Recommendation method and device, electronic device and readable storage medium

Abstract

The invention provides a recommendation method and device, an electronic device and a readable storage medium. The recommendation method comprises the steps of obtaining the historical information ofa user; determining a key demand of the user according to the historical information; extracting the candidate commodities matched with the key requirements from a preset merchant list database; extracting the commodity sales information of the candidate commodities; according to the commodity sales information, obtaining a commodity sales cost performance index meeting the key requirement; and according to the commodity sales cost performance index, displaying the commodity aiming at the commodity sales information to the user, so that the problem that in the prior art, the commodities recommended according to the user requirements need to be further screened by users is solved.

Description

technical field [0001] The present disclosure relates to the technical field of recommendation, and in particular to a recommendation method, a recommendation device, electronic equipment and a readable storage medium. Background technique [0002] Obtaining the user's consumption tendency according to the search behavior information provided by the user, and recommending corresponding products to the user is a widely used commodity recommendation method at present. [0003] In the existing technology, in the technical scheme of recommending information based on users’ attention to products, the recommendation is generally based on information such as the user’s historical behavior data and product popularity. On the one hand, the disadvantage is that the generalization performance of the products is relatively poor. Products with relatively high popularity, and currently users often give a general-concept product (the so-called general-concept product generally refers to a ...

AI Technical Summary

Problems solved by technology

[0003] In the existing technology, in the technical scheme of recommending information based on users’ attention to products, the recommendation is generally based on information such as the user’s historical behavior data and product popularity. On the one hand, the disadvantage is that the generalization performance of the products is relatively poor. Products with relatively high popularity, and currently users often give a general-concept product (the so-called general-concept product generally refers to a certain category of products, and the category can be large or small, such as "a bag of rice", "a bag of 10KG rice", "A bag of 10KGXX brand rice" is three categories from large to small), rather than a product with clear demand; on the other hand, users are more keen on those products with high popularity, high discount rate and high cost performance, but currently Merchants have a variety of promotion methods, and it is difficult for users to choose a truly affordable and popular product from different merchants

[0004] In this way, the products recommended for users are always not accurate enough, which leads to the problem that users need to compare the sales information such as prices or activities of multiple products obtained from the recommendation list

Images