Commodity sorting processing method and device, equipment, medium and product

Abstract

The invention discloses a commodity sorting processing method and device, equipment, a medium and a product. The method comprises the steps of extracting a comprehensive feature vector of a to-be-sorted commodity sample of a to-be-sorted commodity object corresponding to a commodity query event; inputting the comprehensive feature vector into a sample dynamic routing layer to drive a routing decision model in the sample dynamic routing layer to determine the commodity sorting difficulty of the to-be-sorted commodity samples according to the comprehensive feature vector; querying a target commodity sorting model corresponding to a sorting difficulty interval in which the commodity sorting difficulty is located in a commodity sorting model pool; and inputting the to-be-sorted commodity samples into the target commodity sorting model, and obtaining sorting scores of the to-be-sorted commodity samples to determine ranking positions of the to-be-sorted commodity objects in the queried commodity ranking. According to the invention, a commodity sorting system suitable for e-commerce shops and independent stations is realized, the commodity samples are pushed to the corresponding models for reasoning through dynamic routing, and the processing efficiency is high.

Description

technical field [0001] The present application relates to the field of network e-commerce, in particular to a method for sorting and processing commodities, and also to devices, equipment, non-volatile storage media and computer program products corresponding to the method. Background technique [0002] Existing e-commerce platforms generally provide platform users with commodity query services, so that platform users can provide commodity query services to query the commodities they need to consume. , and will also sort these commodities. Generally, the sorting of commodities can be done with the help of the corresponding neural network, so as to output the commodities that are more in line with the user's shopping habits and preferences to the front position on the page for the user. Browse to the goods you need for consumption at the first time. [0003] In the existing e-commerce platform, there are a variety of e-commerce stores or independent stations as the seller us...

AI Technical Summary

Problems solved by technology

[0003] Existing e-commerce platforms have a variety of e-commerce stores or independent stations as platform sellers to provide sellers with corresponding categories of goods for consumption. Separately model the neural network used for the product sorting processing of different e-commerce stores and independent stations, so that the output results of the product sorting processing of each e-commerce store or independent station are more consistent with the user's experience in e-commerce stores or independent stations. shopping habits and preferences, but because the number of views and sample size of e-commerce stores and independent stations cannot be compared with those of e-commerce platforms, the neural network model that is separately constructed for e-commerce stores or independent stations and applied to commodity ranking is due to the sample size Sparse data leads to poor reasoning ability, and it is impossible to accurately sort out the product rankings that meet user needs for users to use, and the workload of modeling each e-commerce store and independent website is relatively huge, and the high development cost is a challenge for users with massive E-commerce stores and independent e-commerce platforms are not realistic

Images