Rapid and high-accuracy junk mail filtering method

Abstract

The invention discloses a rapid and high-accuracy junk mail filtering method, which relates to a processing method of electronic mails. The method comprises the steps of firstly preprocessing all received mails and extracting the feature information of the mails, then comparing the feature information of the mails with a junk mail filtering database to find out whether a mail the same to a mail in the database or smaller than a certain threshold exists, judging the mail to be a similar mail with a mail in the database if the mail exists, and marking the mail as a junk mail, and recording the repeated emergency of the feature of the mail, or judging the mail as a normal mail and adding the feature information of the mail to the junk mail filtering information database. The method also comprises the steps of accessing mail data, preprocessing mails, extracting mail features, importing weights, detecting whether a mail is a junk mail and the like. The method can improve the recognition speed and the filtering accuracy of junk mails, and has the characteristics of high filtering speed, high accuracy rate, wide application situations and the like.

Description

technical field [0001] The invention relates to an email processing method, in particular to a fast and high-accuracy spam filtering method. Background technique [0002] With the increasing popularity of network e-mail, more and more people use e-mail to transmit information. However, the volume of spam with advertising nature, political purpose and malicious links is also increasing dramatically. According to statistics, at present, more than half of the mail information transmitted on the entire Internet is spam. The proliferation of spam not only brings great interference to users' normal network applications, but also occupies a huge amount of network bandwidth, wasting a lot of bandwidth of network operators and network end users. At present, there have been many related researches on the filtering of Internet spam, which are mainly divided into filtering methods based on black and white lists, filtering methods based on rules and filtering methods based on content. ...

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention is to provide a fast and high-accuracy spam filtering method to solve the problems of lack of accuracy, heavy spam filtering server load, and increased transmission delay of normal mail in the prior art. Inadequacies

Images