Mail classification method and device

Abstract

Embodiments of the present invention provide a mail classification method and device. In one embodiment, the method includes: processing the received email text, and mapping the email text into an initial vector; using a stack autoencoder to process the initial vector to obtain an output vector; performing an output vector on the output vector Classifying, judging whether the email is spam according to the classification of the output vector. Through the above method and device, the identification efficiency of spam can be improved, and the user experience can be improved.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a mail classification method and device. Background technique [0002] Due to the popularity of network technology, e-mail has developed into one of the important means of communication between modern network users due to its fast transmission speed and low cost. However, as the popularity of e-mail increases, the amount of spam is also increasing year by year. Spam has grown to a critical mass around the world. Therefore, how to use a more efficient spam identification method has become a hot spot for relevant researchers. At present, the commonly used spam filtering techniques can be divided into several categories: (1) keyword filtering based on email subject and email text; (2) filtering based on black and white lists; (3) filtering based on rules; (4) filtering based on Intent detection and filtering; (5) content-based filtering, etc. However, the identificatio...

AI Technical Summary

Problems solved by technology

However, the identification and classification of spam still needs to be improved

Images