Illegal domain name recognition method and device

Abstract

The invention provides an illegal domain name recognition method and an illegal domain name recognition device. The illegal domain name recognition method comprises the steps of: obtaining domain name access behavior information and generating a co-occurrence matrix according to the domain name access behavior information, wherein elements in the co-occurrence matrix are used for indicating times that users corresponding to the line of the elements access to domain names corresponding to the row of the elements; conducting clustering analysis to the co-occurrence matrix according to a clustering algorithm and dividing the domain names corresponding to each row in the co-occurrence matrix into a plurality of domain name subsets; and determining the legality of the domain names in each domain name subset according to an illegal domain name list. The illegal domain name recognition device comprises a co-occurrence matrix generation module, a domain name subset dividing module and a legality determining module. The illegal domain name recognition method and the illegal domain name recognition device can analyze optical correlation among the domain names aiming at the particularity of the illegal domain names to differentiate the illegal domain names from the legal domain names, and therefore the recognition efficiency of illegal websites is improved.

Description

technical field [0001] The invention relates to information technology, in particular to a method and device for identifying an illegal domain name. Background technique [0002] Domain name is the basic resource of the Internet, which is equivalent to the house number on the Internet. It is used to identify computers on the Internet and is the carrier of various Internet applications such as websites and e-mails. Illegal domain names refer to domain names that exist for the purpose of engaging in bad applications such as reactionary, pornographic, and gambling websites, or other abnormal applications. [0003] Currently, there are mainly two methods for identifying illegal domain names. First, the relevant domain name management agencies manually judge whether the domain name is suspected of being illegal by reviewing the registration information of the domain name and the content of the website under its jurisdiction. The second is to use web page extraction, text mining...

AI Technical Summary

Problems solved by technology

[0004] The above two methods of identifying illegal domain names have a certain degree of disadvantages in practical application

The first manual identification method usually requires a lot of manpower and material resources, and is inefficient. Faced with tens of millions of domain name registrations, this method obviously cannot realize timely and effective identification of illegal domain names.

Although the second automatic identification method makes up for the shortcomings of the above methods to a certain extent, the process of extracting and storing website content under massive domain names is still cumbersome. It not only needs to consume a lot of storage resources, but also considers the real-time update of the database.

In addition, the process of analyzing the stored content through relevant text mining algorithms is also complicated and has low efficiency

Images