Method and system for preventing phone fraud based on end-side network cloud collaboration

A technology of telephone and network cloud, applied in telephone communication, electrical components, automatic switching office, etc., can solve the problems such as the need to improve the recognition efficiency and accuracy, the inaction of the perpetrators of telephone fraud, and the increase of terminal complexity and cost, etc. Achieve the effect of reducing the number and transmission path length, ensuring reliability, and improving security

Pending Publication Date: 2021-10-29
SHANDONG NORMAL UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] (1) The terminal needs to monitor the content of the call in real time during the call, which increases the complexity and cost of the terminal
[0008] (2) In the process of preventing telephone fraud, the coordination of terminals, multi-access edge computing nodes, network, and cloud is not fully utilized, and the recognition efficiency and accuracy need to be improved
[0009] (3) When suspicious or dangerous content is analyzed, th

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
  • Method and system for preventing phone fraud based on end-side network cloud collaboration
  • Method and system for preventing phone fraud based on end-side network cloud collaboration
  • Method and system for preventing phone fraud based on end-side network cloud collaboration

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] 5G mobile communication technology not only considers meeting the communication needs between people, but also meets the communication needs between people and things, and things and things. Therefore, network slicing is introduced. Network slicing is to divide a physical network into multiple end-to-end through virtualization. Logical network, each virtual network corresponds to different application scenarios. At present, there are mainly three types of slices: eMBB (enhanced mobile broadband), mMTC (massive machine connection) and uRLLC (ultra-high reliability, low latency). Slicing can provide mS-level delay and 99.999% reliability. On the other hand, through logical isolation, network transmission is safer. In addition, edge computing (MEC) technology, which evolved from traditional cloud computing technology, sinks strong computing resources and efficient services to the edge of the network, thereby having lower latency, lower Energy efficiency and better privacy...

Embodiment 2

[0071] Such as figure 2 As shown, this embodiment provides a multi-access edge computing platform, including:

[0072] The first receiving unit is configured to receive call characteristic information sent by the terminal, and the call characteristic information is sent after the terminal performs a preliminary diagnosis on the caller number and sensitive words;

[0073] The second receiving unit is configured to receive the telephone fraud identification model sent by the cloud, and the telephone fraud identification model is constructed and trained by the cloud based on the training samples;

[0074] The decision-making unit is configured to judge the call characteristic information based on the telephone fraud identification model;

[0075] The sending unit is configured to send alarm information to the terminal according to the judgment result, and upload the call feature information and the judgment result to the cloud, so that the cloud can update the training samples ...

Embodiment 3

[0079] Such as image 3 As shown, the present embodiment provides a cloud platform, including:

[0080] The computing unit is configured to construct and train a telephone fraud recognition model and preliminary diagnosis and recognition rules based on training samples;

[0081] The sending unit is configured to send the phone fraud recognition model to the multi-access edge computing platform, and send the preliminary diagnosis and recognition rules to the terminal;

[0082] The receiving unit is configured to receive the call characteristic information and the judgment result uploaded by the multi-access edge computing platform.

[0083] In this embodiment, the cloud platform further includes a storage unit configured to store the telephone fraud information uploaded by the multi-access edge computing platform.

[0084] In this embodiment, the cloud platform further includes an update unit configured to update the training samples according to the phone fraud information u...

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 invention discloses a method and a system for preventing phone fraud based on end-side network cloud collaboration, which are implemented at a multi-access edge computing node and comprise the following steps: receiving call feature information sent by a terminal, and sending the call feature information after the terminal performs preliminary diagnosis on an incoming call number; receiving a telephone fraud recognition model sent by the cloud, wherein the telephone fraud recognition model is constructed and trained by the cloud based on the training sample; and judging the call feature information based on the telephone fraud recognition model, sending alarm information to the terminal according to a judgment result, and uploading the call feature information and the judgment result to a cloud end, so that the cloud end updates the training sample and optimizes the telephone fraud recognition model. Call features obtained at a terminal and an identification model pre-trained at a cloud end are sent to a multi-access edge computing node, an identification and judgment process is performed at the multi-access edge computing node, the synergistic effect of the terminal, the multi-access edge computing node, a network and the cloud end is fully played, the terminal complexity is not increased, and the identification efficiency and accuracy are effectively improved.

Description

technical field [0001] The present invention relates to the technical field of mobile communication, in particular to a method and system for preventing phone fraud based on terminal-edge-network-cloud collaboration. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] At present, there are two main methods to prevent telephone fraud. One is Internet companies such as Baidu, Qihoo, and Tencent. Through the terminal software of mobile assistants, numbers, and mobile housekeepers, users spontaneously mark the received numbers and record them in the background. After a large number of user's marking information, a number marking database is established, which is sent to all terminals through the server to prompt users. Another type of recognition method is to use speech recognition technology to identify whether key speech semantics appear in a s...

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): H04M3/22H04W12/12
CPCH04M3/2281H04W12/12
Inventor 冯传奋徐磊付宏志许鸿奎
Owner SHANDONG NORMAL UNIV
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap