Real-time monitoring and filtering system for mobile SMS

This paper proposes a new method of real-time information monitoring and filtering for mobile short messaging service(SMs)system.This method implements the mobile SMs real-time monitoring and filtering by combining the Pinyin Fuzzed Keyword Matching Technology with dynamical adjustment of the users’credit-grade according to the SMs’s behavior characters.This method firstly classifies the SMs into three categories:legal SMs,doubtful SMs and junk SMs,then creates the keyword dictionary by Bayesian Learning and runs parallel real-time filtering on polynuclear hardware platform.It enhances the junk message interception rate and the processing speed of short message service center(SMSC),reduces the misjudgment rate for the monitoring center,and meanwhile gives consideration to interests of both the operators and customers.