RNNs-based method for automatic safety checking of short message

A SMS, security technology, applied in natural language data processing, instruments, computing and other directions, can solve the problems of discrimination, difficult expansion, inconsistent prison rules and so on

Inactive Publication Date: 2017-05-17
SHANDONG UNIV
View PDF2 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although formulating rules is sometimes effective, manual writing takes a lot of time, and it is difficult to expand, and the rules of each prison are not uniform, and some unreasonable sentence patterns cannot be judged by the rules

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
  • RNNs-based method for automatic safety checking of short message
  • RNNs-based method for automatic safety checking of short message
  • RNNs-based method for automatic safety checking of short message

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0060] A method for automatic security audit of SMS based on RNNs, such as figure 1 As shown, the specific steps include:

[0061] (1) Preprocessing is carried out to historical text message data, and preprocessing includes removing noise, Chinese word segmentation; Described removing noise includes removing the punctuation mark in the note, rejecting the note that word count is less than 3; Participle.

[0062] Words are the smallest meaningful language components that can move independently. Spaces are used as natural delimiters between English words, while Chinese uses characters as the basic writing unit, and there is no obvious distinguishing mark between words. Therefore, Chinese Word analysis is the foundation and key of Chinese information processing. We tag words according to the part of speech of each word in the sentence. For example: "We form a team", the part-of-speech tag is: we ad / combination v / cheng v / one m / team n / , the result of Chinese word segmentation is...

Embodiment 2

[0091] According to the method for a kind of RNNs-based short message automatic security review described in embodiment 1, its difference is:

[0092] Described step (2), extract feature based on the CBOW model of Hierarchical Softmax, the block diagram of CBOW model is as figure 2 As shown, it specifically includes: maximizing the optimization function of the CBOW model based on Hierarchical Softmax, and training to obtain the word vector of each Chinese word segmentation; the optimization function of the CBOW model based on Hierarchical Softmax is shown in formula (I):

[0093]

[0094] C is a corpus, and w refers to any word obtained after Chinese word segmentation in step (1); Context(w) is the context of w.

[0095] The word vector of each word is trained by maximizing this likelihood function. When the training converges, words with similar meanings will be mapped to similar positions in the vector space. In our model, word vectors are trained through Sogou corpus, ...

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 relates to an RNNs-based method for automatic safety checking of a short message. The method specifically comprises the steps that (1) historical data is pre-processed, wherein preprocessing comprises noise removal and Chinese word segmentation; (2) characteristics of the historical data which is already pre-processed at the step (1) are extracted, so word vectors can be generated; and (3) a classification model which integrates RNNs and Naive Bayes is used to conduct real-time classification of short message texts. According to the invention, workloads of police officers in manual checking are reduced.

Description

technical field [0001] The invention relates to a method for automatic security review of short messages based on RNNs, and belongs to the technical fields of natural language processing, deep learning, named entity recognition, and the like. Background technique [0002] With the development of the Internet and information technology, in order to improve the caring services for prisoners, many prisons have opened SMS service content. Inmates can send text messages (text content) to their families through specific devices, which improves the family relationship between prisoners and their families. , to improve the level of renovation quality. [0003] At present, the SMS service is very popular among prisoners, so the number of messages sent is very large, especially during holidays. These SMS messages need to be manually reviewed by the police, which is time-consuming and labor-intensive, and brings a great burden to the work of the police. Some places have adopted some t...

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): G06F17/30G06F17/27G06K9/62
CPCG06F16/355G06F40/284G06F18/24155
Inventor 李玉军油丽娜王玥张洁
Owner SHANDONG 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