Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Intelligent information interception method based on big data and neural network

A technology of neural network and neural network model, which is applied in the field of information intelligent interception based on big data and neural network, can solve the problems of misinterception of information, third-party platform account can not be effectively intercepted, etc., to simplify the algorithm and speed up data processing , Speed ​​up the effect of processing and judgment

Pending Publication Date: 2021-06-04
杭州宽信科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The invention provides an information intelligent interception method based on big data and neural network, aiming to solve the problem in the prior art that the network links and third-party platform accounts contained in the information cannot be effectively intercepted or the information is incorrectly intercepted

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
  • Intelligent information interception method based on big data and neural network
  • Intelligent information interception method based on big data and neural network
  • Intelligent information interception method based on big data and neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0054] Such as figure 1 As shown, an information intelligent interception method based on big data and neural network includes the following steps:

[0055] S110. Obtain the first word vector of the first target content in the information to be recognized, input the first word vector into the neural network model for parallel training, and output the first confidence degree of the first target content;

[0056] S120. Obtain the probability that the junk information contains the preset second target content, perform model training according to the probability and the first confidence degree, and output the second confidence degree of the information to be identified;

[0057] S130. Obtain a past credit record of the communication method that sends the information to be identified, and judge whether to intercept the information to be identified based on the second confidence level and the past credit record.

[0058] According to Embodiment 1, it can be seen that the present in...

Embodiment 2

[0060] Such as figure 2 As shown, an information intelligent interception method based on big data and neural network, including:

[0061] S210. Perform semantic analysis on the information to be identified by using regular expressions, and obtain the first word vector of the first target content in the information to be identified. The first target content includes keywords, network links, and third-party platform accounts ;

[0062] S220. Preset the second word vector of the second target content, the second target content includes illegal keywords, illegal network links, and illegal third-party platform accounts, and input the first word vector and the second word vector neural network model;

[0063] S230. Perform summation and normalization processing on the first and second word vectors according to the neural network model, and output the first confidence degree of the keyword, network link, and third-party platform account;

[0064] S240. Obtain the probability tha...

Embodiment 3

[0068] Such as image 3 As shown, an information intelligent interception method based on big data and neural network, including:

[0069] S310. Obtain the first word vector of the first target content in the information to be recognized, input the first word vector into the neural network model for parallel training, and output the first confidence degree of the first target content;

[0070] S320. Using big data analysis technology to obtain the probability that the spam contains the second target content, and the second target content includes illegal keywords, illegal network links, and illegal third-party platform accounts;

[0071] S330. Input the first confidence degree and the probability into a neural network model for training, and obtain a second confidence degree of the information to be recognized, where the second confidence degree of the information to be recognized includes whether the information to be recognized is Confidence of spam;

[0072] S340. Obtain ...

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 an intelligent information interception method based on big data and a neural network. The method comprises the following steps: obtaining a first word vector of first target content in to-be-recognized information, inputting the first word vector into a neural network model for training, and outputting a first confidence coefficient of the first target content; obtaining the probability that junk information contains preset second target content, performing model training according to the probability and the first confidence coefficient, and outputting a second confidence coefficient of the to-be-recognized information; and obtaining a past credit record of a communication mode for sending the to-be-recognized information, and judging whether to intercept the to-be-recognized information based on the second confidence coefficient and the past credit record. According to the method, the information including the network link and the third-party platform account is effectively recognized, so that the probability of missing interception is reduced, and the phenomenon of mistakenly intercepting some non-junk information including similar junk information keywords and some smile information is reduced.

Description

technical field [0001] The invention relates to the field of communication technology, in particular to an information intelligent interception method based on big data and a neural network. Background technique [0002] With the continuous penetration of security issues such as network login and user identity authentication, the information industry has ushered in a period of recovery. In 2019, the national information business volume increased by 37.5% compared with the previous year, and the growth rate increased by 23.5 percentage points. The recovery of the information industry and the Internet The common development of the Internet has led to the fact that the content and types of information are no longer in a single form. Content such as network links, third-party platform accounts, and Internet terms appear in the information text, and forms such as sales information, Taobao swiping orders, and pyramid schemes also emerge in endlessly. Nowadays, Most of the informat...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F21/45G06F40/289G06F40/30G06N3/04G06N3/08
CPCG06F21/45G06F40/30G06F40/289G06N3/08G06N3/045
Inventor 骆利华徐锐
Owner 杭州宽信科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com