Commodity object automatic classification method and device, equipment, medium and product

Abstract

The invention relates to the technical field of e-commerce information, and discloses a commodity object automatic classification method and device, equipment, a medium and a product, and the method comprises the steps of obtaining a commodity object, and extracting an abstract text and a commodity picture corresponding to the commodity object; respectively carrying out feature extraction on the abstract text and the commodity picture to correspondingly obtain a text feature vector and a picture feature vector, and splicing the text feature vector and the picture feature vector into a comprehensive feature vector; performing multi-level classification processing based on the comprehensive feature vector to obtain a tag set corresponding to the commodity object, the tag set comprising a plurality of classification tags forming a hierarchical membership relationship in a multi-level classification structure; and marking each classification label in the label set for the commodity object. According to the invention, accurate and efficient classification of the commodity objects of the e-commerce platform can be realized, the storage and access efficiency of mass data in the e-commerce platform can be improved, and the method has a wide application scene.

Description

technical field [0001] The present application relates to the field of e-commerce information technology, and in particular to a method for automatically classifying commodity objects and corresponding devices, computer equipment, computer-readable storage media, and computer program products. Background technique [0002] There are many commodities involved in the e-commerce platform, and the number of commodities often reaches the level of thousands or more than ten thousand. Usually, it is necessary to use multi-level categories to organize them efficiently. Among multi-level categories, subcategories usually belong to the parent category, and are expanded layer by layer to form a "category tree". Considering that the deeper the level of the category tree, the greater the amount of loss. Therefore, the category tree usually includes three or four levels, and generally does not exceed five levels. At the data level, the category tree realizes the organization of massive c...

AI Technical Summary

Problems solved by technology

The existing technology usually only classifies a small number or even a single classification level on the basis of pictures, and the implementation logic is simple, but it seems stretched and often difficult to deal with the application scenarios of e-commerce platforms with a large number of commodity objects. Accurate Classification of Commodity Objects

Images