Assessing Semantic Similarities Among Geospatial Entity Classes

Semantic similarity among geospatial entity classes is an important theoretic problem in categorical database generalization. There are few researches on semantic similarity among geospatial entity classes at home and abroad. The main reasons lie in two aspects: One reason is that it is not convenient to calculate the similarity. The other reason is that the semantic similarity should discover the deeper information among geospatial entity classes and it is very difficult. Whereas semantic similarity is very important for categorical database generalization, this paper researches the theories of semantic similarity and investigates existing methods and presents new calculative method used ontology.The main research contents and new calculation methods in the dissertation are follows:1. The semantic relations are defined and classified; the characteristics of semantic relations and semantic similarity are described.2. After referring many technical literatures and deeply analyzing development of this research presently at home and abroad, the author investigated existing methods of semantic similarity and appraised them.3. The method of semantics expression of geospatial entity classes based on ontology is put forward.4. Semantic similarity model among geospatial entity classes is constructed.5. The semantic of land-use type is expressed and the similarities between them are computed.6. An experiment of the application of the semantic similarities on land-use database generalization is doing.