Bus stop position recommendation method based on multi-source data hierarchical graph clustering algorithm

Abstract

The invention discloses a bus stop position recommendation method based on a multi-source data hierarchical graph clustering algorithm, and the method comprises the steps: firstly generating a city POI attraction graph network through employing city POI information and taxi passenger flow demand records; then, according to the generated urban site attraction map network, through a hierarchical map clustering method, extracting a region of interest (WROI) with walking scale constraint and high people flow density; and finally, comparing the region of interest with walking scale constraint and high people flow density with the public transport network diagram, and recommending public transport station position arrangement for the blank service region. According to the method, the bus stations with low efficiency and low passenger flow density in the current bus network can be optimized, new station position arrangement can be recommended to the blank service city area, and the pre-judged bus passenger flow rule and density can be given according to the city function.

Description

technical field [0001] The invention relates to the field of location selection and optimization of bus stations, and specifically provides a location recommendation method for bus stations based on a multi-source data hierarchical graph clustering algorithm. Background technique [0002] The optimization and development of the public transport network is crucial to modern urban transportation. Due to its high flexibility, easy deployment, and environmental protection, it is currently one of the main modes of urban travel. However, the share rate of bus trips is declining at present, and the main reasons hindering residents from choosing bus trips include (1) Due to the rapid urban development, the bus service configuration in the new developing area is not timely, resulting in no suitable bus stops within the walking area Available for travel; (2) The arrangement of bus stops is unbalanced, and the passenger flow density in some areas is too high, resulting in crowded bus c...

AI Technical Summary

Problems solved by technology

(1) Since the service area of ​​the bus station is usually an urban pedestrian-sized area with high traffic density, but the density-based clustering methods, such as DBSCAN, K-means clustering, when looking for the ROI suitable for the bus service area, in There are limitations in maintaining the balance between high activity / high density and ROI size, which leads to the inability to control the cluster size of the mined ROI, and often requires cutting operations, which can neither accurately recommend bus service areas nor ensure passenger flow density; 2) due to the The setting follows the principle of space-time demand response, that is, the OD flow of passengers in an area has a certain concentration in time and start-destination, so it is suitable to set up bus stops. The ROI excavated by simply using the cluster of taxi passenger flow will be concentrated on the road Unable to determine the service coverage area and obtain the time-varying passenger travel flow pattern, which has a great impact on the location accuracy of the recommended bus stop and passenger flow prediction

Images