High-speed efc vehicle fee evasion detection method and system based on big data fusion

Abstract

The application provides a high-speed ETC vehicle fee evasion detection method and system based on big data fusion. The method comprises the following steps: acquiring vehicle registration information, real-time passing record information and monitoring information of a preset vehicle; performing corresponding matching processing on the vehicle registration information according to the real-time passing record information and the monitoring information, obtaining a matching result; acquiring historical fee evasion record data; combining the matching result to determine a real-time suspicion level of the preset vehicle; and taking corresponding processing measures according to the real-time suspicion level, so as to realize the high-speed ETC vehicle fee evasion detection technology based on big data fusion.

Description

Technical Field

[0001] This application relates to the field of vehicle toll evasion detection technology, and more specifically, to a method and system for detecting high-speed ETC vehicle toll evasion based on big data fusion. Background Technology

[0002] In the field of highway toll management, toll evasion by ETC vehicles not only causes economic losses but also disrupts normal traffic order. Currently, traditional toll verification methods rely heavily on manual comparison, which is inefficient and has a high rate of missed or incorrect judgments. For example, manual verification is difficult to integrate multi-dimensional data in real time, resulting in a lag in the identification of toll evasion.

[0003] Meanwhile, the existing system does not make sufficient use of the historical toll evasion records of ETC vehicles and cannot dynamically assess the level of suspicion by combining current traffic data. It can only trace back after the toll evasion has occurred, making it difficult to achieve early warning and in-process intervention. In addition, the severity of different toll evasion behaviors varies greatly, and the traditional handling method lacks a graded response mechanism, which can easily lead to excessive intervention in normal traffic or inadequate handling of serious toll evasion behaviors, affecting management efficiency and user experience.

[0004] Effective technical solutions are urgently needed to address the above problems. Summary of the Invention

[0005] The purpose of this application is to provide a method and system for detecting toll evasion by high-speed ETC vehicles based on big data fusion. This method can obtain vehicle registration information, real-time traffic record information, and monitoring information of a preset vehicle. Based on the real-time traffic record information and monitoring information, the method performs corresponding matching processing with the vehicle registration information to obtain matching results. It can also obtain historical toll evasion record data, determine the real-time suspicion level of the preset vehicle based on the matching results, and take corresponding processing measures according to the real-time suspicion level. This method realizes the technology of detecting toll evasion by high-speed ETC vehicles based on big data fusion.

[0006] This application also provides a method for detecting toll evasion by high-speed ETC vehicles based on big data fusion, including the following steps:

[0007] Obtain vehicle registration information, real-time traffic records, and monitoring information for preset vehicles;

[0008] Based on the real-time traffic record information and monitoring information, a matching process is performed with the vehicle registration information to obtain a matching result;

[0009] Obtain historical toll evasion records and combine them with the matching results to determine the real-time suspicion level of the preset vehicle;

[0010] Appropriate measures will be taken based on the real-time suspicion level.

[0011] Optionally, in the high-speed ETC vehicle toll evasion detection method based on big data fusion described in this application, the step of obtaining the vehicle registration information, real-time passage record information, and monitoring information of the preset vehicle includes:

[0012] Obtain vehicle registration information, real-time traffic records, and monitoring information for preset vehicles;

[0013] The vehicle registration information includes license plate number, vehicle type, number of axles, vehicle length, and vehicle height;

[0014] The real-time passage record information includes entrance and exit information, passage time, toll amount, weighing record data, and route information;

[0015] The monitoring information includes vehicle images and vehicle videos.

[0016] Optionally, in the high-speed ETC vehicle toll evasion detection method based on big data fusion described in this application, the step of performing a corresponding matching process between the real-time traffic record information and monitoring information and the vehicle registration information to obtain a matching result includes:

[0017] Vehicle identification results and vehicle appearance feature information are extracted from the captured vehicle images and videos.

[0018] Calculate the shortest path cost based on the entrance and exit points;

[0019] Calculate the theoretical cost based on travel time and route information;

[0020] Based on the vehicle identification result information, vehicle appearance feature information, shortest path cost, theoretical cost amount and weighing record data, a corresponding comparison is performed with the vehicle registration information and billing amount to obtain a matching result;

[0021] The matching results include the type of matched anomaly and the number of matched anomalies;

[0022] The types of matching anomalies include type matching anomalies, rate anomalies, path anomalies, weighing anomalies, and license plate consistency anomalies.

[0023] Optionally, in the high-speed ETC vehicle toll evasion detection method based on big data fusion described in this application, the step of acquiring historical toll evasion record data and determining the real-time suspicion level of the preset vehicle in combination with the matching results includes:

[0024] Obtain the historical toll evasion record data of the preset vehicle, including the number of times the vehicle evaded tolls and the level of suspicion of evading tolls.

[0025] Based on the historical number of fare evasions and the historical fare evasion suspicion level, combined with the number of matched anomalies, the real-time suspicion level is obtained by processing the data through a preset fare evasion suspicion assessment model.

[0026] The real-time suspicion levels include high-risk, medium-risk, and low-risk levels.

[0027] Optionally, in the high-speed ETC vehicle toll evasion detection method based on big data fusion described in this application, the step of taking corresponding processing measures according to the real-time suspicion level includes:

[0028] If the real-time suspicion level is high-risk, corresponding measures will be taken, including on-site interception and control, evidence collection and verification, and accountability.

[0029] If the real-time suspicion level is medium risk, corresponding measures will be taken, including lane verification, information confirmation, and tiered processing.

[0030] If the real-time suspicion level is low-risk, corresponding measures will be taken, including rapid verification, record tracking, and optimized feedback.

[0031] Optionally, in the high-speed ETC vehicle toll evasion detection method based on big data fusion described in this application, the matching anomaly type further includes:

[0032] If the vehicle appearance feature information does not match the number of axles and the vehicle length, then the matching anomaly type is a type matching anomaly.

[0033] If the theoretical cost amount does not match the preset average cost threshold, the matching anomaly type is a rate anomaly.

[0034] If the shortest path cost does not match the billing amount, the matching anomaly type is path anomaly.

[0035] If the weighing record data does not match the number of shafts or the preset mass limit, then the matching anomaly type is a weighing anomaly.

[0036] If the vehicle identification result information does not match the license plate, the matching anomaly type is license plate consistency anomaly.

[0037] Secondly, this application provides a high-speed ETC vehicle toll evasion detection system based on big data fusion. The system includes a memory and a processor. The memory includes a program for a high-speed ETC vehicle toll evasion detection method based on big data fusion. When the processor executes the program for the high-speed ETC vehicle toll evasion detection method based on big data fusion, it performs the following steps:

[0038] Obtain vehicle registration information, real-time traffic records, and monitoring information for preset vehicles;

[0039] Based on the real-time traffic record information and monitoring information, a matching process is performed with the vehicle registration information to obtain a matching result;

[0040] Obtain historical toll evasion records and combine them with the matching results to determine the real-time suspicion level of the preset vehicle;

[0041] Appropriate measures will be taken based on the real-time suspicion level.

[0042] Optionally, in the high-speed ETC vehicle toll evasion detection system based on big data fusion described in this application, the acquisition of vehicle registration information, real-time passage record information, and monitoring information of the preset vehicle includes:

[0043] Obtain vehicle registration information, real-time traffic records, and monitoring information for preset vehicles;

[0044] The vehicle registration information includes license plate number, vehicle type, number of axles, vehicle length, and vehicle height;

[0045] The real-time passage record information includes entrance and exit information, passage time, toll amount, weighing record data, and route information;

[0046] The monitoring information includes vehicle images and vehicle videos.

[0047] Optionally, in the high-speed ETC vehicle toll evasion detection system based on big data fusion described in this application, the step of matching the real-time traffic record information and monitoring information with the vehicle registration information to obtain a matching result includes:

[0048] Vehicle identification results and vehicle appearance feature information are extracted from the captured vehicle images and videos.

[0049] Calculate the shortest path cost based on the entrance and exit points;

[0050] Calculate the theoretical cost based on travel time and route information;

[0051] Based on the vehicle identification result information, vehicle appearance feature information, shortest path cost, theoretical cost amount and weighing record data, a corresponding comparison is performed with the vehicle registration information and billing amount to obtain a matching result;

[0052] The matching results include the type of matched anomaly and the number of matched anomalies;

[0053] The types of matching anomalies include type matching anomalies, rate anomalies, path anomalies, weighing anomalies, and license plate consistency anomalies.

[0054] Optionally, in the high-speed ETC vehicle toll evasion detection system based on big data fusion described in this application, the step of acquiring historical toll evasion record data and determining the real-time suspicion level of the preset vehicle in combination with the matching results includes:

[0055] Obtain the historical toll evasion record data of the preset vehicle, including the number of times the vehicle evaded tolls and the level of suspicion of evading tolls.

[0056] Based on the historical number of fare evasions and the historical fare evasion suspicion level, combined with the number of matched anomalies, the real-time suspicion level is obtained by processing the data through a preset fare evasion suspicion assessment model.

[0057] The real-time suspicion levels include high-risk, medium-risk, and low-risk levels.

[0058] As can be seen from the above, the high-speed ETC vehicle toll evasion detection method and system based on big data fusion provided in this application obtains the vehicle registration information, real-time passage record information and monitoring information of a preset vehicle, performs corresponding matching processing with the vehicle registration information based on the real-time passage record information and monitoring information to obtain the matching result, obtains historical toll evasion record data, determines the real-time suspicion level of the preset vehicle based on the matching result, and takes corresponding processing measures according to the real-time suspicion level, thereby realizing the technology of high-speed ETC vehicle toll evasion detection based on big data fusion.

[0059] Other features and advantages of this application will be set forth in the following description and will be apparent in part from the description or may be learned by practicing embodiments of this application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings. Attached Figure Description

[0060] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0061] Figure 1 A flowchart of a high-speed ETC vehicle toll evasion detection method based on big data fusion provided in this application embodiment;

[0062] Figure 2 A flowchart illustrating the matching results of the high-speed ETC vehicle toll evasion detection method based on big data fusion provided in this application embodiment;

[0063] Figure 3 A flowchart illustrating the determination of the real-time suspicion level of a preset vehicle in the high-speed ETC vehicle toll evasion detection method based on big data fusion provided in this application embodiment;

[0064] Figure 4 This is a flowchart illustrating the corresponding processing measures taken in the high-speed ETC vehicle toll evasion detection method based on big data fusion provided in the embodiments of this application. Detailed Implementation

[0065] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0066] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, the terms "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0067] Please refer to Figure 1 , Figure 1 This is a flowchart of a high-speed ETC vehicle toll evasion detection method based on big data fusion according to some embodiments of this application. This high-speed ETC vehicle toll evasion detection method based on big data fusion is used in terminal devices, such as computers and mobile terminals. The high-speed ETC vehicle toll evasion detection method based on big data fusion includes the following steps:

[0068] S11. Obtain vehicle registration information, real-time traffic record information, and monitoring information of the preset vehicle;

[0069] S12. Based on the real-time traffic record information and monitoring information, perform a corresponding matching process with the vehicle registration information to obtain a matching result;

[0070] S13. Obtain historical toll evasion record data and determine the real-time suspicion level of the preset vehicle based on the matching results;

[0071] S14. Take appropriate measures based on the real-time suspicion level.

[0072] It should be noted that highway tolls are calculated based on vehicle type. Normally, when a vehicle exits the highway network, the system collects the toll based on the entrance and gantry toll information stored in the toll record, allowing passage one vehicle at a time. However, driven by economic interests, a few drivers try various methods to evade tolls, disrupting the normal toll collection order of the toll management department to varying degrees. To reduce toll evasion by ETC-equipped vehicles, the system first obtains pre-set vehicle registration information, including license plate, vehicle type, number of axles, vehicle length, and vehicle height, and real-time passage records, including entrance and exit points, passage time, and toll calculation. The system collects toll amount, weighing record data, route information, and monitoring information, including vehicle capture images and videos. Based on real-time traffic records and monitoring information, it performs matching processing with vehicle registration information to obtain matching results, including the type and number of matching anomalies. It also acquires historical toll evasion records, including the number of historical toll evasions and the historical toll evasion suspicion level. Combined with the matching results, it determines the preset real-time suspicion level of vehicles, including high-risk, medium-risk, and low-risk levels. Appropriate processing measures are taken based on the real-time suspicion level, thereby realizing a technology for detecting toll evasion on highway ETC vehicles based on big data fusion.

[0073] According to an embodiment of the present invention, obtaining the vehicle registration information, real-time traffic record information, and monitoring information of a preset vehicle includes:

[0074] Obtain vehicle registration information, real-time traffic records, and monitoring information for preset vehicles;

[0075] The vehicle registration information includes license plate number, vehicle type, number of axles, vehicle length, and vehicle height;

[0076] The real-time passage record information includes entrance and exit information, passage time, toll amount, weighing record data, and route information;

[0077] The monitoring information includes vehicle images and vehicle videos.

[0078] It should be noted that, to accurately identify vehicle status, three types of key information need to be collected comprehensively. First, there is the pre-registered vehicle information, including the license plate number (a core identifier) ​​and basic parameters such as vehicle type (e.g., sedan, truck), number of axles (related to load standards), and vehicle length and height (used to determine if it exceeds limits). This information is crucial for vehicle identity verification. Second, there is real-time traffic record information, including the vehicle's entrance and exit locations, clearly indicating the travel route; travel time reflects travel duration and efficiency; toll amount is a direct reference for fee settlement; weighing records can monitor for overloading; and detailed route information allows tracing the entire travel trajectory, providing support for fee calculation and anomaly detection. Finally, there is monitoring information, including vehicle snapshots that clearly show the vehicle's appearance, license plate details, and loading status; and vehicle video recordings that dynamically record the vehicle's driving status, lane-changing behavior, etc.

[0079] Please refer to Figure 2 , Figure 2 This is a flowchart illustrating the process of obtaining matching results in a high-speed ETC vehicle toll evasion detection method based on big data fusion, as described in some embodiments of this application. According to an embodiment of the present invention, the step of performing a corresponding matching process between the real-time traffic record information and monitoring information and the vehicle registration information to obtain a matching result includes:

[0080] S21. Extract vehicle recognition result information and vehicle appearance feature information based on the vehicle captured images and vehicle captured videos;

[0081] S22. Calculate the shortest path cost based on the entrance and exit;

[0082] S23. Calculate the theoretical cost based on travel time and route information;

[0083] S24. Based on the vehicle identification result information, vehicle appearance feature information, shortest path cost, theoretical cost amount and weighing record data, perform corresponding comparison processing with the vehicle registration information and billing amount to obtain a matching result.

[0084] S25. The matching result includes the type of matching exception and the number of matching exceptions;

[0085] S26. The matching anomaly types include type matching anomaly, rate anomaly, path anomaly, weighing anomaly, and license plate consistency anomaly.

[0086] It should be noted that, based on vehicle capture images and videos, image recognition technology is used to extract vehicle identification information (such as automatically recognized license plate numbers and vehicle model codes) and appearance feature information (including details such as length, height, and number of tires), providing a visual basis for subsequent verification. Combining the location data of the vehicle's entrance and exit, the system automatically calculates the shortest path cost between the two locations as a cost benchmark. Simultaneously, based on travel time and actual path information, combined with the road segment toll standards, the theoretical cost is calculated and compared with the actual billed amount. The extracted vehicle identification results, appearance features, shortest path cost, theoretical cost, and weighing record data are compared one by one with the vehicle registration information (license plate, vehicle model, number of axles, vehicle length, and vehicle height) and the actual billed amount: anomalies such as type matching anomalies, rate anomalies, path anomalies, weighing anomalies, and license plate consistency anomalies are identified. The final matching results include not only the specific anomaly types mentioned above but also the number of each type of anomaly, providing clear data support for accurately locating vehicle traffic problems.

[0087] Please refer to Figure 3 , Figure 3 This is a flowchart illustrating the process of determining the real-time suspicion level of a preset vehicle using a high-speed ETC vehicle toll evasion detection method based on big data fusion, as described in some embodiments of this application. According to embodiments of the present invention, the step of obtaining historical toll evasion record data and determining the real-time suspicion level of the preset vehicle based on the matching results includes:

[0088] S31. Obtain the historical toll evasion record data of the preset vehicle, including the number of historical toll evasions and the historical toll evasion suspicion level;

[0089] S32. Based on the historical number of fare evasions and the historical fare evasion suspicion level, combined with the number of matched anomalies, the real-time suspicion level is obtained by processing the data through a preset fare evasion suspicion assessment model.

[0090] S33. The real-time suspicion level includes high-risk level, medium-risk level and low-risk level.

[0091] It should be noted that, to accurately assess the real-time suspicion of vehicle toll evasion, the historical toll evasion records of the preset vehicle must first be retrieved. This includes the specific number of times toll evasion occurred and the suspicion level corresponding to each instance (e.g., records previously classified as high, medium, or low risk). Then, this historical data is combined with the currently acquired number of matching anomalies and input into a preset toll evasion suspicion assessment model. This model achieves quantitative assessment through a multi-level algorithm: First, a basic weight is assigned to the number of historical toll evasions, with higher weights for more occurrences. Second, a weighted correction is applied based on the historical toll evasion suspicion level, with higher correction coefficients for high-risk historical records than for medium and low risks. Finally, the influence of the current number of matching anomalies is added; the more anomalies, the more significant the boost to the real-time assessment result. Ultimately, the model outputs a real-time suspicion level based on preset thresholds: if the overall score far exceeds the threshold and there are multiple high-risk historical records and a large number of current anomalies, it is classified as high-risk; if the score is in the medium range and both historical records and current anomalies are limited, it is classified as medium-risk; if the score is low, there are no historical toll evasion records, and the number of current anomalies is limited, it is classified as low-risk. Specific level classifications are handled according to actual circumstances and needs.

[0092] Please refer to Figure 4 , Figure 4 This is a flowchart illustrating the corresponding processing measures taken in some embodiments of the high-speed ETC vehicle toll evasion detection method based on big data fusion in this application. According to embodiments of the present invention, taking corresponding processing measures based on the real-time suspicion level includes:

[0093] S41. If the real-time suspicion level is high-risk, corresponding measures shall be taken, including on-site interception and control, evidence collection and verification, and accountability.

[0094] S42. If the real-time suspicion level is medium risk level, take corresponding measures, including lane verification, information confirmation and graded processing.

[0095] S43. If the real-time suspicion level is low risk, take corresponding measures, including rapid verification, recording and tracking, and optimized feedback.

[0096] It should be noted that when a vehicle is determined to be at high risk, an emergency response mechanism must be activated immediately. During the on-site interception and control phase, the barrier in the target lane should be quickly closed, and a warning should be issued via broadcast. If the vehicle attempts to evade the checkpoint, security and traffic police forces should be coordinated to intercept it and prevent accidents. Simultaneously, the vehicle should be guided to a dedicated verification area, and the driver and passengers should be prevented from leaving without authorization. During the evidence collection and verification phase, the vehicle's historical toll collection and toll evasion records should be comprehensively retrieved, and photos of the vehicle's exterior, license plate, and relevant documents should be taken. The driver's statement should be recorded in detail to ensure a complete chain of evidence. During the handling and accountability phase, the vehicle should be ordered to pay the outstanding fees and penalties. Those who refuse to cooperate will be subject to penalties or criminal investigation by relevant departments, and the vehicle information will be added to the toll evasion blacklist. For vehicles at medium risk, precise verification is the core. During lane verification, the toll collector will inquire about any abnormalities on-site and guide the vehicle to the abnormal processing lane. To avoid congesting the main access road; during the information confirmation phase, vehicle registration information is compared with the actual status, ETC account and weighing data are checked, and if necessary, cross-segment information is verified in conjunction with the backend, and tiered processing is carried out according to the verification results: minor violations are given a verbal warning and advised to leave; those with payment discrepancies are ordered to pay; those suspected of high risk cannot be ruled out are temporarily detained for observation, and if the risk escalates, they are transferred to the high-risk handling process; for low-risk levels, the focus is on efficient passage and system optimization; rapid verification is completed through non-contact methods, with toll collectors simply confirming vehicle information, and abnormalities caused by system problems are corrected on the spot before release; in the record and tracking phase, the cause of the warning and the handling result are recorded in detail and included in the operation and maintenance log; in the optimization feedback phase, low-risk data is regularly summarized, the causes of high-frequency anomalies are analyzed, and equipment upgrades and algorithm optimizations are promoted to reduce system misjudgments and balance verification accuracy and passage efficiency.

[0097] According to an embodiment of the present invention, the matching anomaly type further includes:

[0098] If the vehicle appearance feature information does not match the number of axles and the vehicle length, then the matching anomaly type is a type matching anomaly.

[0099] If the theoretical cost amount does not match the preset average cost threshold, the matching anomaly type is a rate anomaly.

[0100] If the shortest path cost does not match the billing amount, the matching anomaly type is path anomaly.

[0101] If the weighing record data does not match the number of shafts or the preset mass limit, then the matching anomaly type is a weighing anomaly.

[0102] If the vehicle identification result information does not match the license plate, the matching anomaly type is license plate consistency anomaly.

[0103] It should be noted that when the vehicle's appearance features do not match the registered number of axles or vehicle length, it is considered a type mismatch. For example, a vehicle registered as a three-axle truck may appear to have only two axles, or the measured length may deviate from the registered length by more than the standard range. These are all considered anomalies and may indicate misrepresentation of the vehicle model. If the theoretical cost does not match the preset average cost threshold, it constitutes a rate anomaly. The preset average cost threshold is calculated based on the average cost of similar vehicles traveling the same route. If a vehicle's theoretical cost is significantly higher or lower than this threshold (e.g., exceeding ±20%), it suggests a possible error in rate calculation or manipulation of costs. When the shortest path cost differs from the actual billed amount... When there is a mismatch, it indicates a path anomaly. The shortest path cost calculated by the system based on the entrance and exit is the baseline cost for normal passage. If the actual billing amount deviates significantly from this, it may mean that the vehicle has taken a detour to evade tolls, tampered with the card, or altered the route. If the weighing record data does not match the preset weight limit corresponding to the number of registered axles, it is considered a weighing anomaly. Vehicles with different numbers of axles have clear load limits. For example, the preset weight limit for a two-axle truck is 18 tons. If the weighing record shows 25 tons, exceeding the limit is considered an overload-related weighing anomaly. Conversely, if the load is far below the reasonable weight without a legitimate reason, it may also indicate toll evasion. When the vehicle identification result information does not match the registered license plate, it is considered a license plate consistency anomaly. For example, if the license plate identified by the captured image is "ABC123" but the registered license plate is "DEF456", or if there are significant differences in the letters and numbers of the license plate, it may involve violations such as using a fake license plate or changing the license plate.

[0104] Secondly, the present invention also discloses a high-speed ETC vehicle toll evasion detection system based on big data fusion, including a memory and a processor. The memory includes a high-speed ETC vehicle toll evasion detection method program based on big data fusion. When the processor executes the high-speed ETC vehicle toll evasion detection method program based on big data fusion, it performs the following steps:

[0105] Obtain vehicle registration information, real-time traffic records, and monitoring information for preset vehicles;

[0106] Based on the real-time traffic record information and monitoring information, a matching process is performed with the vehicle registration information to obtain a matching result;

[0107] Obtain historical toll evasion records and combine them with the matching results to determine the real-time suspicion level of the preset vehicle;

[0108] Appropriate measures will be taken based on the real-time suspicion level.

[0109] It should be noted that highway tolls are calculated based on vehicle type. Normally, when a vehicle exits the highway network, the system collects the toll based on the entrance and gantry toll information stored in the toll record, allowing passage one vehicle at a time. However, driven by economic interests, a few drivers try various methods to evade tolls, disrupting the normal toll collection order of the toll management department to varying degrees. To reduce toll evasion by ETC-equipped vehicles, the system first obtains pre-set vehicle registration information, including license plate, vehicle type, number of axles, vehicle length, and vehicle height, and real-time passage records, including entrance and exit points, passage time, and toll calculation. The system collects toll amount, weighing record data, route information, and monitoring information, including vehicle capture images and videos. Based on real-time traffic records and monitoring information, it performs matching processing with vehicle registration information to obtain matching results, including the type and number of matching anomalies. It also acquires historical toll evasion records, including the number of historical toll evasions and the historical toll evasion suspicion level. Combined with the matching results, it determines the preset real-time suspicion level of vehicles, including high-risk, medium-risk, and low-risk levels. Appropriate processing measures are taken based on the real-time suspicion level, thereby realizing a technology for detecting toll evasion on highway ETC vehicles based on big data fusion.

[0110] According to an embodiment of the present invention, obtaining the vehicle registration information, real-time traffic record information, and monitoring information of a preset vehicle includes:

[0111] Obtain vehicle registration information, real-time traffic records, and monitoring information for preset vehicles;

[0112] The vehicle registration information includes license plate number, vehicle type, number of axles, vehicle length, and vehicle height;

[0113] The real-time passage record information includes entrance and exit information, passage time, toll amount, weighing record data, and route information;

[0114] The monitoring information includes vehicle images and vehicle videos.

[0115] It should be noted that, to accurately identify vehicle status, three types of key information need to be collected comprehensively. First, there is the pre-registered vehicle information, including the license plate number (a core identifier) ​​and basic parameters such as vehicle type (e.g., sedan, truck), number of axles (related to load standards), and vehicle length and height (used to determine if it exceeds limits). This information is crucial for vehicle identity verification. Second, there is real-time traffic record information, including the vehicle's entrance and exit locations, clearly indicating the travel route; travel time reflects travel duration and efficiency; toll amount is a direct reference for fee settlement; weighing records can monitor for overloading; and detailed route information allows tracing the entire travel trajectory, providing support for fee calculation and anomaly detection. Finally, there is monitoring information, including vehicle snapshots that clearly show the vehicle's appearance, license plate details, and loading status; and vehicle video recordings that dynamically record the vehicle's driving status, lane-changing behavior, etc.

[0116] According to an embodiment of the present invention, the step of performing a corresponding matching process between the real-time traffic record information and the monitoring information and the vehicle registration information to obtain a matching result includes:

[0117] Vehicle identification results and vehicle appearance feature information are extracted from the captured vehicle images and videos.

[0118] Calculate the shortest path cost based on the entrance and exit points;

[0119] Calculate the theoretical cost based on travel time and route information;

[0120] Based on the vehicle identification result information, vehicle appearance feature information, shortest path cost, theoretical cost amount and weighing record data, a corresponding comparison is performed with the vehicle registration information and billing amount to obtain a matching result;

[0121] The matching results include the type of matched anomaly and the number of matched anomalies;

[0122] The types of matching anomalies include type matching anomalies, rate anomalies, path anomalies, weighing anomalies, and license plate consistency anomalies.

[0123] It should be noted that, based on vehicle capture images and videos, image recognition technology is used to extract vehicle identification information (such as automatically recognized license plate numbers and vehicle model codes) and appearance feature information (including details such as length, height, and number of tires), providing a visual basis for subsequent verification. Combining the location data of the vehicle's entrance and exit, the system automatically calculates the shortest path cost between the two locations as a cost benchmark. Simultaneously, based on travel time and actual path information, combined with the road segment toll standards, the theoretical cost is calculated and compared with the actual billed amount. The extracted vehicle identification results, appearance features, shortest path cost, theoretical cost, and weighing record data are compared one by one with the vehicle registration information (license plate, vehicle model, number of axles, vehicle length, and vehicle height) and the actual billed amount: anomalies such as type matching anomalies, rate anomalies, path anomalies, weighing anomalies, and license plate consistency anomalies are identified. The final matching results include not only the specific anomaly types mentioned above but also the number of each type of anomaly, providing clear data support for accurately locating vehicle traffic problems.

[0124] According to an embodiment of the present invention, the step of obtaining historical toll evasion record data and determining the real-time suspicion level of the preset vehicle in combination with the matching result includes:

[0125] Obtain the historical toll evasion record data of the preset vehicle, including the number of times the vehicle evaded tolls and the level of suspicion of evading tolls.

[0126] Based on the historical number of fare evasions and the historical fare evasion suspicion level, combined with the number of matched anomalies, the real-time suspicion level is obtained by processing the data through a preset fare evasion suspicion assessment model.

[0127] The real-time suspicion levels include high-risk, medium-risk, and low-risk levels.

[0128] It should be noted that, to accurately assess the real-time suspicion of vehicle toll evasion, the historical toll evasion records of the preset vehicle must first be retrieved. This includes the specific number of times toll evasion occurred and the suspicion level corresponding to each instance (e.g., records previously classified as high, medium, or low risk). Then, this historical data is combined with the currently acquired number of matching anomalies and input into a preset toll evasion suspicion assessment model. This model achieves quantitative assessment through a multi-level algorithm: First, a basic weight is assigned to the number of historical toll evasions, with higher weights for more occurrences. Second, a weighted correction is applied based on the historical toll evasion suspicion level, with higher correction coefficients for high-risk historical records than for medium and low risks. Finally, the influence of the current number of matching anomalies is added; the more anomalies, the more significant the boost to the real-time assessment result. Ultimately, the model outputs a real-time suspicion level based on preset thresholds: if the overall score far exceeds the threshold and there are multiple high-risk historical records and a large number of current anomalies, it is classified as high-risk; if the score is in the medium range and both historical records and current anomalies are limited, it is classified as medium-risk; if the score is low, there are no historical toll evasion records, and the number of current anomalies is limited, it is classified as low-risk. Specific level classifications are handled according to actual circumstances and needs.

[0129] According to an embodiment of the present invention, taking corresponding processing measures based on the real-time suspicion level includes:

[0130] If the real-time suspicion level is high-risk, corresponding measures will be taken, including on-site interception and control, evidence collection and verification, and accountability.

[0131] If the real-time suspicion level is medium risk, corresponding measures will be taken, including lane verification, information confirmation, and tiered processing.

[0132] If the real-time suspicion level is low-risk, corresponding measures will be taken, including rapid verification, record tracking, and optimized feedback.

[0133] It should be noted that when a vehicle is determined to be at high risk, an emergency response mechanism must be activated immediately. During the on-site interception and control phase, the barrier in the target lane should be quickly closed, and a warning should be issued via broadcast. If the vehicle attempts to evade the checkpoint, security and traffic police forces should be coordinated to intercept it and prevent accidents. Simultaneously, the vehicle should be guided to a dedicated verification area, and the driver and passengers should be prevented from leaving without authorization. During the evidence collection and verification phase, the vehicle's historical toll collection and toll evasion records should be comprehensively retrieved, and photos of the vehicle's exterior, license plate, and relevant documents should be taken. The driver's statement should be recorded in detail to ensure a complete chain of evidence. During the handling and accountability phase, the vehicle should be ordered to pay the outstanding fees and penalties. Those who refuse to cooperate will be subject to penalties or criminal investigation by relevant departments, and the vehicle information will be added to the toll evasion blacklist. For vehicles at medium risk, precise verification is the core. During lane verification, the toll collector will inquire about any abnormalities on-site and guide the vehicle to the abnormal processing lane. To avoid congesting the main access road; during the information confirmation phase, vehicle registration information is compared with the actual status, ETC account and weighing data are checked, and if necessary, cross-segment information is verified in conjunction with the backend, and tiered processing is carried out according to the verification results: minor violations are given a verbal warning and advised to leave; those with payment discrepancies are ordered to pay; those suspected of high risk cannot be ruled out are temporarily detained for observation, and if the risk escalates, they are transferred to the high-risk handling process; for low-risk levels, the focus is on efficient passage and system optimization; rapid verification is completed through non-contact methods, with toll collectors simply confirming vehicle information, and abnormalities caused by system problems are corrected on the spot before release; in the record and tracking phase, the cause of the warning and the handling result are recorded in detail and included in the operation and maintenance log; in the optimization feedback phase, low-risk data is regularly summarized, the causes of high-frequency anomalies are analyzed, and equipment upgrades and algorithm optimizations are promoted to reduce system misjudgments and balance verification accuracy and passage efficiency.

[0134] According to an embodiment of the present invention, the matching anomaly type further includes:

[0135] If the vehicle appearance feature information does not match the number of axles and the vehicle length, then the matching anomaly type is a type matching anomaly.

[0136] If the theoretical cost amount does not match the preset average cost threshold, the matching anomaly type is a rate anomaly.

[0137] If the shortest path cost does not match the billing amount, the matching anomaly type is path anomaly.

[0138] If the weighing record data does not match the number of shafts or the preset mass limit, then the matching anomaly type is a weighing anomaly.

[0139] If the vehicle identification result information does not match the license plate, the matching anomaly type is license plate consistency anomaly.

[0140] It should be noted that when the vehicle's appearance features do not match the registered number of axles or vehicle length, it is considered a type mismatch. For example, a vehicle registered as a three-axle truck may appear to have only two axles, or the measured length may deviate from the registered length by more than the standard range. These are all considered anomalies and may indicate misrepresentation of the vehicle model. If the theoretical cost does not match the preset average cost threshold, it constitutes a rate anomaly. The preset average cost threshold is calculated based on the average cost of similar vehicles traveling the same route. If a vehicle's theoretical cost is significantly higher or lower than this threshold (e.g., exceeding ±20%), it suggests a possible error in rate calculation or manipulation of costs. When the shortest path cost differs from the actual billed amount... When there is a mismatch, it indicates a path anomaly. The shortest path cost calculated by the system based on the entrance and exit is the baseline cost for normal passage. If the actual billing amount deviates significantly from this, it may mean that the vehicle has taken a detour to evade tolls, tampered with the card, or altered the route. If the weighing record data does not match the preset weight limit corresponding to the number of registered axles, it is considered a weighing anomaly. Vehicles with different numbers of axles have clear load limits. For example, the preset weight limit for a two-axle truck is 18 tons. If the weighing record shows 25 tons, exceeding the limit is considered an overload-related weighing anomaly. Conversely, if the load is far below the reasonable weight without a legitimate reason, it may also indicate toll evasion. When the vehicle identification result information does not match the registered license plate, it is considered a license plate consistency anomaly. For example, if the license plate identified by the captured image is "ABC123" but the registered license plate is "DEF456", or if there are significant differences in the letters and numbers of the license plate, it may involve violations such as using a fake license plate or changing the license plate.

[0141] The present invention discloses a method and system for detecting toll evasion of high-speed ETC vehicles based on big data fusion. This method acquires vehicle registration information, real-time traffic record information, and monitoring information of a preset vehicle. Based on the real-time traffic record information and monitoring information, it performs corresponding matching processing with the vehicle registration information to obtain matching results. It also acquires historical toll evasion record data and determines the real-time suspicion level of the preset vehicle based on the matching results. Appropriate processing measures are then taken according to the real-time suspicion level, thereby realizing the technology of detecting toll evasion of high-speed ETC vehicles based on big data fusion.

[0142] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0143] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0144] In addition, in the various embodiments of the present invention, each functional unit 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 hardware or in the form of hardware plus software functional units.

[0145] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0146] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

Claims

1. A method for detecting toll evasion by high-speed ETC vehicles based on big data fusion, characterized in that, Includes the following steps: Obtain vehicle registration information, real-time traffic records, and monitoring information for preset vehicles; Based on the real-time traffic record information and monitoring information, a matching process is performed with the vehicle registration information to obtain a matching result; Obtain historical toll evasion records and combine them with the matching results to determine the real-time suspicion level of the preset vehicle; Take appropriate measures based on the real-time suspicion level. The acquisition of vehicle registration information, real-time traffic record information, and monitoring information of the preset vehicle includes: Obtain vehicle registration information, real-time traffic records, and monitoring information for preset vehicles; The vehicle registration information includes license plate number, vehicle type, number of axles, vehicle length, and vehicle height; The real-time passage record information includes entrance and exit information, passage time, toll amount, weighing record data, and route information; The monitoring information includes vehicle captured images and vehicle captured videos; The step of matching the real-time traffic record information and monitoring information with the vehicle registration information to obtain a matching result includes: Vehicle identification results and vehicle appearance feature information are extracted from the captured vehicle images and videos. Calculate the shortest path cost based on the entrance and exit points; Calculate the theoretical cost based on travel time and route information; Based on the vehicle identification result information, vehicle appearance feature information, shortest path cost, theoretical cost amount and weighing record data, a corresponding comparison is performed with the vehicle registration information and billing amount to obtain a matching result; The matching results include the type of matched anomaly and the number of matched anomalies; The types of matching anomalies include type matching anomalies, rate anomalies, path anomalies, weighing anomalies, and license plate consistency anomalies. The matching exception types also include: If the vehicle appearance feature information does not match the number of axles and the vehicle length, then the matching anomaly type is a type matching anomaly. If the theoretical cost amount does not match the preset average cost threshold, the matching anomaly type is a rate anomaly. If the shortest path cost does not match the billing amount, the matching anomaly type is path anomaly. If the weighing record data does not match the number of shafts or the preset mass limit, then the matching anomaly type is a weighing anomaly. If the vehicle identification result information does not match the license plate, the matching anomaly type is license plate consistency anomaly.

2. The method for detecting toll evasion by high-speed ETC vehicles based on big data fusion according to claim 1, characterized in that, The step of obtaining historical toll evasion record data and determining the real-time suspicion level of the preset vehicle based on the matching results includes: Obtain the historical toll evasion record data of the preset vehicle, including the number of times the vehicle evaded tolls and the level of suspicion of evading tolls. Based on the historical number of fare evasions and the historical fare evasion suspicion level, combined with the number of matched anomalies, the real-time suspicion level is obtained by processing the data through a preset fare evasion suspicion assessment model. The real-time suspicion levels include high-risk, medium-risk, and low-risk levels.

3. The method for detecting toll evasion by high-speed ETC vehicles based on big data fusion according to claim 2, characterized in that, The corresponding processing measures based on the real-time suspicion level include: If the real-time suspicion level is high-risk, corresponding measures will be taken, including initiating on-site interception and control, evidence collection and verification, and handling and accountability. If the real-time suspicion level is medium risk, corresponding measures will be taken, including lane verification, information confirmation, and tiered processing. If the real-time suspicion level is low-risk, corresponding measures will be taken, including rapid verification, record tracking, and optimized feedback.

4. A high-speed ETC vehicle toll evasion detection system based on big data fusion, characterized in that, The system includes a memory and a processor. The memory contains a program for a high-speed ETC vehicle toll evasion detection method based on big data fusion. When the processor executes the program for the high-speed ETC vehicle toll evasion detection method based on big data fusion, it performs the following steps: Obtain vehicle registration information, real-time traffic records, and monitoring information for preset vehicles; Based on the real-time traffic record information and monitoring information, a matching process is performed with the vehicle registration information to obtain a matching result; Obtain historical toll evasion records and combine them with the matching results to determine the real-time suspicion level of the preset vehicle; Take appropriate measures based on the real-time suspicion level. The acquisition of vehicle registration information, real-time traffic record information, and monitoring information of the preset vehicle includes: Obtain vehicle registration information, real-time traffic records, and monitoring information for preset vehicles; The vehicle registration information includes license plate number, vehicle type, number of axles, vehicle length, and vehicle height; The real-time passage record information includes entrance and exit information, passage time, toll amount, weighing record data, and route information; The monitoring information includes vehicle captured images and vehicle captured videos; The step of matching the real-time traffic record information and monitoring information with the vehicle registration information to obtain a matching result includes: Vehicle identification results and vehicle appearance feature information are extracted from the captured vehicle images and videos. Calculate the shortest path cost based on the entrance and exit points; Calculate the theoretical cost based on travel time and route information; Based on the vehicle identification result information, vehicle appearance feature information, shortest path cost, theoretical cost amount and weighing record data, a corresponding comparison is performed with the vehicle registration information and billing amount to obtain a matching result; The matching results include the type of matched anomaly and the number of matched anomalies; The types of matching anomalies include type matching anomalies, rate anomalies, path anomalies, weighing anomalies, and license plate consistency anomalies. The matching exception types also include: If the vehicle appearance feature information does not match the number of axles and the vehicle length, then the matching anomaly type is a type matching anomaly. If the theoretical cost amount does not match the preset average cost threshold, the matching anomaly type is a rate anomaly. If the shortest path cost does not match the billing amount, the matching anomaly type is path anomaly. If the weighing record data does not match the number of shafts or the preset mass limit, then the matching anomaly type is a weighing anomaly. If the vehicle identification result information does not match the license plate, the matching anomaly type is license plate consistency anomaly.

5. The high-speed ETC vehicle toll evasion detection system based on big data fusion according to claim 4, characterized in that, The step of obtaining historical toll evasion record data and determining the real-time suspicion level of the preset vehicle based on the matching results includes: Obtain the historical toll evasion record data of the preset vehicle, including the number of times the vehicle evaded tolls and the level of suspicion of evading tolls. Based on the historical number of fare evasions and the historical fare evasion suspicion level, combined with the number of matched anomalies, the real-time suspicion level is obtained by processing the data through a preset fare evasion suspicion assessment model. The real-time suspicion levels include high-risk, medium-risk, and low-risk levels.

Images