A visual analysis method for latent factors in route selection based on online car-hailing trajectory
A technology of route selection and analysis method, applied in the field of transportation, which can solve the problems of complex route selection behavior, insufficient accuracy of GPS equipment, and missing trajectory data.
Active Publication Date: 2022-06-28
NORTHEAST NORMAL UNIVERSITY
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
When the interaction of various factors such as time and driver's style preference is considered comprehensively, the problem of route selection behavior is even more complicated. The difficulties are mainly reflected in the following aspects: First, the trajectory data consists of a series of Due to the lack of accuracy of GPS equipment, there are a large number of missing and wrong values in the collected trajectory data.
Second, under different travel paths, the length of the constructed road trajectory sequence is inconsistent, and it is difficult to measure the similarity of the original trajectory sequence
Third, the potential factors affecting path selection are complex and diverse, and how to effectively quantify their respective influences and conduct reasonable verification is challenging
However, such pilot studies are usually conducted with a limited number of users in a limited space-time scale, such as collecting only morning commute travel data
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0047] The technical solution of the present invention will be further described in detail below in conjunction with the accompanying drawings, but the protection scope of the present invention is not limited to the following description.
[0048] like figure 1 As shown, the road network matching is the process of associating the longitude and latitude information of a series of ordered travel trajectories with the electronic map road network. Its main purpose is to track vehicle driving routes, analyze traffic flow and discover the origin of driving directions. Map matching corresponds to the decoding problem in the Hidden Markov Model (HMM). Based on the Hidden Markov Model, it is to find the hidden sequence that produces this observation sequence under the given observation premise. The hidden sequence represents the specific location of the person or object holding the positioning device, and the observation sequence represents a series of coordinates composed of GPS trac...
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
Login to View More Abstract
The invention discloses a method for visually analyzing latent factors in path selection based on the trajectory of online car-hailing vehicles, which includes the following steps: obtaining a set of trajectory data points of online car-hailing orders, performing road network matching on each trajectory point, and obtaining the location of the road. Number; for each online car-hailing order, extract the road number that the online car-hailing car of the order passes through in the selected interval, convert the road number of each online car-hailing order into a road sequence, and calculate the similarity matrix of the road sequence ;Project the obtained similarity matrix as input, and extract trajectory clusters with similar attributes, extract frequently occurring subsequences as key paths; count the influencing factors related to the driver's path selection for each path, and obtain through the weight model The user's subjective selection of the relevant factors of each path and the analysis of the importance of different factors to the ranking results. The invention provides a visual basis for travel route planning between urban areas, online car-hailing scheduling and traffic guidance.
Description
technical field [0001] The invention relates to the field of transportation, in particular to a method for visually analyzing latent factors in route selection based on online car-hailing trajectories. Background technique [0002] In the era of rapid development of modern information technology, with the application and popularization of GPS equipment, a large amount of moving track information of people and vehicles is collected. These data can truly and comprehensively reflect the relevant information of urban traffic and personnel flow. Urban computing combines urban perception, data acquisition, data management, data analysis, and service provision into a complete process to help understand the nature of various urban phenomena and improve people's living standards. Transportation is one of the most important application domains in urban computing. Many transportation systems analyze the mobility of people within a city by combining multi-source heterogeneous data suc...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06Q10/08G06Q30/06G06Q50/30G08G1/01
CPCG06Q10/08355G06Q30/0645G06Q50/30G08G1/0104G08G1/0125
Inventor 张慧杰吕程蔺依铭田良曲德展
Owner NORTHEAST NORMAL UNIVERSITY