An efficient domain ontology semantic similarity calculation algorithm

Abstract

The invention discloses an efficient domain ontology semantic similarity calculation algorithm, and relates to the field of semantic heterogeneity between multiple application ontologies. At present,a basic semantic similarity algorithm is designed mainly based on two semantic similarity calculation models of information theory and semantic distance by considering factors such as semantic distance, information amount and attributes among concepts along with gradual deepening of research, but the influence of the information amount among the concepts on the semantic similarity is negligible. Aiming at the problems, the method further considers the influence of factors such as the hierarchical order, the node depth and the semantic coincidence degree among concepts on the semantic similarity on the basis of basic semantic similarity calculation. Therefore, the invention provides an efficient domain ontology semantic similarity calculation algorithm by which factors needing to be considered for semantic similarity calculation are supplemented and perfected, and the accuracy and accuracy of concept semantic similarity calculation are improved.

Description

technical field [0001] The invention belongs to the field of computer information processing, and in particular relates to an efficient domain ontology semantic similarity calculation algorithm. Background technique [0002] The traditional ontology-based concept semantic similarity calculation can generally be summarized into the following two types: [0003] (1) The method based on information theory. In information theory, the amount of information can reflect the semantic information contained in a concept, which can be quantified by the probability or weight of the concept and its instance objects. In the method based on information theory, it is believed that if the amount of information shared by two concepts is greater, it means that the two concepts are more similar. In the ontology structure, each concept is a refinement of its ancestor nodes, and each child node can be considered to contain the information content of all its ancestor nodes, so the semantic simila...

AI Technical Summary

Problems solved by technology

[0006] In the process of calculating semantic similarity, the length of semantic distance lacks an objective and rigorous definition in theory, and the method based on semantic distance ignores the influence of node depth and node density.

Images