Product similarity based e-commerce recommendation system and method thereof

Abstract

An embodiment of the invention discloses a product similarity based e-commerce recommendation system and a method thereof. The method of the product similarity based e-commerce recommendation system comprises analyzing e-commerce shopping website log information and performing filtration statics on the log; obtaining product popular information from a product database and performing weight customization; extracting corresponding recommendation information in combination with a user search log and the product popular information, establishing a similar product group through a collaborative filtering algorism which is based on the product similarity, transmitting data of similar products to a recommendation element redis; recommending a search engine with the http serving as a request protocol, supporting two recommendation functions according to different requirements (highly recommendation and browsing history recommendation), obtaining corresponding recommendation element set according to user parameters and expanding search query conditions to research; returning a recommendation result in Json data format. The method of the product similarity based e-commerce recommendation system has the advantages of improving the recommendation accuracy, achieving accurate recommendation of products and satisfying user requirements for selecting individualization products from mass products.

Description

technical field [0001] The invention relates to the field of computer applications, in particular to an e-commerce recommendation system and method based on product similarity. Background technique [0002] The traditional collaborative filtering recommendation system first searches for a group of users with similar interests to the target user, and these users with similar interests are often called neighbor users of the target user. The implementation process is to calculate the interest similarity between the target user and all other users through the cosine similarity algorithm. The specific algorithm is: [0003] T ( x , y ) = x • y | | x | | 2 ...

AI Technical Summary

Problems solved by technology

[0007] However, in the process of realizing the present invention, the inventors of the present invention have found that there are at least the following problems in the prior art: the common interest of the target user's neighbor users and the target user is not only for the interest of the product, but may also be for other aspects interest of

[0008] Therefore, the existing collaborative filtering recommendation system has limitations in the accuracy of recommendation, and it cannot realize accurate recommendation of products, and cannot meet the needs of users to select personalized products from huge products.

Images