Object classification method and device

Abstract

The embodiment of the invention provides an object classification method and device. The method comprises the steps: determining a plurality of candidate classes and the weighted value of each candidate class according to the information of a plurality of to-be-classified objects in an obtained to-be-classified object set; determining target classes in a clustering class comprising the candidate classes according to the weighted values; and classifying the plurality of to-be-classified objects in the to-be-classified object set according to the target classes. According to the invention, the method can achieve the automatic determining of the target classes for the commodities of a merchant, determines the target classes in the plurality of candidate classes according to the weighted values which are used for representing the popularity of the candidate classes, classifies the commodities according to the target classes, brings more convenience to a user for purchasing the commodities according to the target classes, and improves the classification accuracy.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to an object classification method and device. Background technique [0002] In the current mainstream e-commerce platforms, a large number and variety of commodities will be displayed online. In order to facilitate merchants to manage the displayed products and users to purchase the displayed products, before the products are launched, the merchants or website staff will manually set the settings for each displayed product one by one according to the product information such as the characteristics and uses of the products. Classification, for example: the first-level classification of potato chips can be set as snacks, and the second-level classification can be set as puffed food, etc. [0003] However, in the process of implementing the present invention, the inventors found that setting classifications for commodities one by one manually would consume a lot of time for the cla...

AI Technical Summary

Problems solved by technology

[0003] However, in the process of implementing the present invention, the inventors found that setting classifications for commodities one by one manually would consume a lot of time for the classification personnel, and the efficiency of manual classification is very low

In addition, since different people may have different understandings of the product information of the same product, on the one hand, the same product may be classified into different categories in different merchants; on the other hand, the category selected by the user when purchasing the product It may be different from the categories on the website, which may cause inconvenience to users in the process of purchasing products

Images