Method and system for discovering maximum likelihood geographic position of internet users

Abstract

The invention discloses a method and a system for discovering a maximum likelihood geographic position of internet users. The method comprises the following steps: firstly extracting basic data from an original access log in a website platform data source system; then processing and classifying basic data to form user information and Cookie set-associated interlayer data; extracting the interlayer data, extracting out Cookie sets of login users, associating the Cookie sets of the login users with the original access log to obtain all access information sets of the login users, so as to obtain IP sets of the login users; associating the IP sets of the login users with an IP address database to obtain the geographic positions when the login users access the internet; finally, calculating the geographic position at which a new user most frequently or the most likely implements production and operating activities from the access information set of the new user by using the maximum likelihood algorithm. According to the method and the system, IP addresses of a lot of internet users are compared with an existing IP address database, are automatically supplemented and checked, so that the efficiency is high.

Description

technical field [0001] The invention relates to a method and system for discovering the maximum likelihood geographic location of Internet users, which are used for providing maximum likelihood estimation of the geographic location of Internet users, and belong to the Internet technology. Background technique [0002] In Internet companies, there are a large number of access log data generated by user clicks every day. The patent "a method for obtaining precise geographic location information of computers based on IP address information" (patent application number: 200710070601.X) through the IP and IP address in the access log Library matching, you can instantly know the geographic information of the country, province and city where each access behavior is located. And the patent "a system and method for monitoring the geographic location and access status of website visitors" (patent application number: 200710101333.3) can monitor and display the detailed data information ...

AI Technical Summary

Problems solved by technology

[0004] 1. Many Internet sites allow users who are not logged in to access, resulting in empty user identity information in a large number of access logs. In order to expand the analysis sample data, it is necessary for us to determine the user identity of this part of the data as much as possible;

Images