Research On Discipline-Ontology Based Learning Resource Semantic Retrieval

With the development of the Internet, E-Learning has gradually become an important way for learning. More and more enterprises and organizations have built their own E-Learning resources, which bring rich information and more convenience to learners. But, with the increase of learning resources, how to effectively manage learning resources is becoming an urgent problem to be resolved. Further more, most E-Learning Systems adopt keyword-based retrieval method, which is not so effective and efficient and hard to meet the user's requirement.There is much difference among learners and learning resource providers when the semantic of learning resources is understood and expressed, and it is the important reason which causes the above problems. The emergence of Ontology technology provides an effective way to solve the problem. This thesis introduces the Discipline Ontology, which is the formalization of commonly cogitation for concepts and the relationships between concepts existing in some discipline domain. In this thesis the Discipline Ontology be used in the follow two facets:1) Inference rules are defined on the basis of Discipline Ontology. Semantic extension on keyword from user is performed by using Jena inference engine and inference rules, so as to better interpret and describe the requirement; 2) Learning resource metadata is extracted and defined by following Learning Resource Meta-data Specification and Discipline Ontology, so as to provide formal description for learning resources.Based on the discipline-ontology theory, this academic mainly completes the following tasks:First, the semantic retrieval and related technologies are carefully researched, consisting of ontology,ontology language,the ontology Development Kit Jena, and so on. Second, through in-depth study of ontology-related technologies, a discipline-ontology semantic extension method is proposed, both from the direct extension and reasoning extension, which completes semantic extension to the users' submitting keywords, then sort the semantic extended keywords set using the improved similarity formula to get a set of query keywords highly matching with users' needs. After that, the paper constructs Learning Resource Metadata Model (LRMM) in the light of the discipline-ontology theory and Learning Object Metadata Standard (LOM).At last, based on the above work, this issue proposes a discipline-ontology-based learning resources retrieval framework, and designs and implements semantic retrieval Algorithm for Learning Resources with the framework.In this thesis, the application of Ontology technology in learning resource retrieval could support the share and exchange of learning resource in the semantic layer, and could improve the efficiency of learning resource retrieval. This thesis provides an approach for learning resource retrieval, and is able to support the effective access on learning resources.