Detection of unwanted messages (spam)

Abstract

In a telecommunications network, method and apparatus for blocking unwanted messages (spam). Messages are first examined by a fast process which uses rules and data tables to determine whether a message can be passed or is potentially a spam message. If the message is potentially a spam message, the message content is analyzed by a deep process. Advantageously, most messages can be passed or blocked quickly and extensive data processing is required only for the few messages which cannot be categorized by the fast process.

Description

technical field [0001] In a telecommunications network, the invention relates to a method and a device for analyzing messages to detect unwanted messages (spam). Background technique [0002] With the advent of the Internet, it has become easy for senders to send messages to a large number of destinations at little or no cost. These messages include short messages for the short message service. These messages include unsolicited and unwanted messages (spam) which are annoying to message recipients who must clean up these messages and determine whether they are important. Furthermore, they are a nuisance to the carriers of the telecommunication networks used to send these messages, not only because they create customer relationship problems with customers who are annoyed by the flood of spam, but also because these messages occupy network resources. The following two statistics illustrate the seriousness of this problem. In China, in 2003, two trillion Short Message Servi...

AI Technical Summary

Problems solved by technology

[0005] The actual process of detecting whether a particular message is spam is usually very complex and uses a lot of processing power on the network

This can limit the throughput of the network

Images