愛的文物，並推薦給使用者觀賞是博物館建置適性化導覽系統最主要的功能。本篇論文的目的即是在博物館使用情境中建構一個適性化導覽的架構。
為了達到適性化導覽，有兩個主要的議題將被討論。第一個是抓取與表示文物所隱含的知識，第二個是將這些文物知識與參觀者個人屬性資料結合以計算其之間的相似程度。一些初始化的實作也被呈現在此論文中，我們希望這將有助博物館建構適性化導覽系統。

In recent years, context-awareness has played a very significant role in many applications of smart room. These applications can make one computer system adapt to users’ need and provide value-added services to people. In museums, visitors can see and admire various kinds of history relics, but it is impossible to see all of them. Therefore, to provide a context-aware guide for every individual visitor is a main topic for museums.
This research presents an implementation framework for museums to construct their context-aware guide system which retrieves history relics according to visitors’ properties. In order to complete this work, two issues will be addressed. First of all is to capture knowledge of history relics, and second issue is to represent visitor profiles and items’ knowledge in the same system. We will use ontology to model these concepts and Spreading Activation to retrieve history relics.
In this research, an initial work will be presented to illustrate how to capture items’ knowledge in museum. And we hope that this workable framework is useful for museums to develop their guide system.

[1] Brown, P.J., Bovey, J.D. Chen, X. Context-Aware Applications: From the Laboratory to the Marketplace. IEEE Personal Communications, 4(5) 58-64,1997.
[2] Castells, P., Fernández, M., Vallet, D., Mylonas, P., Avrithis, Y.: Self-Tuning Personalized Information Retrieval in an Ontology-Based Framework. 1st IFIP International Workshop on Web Semantics (SWWS 2005). LNCS Vol. 3532 (2005) 455-470.
[3] Chen, H., Finin, T. and Joshi, A. An ontology for context-aware pervasive computing environments. The Knowledge Engineering Review, Cambridge University Press, Vol. 18, pp.197–207, 2003.
[4] Cohen, P. R., AND Kjeldsen, R. Information retrieval by constrained spreading activation in semantic networks. Znf. Prccess. Manage. 23, 2 (1987), 255-268.
[5] Crestani, F. Application of Spreading Activation Techniques in Information Retrieval. Artificial Intelligence Review, 11(6): 453-482, 1997.
[6] Crestani, F. and Lee, P. L. Searching the web by constrained spreading activation. Inf. Proc. Manage. 36, 585–605, 2000.
[7] Definition of the CIDOC Conceptual Reference Model. http://cidoc.ics.forth.gr/, 2007-05-30.
[8] David Vallet, Pablo Castells, Miriam Fernández, Phivos Mylonas. Personalized Content Retrieval in Context Using Ontological Knowledge. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, Vol. 17, No. 3, MARCH 2007.
[9] Gruber, T. R. (1993). A Translation Approach to Portable Ontology Specifications. Knowledge Acquisition, 5, (2):199-220, 1993.
[10] D. Godoy and A. Amandi, Modeling user interests by conceptual clustering, Information Systems 31(4-5), 247–265, 2006.
[11] Hatala, M. and Wakkary, R. "Ontology-based user modeling in an augmented audio reality system for museums," User Modeling and User-Adapted Interaction. 2005.
[12] Hess CK, Campbell RH (2003) A context-aware data management system for ubiquitous computing applications. In: Proceedings of the 23rd International Conference on Distributed Computing Systems, Providence, RI, 19–22 May 2003.
[13] Nathalie Bricon-Souf, Conrad R. Newman, Context awareness in health care: A review, International Journal of Medical Informatics, v 76, n 1, January, 2007, p 2-12.
[14] protégé. http://protege.stanford.edu/, 2007-05-30.