Method and system for analyzing first-time city entering behavior of vehicle

Abstract

The invention discloses a method and a system for analyzing the first-time city entering behavior of a vehicle. The method comprises the steps of acquiring vehicle passing data, and generating a vehicle passing record table and a vehicle city-entering index table according to the vehicle passing data; segmenting the generation time range of a case into a plurality of time periods by adopting a time segmentation function, and transmitting the time periods to an original recording thread pool; calling the original recording thread pool to inquire a vehicle passing record list; according to the plurality of time periods, inquiring the vehicle passing record table in the starting and ending time corresponding to each time period; summarizing all inquiry results to obtain a suspected vehicle data set; segmenting the suspected vehicle data set into a plurality of data segments and transmitting the data segments into a backtracking check thread pool by adopting a record segmentation function;calling the backtracking check thread pool to inquire the vehicle city-entering index table through multiple threads; if the suspected vehicle information is not recorded in the vehicle city-enteringindex table, determining that a vehicle corresponding to the suspected vehicle information is driving into a city for the first time within the generation time range of the case; and merging all processing results to obtain a first-time city entering data set. According to the method and the system, vehicles, driving into the city for the first time, can be efficiently inquired.

Description

technical field [0001] The present invention relates to the technical field of public security, and more specifically, to a method and system for analyzing a vehicle entering a city for the first time. Background technique [0002] In recent years, with the deepening construction of safe cities and skynet projects in various places, it has provided more and more sources of intelligence for the video investigation work of public security organs, especially the data of passing vehicles. As more and more cases are related to vehicles, passing vehicle data has become a key breakthrough point for case detection and arrest of criminal suspects. It can be said that mastering the dynamics of the vehicle will grasp the dynamics of the suspect. As a result, video detection technology has become the fourth largest technology after criminal technology, technical detection technology and network detection technology. [0003] In the process of committing crimes by car, criminals often ...

AI Technical Summary

Problems solved by technology

[0004] There are currently several solutions for the traditional analysis of entering a city for the first time. The most common one is to first remove the duplicate data by license plate number from the vehicle passing data within the incident time range selected by the user, and then remove the duplicate data from the vehicle passing data within the backtracking time range selected by the user. The car data is also deduplicated according to the license plate number, and finally two smaller data sets are obtained, and then the two data sets are correlated to obtain the vehicles that appeared in the time period of the incident but did not appear in the retrospective time period Data; this kind of scheme is easy to implement, but there are obvious shortcomings. First, the backtracking time selected by the user may be quite long. Taking a county with 4 million pieces of vehicle passing data in a day as an example, in order to more accurately determine the first time the user enters the city, he often A backtracking time of more than 30 days will be selected, so that 120 million pieces of data need to be scanned to deduplicate, which takes a long time, and a single query of 5 nodes often takes more than 20 minutes; there is also an improved solution that uses scheduled tasks to periodically Preprocess the passing vehicle data. By establishing monthly and weekly tables, the passing vehicle data will be deduplicated in advance. When the user queries, the time period selected by the user is divided into monthly and weekly segments, and the corresponding table can be read directly. The preprocessed data in , which greatly reduces the processing time, is also the data volume of 4 million a day, select 3 days, go back to 30 days, and the single query time can be compressed to minutes, but the disadvantage of this is also obvious, that is It is necessary to regularly establish deduplicated weekly tables and monthly tables, and most of the data in these tables are actually repeated, which causes a lot of waste of storage space on the server

Images