Logistics freight vehicle transportation supervision system and method based on Internet of Things

Abstract

The invention discloses a logistics freight vehicle transportation supervision system and method based on the Internet of Things, and relates to the technical field of vehicle transportation supervision, the supervision system is constructed based on multi-source data fusion and hierarchical anomaly detection, and the problems of false data and signal interference which are difficult to identify in traditional supervision can be effectively solved; through multi-level comparison and block chain evidence storage, supervision blind areas caused by manual tampering or equipment faults are greatly reduced; meanwhile, the self-learning analysis module dynamically recognizes repeated or regular pseudo data, and by iteratively updating a threshold value and improving an early warning level, false alarms can be remarkably reduced, and accurate positioning of potential anomalies can be enhanced; the real-time performance and traceability of freight vehicle transportation supervision are improved, and the method has significant improvement value for the traditional mode which depends on a single data source and lacks a rapid verification mechanism.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle transportation supervision, and particularly to a logistics freight vehicle transportation supervision system and method based on the Internet of Things. Background Art

[0002] During the transportation supervision of freight vehicles, traditional means mostly rely on GPS, sensors or video surveillance to track the vehicle's movement, and then compare and review various data through a combination of manual and information systems; some means of evading dispatching use signal blind spots or equipment failures to cover up the true driving trajectory and even tamper with vehicle data, making it difficult for the supervision department to detect abnormalities in a timely manner; at the same time, sensors or GPS devices themselves also have problems such as accuracy errors, delays, and network environment limitations. If relying solely on a single data source, once the device fails or data is missing, some supervision areas will be missing.

[0003] To address the above problems, some existing solutions set a certain redundancy in the data source, collecting multiple sensor information and conducting time-sharing spot checks at the same time. However, such solutions are difficult to effectively prevent systematic forgery or deliberate interference in large-scale transportation; once suspicious data appears, it requires manual review item by item, which is time-consuming and laborious, and also causes intervention lag, unable to give timely warnings about potential risks; therefore, how to identify signal changes that do not conform to common sense in batch data and respond quickly has become a difficult problem that needs to be urgently solved in the current transportation supervision of freight vehicles. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] The present invention provides a logistics freight vehicle transportation supervision system and method based on the Internet of Things to solve the current freight vehicle transportation supervision solution, which has the problems that for suspicious data, it requires manual review item by item, is time-consuming and laborious, causes intervention lag, and is unable to give timely warnings about potential risks.

[0006] To solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides a logistics freight vehicle transportation supervision system based on the Internet of Things, which includes,

[0008] An on-vehicle information collection unit, arranged on the freight vehicle, for obtaining the vehicle's positioning coordinates, driving speed, and state sensing data in the vehicle chassis and engine compartment;

[0009] A monitoring platform, including:

[0010] A multi-source verification module, connected to the on-vehicle information collection unit, for comparing the positioning coordinates with real-time road network data and performing a first-level anomaly detection on the vehicle operation parameters and sensor data;

[0011] A distributed comparison module, connected to the multi-source verification module, is used to perform secondary verification on suspected abnormal data. The secondary verification combines weather information, video surveillance data, or road closure records provided by a third-party interface.

[0012] A data storage area is used to store data identified as high-risk abnormal by the distributed comparison module.

[0013] A blockchain recording module is used to perform non-tamperable log registration on the fields of high-risk abnormal data and push the log registration results to the vehicle liability entity and the regulatory department.

[0014] An abnormal alarm unit, connected to the blockchain recording module, when a high-risk abnormality is identified, outputs alarm information to the vehicle liability entity and the monitoring platform to achieve traceable full-process supervision.

[0015] As a preferred solution of the logistics freight vehicle transportation supervision system based on the Internet of Things according to the present invention, wherein: the vehicle-mounted information collection unit combines vehicle vibration, engine temperature, and electrical system data with the vehicle positioning coordinates to form combined data input, so that the multi-source verification module can judge the signal rationality from the aspect of vehicle movement rules and identify potential false data or interference signals from the aspect of vehicle component status.

[0016] As a preferred solution of the logistics freight vehicle transportation supervision system based on the Internet of Things according to the present invention, wherein: in the multi-source verification module, the method of comparing the positioning coordinates with the real-time road network data is as follows:

[0017] Compare the vehicle positioning coordinates with the real-time road network data to obtain a positioning error. The calculation formula is:

[0018]

[0019] Wherein, x represents the current abscissa of the vehicle, y represents the current ordinate of the vehicle, x r represents the expected abscissa of the road network, y r represents the expected ordinate of the road network, and E loc represents the positioning error;

[0020] Construct a running error index by comparing the vehicle running parameters with the sensor data. The calculation formula is:

[0021]

[0022] Wherein, v represents the current speed of the vehicle, θ represents the current heading angle of the vehicle, v r represents the expected speed of the road network, and θ r represents the expected heading angle of the road network, and E runIndicates the running error;

[0023] Construct a comprehensive error for the sensor data deviation, and the calculation formula is:

[0024]

[0025] Among them, ΔI represents the deviation between vehicle vibration and electrical system data, Δω represents the deviation of engine temperature, and S represents the comprehensive error of sensor data; the standard reference data based on vehicle vibration, electrical system data, and engine temperature deviation, and the reference value selected by the system comes from the average value or standard value obtained through calibration and long-term statistics when the equipment is in normal working condition; when the actual data deviates significantly from the reference value, the system will regard it as an abnormal signal, thereby triggering further detection and risk assessment;

[0026] Construct a comprehensive anomaly index by fusing error indicators, and the formula is:

[0027]

[0028] Among them, γ1 represents the positioning error weight, T loc represents the positioning tolerance threshold, γ2 represents the running error weight, T run represents the running tolerance threshold, γ3 represents the sensor data error weight, and F represents the comprehensive anomaly index.

[0029] As a preferred solution of the logistics freight vehicle transportation supervision system based on the Internet of Things described in the present invention, among them: in the multi-source verification module, the steps of performing the first-level anomaly detection on the vehicle operation parameters and sensor data are:

[0030] When the comprehensive anomaly index F exceeds the preset trigger threshold T F the system enters the secondary comparison process, and the calculation formula for the external information fusion index is: V = δ1·W + δ2·V m + δ3·D, where δ1 represents the weather impact weight, W represents the weather impact index, δ2 represents the video surveillance weight, V m represents the video surveillance matching degree index, δ3 represents the road closure weight, D represents the road closure matching index, and V represents the external information fusion index; the constraint conditions for the weights of each information in the multi-source data fusion are all determined by the normalization principle to determine the contribution of each data source in the comprehensive evaluation;

[0031] In addition, set the threshold T F as the threshold for the comprehensive anomaly index to trigger the secondary comparison, and T V as the reference threshold for judging anomalies of the external information fusion index.

[0032] As a preferred solution of the logistics freight vehicle transportation supervision system based on the Internet of Things according to the present invention, in the blockchain recording module, the high-risk abnormal data is stored as evidence;

[0033] Set the abnormal data fields to form a record vector R, R = (t, ID, F, V, η), where t represents the data acquisition time, ID represents the vehicle number, F represents the comprehensive abnormality index, V represents the external information fusion index, and η represents the additional comparison result or risk level; regarding the assignment rule of η, after the secondary comparison is completed, according to the abnormality degree of the comparison result, the result is divided into different risk levels; the system sets several threshold values based on historical detection data and expert experience. When the detection result falls into a certain interval, a predefined risk level is correspondingly assigned. If it is lower than the preset standard, it is determined as low risk, and if it is higher than the preset standard, it is determined as high risk;

[0034] Use the cryptographic hash function to calculate the digest of the record vector. The formula is: H = h(R), where H represents the hash value of the recorded data, h(·) represents the cryptographic hash SHA-256 function, and R is the aforementioned record vector;

[0035] Form the blockchain transaction record with the hash value and other information. The formula is:

[0036] T = {H, σ, Δ},

[0037] where T represents the blockchain transaction record, σ represents the digital signature, which is used to prove the identity of the record sender, Δ represents the transaction timestamp, which records the specific time of this transaction on the blockchain. Once the transaction record T is written into the blockchain, it forms an immutable log registration.

[0038] As a preferred solution of the logistics freight vehicle transportation supervision system based on the Internet of Things according to the present invention, in the blockchain recording module, after the evidence storage is completed, the contract automation logic triggers the alarm push according to the preset conditions. Let the current transaction confirmation number be C. When C ≥ C min At this time, the system automatically generates an alarm message A through the smart contract. A = Alert(ID, H, τ), where C represents the confirmation number of the current transaction, C min represents the minimum confirmation number required to trigger the alarm, A represents the alarm message, Alert(·) represents the alarm generation function, ID represents the vehicle number, H represents the evidence storage hash value, and τ represents the alarm generation time. The smart contract automatically calls the alarm push mechanism after meeting the conditions and pushes the generated A to the vehicle responsible entity and the supervision department to realize the full-link data supervision.

[0039] As a preferred solution of the logistics freight vehicle transportation supervision system based on the Internet of Things according to the present invention, wherein: the monitoring platform further includes a self-learning analysis module for automatically updating the recognition threshold after recording multiple anomalies;

[0040] When repeated or regular abnormal data is found, the warning level is raised and the vehicle abnormal information is sent to an authorized insurance institution or other third-party entity for taking more stringent risk control measures for relevant vehicles and forming a basis for subsequent audits.

[0041] As a preferred solution of the logistics freight vehicle transportation supervision system based on the Internet of Things according to the present invention, wherein: in the self-learning analysis module, the abnormal data recorded within a predetermined time window is statistically analyzed, and the set of its comprehensive abnormal indicators is denoted as wherein, F i represents the comprehensive abnormal indicator at the i-th anomaly, and N represents the total number of anomaly records within this time window;

[0042] The module calculates the mean and standard deviation of the abnormal data. The mean calculation formula is:

[0043]

[0044] wherein, represents the average value of the abnormal indicators, N represents the number of abnormal records, and F i represents the comprehensive abnormal indicator at the i-th anomaly;

[0045] The standard deviation calculation formula is:

[0046]

[0047] wherein, σ F represents the standard deviation of the abnormal indicators;

[0048] When the conditions N≥N min and σ F <∈ are satisfied, the system determines that there are repeated or regular false data. Among them, N min is the minimum number of records for determining repeated anomalies, and ∈ is the standard deviation threshold for determining data consistency. At this time, it is considered that the change range of the abnormal data is small, indicating that there may be systematic anomalies or false data.

[0049] As a preferred solution of the logistics freight vehicle transportation supervision system based on the Internet of Things according to the present invention, wherein: in the self-learning analysis module, a threshold iteration mechanism is adopted to update the original recognition threshold T F , and the update formula is:

[0050]

[0051] wherein, TF represents the original recognition threshold, and β is the learning rate parameter, is the updated recognition threshold, is the mean value of historical anomaly indicators;

[0052] When detecting repeated or regular abnormal data, the alarm level is increased according to the warning mechanism. The alarm level update formula is: L new = L old + ΔL, where L old represents the current warning level, ΔL is the increase in the warning level, and L new is the updated warning level. The smart contract or automation logic triggers a higher-level risk prompt according to this formula and synchronously pushes it to the relevant responsible parties and regulatory departments.

[0053] In the second aspect, the present invention provides a method for supervising the transportation of logistics freight vehicles based on the Internet of Things, including,

[0054] Step S1, obtaining the positioning coordinates, driving speed, and in-vehicle and out-of-vehicle sensing data of the freight vehicle;

[0055] Step S2, comparing the positioning coordinates with the real-time road network information, and comparing the in-vehicle sensing data with the vehicle operating state to obtain the first-level anomaly detection result and mark the suspected abnormal data;

[0056] Step S3, for the marked suspected abnormal data, perform secondary verification in combination with the weather, video, or road closure records provided by the third-party interface. If there are contradictions in the secondary verification, it is determined as a high-risk anomaly;

[0057] Step S4, write the acquisition time, vehicle number, and comparison result corresponding to the high-risk anomaly into the data storage area and perform an immutable log registration;

[0058] Step S5, according to the log registration result, trigger vehicle alarms and anomaly notifications, push corresponding information to the staff, and form a traceable full-process supervision record in the monitoring platform.

[0059] The beneficial effects of the present invention are as follows: The present invention constructs a supervision system based on multi-source data fusion and hierarchical anomaly detection, which can effectively address the problems of false data and signal interference that are difficult to identify in traditional supervision; through multi-level comparison and blockchain evidence storage, the supervision blind spots caused by human tampering or equipment failures are greatly reduced; at the same time, the self-learning analysis module dynamically identifies repeated or regular false data, and by iteratively updating the threshold and increasing the warning level, false alarms can be significantly reduced and the accurate positioning of potential anomalies can be strengthened; it improves the real-time performance and traceability of the supervision of freight vehicle transportation, and has significant improvement value for the existing traditional mode that relies on a single data source and lacks a fast verification mechanism. Description of the Drawings

[0060] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0061] Figure 1 It is a schematic diagram of the framework of the logistics freight vehicle transportation supervision system based on the Internet of Things in Embodiment 1.

[0062] Figure 2 It is a schematic diagram of the process of the logistics freight vehicle transportation supervision method based on the Internet of Things in Embodiment 1. Specific Embodiments

[0063] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following will make a detailed description of the specific embodiments of the present invention in conjunction with the drawings of the specification.

[0064] In the following description, many specific details are set forth in order to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0065] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that can be included in at least one implementation manner of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment that is mutually exclusive with other embodiments.

[0066] Embodiment 1, referring to Figure 1 and Figure 2 , this embodiment provides a logistics freight vehicle transportation supervision system based on the Internet of Things, including:

[0067] An on-vehicle information collection unit, deployed on the freight vehicle, for obtaining the positioning coordinates, driving speed of the vehicle, and status sensing data in the vehicle chassis and engine compartment;

[0068] The on-vehicle information collection unit combines the vehicle vibration, engine temperature, and electrical system data with the vehicle positioning coordinates to form a combined data input, enabling the multi-source verification module to judge the signal rationality from the aspect of the vehicle movement law and identify potential false data or interference signals from the aspect of the vehicle component status;

[0069] A monitoring platform, including:

[0070] A multi-source verification module, connected to the vehicle information collection unit, is used to compare the positioning coordinates with the real-time road network data and perform a first-level anomaly detection on the vehicle operation parameters and sensor data;

[0071] A distributed comparison module, connected to the multi-source verification module, is used to perform secondary verification on the suspected abnormal data. The secondary verification combines the weather information, video surveillance data or road closure records provided by the third-party interface;

[0072] A data storage area is used to store the data identified as high-risk anomalies by the distributed comparison module;

[0073] A blockchain recording module is used to perform an immutable log registration on the fields of the high-risk anomaly data and push the log registration results to the vehicle responsible entity and the regulatory department;

[0074] In the multi-source verification module, the method of comparing the positioning coordinates with the real-time road network data is as follows:

[0075] Compare the vehicle positioning coordinates with the real-time road network data to obtain a positioning error. The calculation formula is:

[0076]

[0077] where x represents the current abscissa of the vehicle, y represents the current ordinate of the vehicle, x r represents the expected abscissa of the road network, y r represents the expected ordinate of the road network, E loc represents the positioning error;

[0078] Construct an operation error index for the comparison of the vehicle operation parameters and sensor data. The calculation formula is:

[0079]

[0080] where v represents the current speed of the vehicle, θ represents the current heading angle of the vehicle, v r represents the expected speed of the road network, θ r represents the expected heading angle of the road network, E run represents the operation error;

[0081] Construct a comprehensive error for the sensor data deviation. The calculation formula is:

[0082]

[0083] Among them, ΔI represents the deviation between vehicle vibration and electrical system data, Δω represents the deviation of engine temperature, and S represents the comprehensive error of sensor data; the standard reference data for vehicle vibration, electrical system data, and engine temperature deviation, and the reference values selected by the system are the average values or standard values obtained through calibration and long-term statistics when the equipment is in normal working condition; when the actual data deviates significantly from the reference value, the system will regard it as an abnormal signal, thus triggering further detection and risk assessment;

[0084] The fusion error index constructs a comprehensive anomaly index, and the formula is:

[0085]

[0086] Among them, γ1 represents the positioning error weight, T loc represents the positioning tolerance threshold, γ2 represents the running error weight, T run represents the running tolerance threshold, γ3 represents the sensor data error weight, and F represents the comprehensive anomaly index;

[0087] In the multi-source verification module, the steps for the first-level anomaly detection of vehicle operating parameters and sensor data are as follows:

[0088] When the comprehensive anomaly index F exceeds the preset trigger threshold T F the system enters the secondary comparison process, and the calculation formula for the external information fusion index is: V = δ1·W + δ2·V m + δ3·D, where δ1 represents the weather influence weight, W represents the weather influence index, δ2 represents the video monitoring weight, V m represents the video monitoring matching degree index, δ3 represents the road closure weight, D represents the road closure matching index, and V represents the external information fusion index; the constraint conditions for the weights of each information in the multi-source data fusion all adopt the normalization principle to determine the contribution of each data source in the comprehensive evaluation;

[0089] In addition, set the threshold T F as the threshold for the comprehensive anomaly index to trigger the secondary comparison, and T V as the reference threshold for judging anomalies of the external information fusion index;

[0090] Specifically, construct the positioning error, running error, and comprehensive error of sensor data to realize the preliminary fusion and anomaly judgment of multi-source data. Each error index forms a comprehensive anomaly index after normalization and weighting processing, which can timely reflect the inconsistency between data. When this index exceeds the set threshold, the system automatically triggers the secondary comparison and uses external information to further verify the data accuracy, effectively reducing the risks brought by data false differences and interference;

[0091] In the blockchain recording module, store evidence for high-risk abnormal data;

[0092] Set the abnormal data fields to form a record vector R, R = (t, ID, F, V, η), where t represents the data collection time, ID represents the vehicle number, F represents the comprehensive abnormal index, V represents the external information fusion index, and η represents the additional comparison result or risk level; regarding the assignment rule of η, after the secondary comparison is completed, according to the degree of abnormality of the comparison result, the result is divided into different risk levels; the system sets several threshold values based on historical detection data and expert experience. When the detection result falls into a certain interval, a predefined risk level is assigned correspondingly. If it is lower than the preset standard, it is determined as a low risk, and if it is higher than the preset standard, it is determined as a high risk;

[0093] Use an encryption hash function to calculate the digest of the record vector. The formula is: H = h(R), where H represents the hash value of the record data, h(·) represents the encryption hash SHA-256 function, and R is the aforementioned record vector;

[0094] Construct a blockchain transaction record by combining the hash value with other information. The formula is:

[0095] T = {H, σ, Δ},

[0096] where T represents the blockchain transaction record, σ represents the digital signature, which is used to prove the identity of the record sender, and Δ represents the transaction timestamp, which records the specific time of this transaction on the blockchain. Once the transaction record T is written into the blockchain, it forms an immutable log registration;

[0097] In the blockchain record module, after the evidence storage is completed, the contract automation logic triggers the alarm push according to the preset conditions. Let the current number of transaction confirmations be C. When C ≥ C min At this time, the system automatically generates an alarm message A through the smart contract. A = Alert(ID, H, τ), where C represents the current number of transaction confirmations, C min represents the minimum number of confirmations required to trigger the alarm, A represents the alarm message, Alert(·) represents the alarm generation function, ID represents the vehicle number, H represents the evidence storage hash value, and τ represents the alarm generation time. The smart contract automatically calls the alarm push mechanism after meeting the conditions and pushes the generated A to the vehicle responsible entity and the regulatory department to achieve full-link data supervision;

[0098] Specifically, here a complete process of blockchain evidence storage and alarm push is constructed. By forming a record vector from the key abnormal data fields, then using an encryption hash function to generate an immutable digest, and saving it in the form of a blockchain transaction record, the authenticity and integrity of the data are guaranteed; at the same time, the smart contract automatically generates and pushes the alarm message according to the preset confirmation number conditions to achieve timely response to data anomalies;

[0099] The monitoring platform also includes a self-learning analysis module that automatically updates the recognition threshold after recording multiple anomalies;

[0100] When repeated or regular abnormal data is found, the warning level is raised and the vehicle abnormality information is sent to authorized insurance institutions or other third-party entities for taking more stringent risk control measures for the relevant vehicles and forming the basis for subsequent audits;

[0101] In the self-learning analysis module, the abnormal data recorded within the predetermined time window is counted, and the comprehensive abnormal index set is recorded as Among them, F i represents the comprehensive abnormality index at the time of the i-th abnormality, and N represents the total number of abnormal records in the time window;

[0102] The module calculates the mean and standard deviation of abnormal data. The mean calculation formula is:

[0103]

[0104] in, represents the average value of the abnormal index, N represents the number of abnormal records, F i represents the comprehensive abnormality index of the i-th abnormality;

[0105] The formula for calculating standard deviation is:

[0106]

[0107] Among them, σ F represents the standard deviation of the abnormal indicator;

[0108] When the condition N≥N is met min And σ F <∈, the system determines that there is repeated or regular pseudo data, where N min is the minimum number of records to determine repeated anomalies, ∈ is the standard deviation threshold for determining data consistency. At this time, it is considered that the change amplitude of the abnormal data is small, indicating that there may be systematic anomalies or false data;

[0109] In the self-learning analysis module, the threshold iteration mechanism is used to update the original recognition threshold T F , the update formula is:

[0110]

[0111] Among them, T F represents the original recognition threshold, β is the learning rate parameter, is the updated recognition threshold, is the mean of historical abnormal indicators;

[0112] When duplicate or regular abnormal data is detected, the warning level is increased according to the warning mechanism. The warning level update formula is: L new = L old + ΔL, where L old represents the current warning level, ΔL is the increase in the warning level, and L new is the updated warning level. The smart contract or automated logic triggers a higher-level risk warning according to this formula and synchronously pushes it to the relevant responsible parties and regulatory authorities;

[0113] Specifically, the function of the system to adaptively adjust the recognition threshold is realized here. By analyzing the mean and standard deviation of historical abnormal data, the repeatability and consistency of the data are captured. When the number of abnormal records reaches the preset threshold and the data fluctuation is small, the threshold is automatically adjusted and the warning level is increased, effectively reducing the risk of misjudgment and timely identifying potential false data;

[0114] The abnormal warning unit is connected to the blockchain record module. When a high-risk abnormality is identified, it outputs a warning message to the vehicle responsible party and the monitoring platform, realizing traceable whole-process supervision.

[0115] This embodiment also provides a supervision method for the above-mentioned logistics freight vehicle transportation supervision system based on the Internet of Things, including:

[0116] Step S1, obtaining the positioning coordinates, driving speed, and in-vehicle and out-of-vehicle sensing data of the freight vehicle;

[0117] Step S2, comparing the positioning coordinates with the real-time road network information, and comparing the in-vehicle sensing data with the vehicle operation status to obtain the first-level abnormal detection result and mark the suspected abnormal data;

[0118] Step S3, for the marked suspected abnormal data, perform secondary verification in combination with the weather, video, or road closure records provided by the third-party interface. If there are contradictions in the secondary verification, it is determined as a high-risk abnormality;

[0119] Step S4, write the acquisition time, vehicle number, and comparison result corresponding to the high-risk abnormality into the data storage area and perform an immutable log registration;

[0120] Step S5, according to the log registration result, trigger vehicle warnings and abnormal notifications, push the corresponding information to the staff, and form a traceable whole-process supervision record in the monitoring platform.

[0121] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. A logistics freight vehicle transportation supervision system based on the Internet of Things, characterized in that: including, a vehicle-mounted information collection unit, arranged on a freight vehicle, for obtaining the positioning coordinates, driving speed of the vehicle, and status sensing data in the vehicle chassis and engine compartment; a monitoring platform, including: a multi-source verification module, connected to the vehicle-mounted information collection unit, for comparing the positioning coordinates with real-time road network data, and performing a first-level anomaly detection on vehicle operation parameters and sensor data; a distributed comparison module, connected to the multi-source verification module, for performing a secondary verification on suspected abnormal data, and the secondary verification combines weather information, video surveillance data or road closure records provided by a third-party interface; a data storage area, for storing data identified as high-risk anomalies by the distributed comparison module; a blockchain recording module, for performing an immutable log registration on the fields of high-risk anomaly data, and pushing the log registration result to the vehicle liability entity and the regulatory department; an anomaly warning unit, connected to the blockchain recording module, when a high-risk anomaly is identified, outputs a warning message to the vehicle liability entity and the monitoring platform.

2. The logistics freight vehicle transportation supervision system based on the Internet of Things according to claim 1, characterized in that: The vehicle-mounted information collection unit combines vehicle vibration, engine temperature, and electrical system data with the vehicle positioning coordinates to form a combined data input.

3. The logistics freight vehicle transportation supervision system based on the Internet of Things according to claim 1, characterized in that: In the multi-source verification module, the method of comparing the positioning coordinates with real-time road network data is: Compare the vehicle positioning coordinates with real-time road network data to obtain a positioning error, and the calculation formula is: Among them, x represents the current abscissa of the vehicle, y represents the current ordinate of the vehicle, x r represents the expected abscissa of the road network, y r represents the expected ordinate of the road network, E loc represents the positioning error; Construct an operation error index for comparing vehicle operation parameters and sensor data, and the calculation formula is: Among them, v represents the current vehicle speed, θ represents the current vehicle heading angle, v r represents the expected road network speed, θ r represents the expected road network heading angle, E run represents the running error; Construct a comprehensive error for sensor data deviation, and the calculation formula is: where, ΔI represents the deviation between vehicle vibration and electrical system data, Δω represents the engine temperature deviation, and S represents the comprehensive error of sensor data; Fuse the error index to construct a comprehensive anomaly index, and the formula is: Among them, γ1 represents the positioning error weight, and T loc represents the positioning tolerance threshold, γ2 represents the running error weight, and T run represents the running tolerance threshold, γ3 represents the sensor data error weight, and F represents the comprehensive anomaly index.

4. The logistics freight vehicle transportation supervision system based on the Internet of Things according to claim 3, characterized in that: In the multi-source verification module, the steps of performing a first-level anomaly detection on vehicle operation parameters and sensor data are: When the comprehensive anomaly index F exceeds the preset trigger threshold T F the system enters the secondary comparison process, and the calculation formula for the external information fusion index is: V = δ1·W + δ2·V m + δ3·D, where δ1 represents the weather impact weight, w represents the weather impact index, δ2 represents the video surveillance weight, V m represents the video surveillance matching degree index, δ3 represents the road closure weight, D represents the road closure matching index, and V represents the external information fusion index; In addition, a threshold value T is set F as the threshold for triggering a secondary comparison for the comprehensive anomaly index.

5. The logistics freight vehicle transportation supervision system based on the Internet of Things according to claim 1, characterized in that: In the blockchain recording module, perform evidence preservation on high-risk anomaly data; Set the abnormal data fields to form a record vector R, R = (t, ID, F, V, η), where, t represents the data collection time, ID represents the vehicle number, F represents the comprehensive anomaly index, V represents the external information fusion index, and η represents the additional comparison result or risk level; Use an encryption hash function to calculate the digest of the record vector, and the formula is: H = h(R), where, H represents the hash value of the record data, h(·) represents the encryption hash SHA-256 function, and R is the aforementioned record vector; Construct a blockchain transaction record with the hash value and other information, and the formula is: T = {H, σ, Δ}, where, T represents the blockchain transaction record, σ represents the digital signature, used to prove the identity of the record sender, and Δ represents the transaction timestamp, recording the specific time of this transaction on the blockchain.

6. The logistics freight vehicle transportation supervision system based on the Internet of Things according to claim 5, characterized in that: In the blockchain recording module, after the deposit is completed, the contract automation logic triggers an alarm push according to preset conditions. Let the current number of transaction confirmations be C. When C ≥ C min is satisfied, the system automatically generates an alarm message A through the smart contract. A = Alert(ID, H, τ), where C represents the number of confirmations of the current transaction, C min represents the minimum number of confirmations required to trigger the alarm, A represents the alarm message, Alert(·) represents the alarm generation function, ID represents the vehicle number, H represents the deposit hash value, and τ represents the alarm generation time. After the conditions are met, the smart contract automatically calls the alarm push mechanism to push the generated A to the vehicle liability entity and the regulatory department.

7. The logistics freight vehicle transportation supervision system based on the Internet of Things according to claim 1, wherein: The monitoring platform further includes a self-learning analysis module, for automatically updating the recognition threshold after recording multiple anomalies; When repeated or regular abnormal data is found, raise the warning level.

8. The logistics freight vehicle transportation supervision system based on the Internet of Things according to claim 7, characterized in that: In the self-learning analysis module, the abnormal data recorded within a predetermined time window is statistically analyzed, and the set of comprehensive abnormal indexes is denoted as where F i represents the comprehensive abnormal index at the i-th abnormality, and N represents the total number of abnormal records within this time window; The module calculates the mean and standard deviation of the abnormal data, and the mean calculation formula is: Among them, represents the average value of abnormal indicators, N represents the number of abnormal records, and F i represents the comprehensive abnormal indicator of the i-th anomaly; The standard deviation calculation formula is: Among them, σ F represents the standard deviation of the abnormal index; When the condition N≥N is satisfied min and σ F <∈, the system determines that there are duplicate or regular pseudo - data. Among them, N min is the minimum number of records for determining duplicate anomalies, and ∈ is the standard - deviation threshold for determining data consistency. At this time, it is considered that the change range of the abnormal data is small, indicating that there may be systematic anomalies or pseudo - data.

9. The logistics freight vehicle transportation supervision system based on the Internet of Things according to claim 8, characterized in that: In the self-learning analysis module, a threshold iteration mechanism is adopted to update the original recognition threshold T F , and the update formula is as follows: Among them, T F represents the original recognition threshold, β is the learning rate parameter, is the updated recognition threshold, is the mean value of historical anomaly indicators; When duplicate or regular abnormal data is detected, the warning level is increased according to the warning mechanism. The warning level update formula is: L new = L old + ΔL, where L old represents the current warning level, ΔL is the increase in the warning level, and L new is the updated warning level.

10. A transportation supervision method for logistics freight vehicles based on the Internet of Things, based on the transportation supervision system for logistics freight vehicles based on the Internet of Things according to any one of claims 1 to 9, characterized in that, including: Step S1: Obtain the positioning coordinates, driving speed, and in-vehicle and out-of-vehicle sensing data of the freight vehicle; Step S2: Compare the positioning coordinates with the real-time road network information, and compare the in-vehicle sensing data with the vehicle operation status to obtain the anomaly detection results at the first level and mark the suspected abnormal data; Step S3: For the marked suspected abnormal data, conduct secondary verification in combination with the weather, video, or road closure records provided by the third-party interface. If there are contradictions in the secondary verification, it is determined as a high-risk anomaly; Step S4: Write the acquisition time, vehicle number, and comparison results corresponding to the high-risk anomaly into the data storage area and perform an immutable log registration; Step S5: According to the log registration results, trigger vehicle alarms and anomaly notifications, push the corresponding information to the staff, and form a traceable full-process supervision record in the monitoring platform.

Images