Personalized recommendation method based on cloud processing mode and applied in e-business environment

Abstract

The invention discloses a personalized recommendation method based on the cloud processing mode and applied in the e-business environment. The personalized recommendation method mainly solves the problem that an existing personalized recommendation method is low in recommendation efficiency and poor in recommendation precision when processing mass data. The personalized recommendation method is divided into an off-line portion and an on-line portion. According to the off-line portion, the Hadoop frame of the cloud computing technology is used for parallel processing of historical data information, an HDFS is used for storing mass data information, and four kinds of parallelized recommendation methods which are suitable for different business stages of e-business are achieved according to the MapReduce programming model. According to the on-line portion, a lightweight data base is arranged and used for storing a user behavior log, a dynamic data collection mechanism is designed and used for reading data which are processed and obtained by the off-line portion in real time, web display and information statistics service are provided, and real-time recommendation information is provided for a user. The personalized recommendation method based on the cloud processing mode and applied in the e-business environment has the remarkable advantages of processing the mass data generated by e-business application.

Description

technical field [0001] The present invention relates to the field of computer network and data mining, specifically to realize a personalized recommendation method based on the cloud computing processing mode for the e-commerce environment, aiming at the massive data characteristics and specific business logic of the current e-commerce application, using the Hadoop framework to store Record user behavior and product information, and use web logs online to dynamically record user current behavior and offline recommendation calculation results to provide fast and efficient personalized recommendation services. Background technique [0002] E-commerce usually refers to a wide range of commercial and trade activities around the world, under the open network environment of the Internet, based on the browser / server application mode, buyers and sellers conduct various business activities without meeting each other, so as to realize online shopping, It is a new type of business oper...

AI Technical Summary

Problems solved by technology

Personalized recommendation analysis for such a huge data set requires a large amount of computing and storage resources. If the centralized analysis and processing mode is still adopted, the recommendation time will be too long and cannot meet the real-time requirements, which will greatly affect the user's shopping experience; the data sparsity problem means that in a large-scale e-commerce environment, products rated by multiple users at the same time are very rare, thus affecting the mining accuracy of similar users; the cold start problem means that it is difficult for new users to calculate neighbors because they have no purchase records And new products are hard to recommend due to less ratings

In view of the above problems, the existing collaborative filtering recommendation methods are difficult to apply to the current e-commerce applications, so a new personalized recommendation method is urgently needed to solve the above problems and achieve fast and efficient recommendation goals

Images