Commodity classification method based on data analysis

Abstract

The invention discloses a commodity classification method based on data analysis. The method comprises the following steps: a characteristic database for commodity classes is established; basic characteristics and special characteristics in the characteristic database are divided; a basic characteristic vector and a special characteristic vector of a to-be-classified commodity are extracted; the to-be-classified commodity is compared with a first basic characteristic vector in a basic characteristic vector set in the characteristic database; the rest basic characteristic vectors are compared to obtain a comparison basic characteristic vector set; a similarity coefficient is calculated to extract a special characteristic vector set with similarity coefficients larger than a preset similarity coefficient; and the special characteristic vector of the to-be-classified commodity is compared with a special characteristic vector with the similarity coefficient larger than the preset similarity coefficient to obtain a comparison special characteristic vector set to screen a commodity class with the highest coefficient in the same class. The commodity characteristics can be effectively distinguished, the commodity classification accuracy is improved, the method is applicable to large-scale classification, and the manual classification time is shortened greatly.

Description

technical field [0001] The invention belongs to the field of commodity classification and counting, and relates to a commodity classification method based on data analysis. Background technique [0002] Commodity classification refers to according to a certain management purpose, in order to meet all or part of the needs of commodity production, circulation and consumption activities, the collection of commodities within the scope of management, and the selected basic characteristics of commodities as classification marks, are successively summarized as follows: Several sub-aggregates (categories) with smaller scope and more consistent characteristics, such as large category, medium category, small category, detailed category, until varieties, detailed categories, etc., so that all commodities within this scope can be clearly distinguished and systematically process. [0003] There are many kinds of commodities. According to incomplete statistics, there are more than 250,00...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a commodity classification method based on data analysis, which solves the problem of high classification error frequency and low classification efficiency in the existing commodity classification process, and it is not convenient to accurately distinguish the types of commodities

Images