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

Method and device for automatically classifying and distributing city events based on depth learning

An automatic classification and deep learning technology, applied in the field of automatic classification and distribution of urban events, can solve the problem of high error rate of processing methods, and achieve the effects of low labor cost, improved delivery accuracy, and improved classification accuracy.

Active Publication Date: 2019-02-12
吉奥时空信息技术股份有限公司
View PDF10 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of the above problems, the purpose of the present invention is to provide a method and device for automatically classifying and dispatching urban events based on deep learning, aiming to solve the problem of high error rate in existing processing methods

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 device for automatically classifying and distributing city events based on depth learning
  • Method and device for automatically classifying and distributing city events based on depth learning
  • Method and device for automatically classifying and distributing city events based on depth learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0071] Such as figure 1 As shown, the deep learning-based automatic classification and distribution method for urban events provided by the embodiment of the present invention includes the following steps:

[0072] Step S1, collecting urban event data and preprocessing.

[0073] Assume that what needs to be collected and preprocessed is the event data of city A. The city event is a city problem reported by citizens through hotlines, government websites, mobile terminals, etc. , the form of urban events may be text or voice, urban events in voice form are used as the input data of the system, voice conversion text can be added, so that it can be used as urban event text data.

[0074] The step S1 specifically includes the following steps:

[0075] Step S1.1. Collect the text data of urban events in the city over the years. Assume that the city is city A, and combine the commonly used word segmentation dictionary to filter the collected text data by word segmentation to obtain...

Embodiment 2

[0108] Such as image 3 As shown, the present invention provides a device for automatically classifying and dispatching urban events based on deep learning, which is used to complete the method for automatically classifying and dispatching urban events based on deep learning provided by the present invention. The device for automatically classifying and dispatching urban events based on deep learning includes :

[0109] Data processing module: used to collect and preprocess urban event data;

[0110] Event classification model building module: used to construct an event classification convolutional neural network model from collected and processed urban event data;

[0111] Geographic coordinate information module: used to calculate the standard geocoding of urban event occurrence places;

[0112] Event dispatching model building block: used to construct urban event dispatching convolutional neural network model;

[0113] Event output module: used to receive the currently i...

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 is applicable to the intelligent technology field of intelligent city information, and provides a method and device for automatically classifying and distributing city events based on depth learning. The method comprises the steps of collecting city event data and preprocessing; according to the collected and processed urban event data,constructing the event classification convolution neural network model; calculating the standard geo-code of the city where the event takes place; constructing a convolution neural network model of urban event dispatch; receiving the current inputcity event data, calling a classification convolution neural network model to output the classification category, obtaining the standard geo-code of the current city event data, then calling the dispatch convolution neural network model to output the specific city event dispatch department. The invention can improve the correctness of the event classification and the accuracy of dispatching. As that convolutional neural network model is dispatched, compared with various uncertainty brought by manual dispatch, the accuracy of machine dispatching is higher, and the machine in the invention can effectively improve the operation efficiency of the system according to a result obtained by a single operation of the model.

Description

technical field [0001] The invention belongs to the technical field of smart city information intelligence, and in particular relates to a method and device for automatically classifying and dispatching urban events based on deep learning. Background technique [0002] The 12345 mayor’s special line platform is a system platform that receives complaints from citizens. Its work flow is as follows: for daily complaints from citizens, the operator at the front desk accepts them, and summarizes the category of the incident according to the content and nature of the incident. , and then transfer the complaint event to the corresponding handling agency or government department according to the category and the place where the event occurred. This process requires the wiring personnel to have a very clear understanding of the nature of all events, the detailed address of the event and the relationship between the corresponding processing department. If the dispatch is wrong, the pr...

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): G06F16/35G06N3/04G06N3/08G06Q50/26
CPCG06N3/08G06Q50/26G06N3/048G06N3/045
Inventor 吴杰王琳杨曦刘奕夫沈满周游宇张定祥贺楷锴官磊张立朱斌寇晓松
Owner 吉奥时空信息技术股份有限公司
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