Commodity recall optimization method and device, equipment, medium and product

Abstract

The invention relates to a commodity recall optimization method and device, equipment, a medium and a product, and the method comprises the steps: obtaining a plurality of commodity data subsets correspondingly recalled by a plurality of preset recall sources, and each subset comprises a recalled commodity and a matching degree representing that the commodity is recalled; determining a plurality of evaluation indexes of each recall source according to the user behavior data corresponding to the commodities in each commodity data subset; according to each evaluation index corresponding to each recall source, respectively summarizing and determining an index score of each recall source; the commodity data subsets are combined into a commodity recommendation set, sorting is carried out according to the actual score of each commodity, and the actual score of each commodity is the product of the matching degree of the commodity and the index score of the recall source of the commodity. According to the method and the device, fine-grained quantification can be performed on the information contribution degrees of the commodities obtained by different recall sources, so that a more accurate final recommendation result can be determined according to the actual scores of the commodities, and the method and the device are suitable for being used by independent sites.

Description

technical field [0001] The present application relates to the field of e-commerce information technology, and in particular, to a method for optimizing commodity recall and its corresponding device, computer equipment, computer-readable storage medium, and computer program product. Background technique [0002] Recommending products in e-commerce platforms is a high-frequency application, which is widely used in product search, product advertisement placement, product screening and other application scenarios, which can improve the efficiency of product matching, make the products of merchants easier to sell, and make consumers User needs are more easily met. [0003] When applying the product recommendation algorithm, one of the key links is the product recall link. In the commodity recall link, by activating multiple preset sources such as recall sources, corresponding commodities can be obtained with different strategies or through different data source channels. Accord...

AI Technical Summary

Problems solved by technology

[0004] The number of products obtained from each recall source is large, and the corresponding information contribution value of each product has not been uniformly quantified. Therefore, the products obtained from different recall sources are generally integrated into the final result, which often makes the final product difficult to meet expectations.

[0005] For such problems, the traditional approach is to adjust the importance of commodities in different recall sources by simply adjusting the weight of each recall source or matching the neural network model based on deep learning. However, since each recall source itself has multiple Commodities, and the number of commodities expected to be obtained in the end is often small. Therefore, this method has a very limited practical effect due to the rough granularity of information processing. Moreover, when it is implemented using a neural network model, its training cost is high. For For online stores deployed as independent sites, it is difficult to achieve results

Images