Traffic emergency identification method and system based on social network platform information

A social network platform and emergency technology, applied in the field of traffic emergency identification based on social network platform information, can solve the problems of mining and utilization of microblog information that has not yet been released to the public

Active Publication Date: 2020-12-08
NANJING UNIV OF SCI & TECH
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In the current monitoring methods of various traffic emergencies, the micro

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
  • Traffic emergency identification method and system based on social network platform information
  • Traffic emergency identification method and system based on social network platform information
  • Traffic emergency identification method and system based on social network platform information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0080] Such as figure 1 As shown, a kind of traffic emergency identification method based on microblog information of the present embodiment comprises the following steps:

[0081] Step S10, data preprocessing: crawling, preliminary screening and digitization of microblog information text;

[0082] Step S20, feature word selection: the information processed in step S10 is divided into training text and test text;

[0083] Step S30, word vector matrix construction: through Boolean weighting, construct the word vector matrix of training text and test text;

[0084] Step S40, event classification recognition: send the constructed test text word vector matrix to the SVM classifier, and then use the classification model to classify, obtain binary classification results, and then screen out traffic emergency information.

[0085] Such as figure 2 As shown, step S10 specifically includes:

[0086] Step S11, realize text crawling by web crawler, specifically: use code program to ...

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 traffic emergency identification method and system based on social network platform information. The method comprises the following steps: crawling, primarily screening and digitalizing social network platform information texts; segmenting the processed information into a training text and a test text; constructing word vector matrixes of the training text and the test text through Boolean weighting; and sending the constructed test text word vector matrix into an SVM classifier, then performing classification by using a classification model to obtain a binarization classification result, and further screening out traffic emergency information. The system comprises a data preprocessing module, a feature word selection module, a word vector matrix construction module and an event classification and recognition module. According to the invention, through mining of social network platform text information and processing and classification processing of a naturallanguage technology (NLP), a new information acquisition mode can be provided for traffic emergency identification so as to assist traffic operation and management related units and departments to realize traffic event monitoring.

Description

technical field [0001] The invention belongs to the field of intelligent transportation, and in particular relates to a method for identifying traffic emergencies based on social network platform information. Background technique [0002] The era of mobile Internet has given birth to a number of social networking platforms used by hundreds of millions of users, such as QQ, WeChat, Weibo, Facebook, Twitter and so on. Users share what they see and hear in real time through social networking platforms. It also contains information related to traffic emergencies. Although traditional traffic detection technologies, such as coils, microwave radar, and video, have more mature applications in traffic incident monitoring, with the continuous expansion of the expressway network, the detection range limitations of traditional technologies have given rise to the The need for updates and innovations in traffic incident monitoring technology. The massive amount of information shared b...

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): G06F16/35G06K9/62G06N3/00G06F40/284G06F40/289G06F16/951G06Q50/00
CPCG06F16/35G06N3/006G06F40/284G06F40/289G06F16/951G06Q50/01G06F18/2411
Inventor 何赏璐刘昭刘英舜
Owner NANJING UNIV OF SCI & TECH
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