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

Method for applying text mining to road traffic accident data processing

A technology of road traffic and text mining, which is applied in electronic digital data processing, text database query, special data processing applications, etc. Due to accurate analysis and efficient processing

Inactive Publication Date: 2019-08-16
CENT SOUTH UNIV
View PDF3 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] To sum up, the quality of traffic accident data needs to be improved urgently, and the existing solutions to the problem of incomplete data have shortcomings such as unreliable repair ability and excessive original data that are difficult to find out by relying on a single accident.

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 for applying text mining to road traffic accident data processing
  • Method for applying text mining to road traffic accident data processing
  • Method for applying text mining to road traffic accident data processing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0026] In this embodiment, the data is firstly processed and the model is constructed. The present invention uses python as the main language, uses the open source library jieba to perform Chinese word segmentation on the sample, and then uses the word2vec model to vectorize the data set in three dimensions, and finally uses volume The product neural network CNN is used to build the TextCNN network to realize the model.

[0027] 1.1 Chinese word segmentation

[0028] Such as figure 1 As shown, Chinese word segmentation refers to the process of recombining Chinese character sequences into word sequences according to the specification of extracting special words. The key step is to remove stop words, which means that in information retrieval, when processing natural language data, some words that are not necessary for this word are filtered out. Words, characters and words that have no actual meaning in text data, so as to save storage space and improve search efficiency.

[0...

Embodiment 2

[0046] A method of text mining applied to road traffic accident data processing, which performs Chinese word segmentation on road traffic accident data samples, three-dimensionally vectorizes the sample data set through a word embedding model, and then builds a large-scale text classification network TextCNN through a neural network CNN The network builds a model and outputs key traffic information.

[0047] Furthermore, the Chinese word segmentation of the road traffic accident data sample includes: on the basis of the universal corpus of the open source library jieba itself, according to the characteristics of the scene, import the traffic safety corpus as a custom lexicon, perform word segmentation on the sample, and then Remove stop words, delete texts that have nothing to do with judgment, and enhance the ability to correct ambiguities.

[0048] Furthermore, the three-dimensional vectorization of the sample data set through the word embedding model further includes: accor...

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 for applying text mining to road traffic accident data processing. The method comprises the following steps of carrying out Chinese word segmentation on the road traffic accident data sample, carrying out three-dimensional vectorization on the sample data set through a word embedding model, establishing a large-scale text classification network TextCNN through a neural network CNN, and outputting key traffic information. According to the invention, the traffic accident record text is processed based on the natural language processing technology. T he python language and the c + + language are comprehensively applied to develop the accident cause repair system, accident data records can be automatically processed on a large scale, the quality of the accidentdata is effectively improved, and the accident cause repair system is easy and convenient to operate, efficient in processing, visual in information and accurate in cause analysis; text data are fully applied and are convenient to use in the process of establishing the model. The manufacturing cost is low, the defect of structural recording of road traffic accidents in China is effectively overcome, and traffic accident data can be efficiently and accurately repaired.

Description

technical field [0001] The invention relates to the technical field of road accident processing, in particular to a method for text mining applied to road traffic accident data processing. Background technique [0002] Driven by the strategy of building a strong transportation country, my country's road transportation has entered a transition period from high-speed growth to high-quality development, and traffic safety issues have attracted much attention and attention. Traffic accident data is the core data source of traffic safety research, providing basic intelligence support for road safety improvement. In recent years, the comprehensive application of the public security traffic management comprehensive application platform ("six-in-one" platform) has effectively improved the informatization level of traffic accident handling and historical accident archiving. However, according to the 2014 Road Traffic Statistical Annual Report of the People's Republic of China, in th...

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): G06F17/27G06F16/33G06F16/35G06N3/04
CPCG06F16/35G06F16/334G06F40/279G06N3/045
Inventor 黄合来周汉楚潘震宇张子钰秦炜志张馨尹丁雨童
Owner CENT SOUTH UNIV
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