Junk short message filtering method based on intelligent algorithm

Abstract

The invention discloses a junk short message filtering method based on an intelligent algorithm. The method comprises the following steps: obtaining an original short message sample; obtaining a sample vocabulary set; for an independent vocabulary in the sample vocabulary set, separately calculating the occurrence probabilities of the vocabulary in a junk short message sample and a non junk short message sample; for any independent vocabulary in the sample vocabulary set, calculating the probability that any short message containing the independent vocabulary is a junk short message; when a plurality of independent vocabularies in the sample vocabulary set occur in any to-be-filtered short message, for each independent vocabulary in the to-be-filtered short message, obtaining the probability that any short message containing the independent vocabulary is a non junk short message; obtaining the probability that the to-be-filtered short message is the junk short message; obtaining a blacklist and white list library; and judging the to-be-filtered short message, and upgrading the blacklist and white list library. By adoption of the junk short message filtering method, the accuracy of filtering the junk short messages can be improved.

Description

technical field [0001] The invention relates to the technical field of software information security. More specifically, it relates to a method for filtering spam short messages based on an intelligent algorithm. Background technique [0002] As we all know, mobile phone users often encounter spam messages, which often bring a lot of inconvenience to mobile phone users. Therefore, spam short messages need to be filtered out. In the prior art, the spam short message interception strategy is relatively simple, and most spam short message filtering methods are realized by means of phone number blacklist or spam word blacklist. The disadvantage of the above-mentioned spam short message filtering method in the prior art is that it is simple and rude, and it is easy to cause misjudgment, and the misjudgment rate is relatively high. [0003] Therefore, it is necessary to provide a method for filtering junk short messages based on an intelligent algorithm. Contents of the inven...

AI Technical Summary

Problems solved by technology

In the prior art, the spam SMS interception strategy is relatively simple, and most spam SMS filtering methods are implemented in the form of phone number blacklist or spam vocabulary blacklist, etc.

The disadvantage of the above-mentioned spam SMS filtering method in the prior art is that it is simple and rude, and it is easy to cause misjudgment, and the misjudgment rate is high

Images