Individualized recommendation method and system based on distributed B2B platform

Abstract

The invention discloses an individualized recommendation method and system based on a B2B platform on a Hadoop platform of a distributed technology. The method comprises the steps that firstly, centralized placement, storage and query are carried out on various data, such as website log files, product information and user information, based on the Hadoop distributed storage technology, and the data are processed fast and efficiently; secondly, the data are preprocessed through a Hive service under the Hadoop platform, a fast and efficient implementation recommendation algorithm is achieved through Map/Reduce; then, the information retrieval and file mining work is achieved on text information through the Map/Reduce, the product information needed in inquiry and purchase by a user is matched, and individualized recommendation information is acquired; finally, large-data storage and query are provided through an HBase service under the Hadoop platform, and website recommendation user responses are improved.

Description

technical field [0001] The present invention relates to the fields of e-commerce and data mining, specifically a distributed-based personalized recommendation method for the B2B e-commerce environment. Aiming at the characteristics of B2B e-commerce carrying massive data, the Hadoop distributed architecture is used to store and record user behaviors and product information, and use it to realize fast and efficient B2B e-commerce personalized recommendation service. Background technique [0002] With the rapid development of the Internet, e-commerce has had a profound impact on the production and life of enterprises and individuals. Commodity categories make it difficult for users to search for the information they need in search engines when their needs are relatively unclear. Further, it is even more difficult for users to need search results that are more in line with their personal interests and hobbies. [0003] At this time, the recommendation engine came into being, a...

AI Technical Summary

Problems solved by technology

But for most B2B websites, there is no user transaction data; for B2C users need to purchase goods, users will frequently log in to the website, making it easier to identify the user, and the user's historical website behavior can only be obtained after the user's identity is clarified However, B2B website users can complete all purchases without logging in to the website, but identity identification has become a difficult point

[0005] Personalized recommendations are widely used in major B2C e-commerce websites, such as Amazon, eBay, Dangdang, Taobao, etc. However, personalized recommendations on B2B platforms face more and greater problems, such as difficult identification of buyers, buyers Behavioral data has a long time span and a large amount. The mainstream recommendation strategy based on the B2C platform can no longer meet the performance needs of B2B personalized recommendation.

Images