Junk short message detecting method and device

Abstract

The invention discloses a junk short message detecting method and device. The method comprises, for a short message to be detected, converting information contained in the short message to be detected into a feature word set which contains at least one feature word; querying every feature word contained in the feature word set in preset inverted index files to determine the number of matched samples and the matching weight between junk short message information samples contained in the inverted index files and the feature word set, and according to the number and the matching weight of the determined samples, determining whether the short message to be detected is a junk short message. The junk short message detecting method and device can well improve the accuracy of junk short message identification, improve the junk message detecting efficiency and achieve good real-time performance.

Description

technical field [0001] The invention relates to the technical field of spam short message filtering methods, in particular to a spam short message detection method and device. Background technique [0002] With the continuous development of wireless communication networks, users are troubled by spam messages sent by criminals while enjoying the convenience brought by various services. [0003] At present, the detection of spam text messages is mainly realized through two methods: one way is to realize the detection of spam text messages through the sending behavior of short messages, which mainly includes the frequency characteristics of sending short messages, the regular characteristics of the called number of short messages, and the regular characteristics of the calling number of short messages Wait for spam messages to be found. Another way is to realize spam message detection by means of content recognition, and generally adopt a pre-designated illegal keyword matchin...

AI Technical Summary

Problems solved by technology

[0014] The first defect: the recognition accuracy of spam text messages is low. For example, if the keyword processing strategy is set strictly, it will easily cause a large number of false interceptions, and if the processing strategy is set loosely, it will not be able to achieve an effective interception effect.

[0015] The second defect: low efficiency and poor real-time detection of spam messages

[0016] To sum up, the spam SMS detection method in the prior art has low accuracy, low efficiency of spam SMS detection, and poor real-time performance.

Images