Transportation driver and vehicle association and management method and system based on two-dimensional code

Abstract

The invention discloses a transportation driver and vehicle association and management method and system based on a two-dimensional code, and relates to the technical field of transportation management. Efficient binding and dynamic association of vehicle and driver information are achieved through the two-dimensional code technology and the Hash algorithm, the problems of information dispersion and updating lag in traditional management are solved, abnormal behaviors in the transportation process can be monitored in real time and early warning signals can be generated in combination with real-time data synchronization and an anomaly detection algorithm, and the safety of the transportation process is improved. In addition, through data aggregation and analysis of early warning records, a comprehensive management data set and a visual report form are generated, accurate decision support is provided for managers, resource configuration is optimized, and the efficiency and the refinement level of transportation management are comprehensively improved.

Description

Technical Field

[0001] This invention relates to the field of transportation management technology, specifically to a method and system for linking and managing transport drivers and vehicles based on QR codes. Background Technology

[0002] Transportation management is a core component of modern logistics, crucial for improving efficiency, ensuring safety, and reducing costs. With the rapid development of the logistics industry, the management needs of transport vehicles and drivers are becoming increasingly complex. Traditional management methods are no longer sufficient to meet the demands for efficiency and accuracy. Currently, vehicle and driver management methods that rely on paper documents or simple spreadsheets generally suffer from problems such as delayed information updates, isolated data, and low efficiency of manual verification. These limitations lead to cumbersome management processes and make it difficult to monitor vehicle status and driver behavior in real time, thereby affecting transportation safety and efficiency.

[0003] Against this backdrop, the core challenge facing transportation management is how to achieve dynamic correlation and real-time interaction of vehicle and driver information. First, vehicle and driver information is stored in a scattered manner, lacking a unified digital entry point, which makes the binding and verification process time-consuming and error-prone. This information fragmentation further leads to the inefficiency of data interaction, making it impossible to obtain real-time vehicle driving status, driver behavior, or cargo information, thus limiting the management platform's ability to provide timely risk warnings. In addition, the lag in data analysis also stems from this, making it difficult for managers to generate accurate performance evaluations or risk predictions based on real-time data, affecting decision-making efficiency. Summary of the Invention

[0004] The purpose of this invention is to provide a method and system for the association and management of transport drivers and vehicles based on QR codes. By utilizing QR code technology, dynamic association and real-time interaction of vehicle and driver information are achieved. Through real-time monitoring and early warning, transportation safety is ensured, and the efficiency and precision of transportation management are improved.

[0005] The objective of this invention can be achieved through the following technical solutions:

[0006] This application provides a method for associating and managing transport drivers and vehicles based on QR codes, including the following steps:

[0007] Based on the structured dataset, a unique identifier is generated using a hash algorithm to obtain a set of vehicle-driver binding identifiers. Then, a QR code generation algorithm is used to encode each binding identifier into a dynamic QR code, generating a set of dynamic QR code images.

[0008] The dynamic QR code image set is pushed to the transportation management terminal through the mobile application interface. The QR code data is protected by an encrypted transmission protocol, resulting in a QR code dataset that can be scanned on the mobile device.

[0009] When scanning a QR code on a mobile device, the QR code data uploaded by the scanning device is obtained, and a decoding algorithm is used to extract the binding identifier and timestamp to obtain the verified binding identifier.

[0010] Based on the verified binding identifier, the corresponding vehicle-driver association data is retrieved from the transportation management system database. Real-time data synchronization technology is used to update the vehicle location, driver behavior, and cargo status to obtain a real-time transportation status dataset.

[0011] Based on the real-time transportation status dataset, anomaly detection algorithms are used to analyze vehicle trajectory deviation and driver fatigue driving abnormal behavior to obtain a risk warning dataset.

[0012] Based on the risk warning dataset, data push technology is used to transmit warning signals to the management terminal via a mobile application interface to obtain a real-time warning record set.

[0013] Based on the real-time early warning record set, data aggregation technology is used to integrate vehicle-driver related data, transportation status, and early warning logs to obtain a comprehensive management dataset.

[0014] Furthermore, the vehicle-driver binding identifier set is obtained, specifically including:

[0015] Obtain a structured dataset, extract the vehicle number and driver identity fields from it, generate input parameter pairs, and mark the input parameter pair as invalid if the vehicle number or driver identity field is missing and discard it to obtain a set of valid input parameter pairs.

[0016] The set of valid input parameters is processed by a hash function H(v,d) to generate a fixed-length unique identifier. The hash function is then used to process the data to obtain a set of unique identifiers corresponding to each vehicle number and driver identity.

[0017] Based on the unique identifier set, a vehicle-driver binding identifier is generated and stored in the binding identifier set. If there are duplicate identifiers in the binding identifier set, the identifier values ​​are compared, the newly generated identifier is retained, and the old identifiers are discarded to obtain the deduplicated binding identifier set.

[0018] Based on the deduplicated set of binding identifiers, obtain the generation timestamp of each binding identifier, append it to the binding identifier record, and then sort it by timestamp to obtain a set of binding identifiers arranged in chronological order;

[0019] From the set of binding identifiers arranged in chronological order, extract the vehicle number and driver identity corresponding to each binding identifier to generate a binding relationship record. If the binding relationship record does not conform to the preset business rules, it is marked as an abnormal record and discarded to obtain a set of binding relationship records that conform to the rules.

[0020] Based on the set of binding relationship records that meet the rules, the final vehicle-driver binding identifier dataset is generated. Then, the dataset is validated to determine its integrity, and the validated binding identifier dataset is obtained.

[0021] Data storage tools are used to save the verified binding identifier dataset to the database. The database index is used to determine whether the storage was successful, and a persistent vehicle-driver binding identifier dataset is obtained.

[0022] Furthermore, a dynamic set of QR code images is generated, specifically including:

[0023] Obtain the set of vehicle-driver binding identifiers, extract each binding identifier from it, generate data input containing vehicle identifier and driver identifier, and then use a QR code generation algorithm to encode each binding identifier, embed a timestamp t and a check bit c to generate a dynamic QR code, where the timestamp t represents the generation time, and the check bit c is calculated by the hash function H(b,t), where b is the binding identifier;

[0024] If the verification bit c of the dynamic QR code matches the expected value, the dynamic QR code is stored as the first image; if they do not match, the QR code is discarded and regenerated.

[0025] The first image is compressed using image processing technology to generate the second image while maintaining the readability of the QR code. Then, based on the second image, it is archived into an image collection using a file storage system to generate a unique file identifier.

[0026] When the file identifier in the image set matches the binding identifier, the dynamic QR code generation is confirmed to be complete, the image set is output, and each dynamic QR code in the image set is decoded by the verification algorithm to extract the timestamp t and check bit c, and the validity of the binding identifier is judged to obtain the verification result.

[0027] Furthermore, the verified binding identifier includes:

[0028] The system acquires QR code data collected by a scanning device on a mobile device, preprocesses the QR code image using image processing technology to obtain clear QR code data, and then extracts the binding identifier and timestamp from the clear QR code data using a decoding algorithm to obtain the extracted binding identifier and timestamp data.

[0029] Based on the extracted timestamp and the current time, the difference between the two is calculated to obtain time difference data. When the time difference data is less than a preset threshold, the QR code is determined to be valid, and a valid binding identifier is obtained.

[0030] The valid binding identifier is encrypted using an encryption algorithm to obtain encrypted binding identifier data. Then, the encrypted binding identifier data is matched with a pre-established database to obtain the corresponding user identity information and obtain the verified identity identifier.

[0031] Based on the verified identity, a binding confirmation message is generated, resulting in the final business binding result.

[0032] Furthermore, a real-time transportation status dataset is obtained, specifically including:

[0033] Using real-time data synchronization technology, location information is obtained from vehicle positioning devices, the location field in vehicle data is updated, and a real-time vehicle location dataset is obtained. Then, behavioral data is obtained through driver behavior monitoring devices. When the behavioral data exceeds a preset threshold, it is marked as abnormal behavior, and a driver behavior analysis dataset is obtained.

[0034] Cargo status information is obtained from cargo sensors, and combined with location information and behavioral data to determine whether the cargo status is normal, thus obtaining a cargo status analysis dataset.

[0035] Based on the vehicle location dataset, behavior analysis dataset, and cargo status analysis dataset, data fusion processing is performed to generate a real-time transportation status dataset.

[0036] Based on the real-time transportation status dataset, a time series analysis algorithm is used to analyze the changing trend of transportation status, obtain a transportation status trend dataset, and then determine whether there are any abnormalities in the transportation process. If there are abnormalities, an abnormality alarm message is generated, and the transportation abnormality detection result is obtained.

[0037] Furthermore, a risk warning dataset is obtained, specifically including:

[0038] Based on the real-time transportation status dataset, the isolated forest algorithm is used for analysis to calculate the abnormal behavior scores of vehicle trajectory deviation and driver fatigue driving, and obtain an abnormal score set. When the scores in the abnormal score set exceed the preset threshold A, a risk warning signal is generated, and a warning signal set is obtained.

[0039] Based on the early warning signal set, time series analysis technology is used to identify the persistence and frequency of abnormal behavior to obtain abnormal behavior patterns. Then, based on the abnormal behavior patterns, cluster analysis technology is used to group similar abnormal behaviors to obtain an abnormal behavior classification set.

[0040] The classification results are obtained from the abnormal behavior classification set to generate a risk warning dataset containing the abnormality type and risk level.

[0041] Furthermore, a set of real-time early warning records is obtained, specifically including:

[0042] Raw data is obtained from the risk warning dataset, and the data is preprocessed using data push technology to obtain a standardized dataset. When there are outliers in the standardized dataset, the outlier type is determined by an anomaly detection algorithm to obtain the anomaly classification result.

[0043] Based on the anomaly classification results, the warning signal is transmitted to the mobile application using the application programming interface, and a transmission completion signal is obtained.

[0044] When the mobile application receives the transmission completion signal, the management terminal generates an early warning log containing the anomaly type, occurrence time and geographical location, obtains the log record, and then uses a real-time update mechanism to store the log record into a record set, thus obtaining a real-time early warning record set;

[0045] The latest records are retrieved from the real-time early warning record set, and the early warning information is transmitted to the management terminal through a push notification mechanism to obtain the final early warning output. When the final early warning output contains high-priority anomalies, the instant alarm mechanism is triggered through the application programming interface to obtain an alarm confirmation signal.

[0046] Furthermore, a comprehensive management dataset is obtained, specifically including:

[0047] The real-time early warning record set is obtained, and data cleaning technology is used to remove duplicate records and missing values ​​to obtain a cleaned record set. Then, the cleaned record set is grouped by clustering algorithm, and a classification dataset is generated based on vehicle association and driver association.

[0048] When the transportation status records in the classification dataset are complete, the weighted average method is used to calculate the transportation efficiency and obtain the transportation efficiency index. When the records are incomplete, the missing values ​​are filled in and the calculation is recalculated to obtain the transportation efficiency index.

[0049] Based on transportation efficiency indicators and early warning logs, a decision tree algorithm is used to analyze driver behavior patterns and generate driver performance scores. Then, risk events are extracted from the early warning logs, and the risk distribution is calculated using frequency statistics to obtain risk distribution data.

[0050] By using data aggregation technology, transportation efficiency indicators, driver performance scores, and risk distribution data are integrated to generate a comprehensive management dataset. Visualization technology is then used to process the comprehensive management dataset to generate analytical reports that include transportation efficiency, driver performance, and risk distribution.

[0051] Furthermore, before obtaining the vehicle-driver binding identifier set, the process includes: obtaining vehicle and driver information from the transportation management system database, using data cleaning techniques to standardize the vehicle number, driver identification, and driving record fields, generating a vehicle-driver association dataset in a unified format, and obtaining a structured data set.

[0052] This application provides a system for linking and managing transport drivers and vehicles based on QR codes, and a method for implementing such linking and management, including:

[0053] The QR code generation module generates a dynamic QR code that binds vehicles and drivers based on a structured data set. It uses a hash algorithm to generate a unique binding identifier set for each vehicle and driver, and then uses a QR code generation algorithm to encode each binding identifier into a dynamic QR code containing a timestamp, generating a dynamic QR code image set.

[0054] The data transmission module pushes a set of dynamic QR code images to the transportation management terminal through the mobile application interface, and protects the QR code data with an encrypted transmission protocol to obtain a QR code dataset that can be scanned on the mobile device.

[0055] The QR code verification module obtains the QR code data uploaded by the scanning device when a QR code is scanned on a mobile phone, uses a decoding algorithm to extract the binding identifier and timestamp, and obtains the verified binding identifier after verification, thus ensuring the validity and security of the QR code.

[0056] The data synchronization module retrieves the corresponding vehicle-driver association data from the transportation management system database based on the verified binding identifier, and uses real-time data synchronization technology to update the vehicle location, driver behavior and cargo status information in real time to obtain a real-time transportation status dataset.

[0057] The anomaly detection module analyzes the real-time transportation status dataset and uses anomaly detection algorithms to monitor vehicle trajectory deviation and driver fatigue driving. When the score of detected abnormal behavior exceeds a preset threshold, a risk warning signal is generated, resulting in a risk warning dataset.

[0058] The early warning push module, based on the risk early warning dataset, uses data push technology to transmit early warning signals to the management terminal through the mobile application interface, generating early warning logs that include the anomaly type, time, and location.

[0059] The data analysis module, based on the real-time early warning record set, uses data aggregation technology to integrate and process vehicle-driver related data, transportation status, and early warning logs, generating analytical reports that include transportation efficiency, driver performance, and risk distribution, thus obtaining a comprehensive management dataset.

[0060] The beneficial effects of this invention are as follows:

[0061] This invention uses QR code technology to dynamically link vehicle and driver information, solving the problems of scattered information storage and lack of a unified digital entry point in traditional management methods. By generating a unique vehicle-driver binding identifier through a hash algorithm and encoding it as a dynamic QR code, it achieves efficient binding and verification of vehicle and driver information. The use of QR codes not only simplifies the information verification process, but also updates vehicle location, driver behavior, and cargo status in real time through real-time data synchronization technology, solving the problem of information update lag. It realizes dynamic association and real-time interaction of vehicle and driver information, significantly improving management efficiency and the timeliness of data interaction.

[0062] By using real-time data synchronization and anomaly detection algorithms, abnormal behaviors such as vehicle trajectory deviation and driver fatigue are monitored and analyzed in real time. When the detected abnormal behavior score exceeds the preset threshold, a risk warning signal is generated and the warning information is promptly transmitted to the management terminal through data push technology. This real-time monitoring and warning mechanism effectively makes up for the shortcomings of traditional management methods that cannot obtain the real-time status of vehicles and drivers, greatly improves the level of safety management in the transportation process, can promptly detect and deal with potential risks, ensure transportation safety, and reduce the accident rate.

[0063] By aggregating and analyzing real-time early warning records, a comprehensive management dataset containing transportation efficiency, driver performance, and risk distribution is generated. Visualization technology is then used to generate analytical reports, providing managers with comprehensive and accurate decision support. This addresses the problems of lagging data analysis and difficulty in generating accurate performance evaluations and risk predictions in traditional management methods. Managers can quickly make scientific and reasonable decisions based on real-time data and analysis results, optimize transportation resource allocation, improve management efficiency, and reduce operating costs, thereby comprehensively enhancing the overall effectiveness and refined management level of transportation management. Attached Figure Description

[0064] To better understand and implement this application, the technical solution is described in detail below with reference to the accompanying drawings.

[0065] Figure 1 This is a flowchart illustrating the method for associating and managing transport drivers and vehicles based on QR codes, as provided in Embodiment 1 of this application.

[0066] Figure 2 A schematic diagram illustrating the process of generating a dynamic QR code image set for the method of associating and managing transport drivers and vehicles based on QR codes provided in Embodiment 1 of this application;

[0067] Figure 3 A flowchart illustrating the verified binding identifier of the method for associating and managing transport drivers and vehicles based on QR codes provided in Embodiment 1 of this application;

[0068] Figure 4 This is a schematic diagram of the structure of a system for associating and managing transport drivers and vehicles based on QR codes, provided in Embodiment 2 of this application. Detailed Implementation

[0069] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, exemplary embodiments will be described in detail below, examples of which are illustrated in the accompanying drawings. In the following description, when referring to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application.

[0070] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0071] The following detailed description of the specific implementation methods, features, and effects of the present invention, in conjunction with the accompanying drawings and preferred embodiments, is provided in detail.

[0072] Example 1

[0073] Please see Figures 1-3 This embodiment provides a method for associating and managing transport drivers and vehicles based on QR codes, including the following steps:

[0074] S1. Based on the structured data set, a unique identifier is generated using a hash algorithm. The hash function H(v,d) takes the vehicle number v and the driver identification d as input and outputs a fixed-length identifier to obtain a set of vehicle-driver binding identifiers. Then, a QR code generation algorithm is used to encode each binding identifier into a dynamic QR code, which contains a timestamp and a check digit, to generate a set of dynamic QR code images.

[0075] Furthermore, the vehicle-driver binding identifier set is obtained, specifically including:

[0076] Obtain a structured dataset, extract the vehicle number and driver identity fields from it, generate input parameter pairs, and mark the input parameter pair as invalid if the vehicle number or driver identity field is missing and discard it to obtain a set of valid input parameter pairs.

[0077] The set of valid input parameters is processed by a hash function H(v,d) to generate a fixed-length unique identifier. The hash function is then used to process the data to obtain a set of unique identifiers corresponding to each vehicle number and driver identity.

[0078] Based on the unique identifier set, a vehicle-driver binding identifier is generated and stored in the binding identifier set. If there are duplicate identifiers in the binding identifier set, the identifier values ​​are compared, the newly generated identifier is retained, and the old identifiers are discarded to obtain the deduplicated binding identifier set.

[0079] Based on the deduplicated set of binding identifiers, obtain the generation timestamp of each binding identifier, append it to the binding identifier record, and then sort it by timestamp to obtain a set of binding identifiers arranged in chronological order;

[0080] From the set of binding identifiers arranged in chronological order, extract the vehicle number and driver identity corresponding to each binding identifier to generate a binding relationship record. If the binding relationship record does not conform to the preset business rules, it is marked as an abnormal record and discarded to obtain a set of binding relationship records that conform to the rules.

[0081] Based on the set of binding relationship records that meet the rules, the final vehicle-driver binding identifier dataset is generated. Then, the dataset is validated to determine its integrity, and the validated binding identifier dataset is obtained.

[0082] Data storage tools are used to save the verified binding identifier dataset to the database. The database index is used to determine whether the storage was successful, and a persistent vehicle-driver binding identifier dataset is obtained.

[0083] Specifically, the vehicle number and driver identification are combined into a unique identifier using the hash function H(v,d), ensuring that each vehicle-driver pair has a unique identifier, which is used to generate a unique binding identifier between the vehicle and the driver; the hash function H(b,t) generates a check bit for each binding identifier, which is used to generate the check bit of the QR code, ensuring the correctness and timeliness of the QR code.

[0084] Specifically, by using hash algorithms and QR code technology, vehicle numbers and driver identification are processed to generate a unique vehicle-driver binding identifier, which is then encoded as a dynamic QR code. This process effectively solves the problem of accurate information association. At the same time, through steps such as deduplication, sorting, verification, and storage, it ensures the integrity and persistence of data, providing an efficient, secure, and dynamic data foundation for transportation management, and significantly improving management efficiency and the reliability of information exchange.

[0085] Furthermore, a dynamic set of QR code images is generated, specifically including:

[0086] S11. Obtain the vehicle-driver binding identifier set, extract each binding identifier from it, generate data input containing vehicle identifier and driver identifier, and then use a QR code generation algorithm to encode each binding identifier, embed timestamp t and check bit c, and generate a dynamic QR code, where timestamp t represents the generation time, and check bit c is calculated by hash function H(b,t), where b is the binding identifier.

[0087] S12. When the verification bit c of the dynamic QR code matches the expected value, the dynamic QR code is stored as the first image. If they do not match, the QR code is discarded and regenerated.

[0088] S13. Using image processing technology, the first image is compressed to generate a second image while maintaining the readability of the QR code. Then, based on the second image, a file storage system is used to archive it into an image collection and generate a unique file identifier.

[0089] S14. When the file identifier in the image set matches the binding identifier, the dynamic QR code generation is confirmed to be complete. The image set is output. The verification algorithm is used to decode each dynamic QR code in the image set, extract the timestamp t and the check bit c, determine the validity of the binding identifier, and obtain the verification result.

[0090] The verification algorithm is a consistency verification algorithm that recalculates the check bit c'=H(b, t) and compares it with the check bit c embedded in the QR code. At the same time, it combines the time stamp t and the current system time to verify whether the time stamp is within the preset validity period. If both pass, the dynamic QR code is determined to be valid.

[0091] Specifically, a dynamic set of QR code images containing vehicle and driver information was generated. Each QR code embeds a timestamp and a check digit to ensure its timeliness and uniqueness. After verification, image compression, and file storage, the final output image set not only maintains the readability of the QR codes but also further confirms the validity of the bound identifier through a verification algorithm. This process achieves efficient generation and management of dynamic QR codes, providing a safe and reliable visual information carrier for transportation management. At the same time, it optimizes data storage and verification processes, improving management efficiency and the accuracy of information exchange.

[0092] S2. Through the mobile application interface, the dynamic QR code image set is pushed to the transportation management terminal, and the QR code data is protected by an encrypted transmission protocol to obtain a QR code dataset that can be scanned on the mobile phone.

[0093] Furthermore, a dataset of QR codes that can be scanned on mobile devices is obtained, specifically including:

[0094] The system obtains a set of dynamic QR code images through the mobile application interface, encrypts the image data using the AES encryption algorithm, generates encrypted QR code data, and pushes the encrypted QR code data to the transportation management terminal via the HTTPS transmission protocol to obtain successfully transmitted QR code data.

[0095] The received encrypted QR code data is decrypted at the transportation management terminal. The data integrity is verified using the SHA-256 algorithm, and decrypted QR code data is generated. If the format of the decrypted QR code data meets the preset standard, the decrypted QR code data is stored in the transportation management terminal to generate a QR code dataset that can be scanned by mobile phones.

[0096] The QR code dataset is obtained from the transportation management terminal through a mobile application. The QR code parsing algorithm is used to extract the QR code content from the dataset and generate a displayable QR code image.

[0097] Based on the content of the QR code image, if the parsing result matches the preset verification code, the QR code image is displayed on the mobile application to obtain a scannable dynamic QR code. When the mobile application successfully scans the QR code image, transportation management-related data is extracted from the QR code image to generate transportation management data for business processing.

[0098] Specifically, it achieves secure transmission and efficient management of dynamic QR code image sets. AES encryption algorithm and HTTPS transmission protocol are used to encrypt and protect the QR code data during transmission, ensuring data integrity and security. After the transportation management terminal decrypts and verifies the integrity of the received data, it generates a QR code dataset that can be scanned by mobile devices. The mobile application parses and verifies the data, displays the scannable dynamic QR codes, and extracts relevant transportation management data for business processing. This process not only ensures data security and accuracy but also improves the convenience and efficiency of transportation management, enabling real-time information sharing and dynamic interaction.

[0099] S3. When scanning a QR code on a mobile device, obtain the QR code data uploaded by the scanning device, use a decoding algorithm to extract the binding identifier and timestamp. If the difference between the timestamp t and the current time is less than the preset threshold T, the QR code is determined to be valid and the binding identifier that has been verified is obtained.

[0100] Furthermore, the verified binding identifier includes:

[0101] S31. Obtain the QR code data collected by the scanning device on the mobile terminal, preprocess the QR code image using image processing technology to obtain clear QR code data, and then extract the binding identifier and timestamp from the clear QR code data using a decoding algorithm to obtain the extracted binding identifier and timestamp data.

[0102] S32. Calculate the difference between the extracted timestamp and the current time to obtain time difference data. If the time difference data is less than a preset threshold, the QR code is determined to be valid, and a valid binding identifier is obtained.

[0103] S33. The validly determined binding identifier is encrypted using an encryption algorithm to obtain encrypted binding identifier data. Then, the encrypted binding identifier data is matched with a pre-established database to obtain the corresponding user identity information and obtain the verified identity identifier.

[0104] S34. Based on the verified identity identifier, generate binding confirmation information to obtain the final business binding result.

[0105] Specifically, by scanning a QR code with a mobile phone, image processing and decoding algorithms are used to extract the binding identifier and timestamp. The validity of the QR code is determined based on the difference between the timestamp and the current time. The binding identifier of a valid QR code is encrypted and matched against the user's identity information in the database to generate binding confirmation information. This process ensures the timeliness and security of the QR code, enabling fast and accurate binding between drivers and vehicles, and improving the efficiency and reliability of transportation management.

[0106] S4. Based on the verified binding identifier, retrieve the corresponding vehicle-driver association data from the transportation management system database, and use real-time data synchronization technology to update the vehicle location, driver behavior and cargo status to obtain a real-time transportation status dataset.

[0107] Furthermore, a real-time transportation status dataset is obtained, specifically including:

[0108] Using real-time data synchronization technology, location information is obtained from vehicle positioning devices, the location field in vehicle data is updated, and a real-time vehicle location dataset is obtained. Then, behavioral data is obtained through driver behavior monitoring devices. When the behavioral data exceeds a preset threshold, it is marked as abnormal behavior, and a driver behavior analysis dataset is obtained.

[0109] Cargo status information is obtained from cargo sensors, and combined with location information and behavioral data to determine whether the cargo status is normal, thus obtaining a cargo status analysis dataset.

[0110] Based on the vehicle location dataset, behavior analysis dataset, and cargo status analysis dataset, data fusion processing is performed to generate a real-time transportation status dataset.

[0111] Based on the real-time transportation status dataset, a time series analysis algorithm is used to analyze the changing trend of transportation status, obtain a transportation status trend dataset, and then determine whether there are any abnormalities in the transportation process. If there are abnormalities, an abnormality alarm message is generated, and the transportation abnormality detection result is obtained.

[0112] Specifically, it enables full-process monitoring of transportation, timely detection of abnormal behaviors or states, and provides real-time and accurate data support for transportation management, thereby improving the safety and management efficiency of the transportation process.

[0113] S5. Based on the real-time transportation status dataset, anomaly detection algorithms are used to analyze abnormal behaviors such as vehicle trajectory deviation and driver fatigue. If the score of the detected abnormal behavior exceeds the preset threshold A, a risk warning signal is generated, and a risk warning dataset is obtained.

[0114] Furthermore, a risk warning dataset is obtained, specifically including:

[0115] Based on the real-time transportation status dataset, the isolated forest algorithm is used for analysis to calculate the abnormal behavior scores of vehicle trajectory deviation and driver fatigue driving, and obtain an abnormal score set. When the scores in the abnormal score set exceed the preset threshold A, a risk warning signal is generated, and a warning signal set is obtained.

[0116] This process involves extracting vehicle trajectory-related data and driver behavior-related data from a real-time transportation status dataset. Driver behavior data includes continuous driving duration, operation frequency, steering wheel turning amplitude, heart rate, and other behavioral monitoring data. This data is then transformed into feature vectors that can be processed by the Isolation Forest algorithm. The Isolation Forest algorithm is used to train and analyze these feature vectors. By constructing multiple isolated trees, the isolation degree of each set of vehicle trajectory data and driver behavior data relative to the normal transportation mode is calculated. This isolation degree represents the degree of deviation of the data from the majority of normal data in the feature space. Higher isolation degrees correspond to higher abnormal behavior scores, thereby generating an abnormal score set for vehicle trajectory deviation and driver fatigue. Subsequently, each score in the abnormal score set is compared with a preset threshold A. This threshold is derived from statistical analysis of historical normal transportation data, such as the score corresponding to the maximum permissible deviation of the trajectory during normal driving and the behavioral feature score under compliant driving duration. If one or more scores exceed the threshold A, it is preliminarily determined that there are abnormal signs of vehicle trajectory deviation or driver fatigue.

[0117] Based on the early warning signal set, time series analysis technology is used to identify the persistence and frequency of abnormal behavior to obtain abnormal behavior patterns. Then, based on the abnormal behavior patterns, cluster analysis technology is used to group similar abnormal behaviors to obtain an abnormal behavior classification set.

[0118] The classification results are obtained from the abnormal behavior classification set to generate a risk warning dataset containing the abnormality type and risk level.

[0119] The abnormal types include: vehicle trajectory deviation, which specifically refers to the deviation of the vehicle's real-time trajectory from the preset planned route exceeding the set range, such as deviation distance or deviation duration exceeding the system's preset threshold, or driving speed significantly deviating from the normal speed limit of the road segment, such as continuous speeding or low-speed lane occupation, which are abnormal paths in the dynamic driving of the vehicle; and driver fatigue driving, which is judged based on data collected by driver behavior monitoring equipment, such as continuous driving time exceeding the legal or company-specified time limit, frequent eye closing, head drooping, slow steering wheel operation, and other behavioral characteristics during driving, which are abnormal driver operation status.

[0120] Risk levels are categorized as follows: High priority, corresponding to serious anomalies that directly lead to safety accidents, such as vehicles deviating significantly from the planned route and heading into prohibited / dangerous areas, or drivers showing obvious signs of fatigue and loss of control. Such anomalies require immediate alarms and intervention from management personnel. Medium priority, corresponding to anomalies that pose safety hazards but are not urgent at the moment, such as vehicles slightly deviating from the route or drivers' continuous driving time approaching a threshold. Such anomalies require the generation of warning logs and pushes to the management terminal to remind users to pay attention to the subsequent status. Low priority, corresponding to minor anomalies with potential risks, such as vehicles quickly correcting themselves after a brief deviation from the route or drivers exhibiting occasional minor operational delays.

[0121] Specifically, by analyzing real-time transportation status data using anomaly detection algorithms (such as the Isolation Forest algorithm), abnormal behaviors such as vehicle trajectory deviation and driver fatigue can be accurately identified, and risk warning signals can be generated based on the scores of these abnormal behaviors. Further, time series analysis and cluster analysis techniques are used to identify and classify the persistence and frequency of abnormal behaviors, generating a risk warning dataset that includes anomaly types and risk levels. This process enables real-time monitoring and early warning of potential risks during transportation, providing managers with timely risk alerts and effectively improving the safety and proactiveness of transportation management.

[0122] S6. Based on the risk warning dataset, data push technology is used to transmit the warning signal to the management terminal through the mobile application interface, generating a warning log containing the anomaly type, time and location, and obtaining a real-time warning record set;

[0123] Furthermore, a set of real-time early warning records is obtained, specifically including:

[0124] Raw data is obtained from the risk warning dataset, and the data is preprocessed using data push technology to obtain a standardized dataset. When there are outliers in the standardized dataset, the outlier type is determined by an anomaly detection algorithm to obtain the anomaly classification result.

[0125] Based on the anomaly classification results, the warning signal is transmitted to the mobile application using the application programming interface, and a transmission completion signal is obtained.

[0126] When the mobile application receives the transmission completion signal, the management terminal generates an early warning log containing the anomaly type, occurrence time and geographical location, obtains the log record, and then uses a real-time update mechanism to store the log record into a record set, thus obtaining a real-time early warning record set;

[0127] The latest records are retrieved from the real-time early warning record set, and the early warning information is transmitted to the management terminal through a push notification mechanism to obtain the final early warning output. When the final early warning output contains high-priority anomalies, the instant alarm mechanism is triggered through the application programming interface to obtain an alarm confirmation signal.

[0128] Specifically, the system enables rapid transmission and real-time updates of early warning information, ensuring that managers can promptly detect anomalies during transportation. Furthermore, for high-priority anomalies, the system alerts managers through an immediate alarm mechanism, further enhancing the response speed and emergency handling capabilities of transportation management.

[0129] S7. Based on the real-time early warning record set, data aggregation technology is used to integrate vehicle-driver related data, transportation status and early warning logs to generate analysis reports that include transportation efficiency, driver performance and risk distribution, thus obtaining a comprehensive management dataset.

[0130] Furthermore, a comprehensive management dataset is obtained, specifically including:

[0131] The real-time early warning record set is obtained, and data cleaning technology is used to remove duplicate records and missing values ​​to obtain a cleaned record set. Then, the cleaned record set is grouped by clustering algorithm, and a classification dataset is generated based on vehicle association and driver association.

[0132] When the transportation status records in the classification dataset are complete, the weighted average method is used to calculate the transportation efficiency and obtain the transportation efficiency index. When the records are incomplete, the missing values ​​are filled in and the calculation is recalculated to obtain the transportation efficiency index.

[0133] Based on transportation efficiency indicators and early warning logs, a decision tree algorithm is used to analyze driver behavior patterns and generate driver performance scores. Then, risk events are extracted from the early warning logs, and the risk distribution is calculated using frequency statistics to obtain risk distribution data.

[0134] The calculation and generation of driver performance scores involves: extracting efficiency features such as on-time rate, on-time completion rate, and fuel / energy consumption from transportation efficiency indicators; extracting the frequency of driver-related anomaly types from warning logs, such as fatigue driving, number of trajectory deviation warnings, high / medium / low priority distribution of anomaly levels, and timeliness of anomaly handling; standardizing and classifying these features to form feature vectors for the decision tree algorithm; then training a decision tree model based on historical driver performance levels (e.g., excellent, good) using the feature vectors, allowing the model to learn the association rules between features and performance levels and determine the weights of each feature (e.g., fatigue driving warnings have a higher weight than minor trajectory deviations, and on-time rate has a higher weight than energy consumption indicators); finally, inputting the real-time feature vectors of the drivers to be scored into the trained model, which classifies drivers into corresponding performance levels through layer-by-layer judgment, converting them into base scores according to level mapping rules (e.g., excellent 90-100 points, good 80-89 points, etc.), and generating a comprehensive driver performance score.

[0135] By using data aggregation technology, transportation efficiency indicators, driver performance scores, and risk distribution data are integrated to generate a comprehensive management dataset. Visualization technology is then used to process the comprehensive management dataset to generate analytical reports that include transportation efficiency, driver performance, and risk distribution.

[0136] Specifically, through data aggregation and analysis technologies, real-time early warning records are integrated with vehicle-driver correlation data, transportation status, and other information to generate a comprehensive management dataset that includes transportation efficiency, driver performance, and risk distribution, presented in the form of visual reports. This process enables comprehensive analysis and efficient display of transportation management data, providing managers with precise decision support, helping to optimize transportation resource allocation, and improving management efficiency and transportation safety.

[0137] Furthermore, before obtaining the vehicle-driver binding identifier set, the process includes: obtaining vehicle and driver information from the transportation management system database, using data cleaning techniques to standardize fields such as vehicle number, driver identification, and driving records, generating a unified format vehicle-driver association dataset, and obtaining a structured data set.

[0138] Furthermore, a structured dataset is obtained, specifically including: obtaining raw data of vehicle numbers, driver identification, and driving records from the transportation management system database; using batch extraction technology to obtain an initial dataset; and using data cleaning technology to remove duplicates and fill in missing values ​​in the vehicle numbers, driver identification, and driving records in the initial dataset to obtain a cleaned dataset.

[0139] When vehicle numbers or driver identifications in the cleaned dataset are in non-standard formats, they are standardized using regular expression matching and transformation rules to obtain a standardized dataset.

[0140] Based on the vehicle numbers and driver identifications in the standardized dataset, an association algorithm is used to establish the mapping relationship between vehicles and drivers, resulting in a vehicle-driver association dataset. Then, the vehicle-driver association dataset is adjusted to a predefined uniform format using format conversion technology, which includes vehicle number, driver identification, and driving record fields, resulting in a formatted dataset.

[0141] Data validation techniques are used to check the integrity and consistency of the formatted dataset. If data anomalies are found, the process is traced back to the cleaning step and reprocessed to obtain a validation dataset. The validation dataset is then saved to a structured data table using database storage technology, and the storage structure is optimized using indexes to obtain a structured data set.

[0142] Example 2

[0143] Please see Figure 4 This embodiment provides a system for associating and managing transport drivers and vehicles based on QR codes, and a method for associating and managing transport drivers and vehicles based on QR codes, including:

[0144] The QR code generation module generates a dynamic QR code that binds vehicles and drivers based on a structured data set. It uses a hash algorithm to generate a unique binding identifier set for each vehicle and driver, and then uses a QR code generation algorithm to encode each binding identifier into a dynamic QR code containing a timestamp, generating a dynamic QR code image set.

[0145] The data transmission module pushes a set of dynamic QR code images to the transportation management terminal through the mobile application interface, and protects the QR code data with an encrypted transmission protocol to obtain a QR code dataset that can be scanned on the mobile device.

[0146] The QR code verification module obtains the QR code data uploaded by the scanning device when a QR code is scanned on a mobile phone, uses a decoding algorithm to extract the binding identifier and timestamp, and obtains the verified binding identifier after verification, thus ensuring the validity and security of the QR code.

[0147] The data synchronization module retrieves the corresponding vehicle-driver association data from the transportation management system database based on the verified binding identifier, and uses real-time data synchronization technology to update the vehicle location, driver behavior and cargo status information in real time to obtain a real-time transportation status dataset.

[0148] The anomaly detection module analyzes the real-time transportation status dataset and uses anomaly detection algorithms to monitor vehicle trajectory deviation and driver fatigue driving. When the score of detected abnormal behavior exceeds a preset threshold, a risk warning signal is generated, resulting in a risk warning dataset.

[0149] The early warning push module, based on the risk early warning dataset, uses data push technology to transmit early warning signals to the management terminal through the mobile application interface, generating early warning logs that include the anomaly type, time, and location.

[0150] The data analysis module, based on the real-time early warning record set, uses data aggregation technology to integrate and process vehicle-driver related data, transportation status, and early warning logs, generating analytical reports that include transportation efficiency, driver performance, and risk distribution, resulting in a comprehensive management dataset that provides strong support for transportation management decisions.

[0151] 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 method for associating and managing transport drivers and vehicles based on QR codes, characterized in that: Includes the following steps: Based on the structured dataset, a unique identifier is generated using a hash algorithm to obtain a set of vehicle-driver binding identifiers. Then, a QR code generation algorithm is used to encode each binding identifier into a dynamic QR code, generating a set of dynamic QR code images. The dynamic QR code image set is pushed to the transportation management terminal through the mobile application interface. The QR code data is protected by an encrypted transmission protocol, resulting in a QR code dataset that can be scanned on the mobile device. When scanning a QR code on a mobile device, the QR code data uploaded by the scanning device is obtained, and a decoding algorithm is used to extract the binding identifier and timestamp to obtain the verified binding identifier. Based on the verified binding identifier, the corresponding vehicle-driver association data is retrieved from the transportation management system database. Real-time data synchronization technology is used to update the vehicle location, driver behavior, and cargo status to obtain a real-time transportation status dataset. Based on the real-time transportation status dataset, anomaly detection algorithms are used to analyze vehicle trajectory deviation and driver fatigue driving abnormal behavior to obtain a risk warning dataset. Based on the risk warning dataset, data push technology is used to transmit warning signals to the management terminal via a mobile application interface to obtain a real-time warning record set. Based on the real-time early warning record set, data aggregation technology is used to integrate vehicle-driver correlation data, transportation status, and early warning logs to obtain a comprehensive management dataset; The obtained comprehensive management dataset includes: The real-time early warning record set is obtained, and data cleaning technology is used to remove duplicate records and missing values ​​to obtain a cleaned record set. Then, the cleaned record set is grouped by clustering algorithm, and a classification dataset is generated based on vehicle association and driver association. When the transportation status records in the classification dataset are complete, the weighted average method is used to calculate the transportation efficiency and obtain the transportation efficiency index. When the records are incomplete, the missing values ​​are filled in and the calculation is recalculated to obtain the transportation efficiency index. Based on transportation efficiency indicators and early warning logs, a decision tree algorithm is used to analyze driver behavior patterns and generate driver performance scores. Then, risk events are extracted from the early warning logs, and the risk distribution is calculated using frequency statistics to obtain risk distribution data. By using data aggregation technology, transportation efficiency indicators, driver performance scores, and risk distribution data are integrated to generate a comprehensive management dataset. Visualization technology is then used to process the comprehensive management dataset to generate analytical reports that include transportation efficiency, driver performance, and risk distribution.

2. The method for associating and managing transport drivers and vehicles based on QR codes according to claim 1, characterized in that: Obtain the vehicle-driver binding identifier set, specifically including: Obtain a structured dataset, extract the vehicle number and driver identity fields from it, generate input parameter pairs, and mark the input parameter pair as invalid if the vehicle number or driver identity field is missing and discard it to obtain a set of valid input parameter pairs. The set of valid input parameters is processed by a hash function H(v,d) to generate a fixed-length unique identifier. The hash function is then used to process the data to obtain a set of unique identifiers corresponding to each vehicle number and driver identity. Based on the unique identifier set, a vehicle-driver binding identifier is generated and stored in the binding identifier set. If there are duplicate identifiers in the binding identifier set, the identifier values ​​are compared, the newly generated identifier is retained, and the old identifiers are discarded to obtain the deduplicated binding identifier set. Based on the deduplicated set of binding identifiers, obtain the generation timestamp of each binding identifier, append it to the binding identifier record, and then sort it by timestamp to obtain a set of binding identifiers arranged in chronological order; From the set of binding identifiers arranged in chronological order, extract the vehicle number and driver identity corresponding to each binding identifier to generate a binding relationship record. If the binding relationship record does not conform to the preset business rules, it is marked as an abnormal record and discarded to obtain a set of binding relationship records that conform to the rules. Based on the set of binding relationship records that meet the rules, the final vehicle-driver binding identifier dataset is generated. Then, the dataset is validated to determine its integrity, and the validated binding identifier dataset is obtained. Data storage tools are used to save the verified binding identifier dataset to the database. The database index is used to determine whether the storage was successful, and a persistent vehicle-driver binding identifier dataset is obtained.

3. The method for associating and managing transport drivers and vehicles based on QR codes according to claim 1, characterized in that: Generate a dynamic set of QR code images, specifically including: Obtain the set of vehicle-driver binding identifiers, extract each binding identifier from it, generate data input containing vehicle identifier and driver identifier, and then use a QR code generation algorithm to encode each binding identifier, embed a timestamp t and a check bit c to generate a dynamic QR code, where the timestamp t represents the generation time, and the check bit c is calculated by the hash function H(b,t), where b is the binding identifier; If the verification bit c of the dynamic QR code matches the expected value, the dynamic QR code is stored as the first image; if they do not match, the QR code is discarded and regenerated. The first image is compressed using image processing technology to generate the second image while maintaining the readability of the QR code. Then, based on the second image, it is archived into an image collection using a file storage system to generate a unique file identifier. When the file identifier in the image set matches the binding identifier, the dynamic QR code generation is confirmed to be complete, the image set is output, and each dynamic QR code in the image set is decoded by the verification algorithm to extract the timestamp t and check bit c, and the validity of the binding identifier is judged to obtain the verification result.

4. The method for associating and managing transport drivers and vehicles based on QR codes according to claim 1, characterized in that: The verified binding identifier includes: The system acquires QR code data collected by a scanning device on a mobile device, preprocesses the QR code image using image processing technology to obtain clear QR code data, and then extracts the binding identifier and timestamp from the clear QR code data using a decoding algorithm to obtain the extracted binding identifier and timestamp data. Based on the extracted timestamp and the current time, the difference between the two is calculated to obtain time difference data. When the time difference data is less than a preset threshold, the QR code is determined to be valid, and a valid binding identifier is obtained. The valid binding identifier is encrypted using an encryption algorithm to obtain encrypted binding identifier data. Then, the encrypted binding identifier data is matched with a pre-established database to obtain the corresponding user identity information and obtain the verified identity identifier. Based on the verified identity, a binding confirmation message is generated, resulting in the final business binding result.

5. The method for associating and managing transport drivers and vehicles based on QR codes according to claim 1, characterized in that: The real-time transportation status dataset is obtained, specifically including: Using real-time data synchronization technology, location information is obtained from vehicle positioning devices, the location field in vehicle data is updated, and a real-time vehicle location dataset is obtained. Then, behavioral data is obtained through driver behavior monitoring devices. When the behavioral data exceeds a preset threshold, it is marked as abnormal behavior, and a driver behavior analysis dataset is obtained. Cargo status information is obtained from cargo sensors, and combined with location information and behavioral data to determine whether the cargo status is normal, thus obtaining a cargo status analysis dataset. Based on the vehicle location dataset, behavior analysis dataset, and cargo status analysis dataset, data fusion processing is performed to generate a real-time transportation status dataset. Based on the real-time transportation status dataset, a time series analysis algorithm is used to analyze the changing trend of transportation status, obtain a transportation status trend dataset, and then determine whether there are any abnormalities in the transportation process. If there are abnormalities, an abnormality alarm message is generated, and the transportation abnormality detection result is obtained.

6. The method for associating and managing transport drivers and vehicles based on QR codes according to claim 1, characterized in that: The risk warning dataset obtained includes: Based on the real-time transportation status dataset, the isolated forest algorithm is used for analysis to calculate the abnormal behavior scores of vehicle trajectory deviation and driver fatigue driving, and obtain an abnormal score set. When the scores in the abnormal score set exceed the preset threshold A, a risk warning signal is generated, and a warning signal set is obtained. Based on the early warning signal set, time series analysis technology is used to identify the persistence and frequency of abnormal behavior to obtain abnormal behavior patterns. Then, based on the abnormal behavior patterns, cluster analysis technology is used to group similar abnormal behaviors to obtain an abnormal behavior classification set. The classification results are obtained from the abnormal behavior classification set to generate a risk warning dataset containing the abnormality type and risk level.

7. The method for associating and managing transport drivers and vehicles based on QR codes according to claim 1, characterized in that: The real-time early warning record set is obtained, specifically including: Raw data is obtained from the risk warning dataset, and the data is preprocessed using data push technology to obtain a standardized dataset. When there are outliers in the standardized dataset, the outlier type is determined by an anomaly detection algorithm to obtain the anomaly classification result. Based on the anomaly classification results, the warning signal is transmitted to the mobile application using the application programming interface, and a transmission completion signal is obtained. When the mobile application receives the transmission completion signal, the management terminal generates an early warning log containing the anomaly type, occurrence time and geographical location, obtains the log record, and then uses a real-time update mechanism to store the log record into a record set, thus obtaining a real-time early warning record set; The latest records are retrieved from the real-time early warning record set, and the early warning information is transmitted to the management terminal through a push notification mechanism to obtain the final early warning output. When the final early warning output contains high-priority anomalies, the instant alarm mechanism is triggered through the application programming interface to obtain an alarm confirmation signal.

8. The method for associating and managing transport drivers and vehicles based on QR codes according to claim 1, characterized in that: Before obtaining the vehicle-driver binding identifier set, the process includes: obtaining vehicle and driver information from the transportation management system database, using data cleaning techniques to standardize the vehicle number, driver identification, and driving record fields, generating a unified format vehicle-driver association dataset, and obtaining a structured data set.

9. A system for associating and managing transport drivers and vehicles based on QR codes, used to implement the method for associating and managing transport drivers and vehicles based on QR codes as described in any one of claims 1-8, characterized in that: include: The QR code generation module generates a dynamic QR code that binds vehicles and drivers based on a structured data set. It uses a hash algorithm to generate a unique binding identifier set for each vehicle and driver, and then uses a QR code generation algorithm to encode each binding identifier into a dynamic QR code containing a timestamp, generating a dynamic QR code image set. The data transmission module pushes a set of dynamic QR code images to the transportation management terminal through the mobile application interface, and protects the QR code data with an encrypted transmission protocol to obtain a QR code dataset that can be scanned on the mobile device. The QR code verification module obtains the QR code data uploaded by the scanning device when a QR code is scanned on a mobile phone, uses a decoding algorithm to extract the binding identifier and timestamp, and obtains the verified binding identifier after verification, thus ensuring the validity and security of the QR code. The data synchronization module retrieves the corresponding vehicle-driver association data from the transportation management system database based on the verified binding identifier, and uses real-time data synchronization technology to update the vehicle location, driver behavior and cargo status information in real time to obtain a real-time transportation status dataset. The anomaly detection module analyzes the real-time transportation status dataset and uses anomaly detection algorithms to monitor vehicle trajectory deviation and driver fatigue driving abnormal behavior. When the score of the detected abnormal behavior exceeds a preset threshold, a risk warning signal is generated, and a risk warning dataset is obtained. The early warning push module, based on the risk early warning dataset, uses data push technology to transmit early warning signals to the management terminal through the mobile application interface, generating early warning logs that include the anomaly type, time, and location. The data analysis module, based on the real-time early warning record set, uses data aggregation technology to integrate and process vehicle-driver related data, transportation status, and early warning logs, generating analytical reports that include transportation efficiency, driver performance, and risk distribution, thus obtaining a comprehensive management dataset.

Images