Transportation monitoring system and method based on location and bay track comparison

Abstract

The application discloses a transport supervision system and method based on position and bayonet track comparison, relates to the technical field of transport supervision, and comprises the following components: a track comparison module, an active traceability triggering module, a multi-data correlation module and a traceability report generation module; the application dynamically calculates a track comprehensive deviation value by combining a time deviation, a position deviation and a weight parameter through a comprehensive deviation anomaly determination algorithm, solves the problem of poor adaptability of a traditional single threshold determination, simultaneously, the active traceability triggering module performs three pre-checks of equipment state, electronic seal and vehicle driving state before determining an anomaly, avoids invalid traceability, reduces resource occupation, and the function of dynamically adjusting a traceability data range further improves traceability pertinence.

Description

Technical Field

[0001] This invention relates to the field of transportation supervision technology, specifically to a transportation supervision system and method based on location and checkpoint trajectory comparison. Background Technology

[0002] With the rapid development of the logistics and transportation industry, the number of transport vehicles and the frequency of transport have increased significantly, and the issues of transportation safety and supervision have become increasingly prominent. Traditional transportation supervision methods mainly rely on manual patrols and fixed-point inspections, which make it difficult to achieve real-time monitoring and dynamic management of transport vehicles throughout the entire process. Especially in high-risk areas such as the transportation of hazardous chemicals, once an abnormal trajectory or violation of regulations occurs, it may lead to serious safety accidents.

[0003] Traditional transportation monitoring technologies suffer from the following main drawbacks: First, trajectory determination methods relying on a single threshold have poor adaptability and struggle to cope with complex scenarios involving different road conditions, cargo types, and transportation times, leading to high false alarm or missed alarm rates. Second, traceability mechanisms lack pre-verification and dynamic adjustment functions, making them prone to ineffective traceability due to checkpoint equipment malfunctions, normal cargo operations, or special vehicle conditions, thus wasting regulatory resources. Furthermore, traditional methods neglect privacy protection when associating data, potentially leading to the leakage of sensitive information, and the lack of a tiered push mechanism results in insufficient regulatory flexibility and low enforcement efficiency.

[0004] In view of the shortcomings of traditional transportation supervision technologies, the transportation supervision system and method based on location and checkpoint trajectory comparison proposed in this invention are particularly important. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of existing technologies and provide a transportation supervision system and method based on location and checkpoint trajectory comparison. It can significantly improve the accuracy of abnormal trajectory judgment and traceability efficiency through a comprehensive deviation anomaly judgment algorithm, triple pre-verification, dynamic traceability data range adjustment and privacy protection data association mechanism. At the same time, the hierarchical push traceability report generation mode optimizes the allocation of regulatory resources and achieves dual protection of safety supervision and data privacy, providing an efficient and reliable intelligent solution for the transportation industry.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: On the one hand, a transportation supervision system based on location and checkpoint trajectory comparison, the system comprising the following components: trajectory comparison module, active tracing trigger module, multi-data association module, and tracing report generation module; The trajectory comparison module compares the satellite positioning trajectory data of the transport vehicle with the time and location records of the vehicle passing through the checkpoint, and uses a custom trajectory anomaly detection algorithm to preprocess the trajectory data. The active tracing trigger module automatically triggers the active tracing mechanism when the trajectory comparison module determines that the trajectory is abnormal, and supports pre-triggered verification and dynamic adjustment of the tracing data range. The multi-data association module: traces back the historical location data of the transport vehicle within 72 hours before the time of the abnormal trajectory occurrence, the vehicle passage records of the corresponding checkpoint, and associates the qualification information of the transport vehicle, cargo attribute information, driver operation records, and positioning equipment maintenance records. It adopts a custom root cause confidence calculation algorithm, performs data association according to priority, and supports data privacy protection processing. The source tracing report generation module generates a visual source tracing report based on the associated data, clarifies the root cause type and confidence level of the abnormal trajectory, and supports the visual presentation, hierarchical push and storage of the report.

[0007] Furthermore, the trajectory comparison module employs a comprehensive deviation anomaly detection algorithm to determine trajectory anomalies, the formula of which is: ,in This is the overall trajectory deviation value, used to determine whether the trajectory is abnormal. This is the difference between the estimated checkpoint crossing time based on the vehicle's location trajectory and the actual checkpoint crossing time. The average card passage time at this checkpoint is calculated by averaging the time data of vehicle passage records at this checkpoint over the past 30 days. This refers to the straight-line distance deviation between the predicted checkpoint position of the vehicle's trajectory and the actual checkpoint position. The effective monitoring radius of this checkpoint is obtained by taking the intersection of the checkpoint's monitoring coverage area and the sensing range of the geomagnetic sensor. The time deviation weight is determined by the clustering analysis results of the tidal traffic flow density at the checkpoint over the past 30 days. The specific clustering algorithm is as follows: K-means clustering is used, with K=4 clusters. The iteration termination condition is that the error of the sum of squares within each cluster is less than 0.001 or the number of iterations reaches 50. Euclidean distance is used as the distance metric. The clustering interval division criteria are as follows: based on the hourly traffic flow density at the checkpoint over the past 30 days, four clustering intervals are defined: low-peak traffic flow: 0-50 vehicles / hour; off-peak traffic flow: 51-150 vehicles / hour; peak traffic flow: 151-300 vehicles / hour; and super-peak traffic flow: >300 vehicles / hour. The weight value range and mapping rule are as follows: ω1 ranges from 0.3 to 0.7. The positional deviation weight is determined by the risk level of the transported goods. When the trajectory is abnormal, the algorithm solves the problem of poor adaptability of traditional single threshold judgment and can improve the accuracy of anomaly judgment.

[0008] Furthermore, before performing trajectory comparison, the trajectory comparison module performs preprocessing steps on the trajectory data and checkpoint data: filtering the vehicle's BeiDou positioning trajectory data to remove jump points and breakpoints caused by signal interference and obstruction; deduplicating the checkpoint vehicle passage record data to remove duplicate records caused by repeated captures by checkpoint equipment and data transmission delays; and converting the processed location trajectory data and checkpoint data into a unified geographic coordinate system to ensure consistent data location benchmarks. This preprocessing improves the accuracy of trajectory comparison.

[0009] Furthermore, before triggering the traceability mechanism, the active traceability triggering module performs three pre-verification steps: retrieving the geomagnetic sensor operation logs and video surveillance equipment online data of the checkpoint corresponding to the abnormal trajectory to confirm that the checkpoint equipment is not in a faulty or offline state; verifying the electronic seal status data of the transport vehicle to confirm that the electronic seal did not trigger abnormal unlocking or alarm during the period when the abnormal trajectory occurred; and retrieving the vehicle's real-time driving status data to confirm that the vehicle is not in a special state of faulty parking or accident handling. The active traceability mechanism is only triggered when all three verifications pass and the trajectory comparison module determines that the trajectory is abnormal. This setting can avoid invalid traceability caused by checkpoint equipment failure, normal cargo operation, or special vehicle status, and reduce unnecessary traceability resource consumption.

[0010] Furthermore, the proactive traceability triggering module dynamically adjusts the historical data range for traceability based on the type of transported goods and the characteristics of the transport route: when the transported goods are Class I or Class II hazardous chemicals, the range of historical location data and checkpoint records for traceability is expanded; when the transported goods are ordinary goods, the range of historical data for traceability is narrowed; when the transport route includes multiple cross-regional checkpoints, the range of checkpoint data for traceability is expanded to adjacent checkpoints of the corresponding checkpoints. This adjustment can improve the targeting of traceability and avoid retrieving invalid data; when the transported goods are Class I or Class II hazardous chemicals, the range of historical location data for traceability is expanded from the default 72 hours before the time of the abnormal trajectory occurrence. The monitoring time is extended to 120 hours, and the checkpoint recording range is expanded to include two adjacent checkpoints upstream and downstream of the abnormal checkpoint and all related checkpoints within a 50-kilometer radius along the route. When the transported goods are ordinary goods, the historical location data range for traceability is reduced to 48 hours, and the checkpoint recording range only retains the checkpoint where the abnormality occurred and one directly adjacent upstream and downstream checkpoint, and is limited to covering related checkpoints within a 20-kilometer radius along the route. When there are ≥2 cross-regional checkpoints that are continuously or intermittently distributed in the transport route, each cross-regional checkpoint is used as the core, and two adjacent checkpoints are extended upstream and downstream, while covering all registered checkpoints within a 30-kilometer radius on both sides of the cross-regional road section, forming a complete checkpoint monitoring chain.

[0011] Furthermore, the multi-data association module uses a root cause confidence calculation algorithm to determine the root cause confidence of the abnormal trajectory, as shown in the formula: ,in The root cause confidence level ranges from 0 to 1. The number of valid data types involved in the association, with a value of 3. For the first The weights of the data categories are determined by the proportion of the corresponding root causes in the historical source data of the past 180 days. For the first The matching degree between the data type and the abnormal trajectory is set to 0 (no match) or 1 (match), and the determination rule for the value is as follows: Category 1 data: Vehicle passage records and vehicle position trajectory data within one hour before and after the occurrence of the abnormal trajectory. Judgment criteria: If the timestamp error between the two types of data is ≤5 minutes and the position coordinate deviation is ≤10% of the effective monitoring radius of the checkpoint, then M1=1; otherwise, M1=0. Category 2 data: Driver operation records and vehicle qualification validity period data. Judgment criteria: If the driver operation record contains unauthorized start / stop or route change operation records during the abnormal trajectory period, or if the vehicle qualification validity period covers the time when the abnormal trajectory occurred, then M2=1; otherwise, M2=0. Category 3 data: Positioning equipment operation and maintenance records and checkpoint equipment operation logs. Judgment criteria: If the positioning equipment operation and maintenance records show that there are unreported fault / offline records of the equipment during the abnormal trajectory period, or the checkpoint equipment operation log shows that there are signal interruption and capture failure records during the corresponding period, and the signal loss period of the abnormal trajectory completely overlaps with the period of signal loss, then M3=1; otherwise, M3=0. This is an environmental correction term, determined by the regional signal coverage strength and weather conditions during the period in which the abnormal trajectory occurred. The specific calculation steps are as follows: Regional signal coverage strength classification and corresponding Value: Strong Coverage: ; Mid-coverage: Weak coverage: Range Coverage: Weather condition classification and corresponding measures Value: Sunny: Mild impact: Moderate impact: Severe impact: Weighted calculation formula: ,in The signal weight is set to 0.6. Assuming a weather weight, take 0.4, and The value range is limited to 0.01-0.20. When the calculation result exceeds the range, the boundary value is used. When the root cause is determined, it can be directly identified as the core reason for the abnormal trajectory, thus improving the accuracy of root cause determination.

[0012] Furthermore, when the multi-data association module performs data association, it follows a fixed priority order: first, it retrieves checkpoint vehicle passage records and vehicle location trajectory data within one hour before and after the occurrence of the abnormal trajectory to achieve precise alignment of the timeline; second, it retrieves the vehicle's driver operation records and vehicle qualification validity data to match and verify with the time points of the abnormal trajectory; finally, it retrieves the positioning device's maintenance records and checkpoint device operation logs to cross-verify with the time points of signal interruption and no checkpoint passage records for the abnormal trajectory. This priority setting can quickly lock down core data directly related to the abnormal trajectory, improving the efficiency of data association.

[0013] Furthermore, when the multi-data association module performs data association, it executes three privacy protection steps: desensitizing the driver's personal identity information and the vehicle's specific identification information, retaining only the hash value of the operation time and qualification number used for association; desensitizing the specific details of the goods, retaining only the risk level and transportation type information of the goods; and completing all data association processing at the edge node of the transportation supervision system without uploading the original sensitive data to the cloud server. This setting meets data security requirements and protects the privacy of transportation participants.

[0014] Furthermore, after generating a visual traceability report, the traceability report generation module performs a tiered push procedure: if the root cause confidence level reaches a preset high confidence level, the traceability report is directly pushed to the transportation supervision and enforcement terminal in the corresponding region; if the root cause confidence level does not reach the high confidence level, the traceability report is first pushed to the transportation company's supervision terminal, requiring the company to submit an explanation of the anomaly. After the company submits the explanation, the report and explanation are then pushed to the supervision terminal together. At the same time, all pushed reports are automatically stored in the evidence chain database of the supervision system for subsequent supervision and verification. This tiered push mechanism can improve the flexibility of supervision and reduce the waste of enforcement resources.

[0015] On the other hand, the transportation supervision method based on location and checkpoint trajectory comparison is characterized by the following specific steps: Trajectory comparison steps: First, preprocess the satellite positioning trajectory data of the transport vehicle and the time and location records of the vehicle passing through the checkpoint. Then, use a custom trajectory anomaly detection algorithm to compare the preprocessed trajectory data with the checkpoint data to determine whether there is an abnormal trajectory. Active tracing triggering steps: If an abnormal trajectory is determined, first perform pre-verification of the status of checkpoint equipment, vehicle electronic seal status, and vehicle driving status, and then dynamically adjust the tracing data range according to the type of transported goods and the characteristics of the transport route to trigger the active tracing mechanism. Multi-data association steps: trace back the historical location data and corresponding checkpoint vehicle passage records within 72 hours before the time of the abnormal trajectory occurrence, associate the transport vehicle qualification information, cargo attribute information, driver operation records, and positioning device maintenance records according to preset priorities, calculate the root cause confidence using a custom root cause confidence calculation algorithm, and perform privacy protection processing on the associated data at the same time. Source tracing report generation steps: Generate a visual source tracing report based on the associated data, clarify the root cause type and confidence level of the abnormal trajectory, and then perform hierarchical push and tamper-proof storage operations on the source tracing report.

[0016] Compared with existing technologies, this transportation supervision system and method based on location and checkpoint trajectory comparison has the following advantages: This system solves the problem of poor adaptability of traditional single threshold judgment by using a comprehensive deviation anomaly judgment algorithm that combines time deviation, position deviation and weight parameters to dynamically calculate the comprehensive trajectory deviation value. At the same time, the active tracing trigger module performs triple pre-verification of equipment status, electronic seal and vehicle driving status before judging anomalies, avoiding invalid tracing, reducing resource consumption, and the function of dynamically adjusting the tracing data range further improves the tracing targeting.

[0017] Second, this system employs anonymization processing when associating sensitive data such as driver operation records and cargo information through a multi-data association module. Furthermore, all data processing is completed at edge nodes, avoiding the uploading of raw data to the cloud and meeting data security requirements. The traceability report generation module uses a tiered push mechanism, which reduces the waste of law enforcement resources and ensures the traceability of regulatory verification.

[0018] Other advantages, objectives and features of the invention will be set forth in part in the description which follows, and in part will be apparent to those skilled in the art from the following examination or study, or may be learned from the practice of the invention. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0020] Figure 1 This is a flowchart of a transportation monitoring system based on location and checkpoint trajectory comparison; Figure 2 This is a flowchart illustrating the core processing steps for tracing abnormal trajectories in a transportation monitoring system based on location and checkpoint trajectory comparison. Figure 3This is a flowchart of a transportation supervision method based on location and checkpoint trajectory comparison. Detailed Implementation

[0021] To further illustrate the technical means and effects of the present invention in achieving its intended purpose, the following detailed description of the specific implementation methods, structures, features, and effects of the present invention, in conjunction with the accompanying drawings and preferred embodiments, is provided below.

[0022] Example 1 A chemical company needs to transport Class A hazardous chemicals from location A to location C. The transportation route passes through three cross-regional cloud-based checkpoints. The entire transportation process relies on the cloud-based checkpoint system for real-time monitoring of the transportation trajectory. The transport vehicles are equipped with BeiDou positioning devices, electronic seals, and compliant positioning terminals. Each cloud-based checkpoint is equipped with geomagnetic sensors and high-definition video surveillance equipment. Figure 1 As shown.

[0023] After the transport vehicle starts, the cloud checkpoint system automatically collects the vehicle's BeiDou positioning trajectory data and the vehicle passage time and location records of checkpoints A, B, and C, as well as related checkpoints along the route. First, the BeiDou positioning trajectory data is filtered, and duplicate records of all checkpoint passages are deduplicated. Then, both types of data are converted to a standard geographic coordinate system to ensure consistent location benchmarks. Subsequently, a comprehensive deviation anomaly judgment algorithm is used, with the formula: ,in This is the overall deviation value of the trajectory. This is the difference between the estimated checkpoint crossing time based on the vehicle's location trajectory and the actual checkpoint crossing time. This represents the average card processing time at this checkpoint. This refers to the straight-line distance deviation between the predicted checkpoint position of the vehicle's trajectory and the actual checkpoint position. This is the effective monitoring radius of the checkpoint. As time deviation weight, Using positional deviation as the weight, the processed trajectory data is compared with the checkpoint data, and it is ultimately determined that the vehicle's trajectory at checkpoint B is abnormal.

[0024] After determining the trajectory anomaly, the system first performs three pre-verification checks: retrieving the operation log of the geomagnetic sensor at checkpoint B and online data from the video surveillance equipment to confirm that the checkpoint equipment is fault-free and not offline; verifying the vehicle's electronic seal status data to confirm that no abnormal unlocking or alarm was triggered during the abnormal period; and retrieving the vehicle's real-time driving status data to confirm that the vehicle is not in a special state such as a breakdown stop or accident handling. All three checks pass. Because the transported goods are Class I hazardous chemicals, and the route includes multiple cross-regional checkpoints, the system dynamically adjusts the traceability scope, expanding the query span of historical location data and checkpoint records, and extending the traceability checkpoint data range to adjacent and related checkpoints at checkpoints A, B, and C. Then, the active traceability mechanism is formally triggered. Figure 2 As shown.

[0025] The system backtracks vehicle historical location data for the 72 hours prior to the occurrence of the abnormal trajectory, as well as vehicle passage records at checkpoints A, B, and C and adjacent related checkpoints. Data association is performed according to preset priorities, prioritizing the retrieval of all relevant checkpoint passage records and vehicle location trajectory data within one hour before and after the abnormal trajectory occurrence to achieve precise timeline alignment. Next, driver operation records and vehicle qualification validity data are retrieved and matched with the abnormal trajectory time point for verification. Finally, positioning device maintenance records and operation logs of relevant checkpoint devices are retrieved and cross-validated with periods of signal interruption and no checkpoint records in the abnormal trajectory. During the association process, three privacy protection measures are implemented: driver personal identity information and vehicle identification information are anonymized, retaining only the hash value of the operation time and qualification number; specific details of liquid chlorine transportation are anonymized, retaining only the risk level of Class I hazardous chemicals and the type of dangerous goods transportation. All data processing is completed at the edge nodes of the cloud checkpoint system, without uploading raw sensitive data to the cloud server. A root cause confidence calculation algorithm is also used, with the formula: ,in Root cause confidence The number of valid data types involved in the association. For the first Weights of class data For the first The degree of matching between class data and abnormal trajectories. For environmental correction items, the confidence level of the abnormal root cause is calculated by combining the weights and matching degrees of various related data.

[0026] A visual traceability report is generated based on all related data, clearly identifying the root cause of the abnormal trajectory as the driver temporarily deviating from the planned route to unload unrelated goods, with the root cause confidence level reaching a preset high confidence standard. The system directly pushes the traceability report to the joint transportation supervision and enforcement terminal in locations A, B, and C. Simultaneously, the report is automatically stored in the evidence chain database of the cloud checkpoint supervision system for subsequent supervision verification and enforcement evidence collection, such as... Figure 3 As shown.

[0027] Example 2 A logistics company undertakes local delivery services for ordinary daily necessities. The transportation route only includes two local, non-cross-regional cloud checkpoints. Vehicles are equipped with standard BeiDou positioning devices and electronic seals. Checkpoints D and E both have complete vehicle passage record collection and equipment status monitoring functions. The entire transportation process is monitored through a cloud checkpoint system. Figure 1 As shown.

[0028] After the vehicle departs, the cloud checkpoint system simultaneously collects the vehicle's BeiDou positioning trajectory data and the vehicle passage time and location records of checkpoints D and E. First, the BeiDou positioning trajectory data is filtered, and the vehicle passage records of checkpoints D and E are deduplicated. Then, the two types of data are uniformly converted into a standard geographic coordinate system to ensure that the location benchmark is consistent. The processed data is compared with the comprehensive deviation anomaly judgment algorithm, and finally it is determined that the vehicle's passage trajectory at checkpoint D is abnormal.

[0029] After determining the trajectory anomaly, the system initiates three pre-verification checks: first, it retrieves the operation logs of the geomagnetic sensor at checkpoint D and online data from the video surveillance equipment to confirm that the equipment is operating normally and not offline; second, it verifies the vehicle's electronic seal status data to confirm that there were no abnormal unlockings or alarms during the abnormal period; and third, it retrieves the vehicle's real-time driving status data to confirm that the vehicle is not in a special state such as a breakdown stop or accident handling. All three checks pass. Because the transported goods are ordinary goods and the route does not cross regional checkpoints, the system dynamically adjusts the traceability scope, narrowing the query span between historical location data and checkpoint records, and then triggers an active traceability mechanism, such as... Figure 2 As shown.

[0030] The system traces vehicle historical location data and vehicle passage records at checkpoints D and E within 72 hours prior to the occurrence of the abnormal trajectory. Data association is performed according to preset priorities, prioritizing the retrieval of vehicle passage records and vehicle location trajectory data at checkpoints D and E within one hour before and after the abnormal trajectory occurrence to achieve precise timeline alignment. Next, driver operation records and vehicle qualification validity data are retrieved and matched with the abnormal trajectory time point for verification. Finally, positioning device maintenance records and D and E checkpoint device operation logs are retrieved and cross-validated with the signal interruption period in the abnormal trajectory. Privacy protection measures are implemented during the association process, desensitizing driver personal information and vehicle identification information, retaining only the hash value of the operation time and qualification number. Specific transportation details for ordinary daily necessities are desensitized, retaining only the risk level and transportation type information for ordinary goods. All data processing is completed at the edge nodes of the cloud checkpoint system, without uploading raw sensitive data to the cloud. Simultaneously, a root cause confidence calculation algorithm is used, combining the weights and matching degrees of various data types to calculate the confidence of the abnormal root cause.

[0031] Based on the associated data, a visualized traceability report is generated, clearly identifying the root cause of the abnormal trajectory as a brief interference from surrounding electromagnetic signals on the positioning device, with the root cause confidence level failing to reach the preset high confidence standard. The system first pushes the traceability report to the logistics company's monitoring terminal, requiring the company to submit an explanation of the anomaly within a specified timeframe. After the company submits a detection report on the signal interference from the positioning device and a rectification commitment, the system pushes the traceability report and the company's explanation together to the local transportation monitoring terminal. Simultaneously, all relevant documents are automatically stored in the evidence chain database of the cloud checkpoint monitoring system for subsequent regulatory verification, such as... Figure 3 As shown.

[0032] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A transportation monitoring system based on location and checkpoint trajectory comparison, characterized in that, The system comprises the following components: a trajectory comparison module, an active source tracing triggering module, a multi-data association module, and a source tracing report generation module. The trajectory comparison module compares the satellite positioning trajectory data of the transport vehicle with the time and location records of the vehicle passing through the checkpoint, performs trajectory anomaly detection, and preprocesses the trajectory data; it then uses a comprehensive deviation anomaly detection algorithm to determine trajectory anomalies, with the following formula: ,in This is the overall deviation value of the trajectory. This is the difference between the estimated checkpoint crossing time based on the vehicle's location trajectory and the actual checkpoint crossing time. This represents the average card processing time at this checkpoint. This refers to the straight-line distance deviation between the predicted checkpoint position of the vehicle's trajectory and the actual checkpoint position. This is the effective monitoring radius of the checkpoint. As time deviation weight, As the position deviation weight, when At that time, it was determined to be an abnormal trajectory; The active tracing trigger module automatically triggers the active tracing mechanism when the trajectory comparison module determines that the trajectory is abnormal, and supports pre-triggered verification and dynamic adjustment of the tracing data range. The multi-data association module: traces back historical location data and corresponding checkpoint passage records within 72 hours prior to the occurrence of the abnormal trajectory of the transport vehicle, and simultaneously associates the transport vehicle's qualification information, cargo attribute information, driver operation records, and positioning device maintenance records. It employs a root cause confidence calculation algorithm, performs data association according to priority, and supports data privacy protection processing. The root cause confidence score of the abnormal trajectory is determined using the root cause confidence calculation algorithm, with the following formula: ,in For the root cause confidence level, The number of valid data types involved in the association. For the first Weights of class data For the first The degree of matching between class data and abnormal trajectories. For environmental correction items, when When this happens, the corresponding root cause is directly determined to be the core reason for the abnormal trajectory; The source tracing report generation module generates a visual source tracing report based on the associated data, clarifies the root cause type and confidence level of the abnormal trajectory, and supports the visual presentation, hierarchical push and storage of the report.

2. The transportation supervision system based on location and checkpoint trajectory comparison according to claim 1, characterized in that, Before performing trajectory comparison, the trajectory comparison module performs preprocessing steps on the trajectory data and checkpoint data: filtering the vehicle's BeiDou positioning trajectory data; deduplicating the vehicle passage record data at the checkpoint; and converting the processed location trajectory data and checkpoint data into a unified geographic coordinate system to ensure that the location reference of the data is consistent.

3. The transportation supervision system based on location and checkpoint trajectory comparison according to claim 1, characterized in that, Before triggering the source tracing mechanism, the active source tracing trigger module performs three pre-verification steps: retrieving the geomagnetic sensor operation log and video surveillance equipment online data of the checkpoint corresponding to the abnormal trajectory to confirm that the checkpoint equipment is not in a faulty or offline state; verifying the electronic seal status data of the transport vehicle to confirm that the electronic seal did not trigger abnormal unlocking or alarm during the period when the abnormal trajectory occurred; and retrieving the vehicle's real-time driving status data to confirm that the vehicle is not in a special state of fault parking or accident handling. The active source tracing mechanism is only triggered when all three verifications pass and the trajectory comparison module determines that the trajectory is abnormal.

4. The transportation monitoring system based on location and checkpoint trajectory comparison according to claim 1, characterized in that, The active traceability triggering module dynamically adjusts the historical data range of traceability based on the type of transported goods and the characteristics of the transport route: when the transported goods are Class I or Class II hazardous chemicals, the range of historical location data and checkpoint records for traceability is expanded; when the transported goods are ordinary goods, the range of historical data for traceability is narrowed; when the transport route includes multiple cross-regional checkpoints, the range of checkpoint data for traceability is expanded to the adjacent checkpoints of the corresponding checkpoints.

5. The transportation supervision system based on location and checkpoint trajectory comparison according to claim 1, characterized in that, When the multi-data association module performs data association, it follows the steps with a fixed priority: First, it retrieves the checkpoint vehicle passage records and vehicle location trajectory data within one hour before and after the abnormal trajectory occurred to achieve precise alignment of the timeline; second, it retrieves the vehicle driver operation records and vehicle qualification validity data to match and verify with the time point of the abnormal trajectory; finally, it retrieves the operation and maintenance records of the positioning device and the device operation log of the checkpoint to cross-verify with the time points of signal interruption and no record of passage through the checkpoint in the abnormal trajectory.

6. The transportation supervision system based on location and checkpoint trajectory comparison according to claim 1, characterized in that, When the multi-data association module performs data association, it executes three privacy protection steps: desensitizing the driver's personal identity information and the vehicle's specific identification information, retaining only the hash value of the operation time and qualification number used for association; desensitizing the specific details of the goods, retaining only the risk level and transportation type information of the goods; and completing all data association processing at the edge node of the transportation supervision system, without uploading the original sensitive data to the cloud server.

7. The transportation supervision system based on location and checkpoint trajectory comparison according to claim 1, characterized in that, After the traceability report generation module generates a visual traceability report, it will perform a tiered push procedure: if the root cause confidence level reaches the preset high confidence level standard, the traceability report will be directly pushed to the transportation supervision and law enforcement terminal in the corresponding area. If the root cause confidence level does not reach the high confidence level standard, the traceability report will first be pushed to the transportation company's regulatory terminal, requiring the company to submit an explanation of the anomaly. After the company submits the explanation, the report and explanation will be pushed to the regulatory terminal together. At the same time, all pushed reports will be automatically stored in the evidence chain database of the regulatory system for subsequent regulatory verification.

8. A transportation supervision method based on location and checkpoint trajectory comparison, applicable to the transportation supervision system based on location and checkpoint trajectory comparison as described in any one of claims 1-7, characterized in that, The specific steps of this method are as follows: Trajectory comparison steps: First, preprocess the satellite positioning trajectory data of the transport vehicle and the time and location records of the vehicle passing through the checkpoint. Then, use a custom trajectory anomaly detection algorithm to compare the preprocessed trajectory data with the checkpoint data to determine whether there is an abnormal trajectory. Active tracing triggering steps: If an abnormal trajectory is determined, first perform pre-verification of the status of checkpoint equipment, vehicle electronic seal status, and vehicle driving status, and then dynamically adjust the tracing data range according to the type of transported goods and the characteristics of the transport route to trigger the active tracing mechanism. Multi-data association steps: trace back the historical location data and corresponding checkpoint vehicle passage records within 72 hours before the time of the abnormal trajectory occurrence, associate the transport vehicle qualification information, cargo attribute information, driver operation records, and positioning device maintenance records according to preset priorities, calculate the root cause confidence using a custom root cause confidence calculation algorithm, and perform privacy protection processing on the associated data at the same time. Source tracing report generation steps: Generate a visual source tracing report based on the associated data, clarify the root cause type and confidence level of the abnormal trajectory, and then perform hierarchical push and tamper-proof storage operations on the source tracing report.

Images