Research On Semantic-based Knowledge Management Of E-Learning

Compared with people, location and space of the traditional learning resources, the E-Learning is expected to provide standard-based content repositories that allow learners to capture, store, deliver, and manage learning resources. And with the popularity of the E-Learning, Learning Content Management System (LCMS) becomes a promising research area. Now, how to build a scalable learning resource management framework enabling the effective, accurate, semantic-based retrieval of learning resources, is in a way that adapts to the characteristics and interests of the users.The Semantic Web is an extension of the current Web in which information is well-defined and linked in a way for more effective discovery, automation, integration, and reusage across various applications. By incorporating the Semantic Web idea, this paper focuses on the semantic organizing methods of heterogeneous learning resources in a coherent and meaningful scheme.Firstly, the basic situation of Semantic Web is summarized, its present application in E-Learning and the analysis on methods of different Learning Resource Management.Secondly, a layered principle is suggested to model the E-Learning Knowledge environment based on metadata. A layered architecture which consists six layers top-down is built—MKEE (Metadata-based Knowledge Environment of E-Learning), and its opening character has been investigated.Finally, we use a resource management framework which enables the semantic organization of heterogeneous learning resources to improve expressive ability, scalability and cohesiveness. And based on the description logic, a knowledge formal system is defined for the resource modeling and organizing with better expressive and reasoning ability. Another feature of the resource organization model is that the semantic link network model is used to explicitly represent the semantic relationship between the entities of the same type. The design criteria and constraints for SLN, inference rules, and the operations for SLN evolution are also presented for better SLN design and application.