Vehicle OD flow prediction model construction method and vehicle OD flow prediction method

A technology of prediction model and construction method, which is applied in traffic flow detection, neural learning method, biological neural network model, etc. Effect

Active Publication Date: 2019-07-26
CHANGAN UNIV
View PDF3 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The limitation of this method is that it does not make full use of the characteristics of the precis...

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
  • Vehicle OD flow prediction model construction method and vehicle OD flow prediction method
  • Vehicle OD flow prediction model construction method and vehicle OD flow prediction method
  • Vehicle OD flow prediction model construction method and vehicle OD flow prediction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] The OD flow prediction model building method of this embodiment includes:

[0040] Step1, data processing:

[0041] (1) Obtain the taxi trajectory data in the target area, the taxi trajectory data includes the taxi label, license plate number, GPS sampling time, GPS geographic location, and passenger loading status;

[0042] (2) Clean the taxi trajectory data, remove invalid data, format errors and abnormalities, data that have not changed in GPS location within a certain period of time, and are not in the target area, and obtain qualified data;

[0043] Step2, use the map matching algorithm based on Hidden Markov to map the qualified data; the purpose of matching is to correct the error of GPS data;

[0044] Step3, extract OD stream information (comprising the number of trips between ODs and the travel time between ODs) according to the passenger status data from the GPS data of qualified data, the GPS data includes GPS sampling time and GPS geographic location; and t...

Embodiment 2

[0057] The difference between this embodiment and embodiment 1 is that the following operations are performed on the data before data training:

[0058] As shown in Figure 3, the method of rotation and cropping is a compression method obtained by observing the distribution of the obtained matrix. Especially for the travel time matrix and the number of trips matrix in this problem, the block compression process is an existing technology, that is, compressed sparse The storage method of the matrix can be either csr_matrix (Compressed Sparse Row matrix) or csc_matric (Compressed Sparse Column matrix). Both csr_matrix and csc_matric are sparse matrix storage methods in the sparse module of the SciPy toolkit. Scipy is a common software package used in the fields of mathematics, science, and engineering. It can handle problems such as interpolation, integration, optimization, image processing, and sparse matrix storage. The purpose is to facilitate fast access to data, reduce the t...

Embodiment 3

[0060] The city-scale fine-grained taxi OD flow prediction method of the combined travel time of this embodiment includes:

[0061] Step 1, extract a fine-grained representation method of OD flow nested in traffic analysis area and road network, by dividing the urban area into traffic areas, and at the same time locate the departure and destination of taxis on the roads in the traffic area, realize Refined representation of OD streams;

[0062] 1.1 According to the grid division method, the urban road network is divided into grids, with equal intervals in the horizontal and vertical directions, and the urban area is divided into J (32) parts in the horizontal direction, and divided into I in the vertical direction. (32) copies, a total of I×J (1024) rectangular grids can be obtained, and each grid position can be represented by Grid(i, j);

[0063] 1.2 Scan the divided 1024 rectangular grids. The scanning is carried out in the first row and then the column. For each scanned g...

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 vehicle OD flow prediction model construction method and a vehicle OD flow prediction method. In the vehicle OD flow prediction model construction method, a multi-granularityspace partitioning method using grid and road segment nesting is used for representing vehicle OD data at regional and road node levels; the number of trips and travel time between the OD are extracted simultaneously; and a deep prediction model LSTM-traf-deepCNN mixed with CNN and LSTM is used for predicting the OD flow combined with OD travel time. Compared with the traditional OD flow prediction method, the method disclosed by the invention fully considers the implicit relationship between the travel time and the OD flow, and trains the deep network by combining the travel time and the number of trips between the OD; and the obtained model has more accurate predictive power. The invention belongs to the technical field of transportation information engineering and can be used for predicting the OD flow of city-scale taxis.

Description

technical field [0001] The invention relates to vehicle traffic flow prediction technology, in particular to a vehicle OD flow prediction model building method and a vehicle OD flow prediction method. Background technique [0002] The purpose of vehicle OD flow prediction is to know the travel demand between a departure point and destination in a certain period of time in the future, and its time-domain aggregation value can reflect the spatio-temporal distribution of vehicle passenger travel flow and arrival flow. Especially for taxis, accurate forecasting of taxi OD flow is helpful for taxi operation and scheduling, balancing the supply and demand differences between different urban areas, and transferring taxis in areas with oversupply to areas with undersupply. [0003] For urban vehicles, the trajectory data records the passenger status, GPS trajectory and time. Through the analysis of passenger status changes, combined with GPS location information, the passengers' pic...

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): G08G1/01G06N3/04G06N3/08
CPCG08G1/0125G06N3/08G06N3/045G06N3/044
Inventor 陈柘赵斌张凯段宗涛唐蕾樊娜杨云倪圆圆
Owner CHANGAN UNIV
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap