Data-driven urban road network traffic zone multi-level division method

Abstract

The invention discloses a data-driven urban road network traffic zone multi-level division method. The method comprises the following steps: S1, clearing out a division region, and acquiring travelingdata of the division region, wherein the travelling data comprises origin-destination attribute information of the traveling; S2, extracting effective traveling data in combination with an actual demand through the traveling data of the S1; S3, counting a traveling origin-destination pair and the corresponding traveling quantity based on the effective traveling data; S4, constructing a travellingnetwork of the division region by applying the traveling origin-destination pair and the corresponding traveling quantity data; and S5, performing traffic zone division on the division region by applying the community discovery algorithm by combining the traveling network of the S4. Based on the traveling data, the data size is large, the research space-time range is large, and the traveling activity of the whole urban road network can be comprehensively and really reflected, the analysis result is more real; secondly, the corresponding traveling data is acquired according to actual demand to accomplish the multi-level dynamic division of the specific traffic zone, and the flexibility and the pertinence of the method are strong.

Description

Technical field [0001] The present invention relates to the technical field of traffic engineering, and more specifically, to a data-driven multi-level division method of urban road network traffic districts. Background technique [0002] A traffic zone refers to a collection of nodes and road sections with a certain degree of traffic relevance and traffic similarity. There are certain differences in the temporal and spatial characteristics of traffic in different traffic zones. In recent years, with the continuous acceleration of urbanization, the scale of urban roads is also increasing, the road network is crisscrossed, and the transportation network is becoming more and more complex. In order to enhance the operability of traffic investigation, the workload of traffic investigation should be reduced as much as possible. The complexity of traffic forecast analysis divides the entire urban traffic network into several traffic areas, and then conducts relevant traffic analysis fo...

AI Technical Summary

Problems solved by technology

All the above methods have certain limitations. They are greatly affected by the physical facilities in the road network, and are easily affected by factors such as administrative divisions and natural barriers. Manual intervention is required, and there is strong subjectivity, which makes the representativeness and persuasiveness of the classification results not strong

In addition, the division process of the traffic area is relatively mechanical, and it is difficult to adjust flexibly according to the actual situation, that is, it is impossible to realize the multi-level dynamic division of the traffic area

Images