Identification method and device for junk short messages and storage medium

A technology of spam SMS and identification method, applied in the field of communication, can solve the problems affecting the accuracy of the identification system, calibration errors, etc.

Active Publication Date: 2019-03-01
CHINA MOBILE COMM GRP CO LTD
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the large number of SMS samples that need to be calibrated and need to be updated regularly, in practical applications,

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Identification method and device for junk short messages and storage medium
  • Identification method and device for junk short messages and storage medium
  • Identification method and device for junk short messages and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0061] see figure 1 , which shows a method for identifying spam messages provided by an embodiment of the present invention, the method can be applied to a network device having a spam message identification function or a requirement for identifying spam messages, and the method may include:

[0062] S101: Generate a first fingerprint database and a first classifier according to the short message samples in the short message sample database and the instruction information corresponding to each short message sample;

[0063] Wherein, the indication information is used to indicate whether the short message sample is a spam short message;

[0064] S102: Train the SMS sample library, the first fingerprint library and the first classifier according to the set butterfly cross-training strategy to obtain the trained second fingerprint library and the trained second classifier;

[0065] S103: Verify the short message to be verified based on the set serial verification strategy, the s...

Embodiment 2

[0123] Based on the same technical idea of ​​the foregoing embodiments, see Figure 8 , which shows a schematic structural diagram of a device 80 provided by an embodiment of the present invention, the device 80 may include:

[0124] A memory 801 storing a junk message identification program;

[0125] The processor 802 is configured to execute the junk message identification program to perform the following operations:

[0126] Generate the first fingerprint library and the first classifier according to the short message samples in the short message sample library and the indication information corresponding to each short message sample; Wherein, the indication information is used to indicate whether the short message sample is a junk message;

[0127] The short message sample library, the first fingerprint library and the first classifier are trained according to the set butterfly cross training strategy to obtain the trained second fingerprint library and the trained second...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The embodiment of the invention discloses an identification method and device for junk short messages and a storage medium. The method can comprise the steps of: generating a first fingerprint libraryand a first classifier according to short message samples in a short message sample library and indication information corresponding to each short message sample, wherein the indication information is used for indicating whether the corresponding short message samples are junk short messages; training the short message sample library, the first fingerprint library and the first classifier according to a set butterfly cross training strategy to obtain a second fingerprint library after training and a second classifier after training; and based on a set serial verification strategy, the secondfingerprint library and the second classifier, verifying a to-be-verified short message, and determining a verification result of the to-be-verified short message, wherein the verification result comprises that the to-be-verified short message is a junk short message or the to-be-verified short message is not a junk short message. Complementation of two junk short message identification technologies can be implemented, and a success rate of identification can also be improved.

Description

technical field [0001] The invention relates to the technical field of communications, in particular to a spam short message identification method, device and storage medium. Background technique [0002] With the development of the SMS service, more and more users are harassed by spam messages. At present, the identification technology of spam text messages usually adopts the identification method based on machine learning. Such a method needs to learn from a large number of manually calibrated text message samples, so that the machine has the ability to automatically classify text messages. [0003] At present, spam SMS identification methods based on machine learning are mainly divided into two categories: fingerprint matching method and classifier method. Among them, the fingerprint matching method is a fuzzy matching method. Its principle is to firstly extract the fingerprint features of the calibrated SMS samples based on SimHash and other deduplication algorithms, an...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): H04W4/14H04W12/12G06K9/00G06K9/62H04W12/128
CPCH04W4/14H04W12/12G06V40/1365G06F18/24G06F18/214
Inventor 张滨娄涛林华生贾强周莹
Owner CHINA MOBILE COMM GRP CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products