Product recommendation method and device, electronic equipment and storage medium

Abstract

The invention relates to the field of artificial intelligence, and discloses a product recommendation method, which comprises the steps of obtaining a user image, performing face feature recognition on the user image by utilizing a pre-trained face feature recognition model to obtain a face feature image, and preprocessing the face feature image to obtain a standard face image; carrying out portrait matching on the standard face image and a user portrait in a pre-created user portrait library, and taking the user portrait successfully matched with the portrait as a target user portrait of thestandard face image; querying user information of the standard face image from a target user portrait, and performing feature extraction on the user information to obtain user feature information; andselecting a product of which the association degree with the user feature information exceeds a preset threshold from the to-be-recommended products, and pushing the selected product to a corresponding user. The invention also relates to a blockchain technology, wherein user feature information can be stored in a blockchain. The product recommendation accuracy can be improved.

Description

Technical field[0001]The present invention relates to the field of artificial intelligence, and more particularly to a product recommendation method, device, electronic device, and computer readable storage medium.Background technique[0002]Product recommendation refers to a process of pushing products to a user. It is applied to different business scenarios. Based on product recommendation, it can realize product promotion. For example, in business product operations, in order to let users understand the business as much as possible Products, improve business products sales, and the push of business products is extremely important.[0003]At present, the product recommendation method is usually based on user group portrait analysis, pushing the corresponding product to the user, such a product recommendation method cannot accurately position the user's range range, so that the specific user preference information cannot be accurately portrayed, which in turn affects the accuracy of th...

AI Technical Summary

Problems solved by technology

[0003] At present, product recommendation methods are usually based on the analysis of user group portraits, and push corresponding products to users. Such product recommendation methods cannot accurately locate the range of users, so that they cannot accurately describe specific user preference information, which in turn will affect the accuracy of product recommendations.

Images