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

Bus track similarity calculation method based on twin neural network

A technology of neural network and calculation method, applied in the direction of biological neural network model, neural learning method, calculation, etc., to achieve the effect of optimizing generalization ability, increasing feature distance, and reducing feature distance

Pending Publication Date: 2022-08-05
ZHENGZHOU TIAMAES TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] Aiming at the current defects and problems in the calculation of bus trajectory similarity, the present invention provides a method for calculating the similarity of bus trajectory based on twin neural networks

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
  • Bus track similarity calculation method based on twin neural network
  • Bus track similarity calculation method based on twin neural network
  • Bus track similarity calculation method based on twin neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] Embodiment 1: This embodiment provides a method for calculating the similarity of public transport tracks based on a twin neural network, and the method includes the following steps:

[0033] Step 1: Build a bus line set, select two bus lines from the bus line set, and perform line preprocessing on the two bus lines respectively; the line preprocessing includes the following steps:

[0034] S1. Obtain the spatial coordinate point sequence of the line

[0035] S2. Encrypt the nodes of the line;

[0036] S3. Convert the space coordinate point from the plane coordinate to the polar coordinate

[0037] S4. Complete the embedded vectorized expression of the data in combination with the neural network;

[0038] Step 2. Sample data organization

[0039] Translate the bus lines, take the translated lines as similar trajectories, and use them as positive samples, randomly sample from the line set to obtain negative samples, and obtain organized training samples, each of which...

Embodiment 2

[0050] Embodiment 2: This embodiment provides a method for calculating the similarity of public transport tracks based on a twin neural network. The following is a calculation process and method for similarity of public transport tracks through line preprocessing, sample data organization, model construction, model training and prediction. describe.

[0051] 1. Line preprocessing

[0052] Points, lines, and areas are the three core spatial data types, and bus lines are typical line spatial data types. In the field of GIS, a line is composed of an ordered sequence of points. In this embodiment, the Open Geospatial Consortium (OGC) (Open GIS Consortium) formulates a line-spatial data type vector structure represented by the Well-know Text text markup language, such as LineString(((0 ,0),(1,1))), where ((0,0)(1,1)) is the sequence of spatial coordinate points representing the line.

[0053] This embodiment encrypts the nodes of the line space data, and also considers the partic...

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 belongs to the technical field of public transportation, and particularly relates to a bus track similarity calculation method based on a twin neural network. According to the method, two bus routes are selected from a bus route set, space coordinate point sequences of the routes are obtained for the two bus routes respectively, nodes are encrypted, then space coordinate points are converted into polar coordinates, embedded vectorization expression of data is completed in combination with a neural network, the learning ability of a deep learning algorithm is fully utilized, and the method is more efficient and more reliable. And feature extraction is carried out through the line expression after neural network conversion, and similarity calculation is carried out. According to the method, the feature distance between the similar lines can be reduced, and meanwhile, the feature distance between the dissimilar lines can be increased, so that the similarity measurement of the spatial linear units is more accurate and has better generalization ability.

Description

technical field [0001] The invention belongs to the technical field of public transportation, and in particular relates to a method for calculating the similarity of public transportation tracks based on a twin neural network. Background technique [0002] The bus line is a typical spatial type of data, and its source can be the bus line planning or management system, or the actual running track of the bus line (collecting coordinate points through the vehicle-mounted GPS). Measuring the similarity of bus lines in spatial location and spatial structure can provide a basis and reference for the optimization of bus network. [0003] Similarity is a fundamental problem in artificial intelligence research. Image classification can be understood as calculating the similarity between the image to be classified and known types, while text classification can be understood as the semantic similarity between the text to be classified and known types. Similarity is the core research ...

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): G06F16/29G06K9/62G06N3/04G06N3/08G06Q50/26
CPCG06F16/29G06N3/084G06Q50/26G06N3/045G06F18/22Y02T10/40
Inventor 郭建国郑东东渠华孙浩普秀霞王宏刚李俊辉邓杰荣张洋存
Owner ZHENGZHOU TIAMAES TECH
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