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

Travel target point identification method and device, and model development and evaluation method and device

A technology for identifying models and evaluating methods, which is applied in the field of data processing and can solve problems such as the inability to effectively reflect the fit of classification models.

Inactive Publication Date: 2020-01-10
RES INST OF HIGHWAY MINIST OF TRANSPORT
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Therefore, the technical problem to be solved by the present invention is that the model evaluation method of the prior art cannot effectively reflect the degree of fit between the output result of the classification model and the real situation, thereby providing a target point recognition method and device, model development, evaluation Method and device

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
  • Travel target point identification method and device, and model development and evaluation method and device
  • Travel target point identification method and device, and model development and evaluation method and device
  • Travel target point identification method and device, and model development and evaluation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] Among the current identification methods for transfer points in the process of traffic travel, the more accurate and fast method is to identify the transfer points through the classification model. There is an error between the sequence and the sequence formed by the real transfer point, such as figure 1 As shown, two transition point sequences identified by the classification model are listed, and the identified transition point sequences are compared with the real transition point sequences, from figure 1 It can be seen that there is a dislocation and expansion in the time series between the recognition transition point sequence identified by the existing model and the real transition point sequence.

[0041] An embodiment of the present invention provides a method for evaluating a travel target point recognition model, such as figure 2 shown, including the following steps:

[0042] Step S110: Identify the travel data according to the preset travel target point rec...

Embodiment 2

[0081] An embodiment of the present invention provides a method for developing a travel target point recognition model, such as Figure 7 shown, including:

[0082] Step S210: Obtain multiple pieces of travel data, the travel data includes a training set and a verification set, wherein each piece of travel data consists of multiple sampling points.

[0083] Step S220: Extract the feature values ​​of each sampling point in the training set and the feature values ​​of each sampling point in the verification set.

[0084] In a specific embodiment, the eigenvalue of each sampling point is calculated based on the sampling point sequence formed by N time length windows before and after the sampling point, when the eigenvalues ​​of the N sampling points before and after the travel data, the point Since the window calculation conditions are not satisfied, its eigenvalues ​​cannot be calculated. In this embodiment, referring to the padding algorithm of the filter in the convolutional ...

Embodiment 3

[0115] An embodiment of the present invention provides a method for identifying travel target points, such as Figure 13 shown, including:

[0116] Step S310: Obtain travel data to be predicted, each travel data is composed of multiple sampling points;

[0117] Step S320: Extract the feature values ​​of each sampling point in the travel data to be predicted. For detailed description, see the description of step S220 in the above-mentioned embodiment 2.

[0118] Step S330: Input the characteristic value of each sampling point in the travel data to be predicted into the travel target point recognition model to obtain the target point sequence. The travel target point recognition model is obtained according to the travel target point recognition model development method provided in the above-mentioned embodiment 2, described in detail See the description of the travel target point recognition model development method in the above-mentioned embodiment 2.

[0119] The travel targ...

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 provides a travel target point identification method and device, and a model development and evaluation method and device, and the travel target point identification method mainly comprises the steps: carrying out the identification of travel data according to a preset travel target point identification model, and generating an identification conversion point sequence; obtaining a real conversion point sequence of the travel data; calculating a preset model evaluation index according to the identification conversion point sequence and the real conversion point sequence, wherein the preset model evaluation index comprises a target behavior start-stop moment error, a target behavior duration error, a target behavior center point offset distance and an accuracy rate; and determining an evaluation result of the travel target point identification model according to a preset model evaluation index. Through the implementation of the method and the device, the evaluation result not only reflects the accuracy, but also can reflect the error conditions such as stretching and staggering on the time sequence between the conversion point sequence identified by the travel target point identification model and the real conversion point sequence, so that the evaluation result is more practical.

Description

technical field [0001] The invention relates to the field of data processing, in particular to a travel target point recognition method and device, model development and evaluation method and device. Background technique [0002] Urban diseases such as traffic congestion caused by the imbalance between traffic demand and supply will cause unnecessary economic losses. At the same time, traffic management faces endless new challenges. Whether it is traffic infrastructure construction, traffic organization management, or traffic operation management, traffic demand analysis is required. , travel characteristics analysis, master traffic demand characteristics. Traffic behavior is a derived demand, people are always the main body of traffic, and people's preferences (attribute characteristics) are factors that determine travel characteristics such as traffic travel modes. Therefore, the analysis of the characteristics of traffic travel should start from each traffic subject, and...

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): G06Q10/06G06Q50/26G06N20/20G06N3/04G06N3/08G06F16/29
CPCG06Q50/26G06Q10/06393G06N20/20G06N3/08G06F16/29G06N3/045
Inventor 查文斌刘冬梅张劲泉赵琳张晓亮郭宇奇侯德藻汪林王文静王海鹏乔国梁王晶丁丽媛
Owner RES INST OF HIGHWAY MINIST OF TRANSPORT
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