Vehicle data processing method and system based on ETC data

Abstract

The invention relates to the technical field of traffic control systems, and particularly discloses a vehicle data processing method and system based on ETC data, and the method comprises the steps: obtaining the historical traffic information of a to-be-evaluated vehicle in a historical evaluation period and the driving feature data of the to-be-evaluated vehicle in a current evaluation period through a traffic feature management platform; a driving characteristic danger threshold value of the to-be-evaluated vehicle in the historical evaluation period and a driving characteristic danger value of the to-be-evaluated vehicle in the current evaluation period are evaluated respectively; comparing the driving characteristic danger value of the to-be-evaluated vehicle in the current evaluation period with the driving characteristic danger threshold value of the to-be-evaluated vehicle in the historical evaluation period to obtain a driving characteristic danger value comparison result; and according to the comparison result of the driving characteristic danger values, whether the driving characteristic data of the to-be-evaluated vehicle in the current evaluation time period is subjected to early warning prompt is judged, so that the traffic information in the traffic characteristic archive is higher in effectiveness and higher in practicability.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic control systems, and in particular to a vehicle data processing method and system based on ETC data. Background Art

[0002] With the gradual improvement of the expressway network and the continuous increase in the number of vehicles traveling on expressways, the traffic flow on expressways has also shown a rapid growth trend. Expressways generate massive amounts of traffic data every day. The accumulation of these data provides a rich data source for the establishment of vehicle data processing methods and systems based on ETC data. The construction of smart expressways is an important development direction in the current transportation field. The vehicle traffic feature archive is the key to the construction of smart expressways and will help to intelligently manage the transportation field.

[0003] For example, the invention patent with the announcement number CN116071931 B announces a method and system for predicting vehicle information on a highway, including the following steps: step S1, collecting the original vehicle traffic raw data information and performing a first processing operation to obtain the first data, and formatting and storing it; step S2, performing a first filtering operation on the first data obtained after the original information is processed to obtain the second data; step S3, calculating the physical information credibility weight measurement value for the second data obtained after the first filtering operation; step S4, performing a third correction on the old historical archive information measurement value and updating and evolving it; step S5, merging and storing the physical information credibility weight measurement value obtained in step S3 and the measurement value after the third correction in step S4; step S6, generating the real physical information of vehicle prediction from the measurement value generated in step S5 based on the vehicle information to be queried.

[0004] For example, the invention patent with announcement number CN114446052B announces a highway event detection method and device based on multi-source data multi-level fusion, which uses the existing coils, microwaves and video detectors on the highway to collect road traffic flow data in real time and build a road traffic safety cloud platform; according to the layout positions of different detectors, the original coil / microwave detector layout intervals of the highway are divided into several small intervals; the cross-sectional traffic flow feature variable set based on coil / microwave data and the microscopic vehicle behavior feature variable set based on video data are constructed respectively under the event state; in order to achieve unified representation of multi-source information, a traffic event detection model based on a multi-level deep automatic encoding network is constructed; the aggregated data between small intervals is used as input, and the traffic event detection results are output through the model.

[0005] In combination with the above technical solutions, it is found that when the vehicle information passing through the highway is currently detected, only the vehicle traffic information is simply analyzed, and no further judgment is made based on the analysis results, which makes the application efficiency of the analysis results low, and will cause this information to be unable to adapt to the highway traffic feature detection scenario, so that the data analysis is invalid. Summary of the invention

[0006] In view of the deficiencies in the prior art, the present invention provides a vehicle data processing method and system based on ETC data, which can effectively solve the problems involved in the above-mentioned background technology.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: The first aspect of the present invention provides a vehicle data processing method based on ETC data, including: S1. The traffic characteristic management platform obtains the historical traffic information of the vehicle to be evaluated in the historical evaluation cycle and the driving characteristic data of the vehicle to be evaluated in the current evaluation period, and respectively evaluates the stable evaluation value of the driving characteristics of the vehicle to be evaluated in the historical evaluation cycle and the driving characteristic hazard value of the vehicle to be evaluated in the current evaluation period; S2. The driving characteristic hazard threshold of the vehicle to be evaluated in the historical evaluation cycle is matched with the driving characteristic hazard value of the vehicle to be evaluated in the current evaluation period, and the driving characteristic hazard value of the vehicle to be evaluated in the historical evaluation period is compared with the driving characteristic hazard threshold of the vehicle to be evaluated in the historical evaluation period to obtain a driving characteristic hazard value comparison result, and determine whether to issue an early warning prompt for the driving characteristic data of the vehicle to be evaluated in the current evaluation period according to the driving characteristic hazard value comparison result.

[0008] As a further solution, the historical traffic information of the vehicle to be evaluated during the historical evaluation period specifically includes the average daily number of passes, average travel time, average travel speed, proportion of bad weather time, and proportion of late night travel time of the vehicle to be evaluated during the historical evaluation period.

[0009] As a further solution, the evaluation of the stable evaluation value of the driving characteristics of the vehicle to be evaluated in the historical evaluation cycle is performed in the following specific evaluation process:

[0010] Through the average daily number of passes, average travel time, average travel speed, proportion of bad weather time, and proportion of late-night travel time of the vehicle to be evaluated during the historical evaluation period, a comprehensive analysis is made to determine a stable evaluation value of the driving characteristics of the vehicle to be evaluated during the historical evaluation period.

[0011] As a further solution, the driving characteristic risk value of the vehicle to be evaluated in the current evaluation period is specifically analyzed as follows:

[0012] The travel speed of the vehicle to be evaluated in the current evaluation period is obtained by ratioing the travel mileage of the vehicle to be evaluated in the current evaluation period with the duration corresponding to the current evaluation period.

[0013] The driving characteristic hazard value of the vehicle to be evaluated in the current evaluation period is comprehensively analyzed through the travel speed, number of emergency braking times and proportion of late-night travel time of the vehicle to be evaluated in the current evaluation period.

[0014] As a further solution, the determination of whether to issue an early warning for the driving characteristic data of the vehicle to be evaluated within the current evaluation period according to the driving characteristic risk value comparison result is carried out in the following specific analysis process:

[0015] If the driving characteristic danger value comparison result is that the driving characteristic danger value is greater than or equal to the driving characteristic danger threshold, it is necessary to issue an early warning prompt for the driving characteristic data of the vehicle to be evaluated within the current evaluation period.

[0016] If the driving characteristic danger value comparison result is that the driving characteristic danger value is less than the driving characteristic danger threshold, there is no need to issue an early warning prompt for the driving characteristic data of the vehicle to be evaluated during the current evaluation period, and the driving characteristic data is stored in the traffic characteristic archive sub-library.

[0017] As a further solution, the driving characteristic data of the vehicle to be evaluated in the current evaluation period is given an early warning prompt, and the specific early warning prompt process is:

[0018] The highway section information of the vehicle to be evaluated in the current evaluation period is obtained, and combined with the driving characteristic hazard value of the vehicle to be evaluated in the current evaluation period, the driving characteristic abnormality index of the vehicle to be evaluated in the current evaluation period is comprehensively obtained, thereby matching the driving characteristic reference data of the vehicle to be evaluated, and performing one-to-one difference processing with the driving characteristic data of the vehicle to be evaluated in the current evaluation period to obtain the driving characteristic deviation data, and finally issuing an early warning prompt for the driving characteristic deviation data of the vehicle to be evaluated.

[0019] As a further solution, the driving characteristic abnormality index of the vehicle to be evaluated in the current evaluation period is obtained by comprehensive analysis, and the specific analysis process is as follows:

[0020] The highway section information of the vehicle to be evaluated in the current evaluation period includes the traffic volume, traffic density and number of intersections of the highway evaluation section in the current evaluation period.

[0021] The driving characteristic abnormality index of the vehicle to be evaluated during the current evaluation period is obtained by comprehensively analyzing the traffic volume, traffic density, number of intersections of the highway evaluation section during the current evaluation period, and the driving characteristic hazard value of the vehicle to be evaluated during the current evaluation period. The specific acquisition method is as follows:

[0022]

[0023] Wherein, ADCI represents the driving characteristic abnormality index of the vehicle to be evaluated in the current evaluation period, VDV represents the driving characteristic danger value of the vehicle to be evaluated in the current evaluation period, VDCT represents the driving characteristic stable evaluation value of the vehicle to be evaluated in the historical evaluation period, TV represents the traffic volume of the highway evaluation section in the current evaluation period, TD represents the traffic density of the highway evaluation section in the current evaluation period, NJ represents the number of intersections of the highway evaluation section in the current evaluation period, ζ1 represents the driving characteristic abnormality influence coefficient of the traffic volume preset in the traffic characteristic library, ζ2 represents the driving characteristic abnormality influence coefficient of the traffic density preset in the traffic characteristic library, ζ3 represents the driving characteristic abnormality influence coefficient of the number of intersections preset in the traffic characteristic library, and ζ4 represents the driving characteristic abnormality correction coefficient corresponding to the driving characteristic danger deviation value preset in the traffic characteristic library.

[0024] A second aspect of the present invention provides a vehicle data processing system based on ETC data, comprising:

[0025] The driving characteristics assessment module is used for the traffic characteristics management platform to obtain the historical traffic information of the vehicle to be assessed during the historical assessment cycle and the driving characteristics data of the vehicle to be assessed during the current assessment period, and to respectively assess the stable assessment value of the driving characteristics of the vehicle to be assessed during the historical assessment cycle and the driving characteristics danger value of the vehicle to be assessed during the current assessment period.

[0026] The driving characteristic warning module is used to match the driving characteristic danger threshold of the vehicle to be evaluated in the historical evaluation period through the stable evaluation value of the driving characteristics of the vehicle to be evaluated in the historical evaluation period, compare the driving characteristic danger value of the vehicle to be evaluated in the current evaluation period with the driving characteristic danger threshold of the vehicle to be evaluated in the historical evaluation period, obtain the driving characteristic danger value comparison result, and determine whether to issue a warning prompt for the driving characteristic data of the vehicle to be evaluated in the current evaluation period based on the driving characteristic danger value comparison result.

[0027] Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects:

[0028] (1) The present invention obtains the historical traffic information of the vehicle to be evaluated in the historical evaluation cycle and the driving characteristic data of the vehicle to be evaluated in the current evaluation period through the traffic characteristic management platform, and respectively evaluates the driving characteristic hazard threshold of the vehicle to be evaluated in the historical evaluation cycle and the driving characteristic hazard value of the vehicle to be evaluated in the current evaluation period, and then compares the driving characteristic hazard value of the vehicle to be evaluated in the current evaluation period with the driving characteristic hazard threshold of the vehicle to be evaluated in the historical evaluation cycle to obtain a driving characteristic hazard value comparison result, and determines whether to issue an early warning prompt for the driving characteristic data of the vehicle to be evaluated in the current evaluation period according to the driving characteristic hazard value comparison result, which helps to timely discover and correct potential driving risks, thereby improving driving safety and ultimately making the stored data effective and complete.

[0029] (2) The present invention obtains the historical traffic information of the vehicle to be evaluated in the historical evaluation cycle and the driving characteristic data of the vehicle to be evaluated in the current evaluation period through the traffic characteristic management platform, and respectively evaluates the driving characteristic danger threshold of the vehicle to be evaluated in the historical evaluation cycle and the driving characteristic danger value of the vehicle to be evaluated in the current evaluation period, comprehensively considering various dangerous situations of driving characteristics, and identifying traffic congestion, accident-prone areas, etc. by analyzing the data, so that the traffic characteristic archive can be continuously optimized and upgraded, and can continuously accumulate rich vehicle driving data.

[0030] (3) The present invention compares the driving characteristic hazard value of the vehicle to be evaluated in the current evaluation period with the driving characteristic hazard threshold of the vehicle to be evaluated in the historical evaluation period to obtain a driving characteristic hazard value comparison result. When the driving characteristic hazard value is less than the driving characteristic hazard threshold, it indicates that the driving characteristics are safe. The driving characteristic data is stored in the traffic characteristic archive sub-library, which improves the validity and integrity of the data and provides a solid foundation for establishing a comprehensive and complete vehicle traffic characteristic archive.

[0031] (4) The present invention can more accurately reflect the driving status of the vehicle and improve the accuracy and reliability of the warning by determining whether to issue a warning for the driving characteristic data of the vehicle to be evaluated within the current evaluation period based on the comparison result of the driving characteristic hazard value. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The present invention is further described using the accompanying drawings, but the embodiments in the accompanying drawings do not constitute any limitation to the present invention. A person skilled in the art can obtain other drawings based on the following drawings without creative work.

[0033] Figure 1 The figure is a schematic flow chart of the method steps of the present invention.

[0034] Figure 2It is a schematic diagram of system module connection of the present invention.

[0035] Figure 3 The present invention is a flowchart of the scheme involved. DETAILED DESCRIPTION

[0036] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0037] See also Figure 1 As shown, the first aspect of the present invention provides a vehicle data processing method based on ETC data, including: S1. The traffic characteristic management platform obtains the historical traffic information of the vehicle to be evaluated in the historical evaluation cycle and the driving characteristic data of the vehicle to be evaluated in the current evaluation period, and respectively evaluates the stable evaluation value of the driving characteristics of the vehicle to be evaluated in the historical evaluation cycle and the driving characteristic danger value of the vehicle to be evaluated in the current evaluation period.

[0038] Based on the specific analysis of the driving status of a single vehicle, the general solution flow chart is as follows: Figure 3 As shown, Figure 3 It is shown in the figure that the driving characteristic danger value is compared with the driving characteristic danger threshold, and two different processing methods are obtained. If the driving characteristic danger value is greater than or equal to the driving characteristic danger threshold, it is necessary to issue an early warning prompt for the driving characteristic data; if the driving characteristic danger value is less than the driving characteristic danger threshold, the driving characteristic data is stored in the traffic characteristic archive sub-library, thereby improving the safety of vehicle driving.

[0039] In this embodiment, the above-mentioned traffic characteristic management platform refers to a platform for performing data analysis and evaluation on the historical traffic information and driving characteristic data of the vehicle to be evaluated. This traffic characteristic management platform can be connected through the Internet of Things, thereby receiving the historical traffic information and driving characteristic data of the vehicle to be evaluated through the Internet of Things, and finally evaluating the driving characteristic danger threshold of the vehicle to be evaluated within the historical evaluation period and the driving characteristic danger value of the vehicle to be evaluated in the current evaluation period; since the traffic characteristic management platform includes a SIEM (security information and event management) system and an OBD (on-board diagnostics) system, it can monitor and record the vehicle's driving status in real time, including the number of passes, travel time, weather data, travel time, travel mileage, and emergency braking conditions.

[0040] Specifically, the historical traffic information of the vehicle to be evaluated during the historical evaluation period includes the average daily number of passes, average travel time, average travel speed, proportion of bad weather time, and proportion of late night travel time of the vehicle to be evaluated during the historical evaluation period.

[0041] It should be explained that the above-mentioned historical evaluation cycle can be obtained through the SIEM system built into the traffic characteristic management platform. Specifically, it refers to the time interval extending from a certain moment in the past to the present when evaluating the historical driving characteristics of the vehicle to be evaluated, which is recorded as the historical evaluation cycle. The specific duration is determined based on the availability and completeness of the existing data and the traffic conditions of the vehicle to be evaluated, and can be three months, six months or one year.

[0042] It should be explained that the average daily number of passes of the above-mentioned vehicles to be evaluated during the historical evaluation period can be obtained by extracting each pass data of the vehicles to be evaluated during the historical evaluation period from the pass feature management platform, sorting the collected pass data by date, counting the number of passes per day, adding the number of passes per day in the historical evaluation period, and then dividing it by the number of days in the evaluation period to obtain the average daily number of passes.

[0043] It should be explained that the average travel time of the above-mentioned vehicle to be evaluated during the historical evaluation period can be obtained by extracting the start time and end time of each pass of the vehicle to be evaluated from the pass feature management platform, thereby calculating the duration of each pass, adding up the duration of all passes in the historical evaluation period, and then dividing it by the total number of passes to obtain the average travel time.

[0044] It should be explained that the average travel speed of the above-mentioned vehicles to be evaluated during the historical evaluation period can be obtained by extracting the distance and time of each pass from the pass feature management platform, and calculating the speed of each pass thereby, adding up the speeds of all passes during the historical evaluation period, and then dividing by the total number of passes to obtain the average travel speed.

[0045] It should be explained that the proportion of bad weather time of the above-mentioned vehicles to be evaluated during the historical evaluation period can be obtained by extracting the traffic data of the vehicles to be evaluated during the historical evaluation period and the weather data of the same period from the traffic feature management platform, identifying the time periods of bad weather (including heavy rain, heavy snow, strong wind, haze, hail, sandstorm, etc.) according to the weather data, and counting the time when the vehicles to be evaluated pass through the bad weather periods, dividing the time when the bad weather passes by the total time when the bad weather passes, to obtain the proportion of the bad weather time.

[0046] It should be explained that the proportion of late-night travel time of the above-mentioned vehicles to be evaluated during the historical evaluation period can be obtained by extracting the travel data and travel time of the vehicles to be evaluated during the historical evaluation period from the traffic feature management platform, and counting the travel time of the vehicles to be evaluated during the late-night period (all entrances and exits are between 23:00 and 5:00 the next day), dividing the late-night travel time by the total travel time, and obtaining the proportion of late-night travel time.

[0047] Furthermore, the evaluation process of evaluating the stable evaluation value of the driving characteristics of the vehicle to be evaluated within the historical evaluation period is as follows:

[0048] The stable evaluation value of the driving characteristics of the vehicle to be evaluated during the historical evaluation period is comprehensively analyzed by analyzing the average daily number of trips, average travel time, average travel speed, proportion of bad weather time, and proportion of late-night travel time of the vehicle to be evaluated during the historical evaluation period. The specific acquisition method is: VDCT = (1 + ω1*ADT + ω2*ADP) -e +arccot(ω3*PTS+ω4*PLT+ω5*ATS);

[0049] Where ADT represents the average daily number of trips of the vehicle to be evaluated during the historical evaluation period, specifically, it refers to the average number of trips per day of the vehicle to be evaluated during the historical evaluation period.

[0050] ADP refers to the average travel time of the vehicle to be evaluated during the historical evaluation period. Specifically, it refers to the average time spent on each pass of the vehicle to be evaluated during the historical evaluation period.

[0051] PTS represents the proportion of bad weather time for the vehicle to be evaluated during the historical evaluation period. Specifically, it refers to the ratio of the total time that the vehicle to be evaluated is traveling in bad weather conditions during the historical evaluation period to the total driving time of the vehicle during the entire historical evaluation period.

[0052] PLT represents the proportion of late-night travel time of the vehicle to be evaluated during the historical evaluation period. Specifically, it refers to the ratio of the total travel time of the vehicle to be evaluated in the late night (entrances and exits are between 23:00 and 5:00 the next day) during the historical evaluation period to the total travel time of the vehicle in the entire historical evaluation period.

[0053] ATS refers to the average travel speed of the vehicle to be evaluated during the historical evaluation period, specifically, the average speed of the vehicle to be evaluated when traveling on the road during the historical evaluation period.

[0054] e is a natural constant, ω1 represents the driving characteristic influence index of the average daily pass times preset in the traffic characteristic library, which represents the proportion of the average daily pass times of the vehicle to be evaluated during the historical evaluation period to the driving characteristic danger threshold. The traffic characteristic library stores the corresponding relationship between the driving characteristic influence index. For example, the real-time average daily pass times of the vehicle to be evaluated during the historical evaluation period and the driving characteristic danger threshold can be input into the traffic characteristic library. The traffic characteristic library automatically matches the driving characteristic influence index corresponding to the average daily pass times according to the preset corresponding relationship between the driving characteristic influence index.

[0055] ω2 represents the driving characteristic influence index of the average travel time preset in the traffic characteristic library, which represents the proportion of the average travel time of the vehicle to be evaluated during the historical evaluation period to the driving characteristic danger threshold. The traffic characteristic library stores the corresponding relationship between the driving characteristic influence index. For example, the real-time average travel time and the driving characteristic danger threshold of the vehicle to be evaluated during the historical evaluation period can be input into the traffic characteristic library. The traffic characteristic library automatically matches the driving characteristic influence index corresponding to the average travel time according to the preset corresponding relationship between the driving characteristic influence index.

[0056] ω3 represents the driving characteristic impact index of the bad weather duration ratio preset in the traffic characteristic library, which represents the proportion of the bad weather duration ratio of the vehicle to be evaluated in the historical evaluation period to the driving characteristic danger threshold. The traffic characteristic library stores the corresponding relationship between the driving characteristic impact index. For example, the real-time bad weather duration ratio of the vehicle to be evaluated in the historical evaluation period and the driving characteristic danger threshold can be input into the traffic characteristic library. The traffic characteristic library automatically matches the driving characteristic impact index corresponding to the bad weather duration ratio according to the preset driving characteristic impact index corresponding relationship.

[0057] ω4 represents the driving characteristic impact index of the proportion of late-night travel time preset in the traffic characteristic library, which represents the proportion of the proportion of late-night travel time of the vehicle to be evaluated in the historical evaluation period to the driving characteristic danger threshold. The traffic characteristic library stores the corresponding relationship between the driving characteristic impact index. For example, the real-time proportion of late-night travel time of the vehicle to be evaluated in the historical evaluation period and the driving characteristic danger threshold can be input into the traffic characteristic library. The traffic characteristic library automatically matches the driving characteristic impact index corresponding to the proportion of late-night travel time according to the preset corresponding relationship between the driving characteristic impact index.

[0058] ω5 represents the driving characteristic influence index of the average traffic speed preset in the traffic characteristic library, which represents the proportion of the average traffic speed of the vehicle to be evaluated during the historical evaluation period to the driving characteristic danger threshold. The traffic characteristic library stores the corresponding relationship of the driving characteristic influence index. For example, the real-time average traffic speed of the vehicle to be evaluated during the historical evaluation period and the driving characteristic danger threshold can be input into the traffic characteristic library. The traffic characteristic library automatically matches the driving characteristic influence index corresponding to the average traffic speed according to the preset corresponding relationship of the driving characteristic influence index.

[0059] VDCT represents the driving characteristic stability evaluation value of the vehicle to be evaluated during the historical evaluation period. Specifically, in the process of evaluating the driving characteristics of the vehicle to be evaluated during the historical evaluation period, the driving characteristic stability evaluation value of the vehicle to be evaluated during the historical evaluation period is comprehensively analyzed through the average daily number of passes, average travel time per trip, average travel speed, proportion of bad weather time, and proportion of late-night travel time of the vehicle to be evaluated during the historical evaluation period. A high average daily number of passes means that the vehicle is used frequently, while a long average travel time may mean that a single trip is long or that traffic jams are often encountered, indicating that the vehicle is in a state of long-term continuous driving, and the driver's fatigue level increases, resulting in a decrease in the driving characteristic stability evaluation value; when the vehicle is driven in the late night period and encounters bad weather, the travel time will increase due to limited vision, deteriorating road conditions and the possibility of driver fatigue, thereby resulting in a decrease in the driving characteristic stability evaluation value. Under these unfavorable conditions, if the average travel speed is still high, the accident risk will increase significantly, resulting in a decrease in the driving characteristic stability evaluation value.

[0060] Specifically, the driving characteristic data of the vehicle to be evaluated during the current evaluation period specifically include the mileage, number of emergency braking times and proportion of late-night travel time of the vehicle to be evaluated during the current evaluation period.

[0061] It should be explained that the above-mentioned current evaluation period can be obtained through the SIEM system built into the traffic feature management platform. Specifically, it refers to the time interval of the entire day (from 0:00 to 24:00 on the same day) considered when evaluating the current driving characteristics of the vehicle to be evaluated, which is recorded as the current evaluation period.

[0062] It should be explained that the mileage and number of emergency braking times of the above-mentioned vehicles to be evaluated in the current evaluation period can be obtained through the traffic feature management platform; the proportion of late-night travel time of the above-mentioned vehicles to be evaluated in the current evaluation period can be obtained by extracting the travel data and travel time of the vehicles to be evaluated in the current evaluation period from the traffic feature management platform, and counting the travel time of the vehicles to be evaluated in the late night period (entrances and exits are between 23:00 and 5:00 the next day), dividing the late-night travel time by the total travel time, and obtaining the proportion of late-night travel time.

[0063] Furthermore, the specific analysis process of the driving characteristic risk value of the vehicle to be evaluated in the current evaluation period is as follows:

[0064] The travel speed of the vehicle to be evaluated in the current evaluation period is obtained by ratioing the travel mileage of the vehicle to be evaluated in the current evaluation period with the duration corresponding to the current evaluation period.

[0065] The driving characteristic risk value of the vehicle to be evaluated during the current evaluation period is comprehensively analyzed by the speed, emergency braking times, and the proportion of late-night travel time of the vehicle to be evaluated during the current evaluation period. The specific acquisition method is as follows:

[0066]

[0067] Wherein, ASP represents the speed of the vehicle to be evaluated during the current evaluation period. Specifically, it refers to the speed obtained by ratioing the mileage of the vehicle to be evaluated during the current evaluation period with the duration corresponding to the current evaluation period.

[0068] ΔASP represents a preset reference value of the travel speed in the travel feature library, specifically refers to the best adaptation value of the travel speed of the vehicle to be evaluated set for the vehicle to be evaluated in the current evaluation period.

[0069] EBN indicates the number of emergency braking times of the vehicle to be evaluated during the current evaluation period. Specifically, it refers to the number of braking times of the vehicle to be evaluated during the current evaluation period due to an emergency or the need to reduce the speed quickly to avoid potential danger. Emergency braking is defined as when the vehicle speed exceeds 30 km / h, if the brake pedal changes from being completely not depressed to being depressed more than 50% within 0.2 seconds, it is considered an emergency braking, which is not an ordinary deceleration or parking brake, but requires the brake pedal to be depressed quickly and forcefully to significantly reduce the vehicle speed in a short period of time.

[0070] PLT0 represents the proportion of late-night travel time of the vehicle to be evaluated during the current evaluation period. Specifically, it refers to the ratio of the total travel time of the vehicle to be evaluated in the late night (entrances and exits are between 23:00 and 5:00 the next day) during the current evaluation period to the total travel time of the vehicle in the entire current evaluation period.

[0071] β1 represents the vehicle driving characteristic correction value of the travel speed preset in the travel characteristic library, which represents the proportion of the travel speed of the vehicle to be evaluated in the current evaluation period to the driving characteristic danger value. The travel characteristic library stores the corresponding relationship between the vehicle driving characteristic correction values. For example, the real-time travel speed and driving characteristic danger value of the vehicle to be evaluated in the current evaluation period can be input into the travel characteristic library. The travel characteristic library automatically matches the vehicle driving characteristic correction value corresponding to the travel speed of the vehicle to be evaluated according to the preset corresponding relationship between the vehicle driving characteristic correction values.

[0072] β2 represents the vehicle driving characteristic impact value of the number of emergency brakings preset in the traffic characteristic library, which represents the proportion of the number of emergency brakings of the vehicle to be evaluated in the current evaluation period to the driving characteristic danger value. The traffic characteristic library stores the corresponding relationship between the vehicle driving characteristic impact values. For example, the real-time number of emergency brakings of the vehicle to be evaluated in the current evaluation period and the driving characteristic danger value can be input into the traffic characteristic library. The traffic characteristic library automatically matches the vehicle driving characteristic impact value corresponding to the number of emergency brakings of the vehicle to be evaluated according to the preset corresponding relationship between the vehicle driving characteristic impact values.

[0073] β3 represents the vehicle driving characteristic impact value of the late-night travel time ratio preset in the traffic characteristic library, which represents the proportion of the late-night travel time ratio of the vehicle to be evaluated in the current evaluation period to the driving characteristic danger value. The traffic characteristic library stores the corresponding relationship between the vehicle driving characteristic impact values. For example, the real-time late-night travel time ratio and the driving characteristic danger value of the vehicle to be evaluated in the current evaluation period can be input into the traffic characteristic library. The traffic characteristic library automatically matches the vehicle driving characteristic impact value corresponding to the late-night travel time ratio of the vehicle to be evaluated according to the preset vehicle driving characteristic impact value corresponding relationship.

[0074] VDV represents the driving characteristic hazard value of the vehicle to be evaluated in the current evaluation period. Specifically, in the process of evaluating the driving characteristics of the vehicle to be evaluated in the current evaluation period, the driving characteristic hazard value of the vehicle to be evaluated in the current evaluation period is comprehensively analyzed through the travel speed, number of emergency brakes and proportion of late-night travel time of the vehicle to be evaluated in the current evaluation period. When traveling on the highway, if the driver fails to predict the situation ahead in time or maintain a safe distance, the possibility of emergency braking will increase. A large number of emergency brakes may mean that the driver does not react quickly enough or has more aggressive driving habits, resulting in an increase in the driving characteristic hazard value; as the proportion of late-night travel time increases, the risk of emergency braking may increase due to factors such as poor visibility and possible driver fatigue, increasing the risk of skidding and loss of control, thereby increasing the driving characteristic hazard value.

[0075] S2. Match the driving characteristic danger threshold of the vehicle to be evaluated in the historical evaluation cycle with the stable evaluation value of the driving characteristics of the vehicle to be evaluated in the historical evaluation cycle, compare the driving characteristic danger value of the vehicle to be evaluated in the current evaluation period with the driving characteristic danger threshold of the vehicle to be evaluated in the historical evaluation period, obtain the driving characteristic danger value comparison result, and determine whether to issue an early warning prompt for the driving characteristic data of the vehicle to be evaluated in the current evaluation period based on the driving characteristic danger value comparison result.

[0076] It should be explained that the above matching of the driving characteristic danger threshold of the vehicle to be evaluated in the historical evaluation period with the stable evaluation value of the driving characteristic of the vehicle to be evaluated in the historical evaluation period is carried out. The specific matching process is:

[0077] The driving characteristic stability evaluation value of the vehicle to be evaluated within the historical evaluation period is matched with the driving characteristic danger threshold corresponding to each driving characteristic stability evaluation value interval preset in the traffic characteristic library, thereby obtaining the driving characteristic danger threshold of the vehicle to be evaluated within the historical evaluation period.

[0078] The specific matching process of the driving characteristic danger threshold of the above-mentioned vehicle to be evaluated in the historical evaluation period is as follows:

[0079] The driving characteristic stability assessment values ​​and the corresponding driving characteristic danger thresholds are formulated by authoritative highway monitoring agencies or standardization organizations through data collection, collation, and encryption. Each driving characteristic stability assessment value is carefully divided, and the corresponding driving characteristic danger threshold is designed for each driving characteristic stability assessment value range based on vehicle highway traffic safety standards, threat and risk analysis, and business needs and compliance requirements.

[0080] For example, if the driving characteristic stability evaluation value in this example is 3, it belongs to the driving characteristic stability evaluation value interval corresponding to [3, 5], and the driving characteristic danger threshold value corresponding to the driving characteristic stability evaluation value interval preset in the traffic characteristic library is 85.

[0081] Specifically, the driving characteristic risk value comparison result is specifically a first driving characteristic risk value comparison result and a second driving characteristic risk value comparison result.

[0082] The first driving characteristic hazard value comparison result is specifically that the driving characteristic hazard value is greater than or equal to the driving characteristic hazard threshold, wherein the driving characteristic hazard threshold is obtained by comprehensive analysis of the average daily number of passes, average travel time, average travel speed, proportion of bad weather time, and proportion of late-night travel time of the vehicle to be evaluated in the historical evaluation period, and represents the threshold used to determine whether the driving characteristic hazard value reaches the warning level when conducting a driving characteristic evaluation, and is used to help the traffic characteristic management platform determine whether a warning prompt is needed; the above-mentioned driving characteristic hazard value is greater than or equal to the driving characteristic hazard threshold, indicating that the driving characteristic is dangerous and a warning prompt is needed for the driving characteristic data of the vehicle to be evaluated in the current evaluation period.

[0083] The second driving characteristic risk value comparison result is specifically that the driving characteristic risk value is less than the driving characteristic risk threshold value.

[0084] Furthermore, the specific analysis process of determining whether to issue an early warning to the driving characteristic data of the vehicle to be evaluated within the current evaluation period according to the driving characteristic risk value comparison result is as follows:

[0085] If the driving characteristic danger value comparison result is that the driving characteristic danger value is greater than or equal to the driving characteristic danger threshold, it is necessary to issue an early warning prompt for the driving characteristic data of the vehicle to be evaluated within the current evaluation period.

[0086] If the driving characteristic danger value comparison result is that the driving characteristic danger value is less than the driving characteristic danger threshold, there is no need to issue an early warning prompt for the driving characteristic data of the vehicle to be evaluated during the current evaluation period, and the driving characteristic data is stored in the traffic characteristic archive sub-library.

[0087] It should be explained that the above-mentioned traffic characteristic archive sub-library is used to store driving characteristic data, that is, to store vehicle driving data under the driving characteristic safety state (that is, the driving characteristic danger value is less than the driving characteristic danger threshold), including but not limited to the travel speed, number of emergency braking times and proportion of late-night travel time of the vehicle to be evaluated during the current evaluation period, realizing the transformation from data discretization to completeness. The vehicle traffic characteristic archive includes the traffic characteristic archive sub-library; the vehicle traffic characteristic archive also has the following two main functions, the first is data sliding update, this part is the data update through the data sliding algorithm, and the updated data is stored in the traffic characteristic archive sub-library in the traffic characteristic archive.

[0088] In the process of updating the data of the vehicle traffic characteristic archive, it is necessary to use a batch calculation method to first generate the initial values ​​of these variables (such as the number of emergency brakes in the traffic characteristic archive sub-library), and then perform a daily sliding average update (that is, the number of emergency brakes corresponding to the vehicles each day); specifically, at least data within the past six months is selected, and the average value of the number of emergency brakes in this time period that is consistent with the target characteristics is calculated in batches (for example, the number of emergency brakes of vehicles traveling daily for 6 months is selected, and the average number of emergency brakes is obtained by averaging) to ensure the accuracy of the average number of emergency brakes used in subsequent sliding updates. Subsequently, the number of emergency brakes is updated daily to make the variable timely and real-time.

[0089] The following is the specific algorithm content of the sliding update: the sliding average coefficient is uniformly taken as 0.97, and the number of emergency braking times on the nth day is X n , the corresponding emergency braking times calculated based on yesterday's single-day data is d n , then:

[0090] X n =0.97*X n-1 +0.03*d n ;

[0091] Expanded to be:

[0092] X n =0.03*[d n+0.97*d n-1 +(0.97) 2 *d n-2 +(0.97) 3 *d n-3 +......];

[0093] Note that (0.97) 92 ≈0.06, so the situation three months ago (that is, 92 days) has only about 5% impact on the number of emergency brakes, which is relatively small; in addition, the more recent the situation, the greater the impact on the number of emergency brakes; this reflects the timeliness of the number of emergency brakes. The algorithm is based on the days when the vehicle has a driving record, and then calculates the sliding average. It should be noted that the number of emergency brakes only counts the average value of each day in the days with driving records, rather than the average value of all days, that is, the global average value; the two have different meanings, that is, the above d n , d n-1 , d n-2 Waiting is not every day, but every day with a pass record.

[0094] The above sliding update algorithm process is used to maintain variables related to traffic characteristics and perform sliding average updates on a daily basis. All features that can reflect traffic characteristics and whose basic update unit can be as small as "day" are updated in this way. This can best reflect the most recent driving conditions of the vehicle to be evaluated rather than the past period of time, and can take into account both accuracy and real-time performance. In the face of long-term changes in traffic characteristics due to driver replacement or other reasons, this algorithm can gradually converge to new features and best reflect the vehicle's recent real status; the second is a batch calculation module, which is used to store features that are not suitable for updating on a daily basis and require batch calculation in this part of the data, and recalculate the traffic data from the specified time before the current day every day to reflect the traffic conditions of the vehicle to be evaluated within the historical evaluation period, so that the integrity is higher, the system is stronger, the performance is better, and the real-time performance is stronger. It can continuously realize data accumulation and improve accuracy and performance. In the process of highway operation and management, relevant departments may need to monitor the macroscopic operation of the road section and obtain macroscopic data. After having a vehicle traffic feature library, it can be easily connected to such a system to provide additional information gain.

[0095] Specifically, the warning prompt is given to the driving characteristic data of the vehicle to be evaluated in the current evaluation period, and the specific warning prompt process is:

[0096] The highway section information of the vehicle to be evaluated in the current evaluation period is obtained, and combined with the driving characteristic hazard value of the vehicle to be evaluated in the current evaluation period, the driving characteristic abnormality index of the vehicle to be evaluated in the current evaluation period is comprehensively obtained, thereby matching the driving characteristic reference data of the vehicle to be evaluated, and performing one-to-one difference processing with the driving characteristic data of the vehicle to be evaluated in the current evaluation period to obtain the driving characteristic deviation data, and finally issuing an early warning prompt for the driving characteristic deviation data of the vehicle to be evaluated.

[0097] It should be explained that the driving characteristic deviation data of the above-mentioned vehicle to be evaluated is used for early warning prompts, and the specific early warning prompt process is as follows:

[0098] The driving characteristic anomaly index of the vehicle to be evaluated in the current evaluation period is matched with the driving characteristic reference data corresponding to each driving characteristic anomaly index interval preset in the traffic characteristic library, thereby obtaining the driving characteristic reference data of the vehicle to be evaluated, and performing one-to-one difference processing with the above-mentioned driving characteristic data of the vehicle to be evaluated in the current evaluation period to obtain the driving characteristic deviation data, and finally providing the vehicle with a driving characteristic early warning prompt through the driving characteristic deviation data of the vehicle to be evaluated.

[0099] The above driving characteristic reference data is constructed through scientific collection, preprocessing and analysis. Each driving characteristic abnormality index is carefully divided, and for each driving characteristic abnormality index range, the corresponding driving characteristic reference data is designed based on key factors such as driving characteristic indicators, traffic status data, and historical driving characteristic data.

[0100] For example, in this example, during the current evaluation period, the number of emergency braking times of the vehicle to be evaluated is 3 times; if the number of emergency braking times in the above driving characteristic reference data is 2 times, it is necessary to issue an early warning for the number of emergency braking times in the driving characteristic data of the vehicle to be evaluated during the current evaluation period, that is, the display interface in the traffic characteristic management platform displays a red alarm, and the specific alarm content is "In the current road section, the number of emergency braking times exceeds 1 time, and the vehicle needs to keep driving smoothly to improve driving safety."

[0101] Furthermore, the driving characteristic abnormality index of the vehicle to be evaluated in the current evaluation period is obtained by comprehensive analysis, and the specific analysis process is as follows:

[0102] The highway section information of the vehicle to be evaluated in the current evaluation period includes the traffic volume, traffic density and number of intersections of the highway evaluation section in the current evaluation period.

[0103] It should be explained that the traffic volume of the above-mentioned highway assessment section during the current assessment period can be monitored in real time by traffic cameras installed on the highway and the vehicle passing conditions can be recorded, so as to calculate the traffic volume; the traffic density of the above-mentioned highway assessment section during the current assessment period can be obtained by taking timed photographs of the highway assessment section by traffic cameras installed on the highway, and then calculating the number of vehicles by image processing technology, and then dividing it by the length of the highway assessment section to obtain the traffic density; the number of intersections of the above-mentioned highway assessment section during the current assessment period can be obtained by querying the intersection information of the highway assessment section through the geographic information system, and obtaining the number of intersections by statistics.

[0104] The driving characteristic abnormality index of the vehicle to be evaluated during the current evaluation period is obtained by comprehensively analyzing the traffic volume, traffic density, number of intersections of the highway evaluation section during the current evaluation period, and the driving characteristic hazard value of the vehicle to be evaluated during the current evaluation period. The specific acquisition method is as follows:

[0105]

[0106] Wherein, VDV represents the driving characteristic danger value of the vehicle to be evaluated in the current evaluation period, which is obtained through comprehensive analysis of the vehicle's speed, number of emergency braking times, and proportion of late-night travel time in the current evaluation period.

[0107] VDCT represents the stable evaluation value of the driving characteristics of the vehicle to be evaluated during the historical evaluation period, which is obtained by comprehensively analyzing the average daily number of passes, average travel time, average travel speed, proportion of bad weather time, and proportion of late-night travel time of the vehicle to be evaluated during the historical evaluation period.

[0108] TV represents the traffic volume of the highway assessment section during the current assessment period, specifically the total number of vehicles passing through the highway assessment section during the current assessment period.

[0109] TD represents the traffic density of the highway assessment section during the current assessment period, specifically the number of vehicles on a unit length of highway lane during the current assessment period.

[0110] NJ represents the number of intersections on the highway assessment section during the current assessment period, specifically the total number of intersections that actually exist on the highway assessment section during the current assessment period. The intersections here include intersections formed by other roads (such as ramps, connecting lines, local roads, etc.) that intersect with the main line of the highway, as well as intersections formed by interchanges within the highway.

[0111] ζ1 represents the driving characteristic abnormality influence coefficient of the traffic flow preset in the traffic characteristic library, which represents the proportion of the traffic flow of the highway evaluation section in the current evaluation period to the driving characteristic abnormality index. The traffic characteristic library stores the corresponding relationship between the driving characteristic abnormality influence coefficients. For example, the real-time traffic flow and the driving characteristic abnormality index of the highway evaluation section in the current evaluation period can be input into the traffic characteristic library. The traffic characteristic library automatically matches the driving characteristic abnormality influence coefficient corresponding to the traffic flow of the highway evaluation section according to the preset corresponding relationship between the driving characteristic abnormality influence coefficients.

[0112] ζ2 represents the driving characteristic anomaly influence coefficient of the traffic density preset in the traffic characteristic library, which represents the proportion of the traffic density of the highway assessment section in the current assessment period to the driving characteristic anomaly index. The traffic characteristic library stores the corresponding relationship between the driving characteristic anomaly influence coefficients. For example, the real-time traffic density and driving characteristic anomaly index of the highway assessment section in the current assessment period can be input into the traffic characteristic library. The traffic characteristic library automatically matches the driving characteristic anomaly influence coefficient corresponding to the traffic density of the highway assessment section according to the preset corresponding relationship between the driving characteristic anomaly influence coefficients.

[0113] ζ3 represents the driving characteristic anomaly influence coefficient of the preset number of intersections in the traffic characteristic library, which represents the proportion of the number of intersections of the highway assessment section in the current assessment period to the driving characteristic anomaly index. The traffic characteristic library stores the corresponding relationship between driving characteristic anomaly influence coefficients. For example, the real-time number of intersections of the highway assessment section in the current assessment period and the driving characteristic anomaly index can be input into the traffic characteristic library. The traffic characteristic library automatically matches the driving characteristic anomaly influence coefficient corresponding to the number of intersections of the highway assessment section according to the preset corresponding relationship between driving characteristic anomaly influence coefficients.

[0114] ζ4 represents the driving characteristic abnormality correction coefficient corresponding to the driving characteristic dangerous deviation value preset in the traffic characteristic library, and represents the proportion of the driving characteristic dangerous deviation value to the driving characteristic abnormality index. The traffic characteristic library stores the corresponding relationship of the driving characteristic abnormality correction coefficient. For example, the real-time driving characteristic dangerous deviation value and the driving characteristic abnormality index can be input into the traffic characteristic library, and the traffic characteristic library automatically matches the driving characteristic abnormality correction coefficient corresponding to the driving characteristic dangerous deviation value according to the preset corresponding relationship of the driving characteristic abnormality correction coefficient.

[0115] ADCI represents the driving characteristic abnormality index of the vehicle to be evaluated in the current evaluation period. Specifically, in the process of evaluating the degree of driving characteristic abnormality of the vehicle to be evaluated in the current evaluation period, the driving characteristic abnormality index of the vehicle to be evaluated in the current evaluation period is obtained by comprehensively considering the traffic volume, traffic density, number of intersections of the highway evaluation section in the current evaluation period and the driving characteristic hazard value of the vehicle to be evaluated in the current evaluation period. An increase in traffic volume will lead to an increase in traffic density. When it exceeds the carrying capacity of the road, it will cause traffic congestion and increased driving risks. When the traffic volume is large, the traffic density is high or the number of intersections is large, the vehicle to be evaluated may need to brake, accelerate and turn more frequently, thereby increasing the driving characteristic abnormality index.

[0116] Reference Figure 2 As shown, the second aspect of the present invention provides a vehicle data processing system based on ETC data, including: a driving characteristic evaluation module, a driving characteristic warning module and a traffic characteristic library.

[0117] The driving characteristic evaluation module is connected to the driving characteristic warning module, and the traffic characteristic library is connected to the driving characteristic evaluation module and the driving characteristic warning module respectively.

[0118] The driving characteristic assessment module is used by the traffic characteristic management platform to obtain the historical traffic information of the vehicle to be assessed in the historical assessment cycle and the driving characteristic data of the vehicle to be assessed in the current assessment period, and to respectively assess the stable assessment value of the driving characteristics of the vehicle to be assessed in the historical assessment cycle and the driving characteristic danger value of the vehicle to be assessed in the current assessment period.

[0119] The driving characteristic warning module is used to match the driving characteristic danger threshold of the vehicle to be evaluated in the historical evaluation cycle through the stable evaluation value of the driving characteristics of the vehicle to be evaluated in the historical evaluation cycle, compare the driving characteristic danger value of the vehicle to be evaluated in the current evaluation period with the driving characteristic danger threshold of the vehicle to be evaluated in the historical evaluation period, obtain the driving characteristic danger value comparison result, and determine whether to issue a warning prompt for the driving characteristic data of the vehicle to be evaluated in the current evaluation period according to the driving characteristic danger value comparison result.

[0120] The traffic characteristic library is used to store the driving characteristic danger threshold of the vehicle to be evaluated within the historical evaluation period, the driving characteristic influence index of the average daily number of passes, the driving characteristic influence index of the average travel time, the driving characteristic influence index of the proportion of bad weather time, the driving characteristic influence index of the proportion of late night travel time, the driving characteristic influence index of the average travel speed, the travel speed reference value, the vehicle driving characteristic correction value of the travel speed, the vehicle driving characteristic influence value of the number of emergency braking times, the vehicle driving characteristic influence value of the proportion of late night travel time, the driving characteristic abnormal influence coefficient of the traffic flow, the driving characteristic abnormal influence coefficient of the traffic density, the driving characteristic abnormal influence coefficient of the number of intersections, the driving characteristic abnormal correction coefficient corresponding to the driving characteristic danger deviation value, and the driving characteristic reference data corresponding to each driving characteristic abnormal index interval.

[0121] The above contents are merely examples and explanations of the structure of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the present invention, they should all fall within the protection scope of the present invention.

Claims

1. A vehicle data processing method based on ETC data, characterized in that: include: S1. The traffic characteristics management platform obtains the historical traffic information of the vehicle to be evaluated in the historical evaluation period and the driving characteristics data of the vehicle to be evaluated in the current evaluation period, and respectively evaluates the driving characteristics stability evaluation value of the vehicle to be evaluated in the historical evaluation period and the driving characteristics danger value of the vehicle to be evaluated in the current evaluation period; S2. Match the driving characteristic danger threshold of the vehicle to be evaluated in the historical evaluation cycle with the stable evaluation value of the driving characteristics of the vehicle to be evaluated in the historical evaluation cycle, compare the driving characteristic danger value of the vehicle to be evaluated in the current evaluation period with the driving characteristic danger threshold of the vehicle to be evaluated in the historical evaluation period, obtain the driving characteristic danger value comparison result, and determine whether to issue an early warning prompt for the driving characteristic data of the vehicle to be evaluated in the current evaluation period based on the driving characteristic danger value comparison result.

2. The vehicle data processing method based on ETC data according to claim 1, characterized in that: The historical traffic information of the vehicle to be evaluated during the historical evaluation period specifically includes the average daily number of passes, average travel time per trip, average travel speed, proportion of bad weather time, and proportion of late-night travel time of the vehicle to be evaluated during the historical evaluation period.

3. The vehicle data processing method based on ETC data according to claim 2 is characterized in that: The evaluation process of evaluating the stable evaluation value of the driving characteristics of the vehicle to be evaluated in the historical evaluation cycle is as follows: Through the average daily number of passes, average travel time, average travel speed, proportion of bad weather time, and proportion of late-night travel time of the vehicle to be evaluated during the historical evaluation period, a comprehensive analysis is made to determine a stable evaluation value of the driving characteristics of the vehicle to be evaluated during the historical evaluation period.

4. The vehicle data processing method based on ETC data according to claim 1, characterized in that: The driving characteristic data of the vehicle to be evaluated during the current evaluation period specifically include the mileage, number of emergency braking times and proportion of late-night driving time of the vehicle to be evaluated during the current evaluation period.

5. The vehicle data processing method based on ETC data according to claim 4 is characterized in that: The specific analysis process of the driving characteristic risk value of the vehicle to be evaluated in the current evaluation period is as follows: The mileage of the vehicle to be evaluated in the current evaluation period is compared with the duration corresponding to the current evaluation period to obtain the travel speed of the vehicle to be evaluated in the current evaluation period; The driving characteristic hazard value of the vehicle to be evaluated in the current evaluation period is comprehensively analyzed through the travel speed, number of emergency braking times and proportion of late-night travel time of the vehicle to be evaluated in the current evaluation period.

6. The vehicle data processing method based on ETC data according to claim 1, characterized in that: The driving characteristic risk value comparison result is specifically a first driving characteristic risk value comparison result and a second driving characteristic risk value comparison result; The first driving characteristic risk value comparison result is specifically that the driving characteristic risk value is greater than or equal to the driving characteristic risk threshold; The second driving characteristic risk value comparison result is specifically that the driving characteristic risk value is less than the driving characteristic risk threshold value.

7. The vehicle data processing method based on ETC data according to claim 1, characterized in that: The specific analysis process of determining whether to issue an early warning prompt for the driving characteristic data of the vehicle to be evaluated within the current evaluation period according to the driving characteristic risk value comparison result is as follows: If the driving characteristic danger value comparison result is that the driving characteristic danger value is greater than or equal to the driving characteristic danger threshold, it is necessary to issue an early warning prompt for the driving characteristic data of the vehicle to be evaluated within the current evaluation period; If the driving characteristic danger value comparison result is that the driving characteristic danger value is less than the driving characteristic danger threshold, there is no need to issue an early warning prompt for the driving characteristic data of the vehicle to be evaluated during the current evaluation period, and the driving characteristic data is stored in the traffic characteristic archive sub-library.

8. The vehicle data processing method based on ETC data according to claim 7 is characterized in that: The specific warning process of the driving characteristic data of the vehicle to be evaluated during the current evaluation period is as follows: The highway section information of the vehicle to be evaluated in the current evaluation period is obtained, and combined with the driving characteristic hazard value of the vehicle to be evaluated in the current evaluation period, the driving characteristic abnormality index of the vehicle to be evaluated in the current evaluation period is comprehensively obtained, thereby matching the driving characteristic reference data of the vehicle to be evaluated, and performing one-to-one difference processing with the driving characteristic data of the vehicle to be evaluated in the current evaluation period to obtain the driving characteristic deviation data, and finally issuing an early warning prompt for the driving characteristic deviation data of the vehicle to be evaluated.

9. The vehicle data processing method based on ETC data according to claim 8, characterized in that: The driving characteristic abnormality index of the vehicle to be evaluated in the current evaluation period is obtained by comprehensive analysis, and the specific analysis process is as follows: The highway section information of the vehicle to be evaluated in the current evaluation period includes the traffic volume, traffic density and number of intersections of the highway evaluation section in the current evaluation period; The driving characteristic abnormality index of the vehicle to be evaluated during the current evaluation period is obtained by comprehensively analyzing the traffic volume, traffic density, number of intersections of the highway evaluation section during the current evaluation period, and the driving characteristic hazard value of the vehicle to be evaluated during the current evaluation period. The specific acquisition method is as follows: Wherein, ADCI represents the driving characteristic abnormality index of the vehicle to be evaluated in the current evaluation period, VDV represents the driving characteristic danger value of the vehicle to be evaluated in the current evaluation period, VDCT represents the driving characteristic stable evaluation value of the vehicle to be evaluated in the historical evaluation period, TV represents the traffic volume of the highway evaluation section in the current evaluation period, TD represents the traffic density of the highway evaluation section in the current evaluation period, NJ represents the number of intersections of the highway evaluation section in the current evaluation period, ζ1 represents the driving characteristic abnormality influence coefficient of the traffic volume preset in the traffic characteristic library, ζ2 represents the driving characteristic abnormality influence coefficient of the traffic density preset in the traffic characteristic library, ζ3 represents the driving characteristic abnormality influence coefficient of the number of intersections preset in the traffic characteristic library, and ζ4 represents the driving characteristic abnormality correction coefficient corresponding to the driving characteristic danger deviation value preset in the traffic characteristic library.

10. A system using the vehicle data processing method based on ETC data as claimed in any one of claims 1 to 9, characterized in that: include: The driving characteristic evaluation module is used for the traffic characteristic management platform to obtain the historical traffic information of the vehicle to be evaluated in the historical evaluation cycle and the driving characteristic data of the vehicle to be evaluated in the current evaluation period, and respectively evaluate the driving characteristic stability evaluation value of the vehicle to be evaluated in the historical evaluation cycle and the driving characteristic danger value of the vehicle to be evaluated in the current evaluation period; The driving characteristic warning module is used to match the driving characteristic danger threshold of the vehicle to be evaluated in the historical evaluation period through the stable evaluation value of the driving characteristics of the vehicle to be evaluated in the historical evaluation period, compare the driving characteristic danger value of the vehicle to be evaluated in the current evaluation period with the driving characteristic danger threshold of the vehicle to be evaluated in the historical evaluation period, obtain the driving characteristic danger value comparison result, and determine whether to issue a warning prompt for the driving characteristic data of the vehicle to be evaluated in the current evaluation period based on the driving characteristic danger value comparison result.

Images