High-speed ETC vehicle toll evasion detection method and system based on big data fusion

Abstract

The invention provides a high-speed ETC vehicle toll evasion detection method and system based on big data fusion. The method comprises the steps of obtaining vehicle registration information, real-time passing record information and monitoring information of a preset vehicle, performing corresponding matching processing with the vehicle registration information according to the real-time passing record information and the monitoring information to obtain a matching result, obtaining historical fee evasion record data, and determining a real-time suspicion level of the preset vehicle in combination with the matching result. And corresponding processing measures are taken according to the real-time suspicion level, so that a high-speed ETC vehicle toll evasion detection technology based on big data fusion is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle fee evasion detection, in particular to a high-speed ETC vehicle fee evasion detection method and system based on big data fusion. BACKGROUND

[0002] In the field of highway toll management, ETC vehicle fee evasion behavior not only causes economic losses, but also disrupts normal traffic order; currently, traditional toll verification methods rely mainly on manual comparison, which has the problems of low efficiency and high rates of missed or mistaken judgments; for example, manual verification cannot integrate multi-dimensional data in real time, resulting in delayed identification of fee evasion behavior.

[0003] At the same time, existing systems do not make full use of ETC vehicle historical fee evasion records, cannot dynamically assess the suspicion level in combination with current traffic data, and often can only trace back after fee evasion behavior occurs, making it difficult to achieve pre-warning and intervention; in addition, different fee evasion behaviors have large differences in severity, and traditional processing methods lack a grading response mechanism, which can easily result in excessive intervention in normal traffic or inadequate handling of serious fee evasion behavior, affecting management efficiency and user experience.

[0004] In view of the above problems, an effective technical solution is currently needed. SUMMARY

[0005] The purpose of the present application is to provide a high-speed ETC vehicle fee evasion detection method and system based on big data fusion, which can obtain vehicle registration information, real-time traffic record information and monitoring information of a preset vehicle, perform corresponding matching processing on the vehicle registration information according to the real-time traffic record information and monitoring information, obtain a matching result, acquire historical fee evasion record data, determine the real-time suspicion level of the preset vehicle in combination with the matching result, and take appropriate processing measures according to the real-time suspicion level, thereby realizing the technology of high-speed ETC vehicle fee evasion detection based on big data fusion.

[0006] The present application also provides a high-speed ETC vehicle fee evasion detection method based on big data fusion, comprising the following steps: Obtain vehicle registration information, real-time traffic record information and monitoring information of a preset vehicle; Perform corresponding matching processing on the vehicle registration information according to the real-time traffic record information and monitoring information, and obtain a matching result; Acquire historical fee evasion record data, and determine the real-time suspicion level of the preset vehicle in combination with the matching result; Take appropriate processing measures according to the real-time suspicion level.

[0007] Optionally, in the high-speed ETC vehicle fee evasion detection method based on big data fusion provided in the application, the vehicle registration information, real-time toll record information and monitoring information of the preset vehicle are obtained, and the method comprises the following steps: obtaining vehicle registration information, real-time toll record information and monitoring information of a preset vehicle; The vehicle registration information includes license plate, vehicle type, number of axles, vehicle length and vehicle height. The real-time toll record information includes entry gate, exit gate, toll time, toll amount, weighing record data and path information. The monitoring information includes vehicle snapshot image and vehicle snapshot video.

[0008] Optionally, in the high-speed ETC vehicle fee evasion detection method based on big data fusion provided in the application, the corresponding matching processing of the real-time toll record information and the monitoring information with the vehicle registration information is performed to obtain a matching result, which comprises the following steps: According to the vehicle snapshot image and the vehicle snapshot video, vehicle identification result information and vehicle appearance feature information are extracted; Calculate the shortest path fee according to the entry gate and the exit gate; According to the toll time and the path information, the theoretical fee amount is calculated; According to the vehicle identification result information, vehicle appearance feature information, shortest path fee, theoretical fee amount and weighing record data, the vehicle registration information and toll amount are compared to obtain a matching result; The matching result includes matching abnormal type and matching abnormal number. The matching abnormal type includes type matching abnormality, rate abnormality, path abnormality, weighing abnormality and license plate consistency abnormality.

[0009] Optionally, in the high-speed ETC vehicle fee evasion detection method based on big data fusion provided in the application, the historical fee evasion record data is obtained, and the real-time suspicion level of the preset vehicle is determined in combination with the matching result, which comprises the following steps: Obtain the historical fee evasion record data of the preset vehicle, including the historical fee evasion times and the historical fee evasion suspicion level; According to the historical fee evasion times and the historical fee evasion suspicion level, the matching abnormal number is processed through a preset fee evasion suspicion evaluation model to obtain a real-time suspicion level; The real-time suspicion level includes high-risk level, medium-risk level and low-risk level.

[0010] Optionally, in the high-speed ETC vehicle fee evasion detection method based on big data fusion provided in the application, the corresponding processing measures are taken according to the real-time suspicion level, which comprises the following steps: If the real-time suspicion level is a high-risk level, corresponding processing measures are taken, including on-site interception and control, evidence fixation and verification, and disposal of accountability; If the real-time suspicion level is a medium-risk level, corresponding processing measures are taken, including lane verification, information confirmation, and hierarchical processing; If the real-time suspicion level is a low-risk level, corresponding processing measures are taken, including rapid verification, record tracking, and optimized feedback.

[0011] Optionally, in the high-speed ETC vehicle fee evasion detection method based on big data fusion provided in the present application, the matching abnormal type further includes: If the vehicle appearance feature information and the number of axles and the vehicle length do not match, the matching abnormal type is a type matching abnormality; If the theoretical fee amount and the preset fee average value threshold do not match, the matching abnormal type is a rate abnormality; If the shortest path fee and the billing amount do not match, the matching abnormal type is a path abnormality; If the weighing record data and the number of axles and the preset mass limit do not match, the matching abnormal type is a weighing abnormality; If the vehicle identification result information and the license plate do not match, the matching abnormal type is a license plate consistency abnormality.

[0012] In a second aspect, the present application provides a high-speed ETC vehicle fee evasion detection system based on big data fusion, which comprises a memory and a processor, wherein the memory comprises a program of a high-speed ETC vehicle fee evasion detection method based on big data fusion, and the program of the high-speed ETC vehicle fee evasion detection method based on big data fusion is executed by the processor to realize the following steps: Obtain vehicle registration information, real-time passing record information, and monitoring information of a preset vehicle; According to the real-time passing record information and the monitoring information, corresponding matching processing is performed with the vehicle registration information to obtain a matching result; Obtain historical fee evasion record data, and determine a real-time suspicion level of the preset vehicle in combination with the matching result; According to the real-time suspicion level, corresponding processing measures are taken.

[0013] Optionally, in the high-speed ETC vehicle fee evasion detection system based on big data fusion provided in the present application, the obtaining of the vehicle registration information, the real-time passing record information, and the monitoring information of the preset vehicle comprises: Obtain vehicle registration information, real-time passing record information, and monitoring information of a preset vehicle; The vehicle registration information includes license plate, vehicle model, number of axles, vehicle length, and vehicle height. The real-time toll record information includes entrance, exit, toll time, billing amount, weighing record data, and path information. The monitoring information includes vehicle snapshot images and vehicle snapshot videos.

[0014] Optionally, in the high-speed ETC vehicle fee evasion detection system based on big data fusion provided in the present application, the corresponding matching processing of the real-time toll record information and the monitoring information with the vehicle registration information is performed to obtain a matching result, which includes: The vehicle recognition result information and the vehicle appearance feature information are extracted from the vehicle snapshot images and the vehicle snapshot videos. The shortest path fee is calculated according to the entrance and the exit. The theoretical fee amount is calculated according to the toll time and the path information. The vehicle registration information and the billing amount are compared according to the vehicle recognition result information, the vehicle appearance feature information, the shortest path fee, the theoretical fee amount, and the weighing record data to obtain a matching result. The matching result includes a matching abnormal type and a matching abnormal number. The matching abnormal type includes a type matching abnormality, a rate abnormality, a path abnormality, a weighing abnormality, and a license plate consistency abnormality.

[0015] Optionally, in the high-speed ETC vehicle fee evasion detection system based on big data fusion provided in the present application, the historical fee evasion record data is obtained, and the real-time suspicion level of the preset vehicle is determined in combination with the matching result, which includes: The historical fee evasion record data of the preset vehicle is obtained, including the historical fee evasion times and the historical fee evasion suspicion level. The real-time suspicion level is obtained by processing the historical fee evasion times and the historical fee evasion suspicion level in combination with the matching abnormal number through a preset fee evasion suspicion evaluation model. The real-time suspicion level includes a high-risk level, a medium-risk level, and a low-risk level.

[0016] As can be seen from the above, the high-speed ETC vehicle fee evasion detection method and system based on big data fusion provided in the present application obtain the vehicle registration information, the real-time toll record information, and the monitoring information of a preset vehicle, perform the corresponding matching processing of the real-time toll record information and the monitoring information with the vehicle registration information to obtain a matching result, obtain the historical fee evasion record data, determine the real-time suspicion level of the preset vehicle in combination with the matching result, and take appropriate processing measures according to the real-time suspicion level, thereby realizing the high-speed ETC vehicle fee evasion detection based on big data fusion.

[0017] Other features and advantages of the present application will be set forth in the following description, and in part will be apparent from the description, or can be learned by practice of the application. The objects and other advantages of the present application will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments of the present application. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be considered as limiting the scope. For those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0019] Figure 1 The flowchart of the high-speed ETC vehicle fee evasion detection method based on big data fusion provided by the embodiments of the present application; Figure 2 The flowchart of obtaining a matching result of the high-speed ETC vehicle fee evasion detection method based on big data fusion provided by the embodiments of the present application; Figure 3 The flowchart of determining a real-time suspicion level of a preset vehicle of the high-speed ETC vehicle fee evasion detection method based on big data fusion provided by the embodiments of the present application; Figure 4 The flowchart of taking corresponding processing measures of the high-speed ETC vehicle fee evasion detection method based on big data fusion provided by the embodiments of the present application. DETAILED DESCRIPTION

[0020] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. The components of the embodiments of the present application described and shown in the drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of the present application.

[0021] It should be noted that similar reference numerals and letters in the following drawings represent similar items, and therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. Meanwhile, in the description of the present application, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0022] Reference is made to Figure 1 , Figure 1 is a flow chart of a high-speed ETC vehicle fee evasion detection method based on big data fusion in some embodiments of the present application. The high-speed ETC vehicle fee evasion detection method based on big data fusion is used in a terminal device, such as a computer, a mobile phone terminal, etc. The high-speed ETC vehicle fee evasion detection method based on big data fusion comprises the following steps: S11, obtaining vehicle registration information, real-time toll record information and monitoring information of a preset vehicle; S12, performing corresponding matching processing on the vehicle registration information according to the real-time toll record information and the monitoring information, and obtaining a matching result; S13, obtaining historical fee evasion record data, and determining a real-time suspicion level of the preset vehicle in combination with the matching result; S14, taking corresponding processing measures according to the real-time suspicion level.

[0023] It should be noted that the highway toll standard is calculated according to the vehicle type. Under normal circumstances, when the vehicle drives off the road network exit, the system completes the collection of the toll according to the entry and gantry charging information in the toll medium, and releases one vehicle with one pole; however, under the drive of economic interests, a small number of drivers will try to use various means to evade tolls, which will interfere with the normal toll order of the toll management department to different degrees; in order to reduce the ETC vehicle fee evasion behavior, first, the vehicle registration information of the preset vehicle is obtained, including the license plate, the vehicle type, the number of shafts, the vehicle length and the vehicle height, the real-time toll record information, including the entry, the exit, the toll time, the toll amount, the weighing record data and the path information, and the monitoring information, including the vehicle snapshot image and the vehicle snapshot video; according to the real-time toll record information and the monitoring information, the corresponding matching processing is performed on the vehicle registration information, and a matching result is obtained, including the matching abnormal type and the matching abnormal number; the historical fee evasion record data is obtained, including the historical fee evasion times and the historical fee evasion suspicion level, the real-time suspicion level of the preset vehicle is determined in combination with the matching result, including the high-risk level, the medium-risk level and the low-risk level; and corresponding processing measures are taken according to the real-time suspicion level, so as to realize the technology of high-speed ETC vehicle fee evasion detection based on big data fusion.

[0024] According to the embodiment of the present application, the vehicle registration information, the real-time toll record information and the monitoring information of the preset vehicle are obtained, comprising: obtaining vehicle registration information, real-time toll record information and monitoring information of a preset vehicle; The vehicle registration information includes the license plate, the vehicle type, the number of shafts, the vehicle length and the vehicle height; The real-time passage record information includes an inbound port, an outbound port, a passage time, a billing amount, weighing record data, and path information. The monitoring information includes a vehicle snapshot image and a vehicle snapshot video.

[0025] It should be noted that, in order to accurately identify the vehicle state, three types of key information need to be comprehensively collected. First, the registration information of the preset vehicle, which covers the core identifier of the license plate number, as well as the basic parameters such as the vehicle type (such as a car, a truck), the number of axles (related to the load standard), the length and height of the vehicle (used to judge whether it is over-limit), etc. These information is an important basis for vehicle identity verification. Second, the real-time passage record information, including the inbound port and outbound port position of the vehicle, can clearly determine the driving path. The passage time can reflect the driving time and efficiency. The billing amount is a direct reference for cost settlement. The weighing record data can monitor whether it is overloaded. The detailed path information can trace the whole driving track, providing support for cost accounting and abnormality judgment. Finally, the monitoring information includes a vehicle snapshot image, which can clearly present the vehicle appearance, license plate details and loading condition. The vehicle snapshot video can dynamically record the vehicle driving state, lane changing behavior, etc.

[0026] Please refer to Figure 2 , Figure 2 is a flowchart of obtaining a matching result of the high-speed ETC vehicle fee evasion detection method based on big data fusion in some embodiments of the present application. According to the embodiment of the present application, the real-time passage record information and the monitoring information are matched with the vehicle registration information to obtain a matching result, including: S21, extracting vehicle identification result information and vehicle appearance feature information according to the vehicle snapshot image and the vehicle snapshot video; S22, calculating the shortest path fee according to the inbound port and the outbound port; S23, calculating the theoretical fee amount according to the passage time and the path information; S24, comparing the vehicle identification result information, the vehicle appearance feature information, the shortest path fee, the theoretical fee amount, and the weighing record data with the vehicle registration information and the billing amount to obtain a matching result; S25, the matching result includes a matching abnormality type and a matching abnormality number; S26, the matching abnormality type includes a type matching abnormality, a rate abnormality, a path abnormality, a weighing abnormality, and a license plate consistency abnormality.

[0027] It should be noted that based on the vehicle snapshot image and video, the image recognition technology is used to extract the vehicle identification result information (such as automatically identified license plate number, vehicle model code) and appearance feature information (including length, height, tire number and other details), to provide visual basis for subsequent verification; combined with the position data of the vehicle entry and exit, the system automatically calculates the shortest path cost between the two places as the cost reference; at the same time, according to the passing time and actual path information, combined with the road section charging standard, the theoretical cost amount is calculated, which is compared with the actual billing amount to form a contrast dimension; the extracted vehicle identification result, appearance feature, shortest path fee, theoretical cost amount and weighing record data are compared with the vehicle registration information (license plate, vehicle model, axle number, vehicle length and vehicle height) and actual billing amount one by one: type matching abnormality, rate abnormality, path abnormality, weighing abnormality and license plate consistency abnormality, etc. are obtained; the final matching result contains the above specific abnormal types, and the number of each type of abnormality is also counted, which provides clear data support for accurately positioning the vehicle passing problem.

[0028] Please refer to Figure 3 , Figure 3 is the flowchart of determining the real-time suspicion level of the preset vehicle in the high-speed ETC vehicle fee evasion detection method based on big data fusion in some embodiments of the present application. According to the embodiments of the present application, the acquisition of historical fee evasion record data and the determination of the real-time suspicion level of the preset vehicle based on the matching result include: S31, acquiring historical fee evasion record data of the preset vehicle, including historical fee evasion times and historical fee evasion suspicion level; S32, according to the historical fee evasion times and historical fee evasion suspicion level, combining the number of matching abnormalities to process through a preset fee evasion suspicion evaluation model to obtain a real-time suspicion level; S33, the real-time suspicion level includes high-risk level, medium-risk level and low-risk level.

[0029] It should be noted that, in order to accurately evaluate the real-time evasion suspicion of the vehicle, the historical evasion record data of the preset vehicle needs to be called first, which includes the specific number of historical evasion and the corresponding suspicion level of each evasion behavior (such as records judged as high, medium and low risk); then, the historical data and the number of matching abnormalities obtained at present are combined and input into the preset evasion suspicion evaluation model, which realizes quantitative evaluation through multi-level algorithm: first, the basic weight of the number of historical evasion is given, the more the number is, the higher the weight value is; second, the historical evasion suspicion level is weighted and corrected, the correction coefficient of high-risk historical record is higher than that of medium and low risk; finally, the influence value of the number of current matching abnormalities is superimposed, the more the number of abnormalities is, the more significant the pulling effect on the real-time evaluation result is; finally, the model outputs the real-time suspicion level according to the preset threshold: if the comprehensive score is much higher than the threshold, and there are multiple high-risk historical records and a large number of current abnormalities, it is judged as high-risk level; if the score is in the middle interval, the historical record and the current abnormality are limited, then it is medium-risk level; if the score is low, there is no historical evasion record and the number of current abnormalities is limited, then it is low-risk level; the specific level division is processed according to the actual situation and demand.

[0030] Please refer to Figure 4 , Figure 4 is the flowchart of taking corresponding processing measures in the high-speed ETC vehicle evasion detection method based on big data fusion in some embodiments of the application. According to the embodiment of the application, the corresponding processing measures are taken according to the real-time suspicion level, which includes: S41, if the real-time suspicion level is high-risk level, corresponding processing measures are taken, including on-site interception and control, evidence fixation and verification, and disposal of accountability; S42, if the real-time suspicion level is medium-risk level, corresponding processing measures are taken, including lane verification, information confirmation and hierarchical processing; S43, if the real-time suspicion level is low-risk level, corresponding processing measures are taken, including rapid verification, record tracking and optimization feedback.

[0031] Need to explain, when the vehicle is determined as high risk level, need to start emergency response mechanism immediately; On-site interception and control link, quickly close the target lane barrier, issue warning through broadcast, if the vehicle tries to rush card, linkage security and police force cooperates to intercept, avoids happening safety accident, simultaneously guides vehicle to special check area, limits the driver to leave arbitrarily; Evidence fixing and verification stage, comprehensively calls vehicle history passing and fee evasion record, shoots vehicle appearance, license plate and relevant certificate photo, records driver statement in detail, ensures evidence chain complete; Disposal accountability link, orders to pay fee and breach of contract fine, refuses to cooperate by the relevant departments to intervene in punishment or case, simultaneously, the vehicle information is included in the fee evasion blacklist; If it is medium risk level, take precise check as core; Lane check, toll collector inquires abnormal situation on site, guides vehicle to abnormal processing lane, avoids blocking main channel; Information confirmation link, compares vehicle registration information and actual state, checks ETC account and weighing data, if necessary, linkage background verifies cross-section information, hierarchical processing according to verification result: slightly irregular is warned orally and persuades to leave; There is fee difference and orders to pay; Cannot exclude high risk suspicion, temporarily detained observation, risk escalation is transferred into high risk processing flow; For low risk level, focuses on efficient passing and system optimization; Fast check is completed through non-contact mode, toll collector simply confirms vehicle information, system problem causes abnormality and is corrected on the spot and released; Record tracking link, detailed registration early warning reason and processing result, is included in operation and maintenance log; Optimization feedback stage, regularly summarizes low risk data, analyzes high frequency abnormality cause, promotes equipment upgrade and algorithm optimization, reduces system misjudgment, balances check precision and passing efficiency.

[0032] According to the embodiment of the application, the matching abnormal type further comprises: If the vehicle appearance feature information and the axle number and the vehicle length do not match, the matching abnormal type is a type matching abnormality; If the theoretical fee amount and the preset fee average value threshold do not match, the matching abnormal type is a rate abnormality; If the shortest path fee and the billing amount do not match, the matching abnormal type is a path abnormality; If the weighing record data and the axle number and the preset mass limit value do not match, the matching abnormal type is a weighing abnormality; If the vehicle identification result information and the license plate do not match, the matching abnormal type is a license plate consistency abnormality.

[0033] It should be noted that when the vehicle appearance feature information does not match the registered number of axles and vehicle length, it is determined that the type matching is abnormal; for example, a vehicle registered as a three-axle truck actually appears as a two-axle truck, or the actual measured length deviates from the registered length by more than the standard range, which belongs to this type of abnormality, and there may be a false report of the vehicle model; if the theoretical fee amount does not match the preset fee average threshold, a rate anomaly is formed; the preset fee average threshold is calculated based on the average fee of vehicles of the same type and the same path, and if the theoretical fee of a vehicle is significantly higher or lower than the threshold (such as more than ± 20%), it may indicate that there is an error in the rate calculation or a suspicion of manual adjustment of the fee; when the shortest path fee does not match the actual billing amount, it is a path anomaly; the shortest path fee calculated by the system based on the entrance and exit is the reference fee for normal travel, and if the actual billing amount deviates significantly from this, it may mean that the vehicle has behaviors such as taking a detour to avoid fees, changing cards to tamper with the path, etc.; if the weighing record data does not match the preset mass limit corresponding to the registered number of axles, it is a weighing anomaly; different number of axles of vehicles have a clear upper limit of load, such as a two-axle truck with a preset mass limit of 18 tons, if the weighing record shows 25 tons, which exceeds the limit, it is determined as an overload type weighing anomaly, otherwise if it is far below the reasonable load and has no valid reason, it may also be a suspicion of fee evasion; when the vehicle identification result information does not match the registered license plate, it is determined that the license plate consistency is abnormal. For example, the license plate identified from the snapshot image is "ABC123", but the registered license plate is "DEF456", or there is a significant difference in the letters and numbers of the license plate, which may involve illegal behaviors such as license plate replacement.

[0034] In a second aspect, the present application also discloses a high-speed ETC vehicle fee evasion detection system based on big data fusion, comprising a memory and a processor, wherein the memory comprises a high-speed ETC vehicle fee evasion detection method program based on big data fusion, and the high-speed ETC vehicle fee evasion detection method program based on big data fusion realizes the following steps when executed by the processor: Obtain vehicle registration information, real-time travel record information and monitoring information of a preset vehicle; According to the real-time travel record information and the monitoring information, corresponding matching processing is performed with the vehicle registration information to obtain a matching result; Obtain historical fee evasion record data, and determine a real-time suspicion level of the preset vehicle in combination with the matching result; According to the real-time suspicion level, take corresponding processing measures.

[0035] It should be noted that the highway toll standard is calculated according to the vehicle type, and under normal circumstances, when the vehicle drives off the road network exit, the system completes the collection of the toll according to the entry and gantry charging information in the toll medium, and releases one vehicle with one pole; however, under the drive of economic benefits, a small number of drivers will try to use various means to evade tolls, which will interfere with the normal toll order of the toll management department to different degrees; in order to reduce the ETC vehicle evasion behavior, first, the vehicle registration information of the preset vehicle is obtained, including the license plate, vehicle type, number of shafts, vehicle length and vehicle height, real-time traffic record information, including the entry port, exit port, toll time, billing amount, weighing record data and path information, and monitoring information, including vehicle snapshot image and vehicle snapshot video; according to the real-time traffic record information and the monitoring information, the vehicle registration information is matched, the matching result is obtained, including the matching abnormal type and the matching abnormal number; the historical evasion record data is obtained, including the historical evasion times and the historical evasion suspicion level, and the real-time suspicion level of the preset vehicle is determined according to the matching result, including the high-risk level, the medium-risk level and the low-risk level; according to the real-time suspicion level, the corresponding processing measures are taken, so that the highway ETC vehicle evasion detection technology based on big data fusion is realized.

[0036] According to the embodiment of the present application, the vehicle registration information, real-time traffic record information and monitoring information of the preset vehicle are obtained, including: The vehicle registration information, real-time traffic record information and monitoring information of the preset vehicle are obtained; The vehicle registration information includes the license plate, vehicle type, number of shafts, vehicle length and vehicle height; The real-time traffic record information includes the entry port, exit port, toll time, billing amount, weighing record data and path information; The monitoring information includes vehicle snapshot image and vehicle snapshot video.

[0037] It should be noted that, in order to accurately identify the vehicle state, three types of key information need to be collected comprehensively, first, the registration information of the preset vehicle, covering the core identification of the license plate number, and the basic parameters such as the vehicle type (such as a car, a truck), the number of shafts (related to the load standard), the length and height of the vehicle (used to judge whether it is over-limit), etc., which are important basis for vehicle identity verification; second, the real-time traffic record information, including the entry port and exit port position of the vehicle, which can clearly determine the driving path; the toll time can reflect the driving time and efficiency; the billing amount is a direct reference for cost settlement; the weighing record data can monitor whether it is overloaded; and the detailed path information can trace the whole driving track, providing support for cost accounting and abnormal judgment; finally, the monitoring information, including the vehicle snapshot image, which can clearly present the vehicle appearance, license plate details and loading condition; the vehicle snapshot video can dynamically record the vehicle driving state, lane changing behavior, etc.

[0038] According to the embodiment of the present application, the corresponding matching processing is performed on the real-time traffic record information and the monitoring information, and the matching result is obtained, comprising: The vehicle identification result information and the vehicle appearance feature information are extracted from the vehicle snapshot image and the vehicle snapshot video; The shortest path fee is calculated according to the inbound port and the outbound port; The theoretical fee amount is calculated according to the passage time and the path information; The matching result is obtained by comparing the vehicle identification result information, the vehicle appearance feature information, the shortest path fee, the theoretical fee amount, and the weighing record data with the vehicle registration information and the billing amount; The matching result includes the matching exception type and the matching exception number; The matching exception type includes the type matching exception, the rate exception, the path exception, the weighing exception, and the license plate consistency exception.

[0039] It should be noted that based on the vehicle snapshot image and the video, the image recognition technology is used to extract the vehicle identification result information (such as the automatically identified license plate number and the vehicle model code) and the appearance feature information (including the length, the height, the tire number, and other details), which provides a visual basis for subsequent verification; combined with the position data of the vehicle inbound port and the outbound port, the system automatically calculates the shortest path fee between the two places as a fee reference; at the same time, according to the passage time and the actual path information, the theoretical fee amount is calculated according to the road section charging standard, which is compared with the actual billing amount; the extracted vehicle identification result, appearance feature, shortest path fee, theoretical fee amount, and weighing record data are compared with the vehicle registration information (license plate, vehicle model, number of axles, vehicle length, and vehicle height) and the actual billing amount one by one: the type matching exception, the rate exception, the path exception, the weighing exception, and the license plate consistency exception are obtained; the finally generated matching result contains the above specific exception types and the number of occurrences of each type of exception, which provides clear data support for accurately positioning the vehicle passage problem.

[0040] According to the embodiment of the present application, the historical fee evasion record data is obtained, and the real-time suspicion level of the preset vehicle is determined according to the matching result, comprising: The historical fee evasion record data of the preset vehicle is obtained, including the historical fee evasion times and the historical fee evasion suspicion level; The real-time suspicion level is obtained by processing the historical fee evasion times and the historical fee evasion suspicion level in combination with the matching exception number through a preset fee evasion suspicion evaluation model; The real-time suspicion level includes a high-risk level, a medium-risk level, and a low-risk level.

[0041] It should be noted that, in order to accurately evaluate the real-time evasion suspicion of the vehicle, the historical evasion record data of the preset vehicle needs to be called first, which covers the specific number of historical evasion and the corresponding suspicion level of each evasion behavior (such as records judged as high, medium and low risk); then, the historical data and the number of matching abnormalities obtained at present are combined and input into a preset evasion suspicion evaluation model, which realizes quantitative evaluation through multi-level algorithm: first, the historical evasion times are given a basic weight, the more the times, the higher the weight value; second, the historical evasion suspicion level is weighted and corrected, the correction coefficient of high-risk historical record is higher than that of medium and low risk; finally, the influence value of the number of current matching abnormalities is superimposed, the more the number of abnormalities, the more significant the pulling effect on the real-time evaluation result; finally, the model outputs the real-time suspicion level according to the preset threshold: if the comprehensive score is far higher than the threshold, and there are multiple high-risk historical records and a large number of current abnormalities, it is judged as high-risk level; the score is in the middle interval, the historical record and the current abnormality are limited, then it is medium-risk level; the score is low, there is no historical evasion record and the number of current abnormalities is limited, that is, low-risk level; the specific level division is processed according to the actual situation and demand.

[0042] According to the embodiment of the application, the corresponding processing measures are taken according to the real-time suspicion level, including: If the real-time suspicion level is high-risk level, the corresponding processing measures are taken, including on-site interception and control, evidence fixation and verification, and disposal of accountability; If the real-time suspicion level is medium-risk level, the corresponding processing measures are taken, including lane verification, information confirmation and hierarchical processing; If the real-time suspicion level is low-risk level, the corresponding processing measures are taken, including rapid verification, record tracking and optimization feedback.

[0043] Need to explain, when the vehicle is determined as high risk level, need to start emergency response mechanism immediately; On-site interception and control link, quickly close the target lane barrier, issue warning through broadcast, if the vehicle tries to rush card, linkage security and police force cooperates to intercept, avoids happening safety accident, simultaneously guides vehicle to special check area, limits the driver to leave arbitrarily; Evidence fixing and verification stage, comprehensively calls vehicle history passing and fee evasion record, shoots vehicle appearance, license plate and relevant certificate photo, records driver statement in detail, ensures evidence chain complete; Disposal accountability link, orders to pay fee and breach of contract fine, refuses to cooperate by the relevant departments to intervene in punishment or case, simultaneously, the vehicle information is included in the fee evasion blacklist; If it is medium risk level, take precise check as core; Lane check, toll collector inquires abnormal situation on site, guides vehicle to abnormal processing lane, avoids blocking main channel; Information confirmation link, compares vehicle registration information and actual state, checks ETC account and weighing data, if necessary, linkage background verifies cross-section information, hierarchical processing according to verification result: slightly irregular is warned orally and persuades to leave; There is fee difference and orders to pay; Cannot exclude high risk suspicion, temporarily detained observation, risk escalation is transferred into high risk processing flow; For low risk level, focuses on efficient passing and system optimization; Fast check is completed through non-contact mode, toll collector simply confirms vehicle information, system problem causes abnormality and is corrected on the spot and released; Record tracking link, detailed registration early warning reason and processing result, is included in operation and maintenance log; Optimization feedback stage, regularly summarizes low risk data, analyzes high frequency abnormality cause, promotes equipment upgrade and algorithm optimization, reduces system misjudgment, balances check precision and passing efficiency.

[0044] According to the embodiment of the application, the matching abnormal type further comprises: If the vehicle appearance feature information and the axle number and the vehicle length do not match, the matching abnormal type is a type matching abnormality; If the theoretical fee amount and the preset fee average value threshold do not match, the matching abnormal type is a rate abnormality; If the shortest path fee and the billing amount do not match, the matching abnormal type is a path abnormality; If the weighing record data and the axle number and the preset mass limit value do not match, the matching abnormal type is a weighing abnormality; If the vehicle identification result information and the license plate do not match, the matching abnormal type is a license plate consistency abnormality.

[0045] It should be noted that when the vehicle appearance feature information does not match the registered number of axles and vehicle length, it is determined that the type matching is abnormal; for example, a vehicle registered as a three-axle truck actually appears as a two-axle truck, or the measured length deviates from the registered length by more than a standard range, which belongs to this type of abnormality, and there may be a false report of the vehicle model; if the theoretical fee amount does not match the preset fee average threshold, a rate anomaly is formed; the preset fee average threshold is calculated based on the average fee of the same type of vehicle and the same path, and if the theoretical fee of a vehicle is significantly higher or lower than the threshold (such as exceeding ± 20%), it may indicate that there is an error in the rate calculation or a suspicion of manual adjustment of the fee; when the shortest path fee does not match the actual billing amount, it is a path anomaly; the shortest path fee calculated by the system according to the entrance and exit is the reference fee for normal travel, and if the actual billing amount deviates greatly from this, it may mean that the vehicle has behaviors such as taking a detour to evade fees, changing cards to tamper with the path, etc.; if the weighing record data does not match the preset mass limit corresponding to the registered number of axles, it is a weighing anomaly; different number of axles of vehicles have a clear upper limit of load, such as a two-axle truck with a preset mass limit of 18 tons, and if the weighing record shows 25 tons, which exceeds the limit, it is determined as an overload type weighing anomaly, and vice versa, if it is far below the reasonable load and has no valid reason, it may also be a suspicion of fee evasion; when the vehicle identification result information does not match the registered license plate, it is determined that the license plate consistency is abnormal. For example, the license plate identified from the snapshot image is "ABC123", but the registered license plate is "DEF456", or there is a significant difference in the letters and numbers of the license plate, which may involve illegal behaviors such as license plate replacement.

[0046] The application discloses a high-speed ETC vehicle fee evasion detection method and system based on big data fusion, which obtains vehicle registration information, real-time travel record information and monitoring information of a preset vehicle, performs corresponding matching processing on the real-time travel record information and the monitoring information and the vehicle registration information, obtains a matching result, acquires historical fee evasion record data, determines a real-time suspicion level of the preset vehicle in combination with the matching result, and takes corresponding processing measures according to the real-time suspicion level, so that the high-speed ETC vehicle fee evasion detection based on big data fusion is realized.

[0047] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only illustrative, for example, the division of the units is only a logical function division, and actual implementation can have another division mode, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed components can be through some interface, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0048] The units described above as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; they can be located in one place or distributed to multiple network units; and some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0049] In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in the form of hardware or in the form of hardware plus software functional units.

[0050] Those of ordinary skill in the art can understand that all or part of the steps of the above method embodiments can be completed by relevant hardware instructed by programs, and the foregoing programs can be stored in readable storage media, and when the programs are executed, steps including the above method embodiments are executed; and the foregoing storage media includes mobile storage devices, read-only memories (ROMs), random access memories (RAMs), magnetic discs or optical discs, and various media that can store program codes.

[0051] Alternatively, the integrated units of the present application, if implemented in the form of software functional modules and sold or used as independent products, can also be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present application can be embodied in the form of software products, which are stored in a storage medium and include a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present application. The foregoing storage medium includes mobile storage devices, ROMs, RAMs, magnetic discs or optical discs, and various media that can store program codes.

Claims

1. A high-speed ETC vehicle evasion detection method based on big data fusion is characterized by: The following steps are involved: Obtain vehicle registration information, real-time traffic record information, and monitoring information of preset vehicles; According to the real-time traffic record information and monitoring information, a corresponding matching process is performed with the vehicle registration information to obtain a matching result; Obtaining historical toll evasion record data and determining the real-time suspicion level of the preset vehicle in combination with the matching results; Take corresponding handling measures according to the real-time suspicion level.

2. The high-speed ETC vehicle evasion detection method based on big data fusion according to claim 1 is characterized in that: The acquisition of vehicle registration information, real-time traffic record information, and monitoring information of a preset vehicle includes: Obtain vehicle registration information, real-time traffic record information, and monitoring information of preset vehicles; The vehicle registration information includes license plate, vehicle model, number of axles, vehicle length and vehicle height; The real-time traffic record information includes the entry and exit points, the passage time, the billing amount, the weighing record data and the route information; The monitoring information includes vehicle captured images and vehicle captured videos.

3. The high-speed ETC vehicle evasion detection method based on big data fusion according to claim 2 is characterized in that: The matching process is performed on the real-time traffic record information and the monitoring information with the vehicle registration information to obtain a matching result, including: Extracting vehicle recognition result information and vehicle appearance feature information based on the captured vehicle image and the captured vehicle video; Calculate the shortest path fee based on the entry and exit points; Calculate theoretical toll amount based on travel time and route information; According to the vehicle identification result information, vehicle appearance feature information, shortest path fee, theoretical fee amount and weighing record data, a corresponding comparison process is performed with the vehicle registration information and the billing amount to obtain a matching result; The matching result includes the matching exception type and the matching exception quantity; The matching anomaly types include type matching anomaly, rate anomaly, route anomaly, weighing anomaly and license plate consistency anomaly.

4. The high-speed ETC vehicle evasion detection method based on big data fusion according to claim 3 is characterized in that: The obtaining of historical toll evasion record data and determining the real-time suspicion level of the preset vehicle in combination with the matching result includes: Obtaining historical fare evasion record data of the preset vehicle, including the number of historical fare evasions and the historical fare evasion suspicion level; The real-time suspicion level is obtained by processing the historical evasion times and the historical evasion suspicion level in combination with the number of matching anomalies through a preset evasion suspicion assessment model; The real-time suspicion level includes a high risk level, a medium risk level, and a low risk level.

5. The high-speed ETC vehicle evasion detection method based on big data fusion according to claim 4 is characterized in that: The taking of corresponding measures according to the real-time suspicion level includes: If the real-time suspicion level is high risk, appropriate measures will be taken, including on-site interception and control, evidence collection and verification, and accountability; If the real-time suspicion level is medium risk, appropriate measures are taken, including lane verification, information confirmation, and graded processing; If the real-time suspicion level is a low-risk level, appropriate handling measures will be taken, including rapid verification, record tracking, and optimized feedback.

6. The high-speed ETC vehicle evasion detection method based on big data fusion according to claim 3 is characterized in that: The matching exception type also includes: If the vehicle appearance feature information does not match the number of axles and vehicle length, the matching exception type is a type matching exception; If the theoretical fee amount does not match the preset fee average threshold, the matching anomaly type is rate anomaly; If the shortest path cost does not match the billing amount, the matching exception type is path exception; If the weighing record data does not match the number of axes and the preset mass limit, the matching exception type is a weighing exception; If the vehicle recognition result information does not match the license plate, the matching exception type is a license plate consistency exception.

7. The high-speed ETC vehicle evasion detection system based on big data fusion is characterized by: The system includes: a memory and a processor, wherein the memory includes a program of a high-speed ETC vehicle evasion detection method based on big data fusion, and when the program of the high-speed ETC vehicle evasion detection method based on big data fusion is executed by the processor, the following steps are implemented: Obtain vehicle registration information, real-time traffic record information, and monitoring information of preset vehicles; According to the real-time traffic record information and monitoring information, a corresponding matching process is performed with the vehicle registration information to obtain a matching result; Obtaining historical toll evasion record data and determining the real-time suspicion level of the preset vehicle in combination with the matching results; Take corresponding handling measures according to the real-time suspicion level.

8. The high-speed ETC vehicle evasion detection system based on big data fusion according to claim 7 is characterized in that: The acquisition of vehicle registration information, real-time traffic record information, and monitoring information of a preset vehicle includes: Obtain vehicle registration information, real-time traffic record information, and monitoring information of preset vehicles; The vehicle registration information includes license plate, vehicle model, number of axles, vehicle length and vehicle height; The real-time traffic record information includes the entry and exit points, the passage time, the billing amount, the weighing record data and the route information; The monitoring information includes vehicle captured images and vehicle captured videos.

9. The high-speed ETC vehicle evasion detection system based on big data fusion according to claim 8 is characterized in that: The matching process is performed on the real-time traffic record information and the monitoring information with the vehicle registration information to obtain a matching result, including: Extracting vehicle recognition result information and vehicle appearance feature information based on the captured vehicle image and the captured vehicle video; Calculate the shortest path fee based on the entry and exit points; Calculate theoretical toll amount based on travel time and route information; According to the vehicle identification result information, vehicle appearance feature information, shortest path fee, theoretical fee amount and weighing record data, a corresponding comparison process is performed with the vehicle registration information and the billing amount to obtain a matching result; The matching result includes the matching exception type and the matching exception quantity; The matching anomaly types include type matching anomaly, rate anomaly, route anomaly, weighing anomaly and license plate consistency anomaly.

10. The high-speed ETC vehicle evasion detection system based on big data fusion according to claim 9 is characterized in that: The obtaining of historical toll evasion record data and determining the real-time suspicion level of the preset vehicle in combination with the matching result includes: Obtaining historical fare evasion record data of the preset vehicle, including the number of historical fare evasions and the historical fare evasion suspicion level; The real-time suspicion level is obtained by processing the historical evasion times and the historical evasion suspicion level in combination with the number of matching anomalies through a preset evasion suspicion assessment model; The real-time suspicion level includes a high risk level, a medium risk level, and a low risk level.

Images