Taxi driving fraud detection method based on space-time cost fusion framework

Abstract

A taxi driving fraud detection method based on a space-time cost fusion framework comprises the following steps: 1) data collection: using a taxi GPS positioning system as a data source, preprocessing original data, and reserving preprocessed traffic flow parameters to ensure the safety of sensitive information and the reliability of an analysis process; 2) abnormal trajectory detection: selecting a common trajectory, and performing multi-aspect comparison on the common trajectory and other trajectories to obtain an anomaly index so as to obtain an abnormal trajectory; 3) region anomaly detection: based on a result obtained in the step 2), calculating the density of each sub-graph in an abnormal trajectory, and obtaining an anomaly index of the region; and 4) result identification: performing comprehensive processing by combining the results obtained in the steps 2) and 3), and further classifying the abnormal trajectory to obtain a conventional abnormal trajectory and an unconventional abnormal trajectory. An abnormal track detection experiment carried out by taking a Wei'an taxi as an example shows that the method has excellent performance on solving the problem.

Description

technical field [0001] The invention relates to a taxi driving fraud detection method, which belongs to the field of urban traffic anomaly detection. The main function is to judge trajectory fraudulent behavior, and it is of great significance for detecting abnormal driving behavior, building a smart city, and the like. Background technique [0002] With the continuous development and popularization of GPS positioning and wireless sensor technology, the information obtained from taxis has become more and more abundant and dense, which provides an opportunity to understand the driver's driving trajectory. In the daily travel of citizens, although many regulations have been adopted against taxi evasion, similar behaviors are still common, which shows that some drivers still have irregular behaviors when they make detours. Therefore, detecting, supervising, and correcting abnormal driving trajectories and detour behaviors of drivers is of positive significance for improving the...

AI Technical Summary

Problems solved by technology

[0003] However, there are still two main shortcomings in various current detection methods: First, most algorithms ignore objective factors that affect vehicle trajectory characteristics. On the other hand, most algorithms ignore the actual road network of the city in the calculation process of the algorithm, and do not really match the trajectory with the actual road network.

Images