More and more corporations deem knowledge not only as their nuclear competitiveness when the face challenge, but also as an intangible asset. Each corporation has different demand and urgency for knowledge management. To realize its demand, you must have enough information first to understand its own knowledge. Therefore, some scholars advance a concept to use ¡§Knowledge Map¡¨ to depict the knowledge a corporation owns and thus help the corporation to find out the distribution and intensity of its knowledge. This study submits a set of methods to construct knowledge map and establishes dimensions of knowledge through literature review and experts¡¦ suggestions. Using this category and knowledge measurement index, a questionnaire evaluation distribution and intensity of a corporation¡¦s knowledge has been established. Academically, this questionnaire can be a reference for relevant studies about constructing knowledge map. In practice, corporations can also use this evaluation tool to conduct knowledge measurement, management and enhancement. In addition, this study has chosen five kinds of industries to conduct a survey and experimental research with this questionnaire. The result finds that there are different distributions and intensity of knowledge to certain extends between knowledge-intensive industries and non-knowledge-intensive industries. This could be a reference for further related study.

In this thesis, we propose a knowledge map integration system to merge distributed knowledge maps into a global knowledge map based on the concept mapping methodology. This system performs the functions of knowledge map integration and knowledge map maintenance. The knowledge map integration function integrates different local knowledge maps specified by distributed organizations into a global knowledge map, and knowledge seekers can access the overall knowledge structure about the domain knowledge. Besides, the local knowledge maps in different organizations vary dynamically due to accumulation of information. Consequently, the demand for knowledge map maintenance increases in order to keep the global knowledge map up to date. The function of knowledge map maintenance can update the variations of every local knowledge map, and change the global structure simultaneously. The knowledge map integration system is evaluated by master thesis repository at National Central Library, and we obtain good results.

In the coming knowledge-based economy era, knowledge structure map (KSM) has becoming more and more important. If learners doing learning without the support of knowledge structure map, it will cause learning alone problem. In order to construct a real KSM, we targeted the MIS domain. By using the National Dissertation and Thesis Abstract System as input source, we first extract different research subjects from keywords and then calculate the relation strength between each keyword pairs. An automatic approach has been developed for constructing KSM for different periods of time. The constructed KSM can help learners to reduce learning alone and provide a good reference for new researchers to seek for related research directions. The proposed method can also be applied to enterprises. They can adopt this method to construct any specific KSM corresponding to their professional domain, the constructed KSM would help new employee to learn better. Furthermore, with the support of KSM, CEO can make a better decision as the KSM would contain internal and external competitive advantages about future directions.

This thesis proposes a knowledge management technique, called knowledge map management system, which consists of three components: knowledge navigation, knowledge seeking, and learning history advisory. The knowledge navigation function helps knowledge seekers to understand the knowledge structure. Similarly, the knowledge-seeking component helps knowledge seekers to retrieve knowledge with its structure. The learning adviser generalizes the knowledge access pattern in problem solving history and advises knowledge in the problem solving process. In this study, we prototype the knowledge map management system to facilitate knowledge sharing activities. In order to keep the knowledge map up to date, we also propose the incremental approach to maintaining knowledge structure with the addition of knowledge artifacts. The knowledge map creation and maintenance functions are evaluated using documents collected from SCTNet and master thesis repository at National Central Library, and result in encouraging results.

Abstract It likes a knowledge ¡§Yellow Pages ¡¨, knowledge map, indicates where is knowledge and how to get it, but doesn¡¦t contain knowledge. The principal purpose of a knowledge map is showing domain expert when someone need expertise. The resources of teachers¡¦ knowledge map, teachers¡¦ professional information, are fragmented by geographic condition. The map is piece not complete one. As rapid development of Internet, the rich webs contents provide a new way to build global teachers¡¦ knowledge map. The goal of this research is constructing¡yTeachers¡¦ Knowledge Map¡zfor sufficient knowledge sharing environment by collecting teachers¡¦ relative information from the web pages automatically and integrating plentiful Internet resource. There are four main purposes of this research, include (1) getting teachers¡¦ vita from web gages. (2) using teachers¡¦ personal vita and others webs¡¦ resources to construct teacher¡¦s professional specialty, and indicate research issues of teachers. (3) reflecting teachers¡¦ social network by web pages to show social information of individual teacher or group. Teachers¡¦ social network can provide information of how to get the expertise. (4) integrating prior purposes to create useful teachers¡¦ knowledge map for sufficient knowledge sharing environment.

Abstract Knowledge map, like the ¡§Yellow Pages¡¨ of knowledge, indicates where knowledge is and how to get it, but doesn¡¦t contain knowledge. The principal purpose of a knowledge map is to show domain expert when someone need expertise. The principal purpose of a knowledge map is to enhance the efficiency to find the exact expertise someone need. In this digital age, it is a trend for e-learning learners to search knowledge on the Internet. However, when learners try to explore knowledge, they will confront the two important problems:¡ucognitive disorientation¡v and ¡uinformation overloading¡v. This research bases on the function of search engine on the Internet, extract the keywords on the web document, and then analyze the relationship between the keywords appearing on web page. So, we can develop the process of knowledge mapping to construct integrated Knowledge Map (KM). It can reduce the cost and time that is essential for the traditional method. With guidance of the KM, learners can find specific knowledge or discover knowledge relationships more effectively when exploring on the Internet. The contributions of this survey are as followings: Collecting keywords of knowledge automatically, Constructing knowledge relation graph, Constructing knowledge hierarchy graph, and Constructing knowledge time trend graph.

This research is aimed to build a social network system for college teachers by retrieving different data sources available on the Internet, the characteristics of the constructed social network are represented in graphic and numeric modes. By applying relationships maintained in the social network, we can find the shortest path between any two researchers or the ego-center social network of any individual teacher according to the input parameters given by a query user.. That is to say we have realized the knowledge map concept for college teachers. In this research, we focus on searching the advisory relationships between advisors and students. . Because after a Ph.D. student graduated, he/she could be an advisor guiding other students, by applying recursion of advisory relationships ¡A we can construct a multi-level hierarchy of family-tree for a given advisor and the family-tree can be viewed as a whole family-tree and just those non-leaf nodes. We also analyzed some interesting characteristics of the created family-tree¡A compared with the human relationships in our real society to evaluate and explain some phenomena happened in our academic society. Furthermore, we combine two information of social network and knowledge map for developing the ANIWEB system, providing web-based query functions for users to search teachers¡¦ social network. Two types of query can be applied, one is searching for teacher¡¦s personal information, such as biography, educational background, specialty and NSC projects; the other is searching for social network information about an interested teacher, such as multi-level advisory relationship, co-advisory relationship, ego-center social network and the shortest path between any two teachers. Users can apply different search patterns for their different needs. For example, a user can first search for those teachers with an expertise of a given research topics, then search for the shortest path from the social network to find out the expert he/she could get in touch.

No description available.

Effective knowledge management of proliferating volume of documents within a knowledge repository is vital to knowledge sharing, reuse, and assimilation. In order to facilitate accesses to documents in a knowledge repository, use of a knowledge map to organize these documents represents a prevailing approach. Document clustering techniques typically are employed to produce knowledge maps. However, existing document clustering techniques are not tailored to individuals¡¦ preferences and therefore are unable to facilitate the generation of knowledge maps from various preferential perspectives. In response, we propose the Preference-Anchored Document Clustering (PAC) technique that takes a user¡¦s categorization preference (represented as a list of anchoring terms) into consideration to generate a knowledge map (or a set of document clusters) from this specific preferential perspective. Our empirical evaluation results show that our proposed technique outperforms the traditional content-based document clustering technique in the high cluster precision area. Furthermore, benchmarked with Oracle Categorizer, our proposed technique also achieves better clustering effectiveness in the high cluster precision area. Overall, our evaluation results demonstrate the feasibility and potential superiority of the proposed PAC technique.

Cognitive Maps (CMs) have shown promise as tools for modelling and simulation of knowledge in computers as representation of real objects, concepts, perceptions or events and their relations. This thesis examines the application of fuzzy theory to the expression of these relations, and investigates the development of a framework to better manage the operations of these relations. The Fuzzy Cognitive Map (FCM) was introduced in 1986 but little progress has been made since. This is because of the difficulty of modifying or extending its reasoning mechanism from causality to relations other than causality, such as associative and deductive reasoning. The ability to express the complex relations between objects and concepts determines the usefulness of the maps. Structuring these concepts and relations in a model so that they can be consistently represented and quickly accessed and anipulated by a computer is the goal of knowledge representation. This forms the main motivation of this research. In this thesis, a novel framework is proposed whereby single-antecedent fuzzy rules can be applied to a directed graph, and reasoning ability is extended to include noncausality. The framework provides a hierarchical structure where a graph in a higher layer represents knowledge at a high level of abstraction, and graphs in a lower layer represent the knowledge in more detail. The framework allows a modular design of knowledge representation and facilitates the creation of a more complex structure for modelling and reasoning. The experiments conducted in this thesis show that the proposed framework is effective and useful for deriving inferences from input data, solving certain classification problems, and for prediction and decision-making.