A Measuring Method of Semantic Discrimination Ability for Association

Abstract

The invention discloses a semantic differentiating capacity measurement method based on incidence relations. The method is established based on a semantic differentiating model, and the semantic differentiating mode is the difference between file space density and file space density of a certain extracted keyword, functions are used for simulating the semantic differentiating model, five different strategies are provided according to the characteristics of statistics and a graph theory, a certain scale of data are used for verifying that the semantic differentiating capacity calculation method based on the semantic differentiating model has high correlated characteristics, and therefore the accuracy of the method is verified. More importantly, the method is applied to file clustering analysis, and it is showed that the semantic differentiating capacity has better development prospects when data mining tasks are processed. Meanwhile, according to the scheme, the functions are used for simulating the semantic differentiating model, and therefore complexity of semantic differentiating capacity calculation is reduced.

Description

technical field [0001] The invention relates to the field of data mining, in particular to a method for measuring semantic distinction ability based on association relationship. Background technique [0002] Association relationship mining finds interesting associations or correlations between item sets in a large amount of data. With the continuous collection and storage of large amounts of data, many people in the industry are more and more interested in mining association relationships from their databases. Discovering interesting correlations from a large number of business transaction records can help many business decisions. Such as assortment design, cross shopping and sale analysis. Although a large number of associations can be mined from the database, the associations have been mined before knowledge discovery, and semantics are rarely taken into account in the method of measuring associations, so most associations lack semantics. [0003] Measuring associations ...

AI Technical Summary

Problems solved by technology

[0006] In view of the lack of semantics and the high complexity of measurement calculations for most of the associations existing in the measurement methods of the existing semantic discrimination ability, the purpose of the present invention is to provide a measurement method for the semantic discrimination ability of the association relationship to solve the current There are technical problems

Images