Analysis methods, devices, electronic equipment, and media for vehicles suspected of entering but not exiting.

Abstract

This disclosure relates to a method, apparatus, electronic device, and medium for analyzing suspected vehicle entries without exits, and pertains to the field of computer technology. The method is applied to a road network divided into different road segments, where different vehicles are identified by their entry data access numbers within each segment. Within a road segment, gantry data is grouped based on the vehicle's travel time between adjacent gantries to obtain travel gantry groups, with data not shared between road segments. Then, based on the access number, target vehicles within the road segment that have entry data but lack first exit data are extracted. The last gantry data of the corresponding travel gantry group is obtained through the access number. If the target vehicle's historical travel data within the road segment is not at a critical point, the second exit data is obtained to determine if it is a predetermined travel type. If not, the target vehicle is determined to be suspected of entering without exiting. This method can construct a closed-loop traffic network and fully analyze vehicle entry and exit data within road segments, improving the accuracy of travel analysis.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and more specifically, to a method for analyzing suspected vehicle entry without exit, an analysis device for analyzing suspected vehicle entry without exit, electronic equipment, and a computer-readable medium. Background Technology

[0002] Highways utilize a large-scale, densely deployed ETC (Electronic Toll Collection) gantry system to charge vehicles based on distance traveled. However, the ETC gantry system has some monitoring loopholes in its non-stop passage mode. For example, criminals may exploit discrepancies between the actual vehicle's license plate and the license plate linked to the ETC system, follow other vehicles at exits, or switch vehicles mid-journey to create a journey trajectory that appears to enter but does not exit, thus evading highway toll payments and leading to inaccurate billing.

[0003] Currently, trip analysis is typically performed based on provincial border exit and entrance data, as well as gantry data. For example, trips with entrance data but no exit data are extracted, and trips with the last gantry data being a provincial border gantry are excluded to identify trips that may have an entrance-only problem, without needing to consider the intermediate trajectory data of the trip.

[0004] However, this scheme has high requirements for the data scope, requiring a complete and fully closed-loop transportation network. Currently, most highways are divided among different authorities, resulting in disconnected travel data that appears as isolated islands, which reduces the accuracy of analyzing vehicle travel that only enters the network but does not exit. Summary of the Invention

[0005] The purpose of this disclosure is to provide a method, apparatus, electronic device, and computer-readable medium for analyzing suspected vehicle entry-without-exit trips, which can improve the accuracy of vehicle entry-without-exit trip analysis.

[0006] According to a first aspect of this disclosure, a method for analyzing vehicles suspected of entering but not exiting is provided. This method is applied to a road network divided into at least two road segments, where different vehicles are identified by their entry data pass numbers. The method may include: grouping gantry data based on the vehicle's travel time between adjacent gantries to obtain travel gantry groups within the road segment, with data not shared between road segments; identifying target vehicles without first exit data among vehicles with entry data within the road segment based on their pass numbers; obtaining the last gantry data in the travel gantry group using the pass number corresponding to the target vehicle; if the last gantry data in the travel gantry group does not correspond to a critical point, obtaining the second exit data of the target vehicle's historical travel within the road segment, where the critical point is located at the boundary between road segments in the road network; and determining that the target vehicle is a suspected vehicle that enters but does not exit if the second exit data is not a predetermined travel type, where predetermined travel types include paper pass passage and passage without a pass medium.

[0007] Optionally, the gantry data includes gantry transaction data, and the travel gantry group includes the travel gantry transaction group. By using the passage number corresponding to the target vehicle, the last gantry data in the travel gantry group is obtained, including: by using the passage number corresponding to the target vehicle, the last gantry transaction data in the travel gantry transaction group corresponding to the target vehicle is obtained.

[0008] Optionally, the gantry data also includes gantry license plate data, and the travel gantry group also includes a travel gantry license plate group. After obtaining the last gantry transaction data in the travel gantry transaction group corresponding to the target vehicle through the passage number corresponding to the target vehicle, the data further includes: if the last gantry transaction data in the travel gantry transaction group is a non-critical point gantry transaction data, obtaining the last gantry license plate data in the travel gantry license plate group corresponding to the non-critical point gantry transaction data through the license plate information and passage number of the target vehicle.

[0009] Optionally, the gantry data also includes vehicle model data, and the travel gantry group also includes the travel gantry license plate recognition vehicle model group. After obtaining the last gantry license plate recognition data in the travel gantry license plate recognition group corresponding to the non-critical point gantry transaction data through the license plate information and passage number of the target vehicle, the process further includes: when the last gantry license plate recognition data in the travel gantry license plate recognition group is non-critical point gantry license plate recognition data, fusing the vehicle model data and gantry license plate recognition data according to the collection time to obtain gantry license plate recognition vehicle model data; grouping the gantry license plate recognition vehicle model data according to the passage time of the target vehicle between adjacent gantries to obtain the travel gantry license plate recognition vehicle model group of the target vehicle; and obtaining the last gantry license plate recognition vehicle model data in the travel gantry license plate recognition vehicle model group corresponding to the non-critical point gantry license plate recognition data through the passage number.

[0010] Optionally, the gantry data also includes roadside unit data. After obtaining the last gantry vehicle model data in the travel gantry vehicle model group corresponding to the non-critical point gantry vehicle model data through the passage number, the data includes: if the last gantry vehicle model data in the travel gantry vehicle model group is a non-critical point gantry vehicle model data, obtaining the roadside unit data through the license plate of the target vehicle.

[0011] Optionally, before grouping the gantry data according to the vehicle's travel time between adjacent gantries to obtain the travel gantry groups within the road segment, the method further includes: cleaning the gantry data and entry data of each vehicle in the road network. The cleaning includes at least one of the following: removing gantry data with illegal license plates; removing entry data from the entry data where the number of times the vehicle enters the same station within a preset entry time range is greater than a first preset number; removing entry data from the entry data where the number of times the vehicle enters the main and auxiliary stations within a preset entry time range is greater than a second preset number; removing gantry data where the vehicle's travel speed between adjacent gantries is less than the minimum travel speed; removing gantry data where the vehicle's travel speed between adjacent gantries is greater than the maximum travel speed; and using a box plot method to identify outliers in the gantry data based on the vehicle's travel speed between adjacent gantries, and removing outliers from the gantry data.

[0012] Optionally, the gantry data can be grouped according to the travel time of the vehicle between adjacent gantries to obtain the travel gantry group within the road segment, including: obtaining the historical average travel time from the first gantry to the second gantry, wherein the first gantry and the second gantry are adjacent in the direction of vehicle travel; and classifying the first gantry and the second gantry into the travel gantry group if the actual travel time of the vehicle from the first gantry to the second gantry is less than or equal to a preset multiple of the historical average travel time.

[0013] Optionally, the road segment includes service areas. After obtaining the historical average travel time from the first gantry to the second gantry, the method further includes: if the actual travel time of a vehicle from the first gantry to the second gantry is greater than a preset multiple of the historical average travel time, and neither the first gantry nor the second gantry is a service area gantry, then the pre-defined travel gantry group is determined as the grouping result, where a service area gantry refers to the gantry to which the service area belongs; if the actual travel time of a vehicle from the first gantry to the second gantry is greater than a preset multiple of the historical average travel time, and both the first gantry and the second gantry are service area gantry and travel in the same direction. In the case of a vehicle traveling from the first gantry to the second gantry, the first gantry and the second gantry are assigned to a travel gantry group. If the actual travel time from the first gantry to the second gantry is greater than a preset multiple of the historical average travel time, and both the first gantry and the second gantry are service area gantries with different travel directions, the assigned travel gantry group is determined as the grouping result.

[0014] According to a second aspect of this disclosure, an analysis device for suspected vehicle entry without exit is provided. This device is applied to a road network divided into at least two road segments. Different vehicles within each road segment are identified by their entry data pass numbers. The device may include: a gantry data grouping module, used to group gantry data based on the vehicle's travel time between adjacent gantries to obtain travel gantry groups within the road segment, where data is not shared between road segments; a target vehicle determination module, used to determine, based on the pass number, a target vehicle among vehicles with entry data within the road segment that does not have first exit data; a gantry data extraction module, used to obtain the last gantry data in the travel gantry group using the pass number corresponding to the target vehicle; a non-critical point judgment module, used to obtain the second exit data of the target vehicle's historical travel within the road segment when the last gantry data in the travel gantry group corresponds to a non-critical point, where the critical point is located at the boundary between road segments in the road network; and a travel analysis determination module, used to determine that the target vehicle is a suspected entry without exit vehicle when the second exit data is not a predetermined travel type, where predetermined travel types include paper pass passage and passage without a pass medium.

[0015] Optionally, the gantry data includes gantry transaction data, the travel gantry group includes travel gantry transaction groups, and the gantry data extraction module is specifically used to obtain the last gantry transaction data in the travel gantry transaction group corresponding to the target vehicle through the passage number corresponding to the target vehicle.

[0016] Optionally, the gantry data also includes gantry identification data, and the travel gantry group also includes a travel gantry identification group. Specifically, the gantry data extraction module is further used to obtain the last gantry identification data in the travel gantry identification group corresponding to the non-critical point gantry transaction data by means of the target vehicle's license plate information and passage number when the last gantry transaction data in the travel gantry transaction group is a non-critical point gantry transaction data.

[0017] Optionally, the gantry data also includes vehicle model data, and the travel gantry group also includes a travel gantry license plate recognition vehicle model group. Specifically, the gantry data extraction module is further used to: merge the vehicle model data and the gantry license plate recognition data according to the collection time when the last gantry license plate recognition data in the travel gantry license plate recognition group is a non-critical point gantry license plate recognition data to obtain gantry license plate recognition vehicle model data; group the gantry license plate recognition vehicle model data according to the passage time of the target vehicle between adjacent gantries to obtain the travel gantry license plate recognition vehicle model group of the target vehicle; and obtain the last gantry license plate recognition vehicle model data in the travel gantry license plate recognition vehicle model group corresponding to the non-critical point gantry license plate recognition data through the passage number.

[0018] Optionally, the gantry data also includes roadside unit data. Specifically, the gantry data extraction module is further used to obtain roadside unit data through the license plate of the target vehicle when the last gantry license plate recognition vehicle data in the travel gantry license plate recognition vehicle group is a non-critical point gantry license plate recognition vehicle data.

[0019] Optionally, the device may further include:

[0020] The data cleaning module is used to clean the gantry data and entrance data of each vehicle in the road network. The cleaning includes at least one of the following: removing gantry data with illegal license plates; removing entrance data where the number of times a vehicle enters the same station within a preset entry time range exceeds a first preset number; removing entrance data where the number of times a vehicle enters the main station and auxiliary station within a preset entry time range exceeds a second preset number; removing gantry data where the vehicle speed between adjacent gantries is less than the minimum speed; removing gantry data where the vehicle speed between adjacent gantries is greater than the maximum speed; and using box plots to identify and remove outliers in the gantry data based on the vehicle speed between adjacent gantries.

[0021] Optionally, the gantry data grouping module is specifically used to obtain the historical average travel time from the first gantry to the second gantry, wherein the first gantry and the second gantry are adjacent in the direction of vehicle travel; if the actual travel time of the vehicle from the first gantry to the second gantry is less than or equal to a preset multiple of the historical average travel time, the first gantry and the second gantry are divided into a travel gantry group.

[0022] Optionally, the road segment includes service areas. Specifically, the gantry data grouping module is further used to determine the pre-defined travel gantry group as the grouping result when the actual travel time of a vehicle from the first gantry to the second gantry is greater than a preset multiple of the historical average travel time, and neither the first nor the second gantry is a service area gantry. A service area gantry refers to the gantry to which the service area belongs. The module is also used when the actual travel time of a vehicle from the first gantry to the second gantry is greater than a preset multiple of the historical average travel time, and both the first and second gantry are service area gantry and travel in the same direction. The first and second gantries are assigned to a travel gantry group. If the actual travel time from the first gantry to the second gantry is greater than a preset multiple of the historical average travel time, and both the first and second gantries are service area gantries with different travel directions, the assigned travel gantry group is determined as the grouping result.

[0023] According to a third aspect of this disclosure, an electronic device is provided, comprising:

[0024] Processor; and

[0025] Memory, used to store computer programs for the processor;

[0026] The processor is configured to implement the above-mentioned analysis method for vehicles suspected of entering but not exiting, as described in the first aspect, by executing a computer program.

[0027] According to a fourth aspect of this disclosure, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the analysis method of suspected vehicle entry without exit as described in the first aspect.

[0028] According to a fifth aspect of this disclosure, a computer program product is provided that, when run on an electronic device, causes the electronic device to perform an analysis method for a vehicle suspected of entering but not exiting, as described in the first aspect.

[0029] The analysis method for suspected vehicle entry without exit provided in this disclosure is applied to a road network divided into at least two road segments, where different vehicles are marked by their entry data pass numbers within each segment. Within each road segment, gantry data is grouped based on the vehicle's travel time between adjacent gantries to obtain travel gantry groups within the segment, with data not shared between segments. Then, based on the pass number, target vehicles within the road segment that have entry data but lack first exit data are extracted. The last gantry data of the corresponding travel gantry group is obtained through the target vehicle's pass number. If the last gantry data corresponds to a non-critical point, the second exit data of the target vehicle's historical travel within the road segment is obtained. Finally, if the second exit data is not a predetermined travel type (e.g., paper pass or pass without a travel medium), the target vehicle is determined to be suspected of entering without exiting. This method addresses the issue of interoperability of gantry data across different road segments in a road network. By performing non-critical point judgments on vehicles with entry data but no exit data in each road segment, it connects the vehicle trajectories between road segments. Based on critical point judgments, a closed-loop traffic network is constructed between road segments. Furthermore, the gantry data is grouped based on travel time to reconstruct the vehicle's trajectory. This allows for a comprehensive and thorough analysis of vehicle entry and exit data within road segments, improving the accuracy of analysis for vehicles entering but not exiting.

[0030] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0031] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure. It is obvious that the drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0032] Figure 1 This is one of the flowcharts of an analysis method for a vehicle suspected of entering but not exiting, provided in an embodiment of this disclosure.

[0033] Figure 2 The second flowchart illustrates the steps of an analysis method for a vehicle suspected of entering but not exiting, as provided in this embodiment of the disclosure.

[0034] Figure 3 This is a schematic diagram of a gantry distribution provided in an embodiment of this disclosure.

[0035] Figure 4 This is an example of a box-shaped diagram provided for an embodiment of this disclosure.

[0036] Figure 5 This is a flowchart illustrating a method for analyzing suspected vehicle entry without exit, as provided in an embodiment of this disclosure.

[0037] Figure 6 This is a flowchart illustrating a method for grouping gantry structures according to an embodiment of the present disclosure.

[0038] Figure 7 This is a structural block diagram of an analysis device for a vehicle suspected of entering but not exiting, provided in an embodiment of this disclosure.

[0039] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0040] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided to make this disclosure more comprehensive and complete, and to fully convey the concept of the exemplary embodiments to those skilled in the art. The described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a full understanding of embodiments of this disclosure. However, those skilled in the art will recognize that the technical solutions of this disclosure can be practiced with one or more specific details omitted, or other methods, components, apparatus, steps, etc., can be employed. In other instances, well-known technical solutions are not shown or described in detail to avoid obscuring various aspects of this disclosure.

[0041] Furthermore, the accompanying drawings are merely illustrative of this disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0042] It should be noted that the data obtained in this public disclosure, including inbound data, outbound data, gantry data, license plate information, etc., are all accessed, collected, stored and used for subsequent analysis and processing after the user or relevant data owner has been clearly informed of the content of the data collection, the purpose of the data, the processing method, etc., and with the consent and authorization of the user or relevant data owner. Furthermore, the public can send the user or relevant data owner the means to access, correct or delete the data, as well as the method to revoke consent or authorization.

[0043] Figure 1This is one of the flowcharts of a method for analyzing suspected vehicles that have entered but not exited, provided in an embodiment of this disclosure. This method can be applied to a road network that is divided into at least two road segments, and different vehicles within each road segment are marked with access numbers from the entry data.

[0044] In this embodiment, the road network can be a complete, interconnected, and closed-loop transportation network covering any region, such as an intra-provincial expressway network bounded by provincial borders. The road network is typically managed by multiple governing bodies, thus dividing it into different road segments. For example, in road network A, segment A1 is managed by expressway company 1, segment A2 by expressway company 2, segment A3 by expressway company 3, and so on. For each road segment, the corresponding governing body is responsible for maintenance and operation, such as setting up toll stations and service areas. When a vehicle enters a road segment through a toll station, vehicle information can be collected to generate entry data for that vehicle, and a unique passage number can be assigned to the vehicle to mark the travel data generated by different vehicles traveling on that road segment.

[0045] like Figure 1 As shown, the method may include steps 101 to 105 as shown below.

[0046] Step 101: Group the gantry data according to the travel time of vehicles between adjacent gantries to obtain the travel gantry groups within the road segment. Data between different road segments is not shared.

[0047] In this embodiment, the gantry refers to the ETC gantry installed on highways. When a vehicle passes through a segmented toll collection system installed on highways, bridges, or other transportation facilities, payment is completed via short-range communication between the vehicle's electronic tag and the microwave antenna installed on the ETC gantry, thus achieving non-stop toll collection. Given a fixed distance between adjacent gantries, the travel time between adjacent gantries for a vehicle in the same journey should also be within the expected range. Too short a travel time may indicate speeding, while too long a travel time may indicate that the vehicle is in different journeys when passing two gantries. The gantry data may include PassID, license plate information, vehicle type information, payment information, and transit timestamps collected from different passing vehicles. Based on the transit timestamps of different vehicles between adjacent gantries in the gantry data, the travel time of the corresponding vehicle can be determined. Therefore, based on the travel time, the gantry data for different vehicles' corresponding journeys are divided into corresponding journey gantry groups to represent a segment of the vehicle's journey within the road segment.

[0048] Step 102: Among the vehicles with entrance data within the road segment, determine the target vehicles that do not have first exit data based on their pass numbers.

[0049] In this embodiment, entry data refers to the data generated when a vehicle enters the road segment from the toll station, and exit data refers to the data generated when a vehicle leaves the road segment from the toll station. Due to the lack of data sharing between road segments, or potential vulnerabilities, actual statistics may show different scenarios: a vehicle may have entry data for the current road segment but exit data for another road segment, or only entry data for the current road segment but no exit data. In this embodiment, since each governing body typically only manages the data of its own toll stations and gantries, and gantry data between different road segments is isolated, vehicles with entry data but no first exit data within a road segment can be used as target vehicles for entry-only trip analysis. These target vehicles are considered to be likely to be entry-only vehicles.

[0050] For example, the gantry data for road segment A1 over a historical period (the past ten days) is statistically analyzed, as shown in Table 1 below:

[0051] Table 1. Statistical Table of Entrance / Exit Data for Road Section A1

[0052]

[0053]

[0054] As can be seen from the gantry data, the traffic flow was higher in the first three days, averaging around 1.2 million vehicles per day, with approximately 30.92% of vehicles having both entrance and exit data for that section of road. The traffic flow decreased slightly in the following seven days, averaging around 700,000 vehicles per day, with approximately 55% of vehicles having both entrance and exit data for that section of road. Based on this, and referring to the data from the following seven days, we can see that approximately 45% of vehicles had entrance data but no exit data for that section of road, totaling approximately 310,000 vehicles.

[0055] It can be seen that in real-world scenarios, analyzing journeys with only entry points and no exits based solely on provincial border exit data ignores intermediate trajectory information during the vehicle's journey. Due to the isolation of entry, exit, and gantry data between road segments, a large amount of vehicle behavior data within a road segment may exist that only involves entry without exit, making it impossible to form a closed loop of vehicle trajectory entry and exit. This results in numerous verification loopholes, potentially overlooking issues such as following vehicles at exits or changing cards mid-journey, leading to inaccurate journey analysis with only entry points and no exits. In this embodiment, the existence of exit data can be queried based on the passage number of the entry data within a road segment. If no exit data is found, the vehicle is considered to potentially have a journey with only entry points and is designated as a target vehicle for further journey analysis.

[0056] Step 103: Obtain the last gantry data of the travel gantry group using the toll number corresponding to the target vehicle. In this embodiment, the travel gantry group can be obtained by grouping the gantry data of all vehicles passing through the road segment. Therefore, when performing travel analysis on the target vehicle, the last gantry data can be obtained from the corresponding travel gantry group based on the toll number corresponding to the target vehicle, so as to obtain the gantry data of the last gantry passed by the target vehicle in its travel within the road segment. Since the exit data of other jurisdictions is lacking, it can be determined by analyzing the vehicle trajectory that during the normal travel of the vehicle, if it enters from the toll station of the current road segment and exits from the toll station of another road segment, the vehicle's travel will usually pass through gantries such as hubs, provincial borders, and destinations to enter other road segments. Therefore, the last gantry data can be obtained from the travel gantry group of the target vehicle in the current road segment to determine whether the target vehicle has entered other road segments.

[0057] Step 104: If the last gantry data in the travel gantry group corresponds to a non-critical point, obtain the second exit data of the target vehicle's historical travel in the road segment. The critical point is located at the boundary between road segments in the road network.

[0058] In this embodiment, a critical point can refer to a gantry or other information collection device set on the boundary between road segments in a road network, while a non-critical point refers to a location that is not on the boundary between road segments. When the last gantry data in the travel gantry group corresponds to a non-critical point, it can be considered that the target vehicle has not crossed the road segment boundary to enter other road segments. At this time, the second exit data of the target vehicle's historical travel in the road segment can be obtained. This second exit data can be the second exit data of the target vehicle's historical travel in the road segment that is closest to the generation time of the current entry data; or it can be that the second exit data of the historical travel is divided by traffic type, and the second exit data with the highest frequency of traffic type is extracted. Through the second exit data, further analysis can be performed to determine the historical reasons for the absence of exit data for the target vehicle in the road segment.

[0059] In an optional embodiment of the method disclosed herein, an information table of all critical points in a road segment can be pre-compiled for subsequent lookup and comparison. As shown in Table 2 below, the gantry information of critical points can be statistically analyzed based on some of the mapping fields shown in the road segment.

[0060] Table 2 Gantry Mapping Fields

[0061]

[0062]

[0063] Step 105: If the second exit data is not the predetermined passage type, determine that the target vehicle is a suspected vehicle that has entered but not exited. The predetermined passage type includes passage with paper pass and passage without passage medium.

[0064] In this embodiment, the predetermined passage type may include passage using paper tickets, passage without a passage medium, or other passage methods that do not generate exit data. Therefore, the absence of second exit data may indicate that the target vehicle is using the predetermined passage type, and the probability that the target vehicle is an entry-only vehicle is low. Conversely, when second exit data is generated but not the predetermined passage type, the probability that the target vehicle is an entry-only vehicle is high, and thus, the target vehicle can be initially identified as a suspected entry-only vehicle. Furthermore, suspected entry-only vehicles can be marked, reported, and verified. This verification can be manual verification, information tracking, historical data analysis, etc., to ultimately determine whether the target vehicle is an entry-only vehicle, ensuring the sufficiency and accuracy of vehicle journey analysis. The vehicle suspected entry-only analysis method provided in this disclosure is applied to a road network divided into at least two road segments, where different vehicles within each road segment are marked with the passage number of the entry data. Within a road segment, gantry data is grouped based on the vehicle's travel time between adjacent gantries to obtain travel gantry groups within the segment, and data between different road segments is not shared. Then, target vehicles within the road segment that have entrance data but no first exit data are extracted based on their passage numbers. The last gantry data of the corresponding travel gantry group is obtained through the target vehicle's passage number. If the last gantry data corresponds to a non-critical point, the second exit data of the target vehicle's historical travel within the road segment is obtained. Finally, if the second exit data is not the predetermined passage type, such as passage with a paper pass or passage without a passage medium, the target vehicle is determined to be a suspected vehicle that has entered but not exited. This method addresses the issue of interoperable gantry data across different road segments in a road network. By performing non-critical point judgments on vehicles with entry data but no exit data in each segment, the vehicle trajectories between road segments can be connected. Based on critical point judgments, a closed-loop traffic network is constructed between road segments. Furthermore, the vehicle's travel trajectory is reconstructed by grouping gantry data based on travel time. This allows for a thorough analysis of vehicle entry and exit data within road segments, improving the accuracy of analysis for vehicles entering but not exiting.

[0065] Figure 2 This is a second flowchart illustrating the steps of a method for analyzing suspected vehicle entry without exit, provided in an embodiment of this disclosure. This method can be applied to a road network divided into at least two road segments, where different vehicles within each segment are marked with a passage number from the entry data. For example... Figure 2 As shown, the method may include the following steps 201 to 212.

[0066] Step 201: Obtain the historical average travel time from the first gantry to the second gantry, where the first gantry and the second gantry are adjacent in the direction of vehicle travel.

[0067] In this embodiment, the first gantry and the second gantry are used to distinguish adjacent gantries on a road segment in the direction of vehicle travel. During normal vehicle travel, the travel trajectory is usually continuous, and the distance between gantries depends on the infrastructure of the governing body. Road conditions also typically remain within a certain range over historical periods. Therefore, the historical average travel time from the first gantry to the second gantry can be used to determine whether the first and second gantries belong to the same trip, thus enabling trip grouping. This historical average travel time can be the average travel time of vehicles of different types and time periods passing through the first and second gantry sequentially, or it can be determined based on different time periods, vehicle types, and directions of travel. This embodiment does not impose specific limitations on the time segments or vehicle information used to determine the historical average travel time.

[0068] For example, among the gantries under the jurisdiction of Highway Company 1, the maximum distance between adjacent gantries is 26.14km, and the average distance is about 4.36km. The passage time of vehicles passing through the first gantry and the second gantry in sequence can be calculated for each hour of each day for the past seven days, and the historical average passage time of vehicles passing through the first gantry and the second gantry in sequence for the past seven days can be determined.

[0069] Step 202: If the actual travel time of the vehicle from the first gantry to the second gantry is less than or equal to a preset multiple of the historical average travel time, the first gantry and the second gantry shall be assigned to the travel gantry group.

[0070] In this embodiment, it can be assumed that the actual travel time of a vehicle passing through the first gantry and the second gantry sequentially during normal driving is correlated with the historical average travel time. When the actual travel time is less than or equal to the historical average travel time, the vehicle's behavior data recorded by the first gantry and the second gantry can be considered to belong to the same trip. However, when the actual travel time is much greater than the historical average travel time, the vehicle's behavior data recorded by the first gantry and the second gantry may not belong to the same trip and further confirmation is required. Therefore, a preset multiple can be set for the historical average travel time. For example, when the actual travel time is less than or equal to the historical average travel time, the difference between the actual travel time and the historical average time can be considered to be within the allowable fluctuation range. Conversely, when the actual travel time is greater than the historical average travel time, the difference between the actual travel time and the historical average time can be considered to be large. In this case, the divided trip gantry group can be determined as the grouping result, and the first gantry and the second gantry can be further confirmed. In this embodiment of the disclosure, the preset multiplier can be determined based on the distribution of travel time of different vehicle models in the historical journey between the gantry, and this embodiment of the disclosure does not impose specific limitations on this.

[0071] For example, if the actual travel time of a vehicle from the first gantry to the second gantry is less than or equal to twice the historical average travel time, then the first gantry and the second gantry will be assigned to the travel gantry group.

[0072] In an optional embodiment of the method disclosed herein, if the road segment includes a service area, then after obtaining the historical average travel time from the first gantry to the second gantry in step 201, steps A1 to A4 may be included as follows:

[0073] Step A1: If the actual travel time of a vehicle from the first gantry to the second gantry is greater than a preset multiple of the historical average travel time, and neither the first gantry nor the second gantry is a service area gantry, then the divided travel gantry group is determined as the grouping result. A service area gantry refers to the gantry to which the service area belongs.

[0074] Step A2: If the actual travel time of a vehicle from the first gantry to the second gantry is greater than a preset multiple of the historical average travel time, and both the first and second gantry are service area gantries and travel in the same direction, then the first and second gantry shall be assigned to the travel gantry group.

[0075] Step A3: If the actual travel time of a vehicle from the first gantry to the second gantry is greater than a preset multiple of the historical average travel time, and both the first and second gantry are service area gantries and have different travel directions, the pre-divided travel gantry group is determined as the grouping result.

[0076] Step A4: If the actual travel time of a vehicle from the first gantry to the second gantry is greater than a preset multiple of the historical average travel time, and either the first gantry or the second gantry is a service area gantry and the travel directions are different, then the divided travel gantry group is determined as the grouping result.

[0077] In this embodiment, a service area refers to a place where vehicles can stop, as well as other infrastructure providing ancillary services such as restaurants, parking lots, gas stations, public restrooms, and vehicle repair shops. During normal driving, a vehicle's stay in a service area can significantly increase the actual travel time, potentially exceeding the historical average. Therefore, when it is determined that the actual travel time from the first gantry to the second gantry is greater than a preset multiple of the historical average travel time, it can be further determined whether the vehicle's stay in the service area is the cause. Since service areas are typically distributed, when a gantry is a service area gantry, it can be considered as one of the preceding and following gantry of that service area. Therefore, when both the first and second gantries are service area gantries, or either one is a service area gantry, the service area may be located between the first and second gantries. In this case, if vehicles travel in the same direction when passing through the first and second gantries sequentially, the actual travel time is significantly longer than the historical average travel time, possibly due to vehicles stopping at the service area. Therefore, the first and second gantries can also be classified into a travel gantry group. Similarly, when neither the first nor the second gantry is a service area gantry, it can be assumed that there are no service areas before or after each of the first and second gantries. In this case, the actual travel time is significantly longer than the historical average travel time. The travel time may be due to the gantry data belonging to different trips, so the grouping result can be based on the already divided trip gantry group; furthermore, if the first gantry and the second gantry are both service area gantry, or either one is a service area gantry, but the vehicle's travel direction recorded by the first gantry and the second gantry is different, it can be considered that the vehicle may have changed its trip during the journey, leaving the road segment from the first gantry or the second gantry instead of passing through the service area. In this case, the actual travel time is much longer than the historical average travel time, which may be due to the gantry data belonging to different trips, so the grouping result can be based on the already divided trip gantry group.

[0078] Figure 3 This is a schematic diagram of a gantry distribution provided in an embodiment of the present disclosure, such as... Figure 3 As shown, adjacent first gantry 301 and second gantry 302 can be determined in the direction of vehicle travel. When both first gantry 301 and second gantry 302 are adjacent to service area 303, service area 303 is located between first gantry 301 and second gantry 302.

[0079] akin, Figure 3As not shown in the diagram, when the first gantry 301 is adjacent to the service area 303, but the second gantry 302 is not adjacent to the service area 303, the service area 303 is located on the side of the first gantry 301 away from the second gantry 302; when the first gantry 301 is not adjacent to the service area 303, but the second gantry 302 is adjacent to the service area 303, the service area 303 is located on the side of the second gantry 302 away from the first gantry 301; when neither the first gantry 301 nor the second gantry 302 is adjacent to the service area 303, no service area 303 is provided in front of or behind the first gantry 301 or the second gantry 302.

[0080] by Figure 3 The historical average travel time for different vehicle types between the first gantry 301 and the second gantry 302 over the past seven days is shown as follows. Specifically, sum(time) represents the total passage time of this vehicle type through the first and second gantries in the last seven days, and count(time) represents the total number of vehicles of this vehicle type through the first and second gantries in the last seven days. Therefore, we have...

[0081] Furthermore, data analysis reveals that the preset multiplier is 2. The first and second gantry are then assigned to the travel gantry group. Then determine whether the first gantry and the second gantry are service area gantry. If both the first gantry and the second gantry are service area gantry and travel in the same direction, classify the first gantry and the second gantry into a travel gantry group; if both the first gantry and the second gantry are service area gantry and travel in different directions, use the already classified travel gantry group as the grouping result; if either the first gantry or the second gantry is not a service area gantry and travels in different directions, use the already classified travel gantry group as the grouping result.

[0082] In an optional embodiment of this method, information on adjacent gantries of all service areas in a road segment can be pre-compiled for subsequent comparison and lookup. As shown in Table 3 below, information on adjacent gantries of service areas can be compiled based on some of the mapping fields shown in the road segment.

[0083] Table 3 Service Area Mapping Fields Table

[0084]

[0085] This disclosure also provides an example of gantry data grouping. Taking vehicle 1 (model A) as an example, its travel trajectory within the road segment sequentially includes gantry A, gantry B, gantry C, gantry D, gantry E, gantry F, gantry H. The interval distance between gantry A and H is shown in Table 4 below:

[0086] Table 4 Example of Gantry Spacing Distance

[0087]

[0088] Based on this, for vehicles of type A, the historical average passage time of adjacent gantries shown in Table 4 was calculated hourly over the past seven days. Taking "Gantry A - Gantry B" as an example, as shown in Table 5 below:

[0089] Table 5. Examples of Historical Average Passage Time for Gantry A-Gantry B

[0090]

[0091] For vehicle type A, the actual travel time on this road segment in the current trip analysis is shown in Table 6 below:

[0092] Table 6. Examples of Actual Vehicle Travel Time

[0093]

[0094]

[0095] As shown in Table 6, starting from gantry A, the actual travel time of vehicles between adjacent gantries from gantry A to gantry H is sequentially traversed and compared with the historical average travel time shown in Table 5. For example, if vehicle 1 of type A passes through gantry A to gantry B between 10:00 and 11:00 on the same day, and the travel time is 33 seconds, which is less than 2*-=80 seconds, then gantry A and gantry B can be assigned to the travel gantry group of vehicle 1.

[0096] Therefore, the actual passage time from gantry B to gantry C is 832 seconds. Assume the passage from gantry B to gantry C occurs between 10:00 and 11:00. If the time is 850 seconds, then gantry B and gantry C are considered to be assigned to the travel gantry group of vehicle 1. Since gantry B is already in the travel gantry group, gantry C can be added to the travel gantry group according to the time sequence.

[0097] Assuming the travel time from gantry E to gantry F is 13 seconds between 10:00 and 11:00, and the actual travel time for vehicle 1 from gantry E to gantry F is 29 seconds, then it can be further determined whether gantry E and gantry F are service area gantries. If both gantry E and gantry F are service area gantries and travel in the same direction, gantry E and gantry F are assigned to a travel gantry group. If both gantry E and gantry F are service area gantries and travel in different directions, the assigned travel gantry group is used as the grouping result. If either or both gantry E and gantry F are not service area gantries and travel in different directions, the assigned travel gantry group is determined as the grouping result.

[0098] Step 203: Among the vehicles with entrance data within the road segment, determine the target vehicles that do not have first exit data based on the passage number.

[0099] In this embodiment of the disclosure, step 203 can be referred to the relevant description of step 102 above. To avoid repetition, it will not be repeated here.

[0100] In an optional embodiment of the method disclosed herein, if the gantry data includes gantry transaction data and the travel gantry group includes travel gantry transaction group, then step 204 may be included after step 203.

[0101] Step 204: Obtain the last gantry transaction data in the trip gantry transaction group corresponding to the target vehicle through the passage number corresponding to the target vehicle.

[0102] In this embodiment of the disclosure, since vehicles traveling normally on highways generate gantry transaction data and gantry identification data when passing through gantries, it is possible to determine whether a vehicle has entered another road segment from the boundary of that road segment based on the gantry transaction data. At this time, within the pre-grouped different vehicle journey gantry transaction groups, the last gantry transaction data in the corresponding journey gantry transaction group can be determined based on the toll number corresponding to the target vehicle. This last gantry transaction data in the journey gantry transaction group is the gantry transaction data generated by the gantry passed by the vehicle at the end point of the same journey on the road segment.

[0103] Based on this, the last gantry transaction data in the travel gantry transaction group can be used as the last gantry data in the travel gantry group, and step 210 can be executed.

[0104] In an optional embodiment of the method disclosed herein, the gantry data may further include gantry identification data, and the travel gantry group may further include the travel gantry identification group. Then, step 205 may be included after step 204.

[0105] Step 205: If the last gantry transaction data in the travel gantry transaction group is a non-critical point gantry transaction data, obtain the last gantry identification data in the travel gantry identification group corresponding to the non-critical point gantry transaction data through the license plate information and passage number of the target vehicle.

[0106] In this embodiment of the disclosure, non-critical point gantry transaction data refers to the gantry that generates the last gantry transaction data in the trip gantry transaction group not being located at a critical point, that is, on the boundary between the road segment and other road segments. In this case, it means that the vehicle did not leave the road segment when passing through the gantry.

[0107] In practical applications, considering the possibility of missing or incorrect gantry transaction data due to special circumstances, such as shielding the passage medium or other special reasons, errors might occur in subsequent gantry transaction data following the non-critical point gantry transaction data, leading to identification errors. Therefore, in addition to the gantry transaction data, gantry license plate recognition data generated when a vehicle passes through the gantry can be obtained as a second option to supplement the missing gantry transaction data. Since the license plate information of the same vehicle may exist at different times on the same road segment, if the last gantry transaction data in the travel gantry transaction group is a non-critical point gantry transaction data, the grouping of its gantry license plate recognition data can be located using the target vehicle's license plate information and passage number to obtain the last gantry license plate recognition data in the travel gantry license plate recognition group corresponding to the non-critical point gantry transaction data.

[0108] Based on this, the last gantry identification data in the travel gantry identification group can be used as the last gantry data in the travel gantry group, and step 210 can be executed.

[0109] In an optional embodiment of the method disclosed herein, the gantry data may further include vehicle model data, and the travel gantry group may further include the travel gantry license plate vehicle model group. Then, step 205 may be followed by steps 206 to 208.

[0110] Step 206: If the last gantry signage data in the travel gantry signage group is a non-critical point gantry signage data, merge the vehicle model data and the gantry signage data according to the collection time to obtain the gantry signage vehicle model data.

[0111] In this embodiment of the disclosure, non-critical point gantry identification data refers to the gantry that generates the last gantry identification data in the travel gantry identification group not being located at a critical point, that is, on the boundary between the road segment and other road segments. In this case, it means that the vehicle did not leave the road segment when passing through the gantry.

[0112] In practical applications, considering the potential for identification errors and data loss in gantry license plate recognition data due to factors such as vehicle density and network fluctuations on road sections, a vehicle type recognizer can be added to identify vehicle types. Vehicle information is extracted using machine vision information technology and multi-dimensional vehicle feature information extraction and analysis technology. The vehicle type data and gantry license plate recognition data are then fused based on the collection time order to combine the vehicle type data and gantry license plate recognition data collected for the same vehicle at the same time, thus obtaining the vehicle's gantry license plate vehicle type data.

[0113] Step 207: Group the gantry license plate recognition vehicle type data according to the travel time of the target vehicle between adjacent gantries to obtain the travel gantry license plate recognition vehicle type group of the target vehicle.

[0114] In this embodiment of the disclosure, the fused gantry license plate recognition vehicle model group can be grouped to obtain travel gantry license plate recognition vehicle model group. Grouping can be performed by referring to the travel gantry license plate recognition group, or by using the relevant descriptions of steps 101 or 201 to 202 described above. This embodiment of the disclosure does not impose specific limitations in this regard.

[0115] Step 208: Obtain the last gantry vehicle model data in the travel gantry vehicle model group corresponding to the non-critical point gantry vehicle model data through the passage number.

[0116] In this embodiment, vehicle model data is used to supplement gantry identification data to avoid inaccurate trip analysis caused by missing or incorrect gantry identification data. When the last gantry identification data in the gantry identification group is a non-critical point gantry identification data, it is possible that this last gantry identification data has been lost. In this case, vehicle model data can be used to supplement the information, determine whether subsequent gantry identification vehicle model data exists, and obtain the last gantry identification vehicle model data in the gantry identification vehicle model group through the vehicle's pass number.

[0117] Based on this, the last gantry vehicle data in the gantry vehicle identification group can be used as the last gantry data in the travel gantry group, and step 210 can be executed.

[0118] In an optional embodiment of the method disclosed herein, the gantry data may further include roadside unit data, and step 209 may be included after step 208.

[0119] Step 209: If the last gantry license plate recognition vehicle data in the travel gantry license plate recognition vehicle group is a non-critical point gantry license plate recognition vehicle data, obtain the roadside unit data through the license plate of the target vehicle.

[0120] In this embodiment, the roadside unit refers to a roadside sensing device and data processing device installed on the roadside to realize vehicle-road cooperation. It can collect information such as road and traffic conditions, and interact with passing vehicles through a communication network to obtain information such as vehicle speed, position, and steering. Therefore, if the last gantry license plate recognition vehicle type data in the travel gantry vehicle type group is not located at a critical point, i.e., at the boundary between another road segment and another road segment, it indicates that the vehicle did not leave the road segment when passing the gantry.

[0121] In practical applications, RSU data can be further used to supplement gantry license plate recognition vehicle data. Through multi-party sensing, RSU data can further avoid possible omissions and errors, and improve the accuracy of trip analysis results.

[0122] Based on this, the roadside unit data of the vehicle can be used as the last gantry data in the travel gantry group, and step 210 can be executed to determine whether the roadside unit data belongs to the critical point RSU. In actual travel analysis, RSUs after the entry data generation time can be confirmed. If the RSUs after the entry data generation time are not critical point RSUs, step 210 can be executed.

[0123] Step 210: If the last gantry data in the travel gantry group corresponds to a non-critical point, obtain the second exit data of the target vehicle's historical travel in the road segment. The critical point is located at the boundary between road segments in the road network.

[0124] In this embodiment of the disclosure, the relevant description of step 104 above can be referred to, and will not be repeated here to avoid repetition. Further, referring to steps 204 to 209 in the above steps, depending on the selection in the specific embodiment, the last gantry data in the travel gantry group can have different data types. It is only necessary to determine whether the position of the gantry or other equipment it points to is located at the critical point of the road segment boundary. This embodiment of the disclosure does not impose specific restrictions on this.

[0125] Step 211: If the second exit data is not the predetermined passage type, determine that the target vehicle is a suspected vehicle that has entered but not exited. The predetermined passage type includes passage with paper pass and passage without passage medium.

[0126] In this embodiment, step 211 can be referred to the relevant description of step 105 above. To avoid repetition, it will not be repeated here.

[0127] In an optional embodiment of the method disclosed herein, the method may further include step B1 before step 201.

[0128] Step B1: Clean the gantry data and entrance data of each vehicle in the road network.

[0129] In this embodiment of the disclosure, it is necessary to exclude vehicles with exit data from toll stations from the collected data. However, the time when a vehicle leaves the toll station during its journey cannot be predicted in advance. Therefore, a large amount of historical vehicle travel trajectories need to be stored in memory, and it is necessary to ensure that the upstream data does not experience delays or out-of-order issues. This places high demands on the real-time performance of data collection, data processing, and storage. Alternatively, offline timed batch calculations can be used to collect and maintain vehicle toll station entry data, exit data, gantry transaction data, gantry identification data, RSU data, etc., including vehicle passage number, vehicle type, vehicle class, entry time, exit time, toll station signs passed through, gantry number, gantry transaction time, gantry identification collection time, etc. It can also store and maintain gantry information, such as gantry number, gantry type, etc., to distinguish gantry located at critical points, etc.

[0130] In practical applications, raw data obtained from vehicle identification via gantries and lane toll collection systems can be used. This data includes front and rear license plate colors, license plate numbers, passage timestamps, gantry information, and vehicle image information. Specific data types can be broadly categorized as ETC gantry transaction logs, ETC gantry license plate recognition logs, image logs, and lane entrance / exit toll collection logs. Based on this, data for trip analysis can be extracted from the raw data. For example, the "ods_chg_dfs_gantry_transaction_result_dt" field can be used to retrieve the ETC gantry transaction log table, obtaining gantry transaction data such as vehicle passage number, gantry number, and gantry transaction time; the "dim_hhy_serverpart_info" field can be used to retrieve the mapping table of front and rear gantry numbers for the service areas within the road segment; and the "dwd_etcs_gantry_baseinfo" field can be used to retrieve basic information about gantries in the road network. The table includes gantry number, gantry-owned road segment, and gantries located at critical points, etc.; the gantry image storage metadata log table is retrieved through the "ods_etcs_gantry_image_jour_result_dt" field to obtain gantry license plate recognition data, including license plate, gantry number, image acquisition time, etc.; the ETC gantry image log table is retrieved through the "ods_chg_rt_dfs_gantry_travelimage_result_dt" field to obtain gantry license plate recognition data, including license plate, gantry number, image acquisition time, etc.; the "ods_etcs_gantry_image_jour_result_dt" field is retrieved through the "ods_etcs_gantry_image_jour_result_dt" field to obtain gantry license plate recognition data, including license plate, gantry number, image acquisition time, etc.; the "ods_etcs_gantry_image_jour_result_dt" field is retrieved through the "ods_etcs_gantry_travelimage ...travel_image_result_dt" field is retrieved through the "ods_etcs_gantry_travel_image_result_dt" field to obtain The "s_chg_rt_entry_jour_result_dt" field retrieves the toll station entrance transaction record, which contains toll records entered by vehicles at the toll station entrance, including vehicle pass number, vehicle type, vehicle model, entry time, license plate number, station number, lane number, etc.; the "ods_chg_rt_exit_jour_result_dt" field retrieves the toll station exit transaction record, which contains toll records entered by vehicles at the toll station exit, including exit time, license plate number, station number, toll method, passage type, payment amount, etc.; the "ods_etl" field retrieves the toll station exit transaction record. The "_rt_merge_vehicle_data_dt" field retrieves RSU data, including license plate number, gantry number, etc.; the "dim_pub_critical_point_gantry_da" field retrieves the gantry mapping table located at the critical point of the road segment, including the gantry number of the critical point; the "hhy_dw.dwd_gantry_data_pass_dt" field retrieves vehicle model data, which is obtained by the vehicle model recognizer and may include the vehicle's license plate number, data collection time, equipment location, and road segment to which the equipment belongs.

[0131] Furthermore, the data collected in real time from gantries and toll stations can be processed. For example, when performing offline scheduled batch calculations, a T+1 result correction table can be generated using Spark SQL tasks. Since gantry and toll station data may have missing data at T+1 and T+2, the acquisition range for inbound and outbound data can be T+3, the acquisition range for gantry transaction data can be from T+3 to T+1, and the acquisition range for gantry signage data and RSU data can be from T+3 to T+2. Meanwhile, dimensional data such as gantry numbers and basic gantry information at service areas and critical points usually do not change with the collection cycle, and the latest dataset can be obtained directly.

[0132] In this embodiment of the disclosure, the collected data can be cleaned before being processed for trip analysis to remove abnormal or erroneous data that may interfere with the analysis results. This includes data that was corrupted during collection or uploading, or data that may show vehicles entering multiple times within a short period. By cleaning the raw data, high-quality data is obtained for subsequent trip analysis, improving the accuracy and reliability of the trip analysis results.

[0133] In an optional embodiment of the method disclosed herein, cleaning may include removing gantry data of illegal license plates.

[0134] In this embodiment, an illegal license plate can refer to license plate information, such as the license plate number or characters, that does not conform to relevant license plate rules. For example, the first character of the license plate information may not be a province abbreviation or other legal character, or the license plate number may have missing digits. Illegal license plates can be filtered and removed from the original data based on the configured rules for license plate information.

[0135] In an optional embodiment of the method disclosed herein, cleaning may include removing entry data from the entry data that has entered the station more than a first preset number of times within a preset entry time range.

[0136] In an optional embodiment of the method disclosed herein, cleaning may include removing entry data from the entry data in which the number of entry times of the main and auxiliary stations within a preset entry time range exceeds a second preset number.

[0137] In this embodiment, the entry data may also contain abnormal data such as a vehicle entering the same toll station multiple times, or entering multiple times at the main and auxiliary toll stations. Normally, a complete driving trajectory should include one entry entry and one exit exit. Depending on the distance between different stations, if the same vehicle enters more times within a preset entry time range than a preset number, such as more than a first preset number of entries at the same station, or more than a second preset number of entries at the main and auxiliary toll stations, then data anomalies may occur. The preset entry time range, the first preset number of entries, and the second preset number of entries can be set according to analysis needs, processing conditions, data quality, and other factors; this embodiment does not impose specific limitations on these settings.

[0138] For example, based on calculations of the minimum distance between different stations and vehicle speed, if a vehicle enters the same station more than twice within 20 minutes, the entry data can be considered abnormal and invalid; or...

[0139] Based on the minimum distance between different stations and the vehicle speed, if a vehicle enters the main or secondary station more than twice within 20 minutes, the entry data can be considered abnormal and invalid.

[0140] In an optional embodiment of the method disclosed herein, cleaning may include removing gantry data where the passage speed of vehicles between adjacent gantries is less than the minimum passage speed.

[0141] In an optional embodiment of the method disclosed herein, cleaning may include removing gantry data where the passage speed of vehicles between adjacent gantries is greater than the maximum passage speed.

[0142] In this embodiment of the disclosure, data cleaning can also be performed based on vehicle speed. Based on vehicle speed limits, driving data with excessively low or high speeds may be considered abnormal and thus require cleaning. In this case, minimum and maximum speeds can be set to evaluate vehicle speed. The values ​​of the minimum and maximum speeds can be set based on historical trajectory data and actual analysis needs; for example, the minimum speed could be 0 km / h and the maximum speed could be 150 km / h.

[0143] In an optional embodiment of the method disclosed herein, cleaning may include identifying outliers in the gantry data using a box plot method based on the vehicle's passage speed between adjacent gantry frames, and removing outliers from the gantry data.

[0144] In this embodiment of the disclosure, for data anomalies that may be caused by problems such as gantry clock malfunctions and network latency, box plots can be used to identify gantry data anomalies based on passage speed. A box plot is a statistical chart used to display the dispersion of data. It can quickly and accurately depict the discrete state of data, thereby extracting outliers without being affected by them, and completing data cleaning.

[0145] Figure 4 An example of a box-type diagram provided for an embodiment of this disclosure, such as... Figure 4 As shown, the speed is calibrated using the upper and lower limits, median, upper quartile, and lower quartile of the traffic speed. Most traffic speeds are distributed within the range shown. Figure 4 Within the shown box range, values ​​exceeding the upper and lower edge limits can be considered outliers and removed. Taking Q3 as the lower quartile and Q1 as the upper quartile as an example, the interquartile range (IQR) is used to determine the upper and lower limits. Specifically, IQR = Q3 - Q1. Therefore, the upper edge limit = Q3 + 1.5 * IQR, and the lower edge limit = Q1 - 1.5 * IQR. In the gantry data, vehicles whose speed between adjacent gantries is higher than the upper edge limit or lower than the lower edge limit can be considered outliers and removed.

[0146] The method for analyzing vehicles suspected of entering but not exiting, provided in this disclosure, is applied to a road network divided into at least two road segments, where different vehicles within each segment are identified by their entry data pass numbers. Within each road segment, gantry data is grouped based on the vehicle's travel time between adjacent gantries to obtain travel gantry groups within the segment, with data not shared between segments. Then, based on the pass number, target vehicles within the road segment that have entry data but lack first exit data are extracted. The last gantry data of the corresponding travel gantry group is obtained using the target vehicle's pass number. If the last gantry data corresponds to a non-critical point, the second exit data of the target vehicle's historical travel within the road segment is obtained. Finally, if the second exit data is not a predetermined travel type (e.g., paper pass or pass without a travel medium), the target vehicle is determined to be a suspected vehicle entering but not exiting. This method addresses the issue of interoperable gantry data across different road segments in a road network. By performing non-critical point judgments on vehicles with entry data but no exit data in each segment, the vehicle trajectories between road segments can be connected. Based on critical point judgments, a closed-loop traffic network is constructed between road segments. Furthermore, the vehicle's travel trajectory is reconstructed by grouping gantry data based on travel time. This allows for a thorough analysis of vehicle entry and exit data within road segments, improving the accuracy of analysis for vehicles entering but not exiting.

[0147] Figure 5 A flowchart illustrating a method for analyzing vehicle journeys with no exits provided in this disclosure is shown below. Figure 5As shown, this method can be applied to a road network divided into at least two road segments. Within each segment, different vehicles are identified by their access pass numbers from the entry data. The gantry data for each vehicle within the segment is grouped based on the vehicle's travel time between adjacent gantries to obtain travel gantry groups within the segment. Data is not shared between road segments. Specifically, this method may include the following steps 501 to 512:

[0148] Step 501: Trip analysis process begins;

[0149] Step 502: Among the vehicles with entrance data in the road segment, obtain the exit data according to the passage number; if exit data exists, proceed to step 511; if no exit data exists, proceed to step 503.

[0150] Step 503: Obtain the last gantry transaction data in the travel gantry transaction group corresponding to the target vehicle by using the passage number corresponding to the target vehicle for which there is no exit data; if the last gantry transaction data in the travel gantry transaction group is critical point gantry transaction data, execute step 511; if the last gantry transaction data in the travel gantry transaction group is non-critical point gantry transaction data, execute step 504.

[0151] Step 504: Obtain the last gantry identification data in the travel gantry identification group corresponding to the non-critical point gantry transaction data through the license plate information and passage number of the target vehicle; if the last gantry identification data in the travel gantry identification group is critical point gantry identification data, execute step 511; if the last gantry identification data in the travel gantry identification group is non-critical point gantry identification data, execute step 505.

[0152] Step 505: Merge vehicle model data and gantry license plate recognition data according to the collection time to obtain gantry license plate recognition vehicle model data;

[0153] Step 506: Group the gantry license plate recognition vehicle type data according to the travel time of the target vehicle between adjacent gantries to obtain the travel gantry license plate recognition vehicle type group of the target vehicle;

[0154] Step 507: Obtain the last gantry signage vehicle data in the travel gantry signage vehicle group corresponding to the non-critical point gantry signage data through the passage number; if the last gantry signage vehicle data in the travel gantry signage vehicle group is the critical point gantry signage vehicle data, proceed to step 511; if the last gantry signage vehicle data in the travel gantry signage vehicle group is the non-critical point gantry signage vehicle data, proceed to step 508.

[0155] Step 508: Obtain roadside unit data through the license plate of the target vehicle; if the roadside unit data is critical point roadside unit data, proceed to step 511; if the roadside unit data is non-critical point roadside unit data, proceed to step 509.

[0156] Step 509: Obtain the second exit data of the target vehicle's historical journey in the road segment; if the second exit data is the planned passage type, proceed to step 511; if the second exit data is not the planned passage type, proceed to step 510.

[0157] Step 510: Determine if the target vehicle is a suspected vehicle that entered but did not exit;

[0158] Step 511: Determine that the target vehicle is not a vehicle that enters but does not exit;

[0159] Step 512: The trip analysis process ends.

[0160] It should be noted that, depending on the data collection conditions, the quality of the collected data, and the actual data analysis conditions and application requirements of the results, those skilled in the art can simplify, disassemble, or combine the above methods. For example, if the last gantry transaction data in the trip gantry transaction group in step 503 is a non-critical point gantry transaction data, step 504 can be further executed to supplement the information using gantry license plate data. Alternatively, step 510 can be executed to determine if the target vehicle is a suspected vehicle that has entered but not exited. Subsequent steps 504, 507, 508, etc., can be deduced similarly. Or, different types of gantry data can be partially combined for analysis. For example, gantry transaction data, vehicle model data, gantry transaction data, roadside unit data, gantry license plate data, roadside unit data, etc., can be used. Those skilled in the art can select the gantry data type for trip analysis according to actual needs.

[0161] Based on this, Figure 6 A flowchart of a method for grouping gantry frames is also provided, such as Figure 6 As shown, the method may include steps 601 to 608 as follows.

[0162] Step 601: Gantry grouping process begins;

[0163] Step 602: Obtain gantry data generated by different vehicles passing through the gantry;

[0164] Step 603: Loop through the gantry data to obtain the historical average travel time of a vehicle between two adjacent gantries and the actual travel time of the vehicle; if the actual travel time is less than or equal to twice the historical average travel time, proceed to step 606; if the actual travel time is greater than twice the historical average travel time, proceed to step 604.

[0165] Step 604: Query the service area gantry mapping table. If neither of the two adjacent gantry is a service area gantry, proceed to step 607. If one of the two adjacent gantry is a service area gantry and the other is not, proceed to step 605. If both of the two adjacent gantry are service area gantry, proceed to step 605.

[0166] Step 605: Obtain the driving direction of the vehicle when it passes two adjacent masts; if the driving directions are the same, proceed to step 606; if the driving directions are different, proceed to step 607.

[0167] Step 606: Assign two adjacent gantry to a travel gantry group;

[0168] Step 607: Determine the grouped travel gantry groups as the grouping results;

[0169] Step 608: The gantry grouping process is complete.

[0170] Figure 7 This disclosure provides a structural block diagram of a vehicle suspected of entering but not exiting analysis device 700. The device 700 is applied to a road network divided into at least two road segments. Different vehicles within each road segment are identified by their entry data passage numbers. The device may include: a gantry data grouping module 701, used to group gantry data according to the vehicle's travel time between adjacent gantries to obtain travel gantry groups within the road segment; data is not shared between road segments. A target vehicle determination module 702, used to determine, based on the passage number, a target vehicle among vehicles with entry data within the road segment that does not have first exit data. Vehicle; gantry data extraction module 703, used to obtain the last gantry data of the travel gantry group through the passage number corresponding to the target vehicle; non-critical point judgment module 704, used to obtain the second exit data of the target vehicle's historical travel in the road segment when the last gantry data in the travel gantry group corresponds to a non-critical point, the critical point is located at the boundary between road segments in the road network; travel analysis determination module 705, used to determine that the target vehicle is a suspected vehicle that enters but does not exit when the second exit data is not the predetermined passage type, the predetermined passage type includes paper passage and passage without passage medium.

[0171] In an optional device embodiment of this disclosure, the gantry data includes gantry transaction data, the travel gantry group includes travel gantry transaction group, and the gantry data extraction module 703 is specifically used to obtain the last gantry transaction data in the travel gantry transaction group corresponding to the target vehicle through the passage number corresponding to the target vehicle.

[0172] In an optional embodiment of the device disclosed herein, the gantry data further includes gantry identification data, and the travel gantry group further includes a travel gantry identification group. The gantry data extraction module 703 is specifically used to obtain the last gantry identification data in the travel gantry identification group corresponding to the non-critical point gantry transaction data by means of the license plate information and passage number of the target vehicle when the last gantry transaction data in the travel gantry transaction group is a non-critical point gantry transaction data.

[0173] In an optional embodiment of the apparatus disclosed herein, the gantry data further includes vehicle model data, and the travel gantry group further includes a travel gantry license plate recognition vehicle model group. The gantry data extraction module 703 is specifically used to, when the last gantry license plate recognition data in the travel gantry license plate recognition group is a non-critical point gantry license plate recognition data, fuse the vehicle model data and the gantry license plate recognition data according to the collection time to obtain gantry license plate recognition vehicle model data; group the gantry license plate recognition vehicle model data according to the passage time of the target vehicle between adjacent gantries to obtain the travel gantry license plate recognition vehicle model group of the target vehicle; and obtain the last gantry license plate recognition vehicle model data in the travel gantry license plate recognition vehicle model group corresponding to the non-critical point gantry license plate recognition data through the passage number.

[0174] In an optional device embodiment of this disclosure, the gantry data further includes roadside unit data. Specifically, the gantry data extraction module 703 is further used to obtain roadside unit data through the license plate of the target vehicle when the last gantry license plate recognition vehicle data in the travel gantry license plate recognition vehicle group is a non-critical point gantry license plate recognition vehicle data.

[0175] In an optional embodiment of this disclosure, the device 700 may further include:

[0176] The data cleaning module is used to clean the gantry data and entrance data of each vehicle in the road network. The cleaning includes at least one of the following: removing gantry data with illegal license plates; removing entrance data where the number of times a vehicle enters the same station within a preset entry time range exceeds a first preset number; removing entrance data where the number of times a vehicle enters the main station and auxiliary station within a preset entry time range exceeds a second preset number; removing gantry data where the vehicle speed between adjacent gantries is less than the minimum speed; removing gantry data where the vehicle speed between adjacent gantries is greater than the maximum speed; and using box plots to identify and remove outliers in the gantry data based on the vehicle speed between adjacent gantries.

[0177] In an optional device embodiment of this disclosure, the gantry data grouping module 701 is specifically used to obtain the historical average travel time from the first gantry to the second gantry, wherein the first gantry and the second gantry are adjacent in the direction of vehicle travel; and when the actual travel time of the vehicle from the first gantry to the second gantry is less than or equal to a preset multiple of the historical average travel time, the first gantry and the second gantry are divided into travel gantry groups.

[0178] In an optional embodiment of the device disclosed herein, the road segment includes service areas. The gantry data grouping module 701 is further configured to, when the actual travel time of a vehicle from the first gantry to the second gantry is greater than a preset multiple of the historical average travel time, and neither the first nor the second gantry is a service area gantry, determine the pre-divided travel gantry group as the grouping result. A service area gantry refers to the gantry to which the service area belongs. The configuration is further configured to, when the actual travel time of a vehicle from the first gantry to the second gantry is greater than a preset multiple of the historical average travel time, and both the first and second gantry are service area gantries and the travel direction is specified... Under the same conditions, the first gantry and the second gantry are assigned to the travel gantry group; if the actual travel time of the vehicle from the first gantry to the second gantry is greater than a preset multiple of the historical average travel time, and both the first gantry and the second gantry are service area gantries and have different travel directions, the assigned travel gantry group is determined as the grouping result; if the actual travel time of the vehicle from the first gantry to the second gantry is greater than a preset multiple of the historical average travel time, and either the first gantry or the second gantry is a service area gantry and has different travel directions, the assigned travel gantry group is determined as the grouping result.

[0179] The analysis device for suspected vehicle entry without exit provided in this disclosure is applied to a road network divided into at least two road segments, where different vehicles are marked with access numbers based on their entry data. Within each road segment, gantry data is grouped based on the vehicle's travel time between adjacent gantries to obtain travel gantry groups within the segment, with data not shared between segments. Then, based on the access number, target vehicles within the road segment that have entry data but lack first exit data are extracted. The last gantry data of the corresponding travel gantry group is obtained through the target vehicle's access number. If the last gantry data corresponds to a non-critical point, the second exit data of the target vehicle's historical travel within the road segment is obtained. Finally, if the second exit data is not a predetermined travel type (e.g., paper ticket travel or travel without a travel medium), the target vehicle is determined to be a suspected entry without exit vehicle. This method addresses the issue of interoperability of gantry data across different road segments in a road network. By performing non-critical point judgments on vehicles with entry data but no exit data in each road segment, it connects the vehicle trajectories between road segments. Based on critical point judgments, a closed-loop traffic network is constructed between road segments. Furthermore, the gantry data is grouped based on travel time to reconstruct the vehicle's travel trajectory. This allows for a thorough analysis of vehicle entry and exit data within road segments, improving the accuracy of analysis for vehicles suspected of entering but not exiting.

[0180] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0181] Furthermore, although the steps of the method in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.

[0182] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, mobile terminal, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0183] In an exemplary embodiment of this disclosure, an electronic device capable of implementing the above-described method is also provided.

[0184] Those skilled in the art will understand that various aspects of this disclosure can be implemented as a system, method, or program product. Therefore, various aspects of this disclosure can be specifically implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or a combination of hardware and software aspects, collectively referred to herein as a "circuit," "module," or "system."

[0185] The following reference Figure 8 To describe an electronic device 800 according to such an embodiment of the present disclosure. Figure 8 The electronic device 800 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0186] like Figure 8 As shown, the electronic device 800 is manifested in the form of a general-purpose computing device. The components of the electronic device 800 may include, but are not limited to: at least one processing unit 810, at least one storage unit 820, and a bus 830 connecting different system components (including storage unit 820 and processing unit 810).

[0187] The storage unit stores program code, which can be executed by the processing unit 810, causing the processing unit 810 to perform the steps described in the "Exemplary Methods" section above according to various exemplary embodiments of this disclosure.

[0188] Storage unit 820 may include a readable medium in the form of a volatile storage unit, such as random access memory (RAM) 8201 and / or cache memory 8202, and may further include a read-only memory (ROM) 8203.

[0189] The storage unit 820 may also include a program / utility 8204 having a set (at least one) of program modules 8205, including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0190] Bus 830 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0191] Electronic device 800 can also communicate with one or more external devices (e.g., keyboard, pointing device, Bluetooth device, etc.), one or more devices that enable a user to interact with electronic device 800, and / or any device that enables electronic device 800 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed through display unit 840 and input / output (I / O) interface 850 connected to display unit 840. Furthermore, electronic device 800 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public network, such as the Internet) via network adapter 860. As shown, network adapter 860 communicates with other modules of electronic device 800 via bus 830. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 800, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0192] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0193] In exemplary embodiments of this disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the methods described above is stored. In some possible implementations, various aspects of this disclosure may also be implemented as a program product including program code, which, when the program product is run on a terminal device, causes the terminal device to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure.

[0194] In embodiments of this disclosure, a program product for implementing the above-described methods is also provided. This product may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the program product of this disclosure is not limited thereto. In this document, a readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0195] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0196] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0197] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0198] Program code for performing the operations of this disclosure can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing devices can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0199] Furthermore, the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of this disclosure and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0200] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the claims.

Claims

1. A method for analyzing vehicles suspected of entering but not exiting, characterized in that, The method is applied to a road network divided into at least two road segments, within which different vehicles are identified by access numbers from entrance data, including: The gantry data is grouped according to the vehicle's travel time between adjacent gantries to obtain the travel gantry group within the road segment. The data between the road segments are not shared. Among the vehicles in the entrance data within the road segment, the target vehicle that does not have the first exit data is determined based on the passage number; Obtain the last gantry data of the travel gantry group using the passage number corresponding to the target vehicle; If the last gantry data in the travel gantry group corresponds to a non-critical point, the second exit data of the target vehicle's historical travel in the road segment is obtained, and the critical point is located at the boundary between road segments in the road network. If the second exit data is not the predetermined passage type, the target vehicle is determined to be a suspected vehicle that enters but does not exit. The predetermined passage type includes passage with paper pass and passage without passage medium.

2. The method according to claim 1, characterized in that, The gantry data includes gantry transaction data, and the travel gantry group includes travel gantry transaction groups. Obtaining the last gantry data entry in the travel gantry group using the pass number corresponding to the target vehicle includes: By using the passage number corresponding to the target vehicle, obtain the last gantry transaction data in the trip gantry transaction group corresponding to the target vehicle.

3. The method according to claim 2, characterized in that, The gantry data also includes gantry identification data, and the travel gantry group also includes a travel gantry identification group. After obtaining the last gantry transaction data in the travel gantry transaction group corresponding to the target vehicle through the passage number corresponding to the target vehicle, the process further includes: If the last gantry transaction data in the travel gantry transaction group is a non-critical point gantry transaction data, the last gantry identification data in the travel gantry identification group corresponding to the non-critical point gantry transaction data is obtained through the license plate information of the target vehicle and the passage number.

4. The method according to claim 3, characterized in that, The gantry data also includes vehicle model data, and the travel gantry group also includes a travel gantry license plate recognition vehicle model group. After obtaining the last gantry license plate recognition data in the travel gantry recognition group corresponding to the non-critical point gantry transaction data through the license plate information of the target vehicle and the passage number, the process further includes: If the last gantry signage data in the travel gantry signage group is a non-critical point gantry signage data, the vehicle model data and the gantry signage data are fused according to the collection time to obtain gantry signage vehicle model data; The gantry license plate recognition vehicle model data is grouped according to the travel time of the target vehicle between adjacent gantries to obtain the travel gantry license plate recognition vehicle model group of the target vehicle; The last gantry vehicle model data in the travel gantry vehicle model group corresponding to the non-critical point gantry vehicle model data is obtained through the passage number.

5. The method according to claim 4, characterized in that, The gantry data also includes roadside unit data. After obtaining the last gantry vehicle data in the travel gantry vehicle group corresponding to the non-critical point gantry identification data through the passage number, the process includes: If the last gantry license plate recognition vehicle data in the travel gantry license plate recognition vehicle group is a non-critical point gantry license plate recognition vehicle data, the roadside unit data is obtained through the license plate of the target vehicle.

6. The method according to claim 1, characterized in that, Before grouping the gantry data according to the vehicle's travel time between adjacent gantry to obtain the travel gantry groups within the road segment, the method further includes: Cleaning is performed on the gantry data and entrance data of each vehicle in the road network, and the cleaning includes at least one of the following: Remove gantry data for illegal license plates; Remove entry data from the entry data that contains more than a first preset number of entries within a preset entry time range; Remove entry data from the entry data where the number of times the main and auxiliary stations enter within a preset entry time range exceeds a second preset number; Remove gantry data where the vehicle's passage speed between adjacent gantry is less than the minimum passage speed; Remove gantry data where the vehicle's passage speed between adjacent gantry is greater than the maximum passage speed; Based on the vehicle's travel speed between adjacent gantries, the box plot method is used to identify outliers in the gantry data and remove them.

7. The method according to any one of claims 1-6, characterized in that, The step of grouping gantry data according to the vehicle's travel time between adjacent gantries to obtain travel gantry groups within the road segment includes: Obtain the historical average passage time from the first gantry to the second gantry, where the first gantry and the second gantry are adjacent in the direction of travel of the vehicle; If the actual travel time of the vehicle from the first gantry to the second gantry is less than or equal to a preset multiple of the historical average travel time, the first gantry and the second gantry are assigned to the travel gantry group.

8. The method according to claim 7, characterized in that, The road segment includes service areas. After obtaining the historical average travel time from the first gantry to the second gantry, the method further includes: If the actual travel time of a vehicle from the first gantry to the second gantry is greater than a preset multiple of the historical average travel time, and neither the first gantry nor the second gantry is a service area gantry, the divided travel gantry group is determined as the grouping result, where the service area gantry refers to the gantry to which the service area belongs; If the actual travel time of a vehicle from the first gantry to the second gantry is greater than a preset multiple of the historical average travel time, and both the first gantry and the second gantry are service area gantries and travel in the same direction, the first gantry and the second gantry are assigned to the travel gantry group. If the actual travel time of a vehicle from the first gantry to the second gantry is greater than a preset multiple of the historical average travel time, and both the first gantry and the second gantry are service area gantries and have different travel directions, the previously divided travel gantry group will be determined as the grouping result. If the actual travel time of a vehicle from the first gantry to the second gantry is greater than a preset multiple of the historical average travel time, and either the first gantry or the second gantry is a service area gantry and the travel directions are different, the already divided travel gantry group will be determined as the grouping result.

9. An analysis device for vehicles suspected of entering but not exiting, characterized in that, The device is applied to a road network divided into at least two road segments, within which different vehicles are identified by access numbers from entrance data, including: The gantry data grouping module is used to group gantry data according to the travel time of vehicles between adjacent gantries to obtain travel gantry groups within the road segment. Data between the road segments is not shared. The target vehicle determination module is used to determine, based on the passage number, a target vehicle that does not have first exit data among the vehicles in the entrance data that exist in the road segment; The gantry data extraction module is used to obtain the last gantry data of the travel gantry group through the passage number corresponding to the target vehicle; The non-critical point determination module is used to obtain the second exit data of the target vehicle's historical journey in the road segment when the last gantry data in the travel gantry group corresponds to a non-critical point, wherein the critical point is located at the boundary between road segments in the road network. The trip analysis and determination module is used to determine that the target vehicle is a suspected vehicle that has entered but not exited when the second exit data is not the predetermined passage type. The predetermined passage type includes passage with paper pass and passage without passage medium.

10. An electronic device, characterized in that, include: processor; as well as Memory for storing the computer program of the processor; The processor is configured to execute the analysis method for suspected vehicle entry without exit as described in any one of claims 1 to 8 by executing the computer program.

11. A computer-readable medium, wherein a computer program is stored on the computer-readable storage medium, characterized in that, When the computer program is executed by the processor, it implements the analysis method for suspected vehicle entry without exit as described in any one of claims 1 to 8.

Images