An efficient robot data similarity calculation algorithm

Abstract

The invention discloses an efficient robot data similarity calculation algorithm, relates to the field of multiple different bodies, and further solves the problem of interoperation among heterogeneous bodies. According to the method, body preprocessing, mapping candidate generation, concept term word similarity calculation, multiple mapping combination and mapping result output are defined. In various mapping methods, concept similarity calculation based on word composition characteristics basically does not need to be supported by other corpus resources except the words themselves, and calculation has the advantages of being direct, fast and the like. However, the existing related methods still have the problems of difficulty in calculating similarity of allogeneic words and synonyms with the same semantics but incompletely consistent writing, imperfect distribution strategy of word weights of conceptual terms to be matched and the like. Aiming at the problems, the invention providesan efficient robot data similarity calculation algorithm to improve the comprehensive effect of body mapping.

Description

technical field [0001] The invention belongs to the field of computer information processing, and in particular relates to an efficient calculation algorithm for robot data similarity. Background technique [0002] Ontology mapping methods can generally be summarized into the following four types: [0003] (1) With the help of the concept similarity calculation method, compare the similarity between projected objects to find the connection between heterogeneous ontologies. The concept is divided into three parts: the synonym set representing the concept, the feature set describing the concept, and the semantic relationship set of the concept. These three parts are used to calculate the similarity and finally determine the mapping relationship between concepts. [0004] (2) Analyze the structural similarity between heterogeneous ontologies, and discover the mapping relationship by writing mapping rules. Sunna et al. proposed a method of using ontology structure graph as con...

AI Technical Summary

Problems solved by technology

[0013] (1) For variant words, synonyms, and near synonyms like "Mutation" (variation) and "Variation", it is difficult to obtain the correct mapping relationship by applying the existing word-based similarity calculation method

Especially when these words are used as the central words of terms expressing ontology concepts, calculation errors will lead to matching errors of corresponding ontology concepts

[0014] (2) The existing algorithm assigns similar weights to the modifiers in the term in an average way, which makes the discrimination of the similarity calculation results poor

Images