Web user flow producing method based on user behavior analysis

Abstract

The invention discloses a web user flow producing method based on user behavior analysis. By means of the method, a web user booking system (WUBS) model is built, considers time intervals and browsing time intervals of requests, and introduces a Markov transfer matrix of a page jumping relation by conducting cluster analysis on visits of a user. The WUBS model is used for describing browsing behaviors of the user and popular degree of a page so that a real user request flow condition can be reflected correctly, and the method is close to a real-time request of the user.

Description

technical field [0001] The invention relates to user behavior analysis technology and network flow generation technology, in particular to a web user flow generation method based on user behavior analysis. Background technique [0002] The Internet is a highly practical field, and relevant research results will be widely accepted only after they have been verified by practice. Therefore, researchers need network test beds to verify new network architectures, protocols, services, etc. As the key equipment of the network test bed, the traffic generator is mainly used to generate realistic network traffic, and its performance indicators have a direct impact on the experimental results. [0003] Currently, there are two main methods for generating network traffic: 1. Network traffic playback—use a network sniffer to sniff the network and record the acquired data in a log file, and then generate traffic based on the content recorded in the log file. Network traffic; 2. Model tr...

AI Technical Summary

Problems solved by technology

The above method SPEC96 only generates network traffic by sending an HTTP Get request from the client to the server, without considering the characteristics of the user's web request (such as request interval, browsing time, page jump relationship, etc.), and is mostly used for stress testing, etc.; although SURGE and Harpoon Some web request features have been added, but it also has its shortcomings: 1. It is limited to the time interval model of request sending, browsing time model, etc., and cannot reflect the jump relationship of each page when the user browses the page, and the visit frequency of the page (ie Page popularity), the traffic generated is very different from the real network traffic 2. The parameters of the traffic generation model used need to be specified in advance, because the parameters of each model are different for different websites, so it is not universal

Images