Commodity recommendation method, apparatus, computer apparatus, and storage medium

Abstract

The invention provides a commodity recommendation method, a device, a computer device and a storage medium. The method comprises the following steps: crawling user behavior data of all users on a preset social platform by using a web crawler technology; obtaining basic information and behavior characteristic information of all users according to the user behavior data; calculating a similar user group of the target user based on basic information and behavioral characteristic information of all the users if an instruction to recommend a commodity to the target user is received; acquiring sub-data of the similar user groups for preset commodities; calculating a recommendation score for each preset commodity for the similar user group based on the rating data; a merchandise being recommendedto the target user according to the recommendation score. The embodiment of the invention utilizes the user behavior data of the social platform to calculate the similar user groups of the users, andbased on the collaborative filtering thought, utilizes the evaluation behavior of the similar user groups to recommend the goods to the users, realizes the personalized recommendation, and improves the accuracy rate of the goods recommendation.

Description

technical field [0001] The present invention relates to the technical field of the Internet, in particular to a commodity recommendation method, device, computer equipment and storage medium. Background technique [0002] With the development of e-commerce, online shopping is becoming more and more popular, and more and more users tend to shop on the Internet. Then, as the variety of commodities becomes higher and higher, after users input query content, the There are too many recommendation results. Even for the same or similar products, the product information will be different, which may be far from the actual needs of users. Users still need to manually filter to get the products they want. Product recommendation poor precision. Contents of the invention [0003] Embodiments of the present invention provide a commodity recommendation method, device, computer equipment, and storage medium, aiming at improving the accuracy of commodity recommendation. [0004] In the f...

AI Technical Summary

Problems solved by technology

[0002] With the development of e-commerce, online shopping is becoming more and more popular, and more and more users tend to shop on the Internet. Then, as the variety of commodities becomes higher and higher, after users input query content, the There are too many recommendation results. Even for the same or similar products, the product information will be different, which may be far from the actual needs of users. Users still need to manually filter to get the products they want. Product recommendation poor precision

Images