| Face to the vast amounts of digital information resources in the information-society, how to find the valuable information which we really need is an increasingly important research topic. Due to the query methods based on keyword can't overcome the shortcomings caused by themselves, traditional information retrieval system feels powerless to get a solution when it face the complex retrieval requirements. Fortunately, the semantic retrieval which based on the traditional information retrieval technology, combined with the technology such as natural language processing and latent semantic analysis for resolving this problem bring some opportunities.The main purpose of this paper is to design and realize a semantic retrieval system in the field of science and technology documents through the resource sharing platform which is built by Science and Technology Department of Shaanxi Province. In the analysis and summary of the current information retrieval researches and technology, the paper proposes a retrieval model based on Semantic Knowledge Base. Specific works include following aspects:1. Semi-automatic create a Semantic Knowledge Base in the field of Science and Technology, and put forward the corresponding knowledge base revision and maintenance method.2. Complete the design and analysis of the system framework by object-oriented and layered architecture model.3. Put forward and realize a semantic search algorithm based on the Semantic Knowledge Base combined with Vector Space Model.4. Put forward and realize a function that can recommend hot resources based on user access behavior analysis.5. Use WEB2.0 related technologies to increase the users experience in the premise of providing accurate retrieval results.After the actual retrieval simulation data were tested and the results showed that the retrieval system within the field in science and technology information has certain theoretical research value and practical feasibility. |
PDF Full Text Request