A vehicle profiling method for long and short distance travel based on highway collected data

Abstract

The present invention is applicable to the field of highway traffic management, and provides a method for profiling vehicles for long and short distance travel based on highway collected data, the method comprising: screening out passenger vehicles in a non-operating state, identifying vehicles with commuting characteristics; predicting the exit and travel distance of commuting vehicles, and generating commuting vehicle portraits. The present invention is based on multi-source data from various types of collection equipment on highways, and performs long / short distance travel vehicle portrait labeling for vehicles in transit. Combined with the identification of commuting vehicles and the analysis of the relevant characteristics of the historical travel characteristics and real-time transit conditions of commuting vehicles, the vehicle portrait analysis model designed for this purpose can more efficiently and accurately achieve the task of portrait labeling of individual vehicles. Give full play to the advantages of traffic big data, provide traffic data analysis and vehicle portrait generation for relevant management departments, reflect vehicle travel characteristic information, improve the accuracy and scientificity of traffic management, and improve traffic management efficiency.

Description

Technical Field

[0001] The present invention belongs to the field of highway traffic management, and in particular relates to a method for profiling vehicles traveling long and short distances based on highway collected data. Background Art

[0002] At present, with the continuous improvement of my country's transportation infrastructure and the continuous growth of the number of motor vehicles, road traffic volume has gradually increased, and most of the vehicles have predictable travel behavior patterns and characteristics. In order to more accurately analyze the traffic conditions of highways and optimize highway traffic management, it is necessary to analyze the information and label the images of vehicles running on highways, which has important practical significance. The data collected by the ETC gantries, toll station entrance and exit equipment and cameras on the highways are the source of high-precision traffic data. They can record the detailed information such as the time, location, license plate number, and vehicle model of the vehicle, providing a solid data foundation for the in-depth analysis of vehicle travel behavior. By mining and analyzing these data, we can fully understand the travel patterns, time distribution, path selection and other information of vehicles, thereby constructing accurate vehicle portraits of long-distance and short-distance vehicles.

[0003] Currently, vehicle profiling based on highway data has not been fully studied and faces some challenges: First, the amount of data collected on highways every day is huge and complex, and the data processing and analysis methods must be both efficient and accurate. Second, how to distinguish the differences in the behavioral characteristics of long-distance and short-distance vehicles requires the establishment of a targeted analysis model. Summary of the invention

[0004] The purpose of the present invention is to provide a method for profiling vehicles traveling long and short distances based on highway collected data, aiming to solve the technical problems existing in the prior art identified in the background technology.

[0005] The present invention is implemented as follows: a vehicle profiling method for long- and short-distance travel based on highway collected data, the method comprising:

[0006] Obtain basic data of vehicles on the highway and pre-process the acquired basic data;

[0007] Compare the information of vehicles entering the toll station, screen out passenger vehicles that are not in operation, analyze the historical frequency of passage and peak hours of the vehicles, and identify vehicles with commuting characteristics;

[0008] Compare the historical travel records of commuter vehicles with the current toll station information entering the highway, predict the exit and travel distance of commuter vehicles, generate commuter vehicle portraits, and classify commuter vehicles into long-distance travel vehicles and short-distance travel vehicles.

[0009] As a further solution of the present invention, the obtaining of basic vehicle data on the highway and preprocessing of the obtained basic data specifically include:

[0010] Extract vehicle basic data from the ETC gantry flow database, toll station entrance and exit database, and camera license plate recognition database;

[0011] Filter out the main data fields from the vehicle basic data and clean up the abnormal and missing data.

[0012] As a further solution of the present invention, the main data fields of the screening are:

[0013] ETC gantry flow data transaction time, gantry H e x value, gantry number, transaction status, transaction card number;

[0014] The entry processing time, entry processing number, toll vehicle type identification, and transaction card number of the toll station entry and exit data;

[0015] The vehicle passing time and current gantry H of the camera license plate recognition data e x value, toll vehicle type identification, and transaction card number.

[0016] As a further solution of the present invention, the comparison of vehicle information entering the toll station, screening out passenger vehicles in a non-operating state, analyzing the historical frequency of passage and peak hours of the vehicle, and identifying vehicles with commuting characteristics specifically includes:

[0017] The ETC at the entrance of the toll station collects the on-board electronic tags of each vehicle to obtain vehicle information;

[0018] The vehicle information in the vehicle information database is retrieved through the camera image license plate recognition, and the information is compared to determine whether the vehicle information matches;

[0019] Screen all vehicle information to obtain a type of passenger car, and perform secondary screening on all the type of passenger cars to obtain a type of passenger car that is an operating vehicle;

[0020] Obtain the historical travel data of all the first-type passenger vehicles that are operating vehicles, and determine the frequency of passing the same pair of toll station entrances and exits every day based on the daily toll station entrance and exit traffic information recorded in the historical travel database;

[0021] Set a frequency threshold to filter the records from toll station entrance to exit that meet the conditions. The conditions include:

[0022] 1. The vehicle attribute of the operating vehicle is a type 1 passenger vehicle;

[0023] 2. The vehicle's passing frequency is greater than the frequency threshold;

[0024] Define the morning peak and evening peak time periods, and for the filtered toll station entrance to toll station exit records, determine whether the vehicle entry and exit time periods are in the morning peak and evening peak periods. If they are in the morning peak and evening peak periods, add a commuting characteristic mark to the vehicle.

[0025] As a further solution of the present invention, the method of predicting the exit and travel distance of a commuter vehicle and generating a commuter vehicle portrait to classify the commuter vehicle into a long-distance travel vehicle and a short-distance travel vehicle specifically includes:

[0026] Obtaining the toll station entrance information of the vehicle with commuter characteristic identification currently entering the expressway, and comparing it with the historical entrance record of the vehicle;

[0027] A trip proportion threshold is set to filter out commuter vehicles whose current toll station entrance locations entering the expressway account for a proportion greater than the trip proportion threshold in historical trip records;

[0028] Based on the filtered commuter vehicles, the time period of entering the toll station entrance is filtered again, and the commuter vehicles are included in the time period of entering the toll station entrance in the vehicle's historical travel;

[0029] Based on the re-screened commuter vehicles, the toll station exit points that commuter vehicles frequently pass through are obtained from the statistical results of each commuter vehicle's historical travel records. e ;

[0030] Set the route overlap rate threshold based on the toll station entry point o and the toll booth exit point e When the overlap rate between the ETC gantry record and the historical route record of the vehicle passing through is greater than the route overlap rate threshold, it is determined that the vehicle will exit at the exit point. e Get off the highway;

[0031] Set the travel distance threshold and calculate the toll station entry point o and the toll booth exit point e If the travel distance is greater than the travel distance threshold, the vehicle is portrayed as a long-distance vehicle, otherwise it is portrayed as a short-distance vehicle.

[0032] The beneficial effects of the present invention are:

[0033] Based on the multi-source data of various types of collection equipment on highways, the present invention performs long / short distance travel vehicle portrait labeling for vehicles in transit, and combines the identification of commuter vehicles with the analysis of the relevant characteristics of commuter vehicles' historical travel characteristics and real-time transit conditions. The vehicle portrait analysis model designed for this purpose can more efficiently and accurately achieve the task of individual-level vehicle portrait labeling. The present invention gives full play to the advantages of traffic big data, provides traffic data analysis and vehicle portrait generation for relevant management departments, reflects vehicle travel feature information, improves the accuracy and scientificity of traffic management, improves traffic management efficiency, and provides strong support for the construction and optimization of intelligent transportation systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 A flowchart of a method for profiling vehicles traveling long and short distances based on highway collected data provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0036] It is understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, without departing from the scope of this application, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script.

[0037] The present invention is based on the multi-source acquisition equipment deployed on the highway as the data foundation, including ETC gantry flow data, toll station entrance and exit data and camera license plate recognition data. Then, based on the vehicle registration information and the travel characteristics in time and space, a group of commuter vehicles with high resolvability of travel patterns and regularities are screened out from all the vehicles running on the highway. Finally, for vehicles with commuter characteristic vehicle identification, the coincidence rate of toll station entrance points, the set of high-frequency toll station exit points, and the coincidence rate of the ETC gantry passed by the current in-transit route and the historical route record of "entry point to high-frequency exit point" are determined one by one, and finally the toll station exit point position of the vehicle is estimated, thereby profiling the long / short distance travel of the vehicle.

[0038] like Figure 1 As shown, the long-distance and short-distance travel vehicle profiling method based on highway collected data includes:

[0039] Basic data preprocessing:

[0040] ①The data is extracted from the ETC gantry flow database, toll station entrance and exit database, and camera license plate recognition database.

[0041] ② Implement correlation analysis of multi-source data and filter out the main data fields, including the recording time and location number of the collection equipment, and the vehicle electronic tag information. The main data fields are shown in Tables 1, 2, and 3 below. After cleaning the abnormal or missing data, they serve as the data basis for subsequent data analysis steps.

[0042] Table 1 Main fields of ETC gantry flow data

[0043] Field Name Field meaning pass_time Transaction time gantry_hex Mast Hex value gantry_id Mast No. trans_status Transaction status, including ETC card and CPC card cpucard_id CPU card (ETC card) number obusn CPC Card Number

[0044] Table 2 Main fields of toll station entrance and exit data

[0045] Field Name Field meaning en_time Entry processing time id Entry Processing Number vehicle_type Toll vehicle type identification card_id CPC card or ETC card number

[0046] Table 3 Main fields of camera license plate recognition data

[0047] Field Name Field meaning pass_time Vehicle passing time gantry_hex Current mast Hex value identify_type Toll vehicle type identification card_id CPC card or ETC card number

[0048] Step 2: Vehicle identification with commuting characteristics:

[0049] ① The ETC at the entrance of the toll station collects vehicle information through the on-board electronic tag. The camera retrieves the vehicle information in the vehicle information database by taking pictures of the license plate and performs information comparison to ensure that the vehicle information matches.

[0050] ② In the vehicle information obtained, first determine whether the vehicle is a type-one passenger car, and only for type-one passenger cars, continue to determine whether the vehicle is an operating vehicle, and only filter out non-operating vehicles, and do not consider other vehicles.

[0051] ③ For vehicles that meet the above steps, the frequency of passing through the same pair of toll station entrances and exits every day is determined based on the daily toll station entrance and exit traffic information recorded in its historical travel database, and the toll station entrance to toll station exit records with a travel frequency greater than the specified threshold are filtered out.

[0052] The specific passing frequency is:

[0053] ;

[0054] In the formula, A function that returns 1 if the condition in the brackets is true and 0 if it is false. Indicates vehicle The entrance toll station gantry in the trajectory sequence; Indicates any selected entrance toll station gantry; Indicates vehicle The exit toll station gantry in the trajectory sequence; Indicates any selected exit toll station gantry; D Indicates the total time in a day.

[0055] ④ For the selected records from toll station entrance to toll station exit, determine whether the vehicle's entry and exit time periods are in the morning peak and evening peak periods (such as 7:00-9:00 in the morning) and evening peak periods (such as 17:00-19:00 in the afternoon). If the time period conditions are met, the vehicle is identified as a vehicle with commuting characteristics.

[0056] Step 3: Long / short distance vehicle portrait:

[0057] ① For vehicles with commuting characteristics, the current toll station entrance into the highway is compared with the historical entrance record of the vehicle to determine whether the proportion of the toll station entrance location in the historical travel record is greater than the specified percentage threshold, and whether the time period of entering the toll station entrance is included in the entry time period range of the toll station entrance location historical record.

[0058] The proportion of toll station entrances currently entering the expressway in historical travel records is as follows:

[0059] ;

[0060] In the formula, Indicates vehicle The entrance toll station gantry in the trajectory sequence; Indicates vehicle A collection of historical entrance toll booth records.

[0061] ② For vehicles that meet the above overlap rate judgment, obtain the vehicle’s entry point at the toll station from the statistical results of the vehicle’s historical travel records. o and entry time, the toll station exit points with high frequency of passing e .

[0062] ③According to the entrance point of the toll station o and the toll booth exit point e The historical route record of the vehicle is combined with the ETC gantry position record currently passing through. When the coincidence rate between the ETC gantry record passing through and the historical route record of the vehicle is greater than the specified percentage threshold, it is determined that the vehicle is highly likely to be at the exit point. e Exit the highway.

[0063] The historical route record of the vehicle is represented by the sequence data of the ETC gantry. The ETC gantry records that the vehicle has passed through are uploaded in real time. The ETC gantry numbers passed through in the uploaded ETC gantry sequence records are calculated, and the overlap rate with the gantry numbers in the historical route records is calculated. Specifically:

[0064] ;

[0065] In the formula, represents the overlap rate, Indicates vehicle The current operational trajectory; A function that returns 1 if the condition in the brackets is true and 0 if it is false. Indicates vehicle In the running track of A gate frame through which Indicates vehicle From Entry Point To the exit point The historical route record of A door frame through which to pass.

[0066] ④Calculate the entrance and exit eo If the travel distance is greater than the specified travel threshold, the vehicle is portrayed as a long-distance travel vehicle, otherwise it is portrayed as a short-distance travel vehicle.

[0067] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0068] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0069] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0070] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0071] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A vehicle profiling method for long and short distance travel based on highway collected data, characterized in that: The method comprises: Obtain basic data of vehicles on the highway and pre-process the acquired basic data; Compare the information of vehicles entering the toll station, screen out passenger vehicles that are not in operation, analyze the historical frequency of passage and peak hours of the vehicles, and identify vehicles with commuting characteristics; Compare the historical travel records of commuter vehicles with the current toll station information entering the highway, predict the exit and travel distance of commuter vehicles, generate commuter vehicle portraits, and classify commuter vehicles into long-distance travel vehicles and short-distance travel vehicles; The step of obtaining basic vehicle data on the highway and preprocessing the obtained basic data specifically includes: Extract vehicle basic data from the ETC gantry flow database, toll station entrance and exit database, and camera license plate recognition database; Filter out the main data fields from the vehicle basic data and clean up the abnormal missing data; The main data fields for the screening are: ETC gantry flow data transaction time, gantry H e x value, gantry number, transaction status, transaction card number; The entry processing time, entry processing number, toll vehicle type identification, and transaction card number of the toll station entry and exit data; The vehicle passing time and current gantry H of the camera license plate recognition data e x value, toll vehicle type identification, transaction card number; The process of comparing the vehicle information entering the toll station, screening out the passenger vehicles that are not in operation, analyzing the historical traffic frequency and peak hours of the vehicles, and identifying the vehicles with commuting characteristics specifically includes: The ETC at the entrance of the toll station collects the on-board electronic tags of each vehicle to obtain vehicle information; The vehicle information in the vehicle information database is retrieved through the camera image license plate recognition, and the information is compared to determine whether the vehicle information matches; Screen all vehicle information to obtain a type of passenger car, and perform secondary screening on all the type of passenger cars to obtain a type of passenger car that is an operating vehicle; Obtain the historical travel data of all the first-type passenger vehicles that are operating vehicles, and determine the frequency of passing through the same pair of toll station entrances and exits every day based on the daily toll station entrance and exit traffic information recorded in the historical travel database; A frequency threshold is set to filter the records from the entrance to the exit of the toll station that meet the conditions, wherein the conditions include: the vehicle attribute of the operating vehicle is a type-one passenger vehicle; the vehicle's passing frequency is greater than the frequency threshold; Define the morning peak and evening peak time periods. For the selected toll station entrance to toll station exit records, determine whether the vehicle entry and exit time periods are in the morning peak and evening peak time periods. If they are in the morning peak and evening peak time periods, add a commuting characteristic mark to the vehicle. The method of predicting the exit and travel distance of commuter vehicles and generating commuter vehicle portraits to classify commuter vehicles into long-distance travel vehicles and short-distance travel vehicles specifically includes: Obtaining the toll station entrance information of the vehicle with commuter characteristic identification currently entering the expressway, and comparing it with the historical entrance record of the vehicle; A trip proportion threshold is set to filter out commuter vehicles whose current toll station entrance locations entering the expressway account for a proportion greater than the trip proportion threshold in historical trip records; Based on the filtered commuter vehicles, the time period of entering the toll station entrance is filtered again, and the commuter vehicles are included in the time period of entering the toll station entrance in the vehicle's historical travel; Based on the re-screened commuter vehicles, the toll station exit points that commuter vehicles frequently pass through are obtained from the statistical results of each commuter vehicle's historical travel records. e ; Set the route overlap rate threshold based on the toll station entry point o and the toll booth exit point e When the overlap rate between the ETC gantry record and the historical route record of the vehicle passing through is greater than the route overlap rate threshold, it is determined that the vehicle will exit at the exit point. e Get off the highway; Set the travel distance threshold and calculate the toll station entry point o and the toll booth exit point e If the travel distance is greater than the travel distance threshold, the vehicle is portrayed as a long-distance vehicle, otherwise it is portrayed as a short-distance vehicle.

2. The method according to claim 1, characterized in that The determination of the frequency of passing through the same pair of toll station entrances and exits in a day is specifically as follows: ； In the formula, A function that returns 1 if the condition in the brackets is true and 0 if it is false. represents the entrance toll station gantry in the trajectory sequence of vehicle i; Indicates any selected entrance toll station gantry; represents the exit toll station gantry in the trajectory sequence of vehicle i; Indicates any selected exit toll station gantry; D Indicates the total time in a day.

3. The method according to claim 1, characterized in that The proportion of the toll station entrance location currently entering the expressway in the historical travel records is specifically: ； In the formula, represents the entrance toll station gantry in the trajectory sequence of vehicle i; Represents the set of historical entrance toll station records for vehicle i.

4. The method according to claim 1, characterized in that The vehicle historical route record is represented by the sequence data of the ETC gantry. The ETC gantry record passed by the vehicle in transit is uploaded in real time. The ETC gantry number passed contained in the uploaded ETC gantry sequence record is calculated, and the overlap rate with the gantry number in the historical route record is calculated. Specifically: ； In the formula, represents the overlap rate, Indicates the on-the-way running trajectory of vehicle i up to the current time; A function that returns 1 if the condition in the brackets is true and 0 if it is false. represents the tth gantry passed by vehicle i in the in-transit running trajectory; Indicates the tth gantry passed by vehicle i in the historical route record from entry point e to exit point o.

Images