A vehicle fake license plate behavior identification method and device based on traffic record analysis

Abstract

The application provides a vehicle fake license plate behavior identification method and device based on passage record analysis, which comprises the following steps: obtaining target passage record data of a target vehicle with a target license plate number; sorting all passage events in the target passage record data according to time; calculating the time interval and / or position deviation of two continuous passage events; and determining whether the target vehicle with the target license plate number has a fake license plate suspicion according to the time interval and / or position deviation of the two continuous passage events.

Description

Technical Field

[0001] This application relates to the field of smart parking management technology, and more specifically, to a method and device for identifying vehicle license plate clone behavior based on traffic record analysis. Background Technology

[0002] Parking management systems generally rely on simple license plate recognition for vehicle management. The system only verifies whether the recognized license plate number is on the valid list; if so, it automatically allows passage. This method is virtually ineffective at identifying "cloned vehicles" (i.e., unauthorized vehicles using authorized license plate numbers). The lack of technology to analyze and monitor cloned vehicles makes it difficult to detect evasion of parking fees, resulting in significant economic losses for vehicle owners and parking lot operators. Summary of the Invention

[0003] In view of this, the purpose of this application is to provide a method and device for identifying vehicle license plate cloning behavior based on traffic record analysis. By determining whether a target vehicle with a target license plate number is suspected of cloning by the time interval and / or positional deviation of two consecutive traffic events, the method improves the ability to identify cloning vehicles, can better detect cloning toll evasion behavior, and thus reduces the economic losses of vehicle owners and parking lot operators.

[0004] In a first aspect, embodiments of this application provide a method for identifying vehicle license plate cloning behavior based on traffic record analysis, the method comprising: Obtain the target passage record data of the target vehicle with the target license plate number, and sort all passage events in the target passage record data according to time; Calculate the time interval and / or positional deviation between two consecutive passage events, and determine whether the target vehicle with the target license plate number is suspected of using a counterfeit license plate based on the time interval and / or positional deviation between the two consecutive passage events.

[0005] In one possible implementation, the step of calculating the time interval and / or positional deviation between two consecutive passage events, and determining whether the target vehicle with the target license plate number is suspected of using a counterfeit license plate based on the time interval and / or positional deviation between the two consecutive passage events, includes: Calculate the time interval between two consecutive passage events of the same type, and compare the time interval between the two consecutive passage events of the same type with a preset first time threshold; wherein, the two consecutive passage events of the same type represent two consecutive entry events or two consecutive exit events. If the time interval between two consecutive passage events of the same type is less than the first time threshold, then it is determined that the target vehicle with the target license plate number is suspected of using a cloned license plate.

[0006] In one possible implementation, the step of calculating the time interval and / or positional deviation between two consecutive passage events, and determining whether the target vehicle with the target license plate number is suspected of using a counterfeit license plate based on the time interval and / or positional deviation between the two consecutive passage events, includes: Calculate the time interval and positional deviation between two consecutive passage events; If the position deviation within the time interval is greater than a preset position deviation threshold, then the target vehicle with the target license plate number is suspected of using a counterfeit license plate.

[0007] In one possible implementation, the method further includes: Obtain the static features of the target vehicle with the target license plate number, and further determine whether the target vehicle with the target license plate number is using a cloned license plate based on the static features; And / or, The dynamic behavior characteristics of the target vehicle with the target license plate number are obtained, and based on the dynamic behavior characteristics, it is further determined whether the target vehicle with the target license plate number is engaging in license plate cloning.

[0008] In one possible implementation, obtaining the static features of the target vehicle with the target license plate number, and further determining whether the target vehicle with the target license plate number is using a cloned license plate based on the static features, includes: The static characteristics of the target vehicle with the target license plate number are retrieved based on the parking lot management database; The static features are compared with the vehicle static feature database of the target vehicle with the target license plate number in multiple dimensions to further determine whether the target vehicle with the target license plate number is engaging in license plate cloning. If it is determined that the target vehicle with the target license plate number is using a cloned license plate, then the two consecutive passage events constitute one abnormal passage record.

[0009] In one possible implementation, obtaining the dynamic behavior characteristics of the target vehicle with the target license plate number, and further determining whether the target vehicle with the target license plate number is using a cloned license plate based on the dynamic behavior characteristics, includes: The dynamic behavioral characteristics of the target vehicle with the target license plate number are obtained; wherein, the dynamic behavioral characteristics include at least long-term behavioral patterns. A baseline for the vehicle traffic model of the target vehicle with the target license plate number is established based on a preset machine learning model and the dynamic behavioral features. If the target vehicle with the target license plate number exhibits behavior that contradicts the baseline of the vehicle traffic model, it is further determined that the target vehicle with the target license plate number is engaging in license plate cloning, and the two consecutive traffic events constitute one abnormal traffic record.

[0010] In one possible implementation, the method further includes: For the target license plate number, count the number of abnormal passages of the target license plate number within a preset period; wherein, the number of abnormal passages represents the number of adjacent event pairs that satisfy the condition that the time interval between two consecutive passage events is less than a preset time threshold; The number of abnormal passages of the target license plate number is compared with a preset risk threshold. If the number of abnormal passages exceeds the preset risk threshold, the target license plate number is determined to be a high-risk suspected clone.

[0011] In one possible implementation, the method further includes: When the time interval between two consecutive passage events is not less than the time threshold, it is determined that the target vehicle with the target license plate number is not suspected of using a fake license plate.

[0012] Secondly, embodiments of this application also provide a vehicle license plate clone behavior recognition device based on traffic record analysis, the device comprising: The calculation module is used to obtain the target passage record data of the target vehicle with the target license plate number, and sort all passage events in the target passage record data according to time. The first determining module is used to calculate the time interval and / or position deviation between two consecutive passage events, and to determine, based on the time interval and / or position deviation between the two consecutive passage events, that the target vehicle with the target license plate number is suspected of using a counterfeit license plate.

[0013] In one possible implementation, the determining module is specifically used for: Calculate the time interval between two consecutive passage events of the same type, and compare the time interval between the two consecutive passage events of the same type with a preset first time threshold; wherein, the two consecutive passage events of the same type represent two consecutive entry events or two consecutive exit events. If the time interval between two consecutive passage events of the same type is less than the first time threshold, then it is determined that the target vehicle with the target license plate number is suspected of using a cloned license plate.

[0014] In one possible implementation, the determining module is specifically used for: Calculate the time interval and positional deviation between two consecutive passage events; If the position deviation within the time interval is greater than a preset position deviation threshold, then the target vehicle with the target license plate number is suspected of using a counterfeit license plate.

[0015] In one possible implementation, the device further includes: The first judgment module is used to obtain the static features of the target vehicle with the target license plate number, and further judge whether the target vehicle with the target license plate number is using a cloned license plate based on the static features; and / or, The second judgment module is used to obtain the dynamic behavior characteristics of the target vehicle with the target license plate number, and further judge whether the target vehicle with the target license plate number has engaged in license plate counterfeiting based on the dynamic behavior characteristics.

[0016] In one possible implementation, the first module is specifically used for: The static characteristics of the target vehicle with the target license plate number are retrieved based on the parking lot management database; The static features are compared with the vehicle static feature database of the target vehicle with the target license plate number in multiple dimensions to further determine whether the target vehicle with the target license plate number is engaging in license plate cloning. If it is determined that the target vehicle with the target license plate number is using a cloned license plate, then the two consecutive passage events constitute one abnormal passage record.

[0017] In one possible implementation, the second determining module is specifically used for: The dynamic behavioral characteristics of the target vehicle with the target license plate number are obtained; wherein, the dynamic behavioral characteristics include at least long-term behavioral patterns. A baseline for the vehicle traffic model of the target vehicle with the target license plate number is established based on a preset machine learning model and the dynamic behavioral features. If the target vehicle with the target license plate number exhibits behavior that contradicts the baseline of the vehicle traffic model, it is further determined that the target vehicle with the target license plate number is engaging in license plate cloning, and the two consecutive traffic events constitute one abnormal traffic record.

[0018] In one possible implementation, the device further includes: The statistics module is used to count the number of abnormal passages of the target license plate number within a preset period; wherein, the number of abnormal passages represents the number of adjacent event pairs that meet the condition that the time interval between two consecutive passage events is less than a preset time threshold. The third judgment module is used to compare the number of abnormal passages of the target license plate number with a preset risk threshold, and when the number of abnormal passages is greater than the preset risk threshold, the target license plate number is judged to be a high-risk suspected clone.

[0019] Thirdly, embodiments of this application provide an electronic device, including: a processor, a storage medium, and a bus. The storage medium stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the storage medium via the bus, and the processor executes the machine-readable instructions to perform the steps of the vehicle license plate clone behavior recognition method based on traffic record analysis as described in any of the first aspects.

[0020] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the vehicle license plate clone behavior identification method based on traffic record analysis as described in any one of the first aspects.

[0021] This application provides a method and apparatus for identifying vehicle license plate cloning based on traffic record analysis. The method acquires traffic record data for a target vehicle with a target license plate number, sorts all traffic events in the target traffic record data by time, and calculates the time interval and / or positional deviation between two consecutive traffic events. Based on the time interval and / or positional deviation between two consecutive traffic events, it determines whether the target vehicle with the target license plate number is suspected of cloning. This application improves the ability to identify cloned vehicles by determining whether a target vehicle with a target license plate number is suspected of cloning through the time interval and / or positional deviation between two consecutive traffic events, thus better detecting cloning toll evasion and reducing economic losses for vehicle owners and parking lot operators.

[0022] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0023] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments 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.

[0024] Figure 1 This is a flowchart of a vehicle license plate clone behavior identification method based on traffic record analysis provided in the embodiments of this application; Figure 2 This is a schematic diagram of the overall process for identifying vehicle license plate cloning. Figure 3 This is a schematic diagram of the vehicle license plate clone behavior recognition device based on traffic record analysis provided in the embodiments of this application; Figure 4This is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the accompanying drawings in this application are for illustrative and descriptive purposes only and are not intended to limit the scope of protection of this application. Furthermore, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of this application. It should be understood that the operations in the flowcharts may not be implemented in sequence, and steps without logical contextual relationships may be reversed or implemented simultaneously. In addition, those skilled in the art, guided by the content of this application, may add one or more other operations to the flowcharts, or remove one or more operations from the flowcharts.

[0026] Furthermore, the described embodiments are merely some, not all, of the embodiments of this application. The components of the embodiments of this application described and illustrated herein can typically 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 to illustrate selected embodiments of the 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.

[0027] It should be noted that the term "comprising" will be used in the embodiments of this application to indicate the presence of the features declared thereafter, but does not exclude the addition of other features.

[0028] Parking management systems typically rely on simple license plate recognition for vehicle access. The system simply verifies if the identified license plate number is on a valid list; if so, it automatically allows entry. This approach is virtually ineffective against cloned vehicles (i.e., unauthorized vehicles using authorized license plate numbers). The lack of technology to analyze and monitor cloned vehicles makes it difficult to detect toll evasion, resulting in significant economic losses for vehicle owners and parking lot operators.

[0029] To address this issue, this application provides a method and apparatus for identifying vehicle license plate cloning behavior based on traffic record analysis. By analyzing the time interval and / or positional deviation between two consecutive traffic events, the method determines whether a target vehicle with a target license plate number is suspected of cloning. This improves the ability to identify cloning vehicles and better detects fare evasion through cloning, thereby reducing economic losses for vehicle owners and parking lot operators.

[0030] Figure 1This is a flowchart of a vehicle license plate clone behavior identification method based on traffic record analysis provided in an embodiment of this application. Figure 1 As shown in the embodiments of this application, the vehicle license plate clone behavior identification method based on traffic record analysis may specifically include: S101. Obtain the target vehicle's traffic record data for the target license plate number, and sort all traffic events in the target traffic record data by time.

[0031] S102. Calculate the time interval and / or position deviation between two consecutive passage events, and determine whether the target vehicle with the target license plate number is suspected of using a cloned license plate based on the time interval and / or position deviation between the two consecutive passage events.

[0032] The above-mentioned vehicle license plate clone behavior identification method based on traffic record analysis determines whether the target vehicle with the target license plate number is suspected of being cloned by the time interval and / or position deviation of two consecutive traffic events. This improves the ability to identify cloned vehicles and can better detect fare evasion by cloning license plates, thereby reducing the economic losses of vehicle owners and parking lot operators.

[0033] The exemplary steps described above in the embodiments of this application are illustrated below with specific examples: S101, obtain the target passage record data of the target vehicle with the target license plate number, and sort all passage events in the target passage record data according to time.

[0034] In this embodiment, the passage events include exit or entry events. All passage events in the target vehicle's target passage record data are sorted by time. For example, ... Figure 2 As shown. For example, sorting all passage events for a license plate number in chronological order.

[0035] Optionally, when obtaining the target passage record data of the target vehicle with the target license plate number, all passage record data of all vehicles within a preset period are collected based on the parking lot management database, and the passage record data is preprocessed to clean up invalid record data; the target passage record data of the target vehicle with the target license plate number is obtained based on the cleaned passage record data.

[0036] The preset period is a preset data collection period, such as 30 days, which means collecting all passage record data within the most recent 30 days; the passage record data includes at least the license plate number, entry time, exit time, and lane name; invalid record data includes, for example, records that are missing the license plate number or the lane name; the vehicles are member vehicles of the parking lot, including monthly pass vehicles, annual pass vehicles, etc., and this application uses monthly pass vehicles as an example for description.

[0037] S102, calculate the time interval and / or position deviation between two consecutive passage events, and determine whether the target vehicle with the target license plate number is suspected of using a cloned license plate based on the time interval and / or position deviation between the two consecutive passage events.

[0038] It should be noted that the calculation involves the time interval and / or positional deviation between two consecutive passage events of the same type. These two consecutive passage events can be of the same type, such as two consecutive entry events or two consecutive exit events, i.e., consecutive exit or consecutive entry passage events.

[0039] In this embodiment, two consecutive (adjacent) passage events represent two consecutive passage events among all passage events for which the target vehicle enjoys access rights at all parking lots (for vehicles with multiple access cards / wallets applicable to multiple parking lots). Here, the time interval is the time interval between the two consecutive passage events, and the position deviation is the deviation between the positions of the target vehicle in the two consecutive passage events. Taking the time interval as an example, the time interval (represented by ΔT in this application) is the time difference between the later passage event and the earlier passage event. The time interval between two consecutive passage events is calculated (ΔT = later passage event time - earlier passage event time). Based on the time interval between the two consecutive passage events, it is determined whether the target vehicle with the target license plate number is suspected of using a cloned license plate, and further judgment is made on whether there is a cloned license plate behavior. For example, based on ΔT, it is determined whether the target vehicle with the target license plate number is suspected of using a cloned license plate, such as... Figure 2 As shown, further verification is required at this point.

[0040] In some implementations, the time interval between two consecutive passage events of the same type is calculated, and this time interval is compared with a preset first time threshold. If the time interval between two consecutive passage events of the same type is less than the first time threshold, then the target vehicle with the target license plate number is suspected of using a cloned license plate. Here, two consecutive passage events of the same type represent two consecutive entry events or two consecutive exit events. For example, taking the time interval ΔT between two consecutive passage events of the same type as an example, the first time threshold is a preset time threshold (represented by T in this application), such as 3 hours. If ΔT < T, then the target vehicle with the target license plate number is suspected of using a cloned license plate.

[0041] In some implementations, the time interval and positional deviation between two consecutive passage events are calculated. If the positional deviation within the time interval is greater than a preset positional deviation threshold, the target vehicle with the target license plate is suspected of using a cloned license plate. For example, calculating the time interval ΔT and positional deviation between two consecutive passage events, if the positional deviation within ΔT is greater than the positional deviation threshold, the target vehicle with the target license plate is suspected of using a cloned license plate. Optionally, when the time interval between two consecutive passage events of the same type is not less than a first time threshold, the target vehicle with the target license plate is determined not to be suspected of using a cloned license plate. In this case, it indicates that the target license plate number poses no risk.

[0042] The vehicle license plate cloning identification method based on traffic record analysis provided in this application obtains the target traffic record data of a target vehicle with a target license plate number. All traffic events in the target traffic record data are sorted by time, and the time interval and / or positional deviation between two consecutive traffic events are calculated. Based on the time interval and / or positional deviation between two consecutive traffic events, it is determined whether the target vehicle with the target license plate number is suspected of using a cloned license plate. This method improves the ability to identify cloned vehicles by determining whether a target vehicle with a target license plate number is suspected of using a cloned license plate through the time interval and / or positional deviation between two consecutive traffic events, thus better detecting fare evasion through cloned license plates and reducing economic losses for vehicle owners and parking lot operators.

[0043] It should be noted that when it is determined that the target vehicle with the target license plate number is suspected of being a cloned vehicle, the vehicle's traffic data is then analyzed using both static feature analysis and dynamic behavior analysis to determine whether the traffic event involves a cloned vehicle and whether it should be recorded as an abnormal traffic record.

[0044] Furthermore, the static features of the target vehicle with the target license plate number are obtained, and based on the static features, it is further determined whether the target vehicle with the target license plate number is engaging in license plate cloning.

[0045] In this embodiment, static features refer to vehicle-related information of the target license plate number. Static features include at least one of the following: physical uniqueness features, electronic tags on the vehicle's windshield, and detailed images of key parts of the vehicle body. For example, static features may include the vehicle's physical uniqueness features (such as the vehicle identification number (VIN, read via geomagnetic induction or ETC device)), the electronic tag (OBU) on the vehicle's windshield, and detailed images of key parts of the vehicle body (such as scratches on the front bumper, wheel style, roof rack installation position, etc.). Based on the static features, it is further determined whether the target vehicle with the target license plate number has engaged in license plate cloning, that is, whether the target vehicle with the target license plate number can pass the verification of the static features. If the verification passes, it indicates that there is no license plate cloning behavior; if the verification fails, it indicates that license plate cloning behavior has occurred. For example, such as... Figure 2as shown

[0046] In some embodiments, static features of the target vehicle with the target license plate number are retrieved based on the parking lot management database; the static features are compared with the vehicle static feature library filed by the user of the target vehicle with the target license plate number in multiple dimensions to further determine whether there is a license plate cloning behavior for the target vehicle with the target license plate number; when it is determined that there is a license plate cloning behavior for the target vehicle with the target license plate number, it is determined that two consecutive passing events constitute 1 abnormal passing record. Among them, the vehicle static feature library includes high-definition vehicle photos and supplementary information submitted during the user's first registration, etc. For example, high-definition vehicle photos and supplementary information submitted by the user of the monthly pass vehicle during the first registration of the monthly pass.

[0047] Specifically, when it is determined that the time interval between two consecutive passing events is less than the preset time threshold, i.e., ΔT < T, and there is a suspicion of license plate cloning, at this time, the static features of the target vehicle with the target license plate number are retrieved and compared with the vehicle feature library filed by the vehicle user in multiple dimensions to identify abnormal phenomena through physical features. For example, the vehicle identification number of the cloned license plate vehicle is inconsistent with the record, or there are significant differences in the body details compared with the recorded photos, etc., to further verify whether there is an abnormal passing record of license plate cloning behavior, and when it is determined that there is a license plate cloning behavior for the target vehicle with the target license plate number, a license plate cloning behavior mark is triggered, and it is determined that these two consecutive passing events constitute 1 abnormal passing record. Further, dynamic behavior features of the target vehicle with the target license plate number are obtained, and based on the dynamic behavior features, it is further determined whether there is a license plate cloning behavior for the target vehicle with the target license plate number.

[0048] In the embodiments of the present application, the dynamic behavior features include at least one of long-term behavior patterns (such as common entry time periods (e.g., 8:00 - 9:00 on weekdays), average parking duration (e.g., 8 hours), preferred parking spaces (fixed parking space numbers), common vehicle owner identities (such as the MAC address of the device bound to the vehicle owner APP)), and based on the dynamic behavior features, it is determined whether there is a license plate cloning behavior for the target vehicle with the target license plate number, that is, whether there is a license plate cloning behavior is verified through the dynamic behavior features. For example, as Figure 2 shown. Here, the single suspicion of license plate cloning and 1 license plate cloning behavior of the target vehicle are regarded as one abnormal passing record, and multiple abnormal passing records are regarded as high risks; or, the single suspicion of license plate cloning of the target vehicle is regarded as one abnormal passing record, and multiple abnormal passing records plus one or more license plate cloning behaviors are regarded as high risks.

[0049] It should be noted that both static and dynamic behavioral features can be used to determine whether a target vehicle with a specific license plate is using a cloned plate. That is, if the static feature verification fails, dynamic behavioral features can be used to further determine whether the vehicle is using a cloned plate. Alternatively, either static or dynamic behavioral features can be used to determine whether a target vehicle is using a cloned plate.

[0050] In some implementations, the dynamic behavior characteristics of the target vehicle with the target license plate number are obtained; a vehicle traffic model baseline for the target vehicle with the target license plate number is established based on a preset machine learning model and the dynamic behavior characteristics; when the target vehicle with the target license plate number exhibits behavior that contradicts the vehicle traffic model baseline, it is further determined that the target vehicle with the target license plate number is engaging in license plate cloning behavior, and it is determined that two consecutive traffic events constitute one abnormal traffic record.

[0051] Among them, dynamic behavioral characteristics include at least long-term behavioral patterns, which include at least one of the following: frequently used entry time, average parking duration, preferred parking space, and frequently used car owner identity.

[0052] Specifically, if static features cannot determine that a vehicle with a target license plate number is engaging in license plate cloning, then dynamic behavioral features are used for further analysis: Long-term behavioral patterns of the vehicle are acquired (such as frequently used entry times (e.g., weekdays 8:00-9:00), average parking duration (e.g., 8 hours), preferred parking spaces (fixed parking space number), and frequently used owner identities (e.g., MAC address of the device used to log in to the owner's app)). These dynamic behavioral features are then combined with machine learning models (such as the Isolation Forest algorithm and time series clustering) to establish a corresponding vehicle traffic model baseline. When a vehicle with that license plate number exhibits behavior contradicting the baseline (e.g., entering outside of registered hours, abnormally shortened parking duration (e.g., only staying for 10 minutes), or frequently changing parking spaces), a license plate cloning behavior flag is triggered, and these two adjacent traffic events are determined to constitute one abnormal traffic record.

[0053] Furthermore, for the target license plate number, the number of abnormal passages of the target license plate number with cloning behavior within a preset period is counted; the number of abnormal passages of the target license plate number is compared with a preset risk threshold, and when the number of abnormal passages exceeds the preset risk threshold, the target license plate number is judged to be a high-risk cloning suspect.

[0054] Among them, the abnormal passage count represents the number of adjacent event pairs that satisfy the condition that the time interval between two consecutive passage events is less than a preset time threshold.

[0055] Specifically, count the total number of abnormal passing records with license plate cloning behavior triggered by the target license plate number within a preset period (e.g., 30 days), that is, accumulate the number of all adjacent event pairs that satisfy ΔT < T. When the total number of abnormal passing records of the target license plate number is greater than the risk threshold (N, e.g., 10), it is determined that the license plate number is a high-risk license plate cloning suspect. For example, as Figure 2 shown.

[0056] Furthermore, generate a high-risk license plate cloning suspect list based on the target license plate number determined to be a high-risk license plate cloning suspect; notify the high-risk license plate cloning suspect list based on a preset notification method. Among them, the high-risk license plate cloning suspect list at least includes the target license plate number, the abnormal times of the target license plate number, and the specific abnormal passing timestamps.

[0057] Specifically, generate a high-risk license plate cloning suspect list according to the target license plate number determined to be a high-risk license plate cloning suspect. The high-risk license plate cloning suspect list should contain detailed information such as the license plate number, abnormal times, and specific abnormal passing timestamps, and notify the high-risk license plate cloning suspect list to relevant personnel through a preset notification method (e.g., message push, SMS, email, or system alarm, etc.) for the management personnel to carry out subsequent manual investigations, verifications, and disposals.

[0058] Thus, based on the time series logic analysis of passing records, this application identifies cloned vehicles, and by mining and defining the core abnormal feature of "the time interval between two consecutive passing events is too short" and performing quantitative statistics and threshold judgment on it, it realizes the active, automated, and data-driven intelligent identification of license plate cloning behavior, effectively solving the malicious fare evasion behavior that cannot be discovered by traditional methods that only rely on static feature comparison.

[0059] To better describe the vehicle license plate cloning behavior identification method based on passing record analysis of this application, the following is described in combination with specific examples.

[0060] Step 1: In the data preparation stage, collect all the passing record data of the monthly pass vehicle "Beijing A12345" in July, a total of 50 records.

[0061] Step 2: After sorting these passing record data by time, determine whether there are abnormal passing records for two consecutive passing events of the same type (set the first time threshold T = 3 hours, and the risk threshold N = 5 times).

[0062] When it is determined that there is a license plate cloning risk, first, according to the static characteristics of the monthly pass vehicle "Beijing A12345", determine whether there is a license plate cloning behavior through physical characteristics. If the physical characteristics verification fails, it is directly counted as 1 abnormal passing record; When the physical feature verification passes, the dynamic behavior feature analysis continues. Analyze the long-term behavior patterns of monthly pass vehicles (such as common entry time periods (8:00 - 9:00 on weekdays), average parking duration (8 hours), preferred parking spaces (fixed parking space numbers)). When the vehicle with license plate "Beijing A12345" exhibits behaviors contradictory to the baseline (such as entering the lot during non-registered time periods, abnormal shortening of parking duration (such as only staying for 10 minutes), frequent changing of parking spaces), a suspected license plate cloning mark is triggered, and it is determined that these two consecutive events constitute 1 abnormal access record. Step 3: According to the processing process in Step 2, a total of 6 abnormal access records of "Beijing A12345" were counted in July.

[0063] Step 4: Determine that the number of abnormal access records 6 > 5 (risk threshold N), and mark the license plate "Beijing A12345" as a high-risk suspected license plate cloning object.

[0064] Step 5: Automatically generate a high-priority alarm in the management background, and send a system message and a text message to the mobile phone of the parking lot manager. For example, "Warning: The abnormal access times (6 times) of the monthly pass vehicle with license plate 'Beijing A12345' this month have exceeded the limit, and there is a major suspicion of license plate cloning. Please verify immediately!" Based on this, the parking lot manager retrieves the surveillance videos of the vehicle's multiple rapid entries and exits. After confirming the existence of a cloned license plate vehicle, corresponding measures can be taken.

[0065] Figure 3 It is a schematic structural diagram of a vehicle license plate cloning behavior recognition device based on access record analysis provided by an embodiment of the present application; as Figure 3 shown, the vehicle license plate cloning behavior recognition device 300 based on access record analysis in an embodiment of the present application may specifically include: A calculation module 301, configured to obtain the target access record data of the target vehicle with the target license plate number, and sort all access events in the target access record data according to time. A first determination module 302, configured to calculate the time interval and / or position deviation between two consecutive access events, and determine that the target vehicle with the target license plate number has a suspicion of license plate cloning according to the time interval and / or position deviation between two consecutive access events.

[0066] In a possible implementation manner, the determination module is specifically configured to: Calculate the time interval between two consecutive access events of the same type, and compare the time interval between two consecutive access events of the same type with a preset first time threshold; wherein, two consecutive access events of the same type represent two consecutive entry events or two consecutive exit events. If the time interval between two consecutive access events of the same type is less than the first time threshold, it is determined that the target vehicle with the target license plate number has a suspicion of license plate cloning.

[0067] In one possible implementation, the determining module is specifically used for: Calculate the time interval and positional deviation between two consecutive passage events; If the position deviation within the time interval is greater than the preset position deviation threshold, then the target vehicle with the target license plate number is suspected of using a cloned license plate.

[0068] In one possible implementation, the apparatus further includes: The first judgment module is used to obtain the static features of the target vehicle with the target license plate number, and further judge whether the target vehicle with the target license plate number has engaged in license plate counterfeiting based on the static features; and / or, The second judgment module is used to obtain the dynamic behavior characteristics of the target vehicle with the target license plate number, and further judge whether the target vehicle with the target license plate number has engaged in license plate cloning based on the dynamic behavior characteristics.

[0069] In one possible implementation, the first module is specifically used for: Retrieve the static features of the target vehicle based on the target license plate number from the parking lot management database; The static features of the target vehicle are compared with the static feature database of the target vehicle registered by the user of the target license plate number in multiple dimensions to further determine whether the target vehicle of the target license plate number is engaged in license plate cloning. If it is determined that the target vehicle with the target license plate number is using a cloned license plate, then two consecutive passage events constitute one abnormal passage record.

[0070] In one possible implementation, the second determination module is specifically used for: Obtain the dynamic behavioral characteristics of the target vehicle with the target license plate number; wherein, the dynamic behavioral characteristics include at least long-term behavioral patterns; A baseline for the vehicle traffic model of the target vehicle with the target license plate number is established based on a pre-defined machine learning model and dynamic behavioral features. If a target vehicle with a target license plate number exhibits behavior that contradicts the baseline of the vehicle traffic model, it is further determined that the target vehicle with the target license plate number is engaging in license plate cloning, and two consecutive traffic events are determined to constitute one abnormal traffic record.

[0071] In one possible implementation, the apparatus further includes: The statistics module is used to count the number of abnormal passes for a target license plate number within a preset period. The number of abnormal passes represents the number of adjacent event pairs that meet the condition that the time interval between two consecutive passes is less than a preset time threshold. The third judgment module is used to compare the number of abnormal passages of the target license plate number with a preset risk threshold, and when the number of abnormal passages exceeds the preset risk threshold, the target license plate number is judged to be a high-risk suspected clone.

[0072] The vehicle license plate cloning behavior identification device based on traffic record analysis provided in this application acquires the target traffic record data of a target vehicle with a target license plate number. It sorts all traffic events in the target traffic record data by time and calculates the time interval and / or positional deviation between two consecutive traffic events. Based on the time interval and / or positional deviation between two consecutive traffic events, it determines whether the target vehicle with the target license plate number is suspected of cloning. This vehicle license plate cloning behavior identification device based on traffic record analysis improves the ability to identify cloned vehicles by determining whether a target vehicle with a target license plate number is suspected of cloning through the time interval and / or positional deviation between two consecutive traffic events, thus better detecting cloning toll evasion and reducing economic losses for vehicle owners and parking lot operators.

[0073] like Figure 4 As shown in the embodiment of this application, an electronic device 400 includes a processor 401, a memory 402, and a bus. The memory 402 stores machine-readable instructions that can be executed by the processor 401. When the electronic device is running, the processor 401 communicates with the memory 402 via the bus. The processor 401 executes the machine-readable instructions to perform the steps of the vehicle license plate clone behavior recognition method based on traffic record analysis described above.

[0074] Specifically, the memory 402 and processor 401 mentioned above can be general-purpose memory and processor, without any specific limitations. When the processor 401 runs the computer program stored in the memory 402, it can execute the above-mentioned vehicle license plate clone behavior recognition method based on traffic record analysis.

[0075] Corresponding to the above-described method for identifying vehicle license plate cloning based on traffic record analysis, this application also provides a computer-readable storage medium storing a computer program. When the computer program is run by a processor, it executes the steps of the above-described method for identifying vehicle license plate cloning based on traffic record analysis.

[0076] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems and devices described above can be referred to the corresponding processes in the method embodiments, and will not be repeated here. In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection can be through some communication interfaces; the indirect coupling or communication connection of devices or modules can be electrical, mechanical, or other forms.

[0077] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0078] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0079] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer 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 steps of the deployment methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0080] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for identifying vehicle license plate clone behavior based on traffic record analysis, characterized in that, The method includes: Obtain the target passage record data of the target vehicle with the target license plate number, and sort all passage events in the target passage record data according to time; Calculate the time interval and / or positional deviation between two consecutive passage events, and determine whether the target vehicle with the target license plate number is suspected of using a counterfeit license plate based on the time interval and / or positional deviation between the two consecutive passage events.

2. The method according to claim 1, characterized in that, The calculation of the time interval and / or positional deviation between two consecutive passage events, and the determination of whether the target vehicle with the target license plate number is suspected of using a counterfeit license plate based on the time interval and / or positional deviation between the two consecutive passage events, includes: Calculate the time interval between two consecutive passage events of the same type, and compare the time interval between the two consecutive passage events of the same type with a preset first time threshold; wherein, the two consecutive passage events of the same type represent two consecutive entry events or two consecutive exit events. If the time interval between two consecutive passage events of the same type is less than the first time threshold, then it is determined that the target vehicle with the target license plate number is suspected of using a cloned license plate.

3. The method according to claim 2, characterized in that, The calculation of the time interval and / or positional deviation between two consecutive passage events, and the determination of whether the target vehicle with the target license plate number is suspected of using a counterfeit license plate based on the time interval and / or positional deviation between the two consecutive passage events, includes: Calculate the time interval and positional deviation between two consecutive passage events; If the position deviation within the time interval is greater than a preset position deviation threshold, then the target vehicle with the target license plate number is suspected of using a counterfeit license plate.

4. The method according to claim 1, characterized in that, The method further includes: Obtain the static features of the target vehicle with the target license plate number, and based on the static features, further determine whether the target vehicle with the target license plate number is using a cloned license plate; and / or, The dynamic behavior characteristics of the target vehicle with the target license plate number are obtained, and based on the dynamic behavior characteristics, it is further determined whether the target vehicle with the target license plate number is engaging in license plate cloning.

5. The method according to claim 4, characterized in that, The step of obtaining the static features of the target vehicle with the target license plate number, and further determining whether the target vehicle with the target license plate number is using a cloned license plate based on the static features, includes: The static characteristics of the target vehicle with the target license plate number are retrieved based on the parking lot management database; The static features are compared with the vehicle static feature database of the target vehicle with the target license plate number in multiple dimensions to further determine whether the target vehicle with the target license plate number is engaging in license plate cloning. If it is determined that the target vehicle with the target license plate number is using a cloned license plate, then the two consecutive passage events constitute one abnormal passage record.

6. The method according to claim 4, characterized in that, The step of obtaining the dynamic behavior characteristics of the target vehicle with the target license plate number, and further determining whether the target vehicle with the target license plate number is using a cloned license plate based on the dynamic behavior characteristics, includes: The dynamic behavioral characteristics of the target vehicle with the target license plate number are obtained; wherein, the dynamic behavioral characteristics include at least long-term behavioral patterns. A baseline for the vehicle traffic model of the target vehicle with the target license plate number is established based on a preset machine learning model and the dynamic behavioral features. If the target vehicle with the target license plate number exhibits behavior that contradicts the baseline of the vehicle traffic model, it is further determined that the target vehicle with the target license plate number is engaging in license plate cloning, and the two consecutive traffic events constitute one abnormal traffic record.

7. The method according to claim 1, characterized in that, The method further includes: For the target license plate number, count the number of abnormal passages where the target license plate number is cloned within a preset period; wherein, the number of abnormal passages represents the number of adjacent event pairs that satisfy the condition that the time interval between two consecutive passage events is less than a preset time threshold; The number of abnormal passages of the target license plate number is compared with a preset risk threshold. If the number of abnormal passages exceeds the preset risk threshold, the target license plate number is determined to be a high-risk suspected clone.

8. A vehicle license plate clone behavior recognition device based on traffic record analysis, characterized in that, The device includes: The calculation module is used to obtain the target passage record data of the target vehicle with the target license plate number, and sort all passage events in the target passage record data according to time. The first determining module is used to calculate the time interval and / or position deviation between two consecutive passage events, and to determine, based on the time interval and / or position deviation between the two consecutive passage events, that the target vehicle with the target license plate number is suspected of using a counterfeit license plate.

9. An electronic device, characterized in that, include: The device includes a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, they perform the steps of the vehicle license plate clone behavior recognition method based on traffic record analysis as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of the vehicle license plate clone behavior identification method based on traffic record analysis as described in any one of claims 1 to 7.

Images