Neural network training method and junk mail filtering method using same

Abstract

The invention provides a method for training a back propagation (BP) neural network for filtering junk mails. Weights among layers in the BP neural network are adjusted through a studying rate by the method. The method comprises the following steps of: calculating the weight of the keyword of a known mail and target values corresponding to various mail types, wherein the different mail types correspond to the different target values; inputting the weight of the known mail into a BP neural network to be trained to acquire an output value; and calculating an offset between the output value and the target value, if a training termination condition is not met, modifying the weight of the BP neural network and performing a next generation of training until the output value meets the training termination condition, wherein generations in a preset numerical value are set as one stage; and the studying rate is updated once every stage.

Description

【Technical field】 [0001] The invention relates to a spam filtering system, in particular to a spam filtering method based on a robust BP neural network. 【Background technique】 [0002] With the popularization of e-mail in people's daily life, the number of junk e-mails stored in users' mailboxes has gradually increased, which has brought a lot of inconvenience to users' viewing and management operations. In order to facilitate their daily management and reading, the modern network e-mail system There is an urgent need for an accurate, real-time, and efficient email classification and filtering technology, which can classify and filter emails according to the sender's mailbox, IP, subject, and email text. [0003] figure 1 It is a block diagram of judging spam in the prior art. see figure 1 As shown in the figure, mails from the Internet are firstly judged by the spam filtering module, and then the judged mails are sent to the Email server. The specific content of the jud...

AI Technical Summary

Problems solved by technology

The classification process of complex data often has nonlinear properties. BP neural network can handle such problems well, but it has the disadvantages of slow training speed and falling into local minimum solutions.

Images