Same-type commodity aggregation method and device, equipment, medium and product

Abstract

The invention relates to the technical field of e-commerce information, and discloses a same-type commodity aggregation method and device, equipment, a medium and a product. The method comprises the steps of: obtaining class labels of commodity objects in a commodity database, wherein the class labels are obtained by calling a pre-trained commodity classification model to classify the commodity information of the commodity objects; obtaining comprehensive feature vectors corresponding to the commodity information of the commodity objects, and calculating the similarity between commodity combinations formed by every two commodity objects under the same class lables, wherein the comprehensive feature vectors are deep semantic feature representations extracted by the commodity classification model; screening out the commodity combination of which the similarity of each class label exceeds a preset threshold value as a same-type commodity combination; and aggregating all the same-type commodity combinations to obtain a same-type commodity list corresponding to each class label. According to the method, same-type commodity can be accurately aggregated, lists of commodities of the same type is constructed, and the user experience is improved.

Description

technical field [0001] The present application relates to the field of e-commerce information technology, and in particular to a method for aggregating products of the same type and corresponding devices, computer equipment, computer-readable storage media, and computer program products. Background technique [0002] The phenomenon of listing the same product on the product interface displayed on the e-commerce platform is common, so that the same product greatly occupies the limited display space of the graphical user interface of the user terminal device, which affects the shopping experience of buyers and users browsing various styles, and also affects Product recommendation success rate. One solution in the prior art is that the background server of the e-commerce platform judges the same product in advance according to the similarity of the product main image or product title of each product object and aggregates the same product for response When the platform user tri...

AI Technical Summary

Problems solved by technology

[0003] Generally speaking, the aggregation of products of the same type on most e-commerce platforms usually uses the text information between product pairs as a feature, and judges whether the same type is based on whether the features are similar, or judges whether the same type is based on whether two products have overlapping pictures, usually This leads to some problems. Specifically, for example, the effect of the method based on image matching is relatively limited. The different shooting angles of the two product display photos may lead to the failure of the identification of the same product, and the description of the two product titles is close to the same. It is obvious that the products should actually be the same model, but because the final judgment is only based on the lack of image matching dimensions, the analysis of the title text matching dimensions leads to a wrong judgment of the product being the same model

Images