Blockchain-based air cargo transportation management method and system

Abstract

The application relates to a kind of blockchain-based air cargo transport management method and system, comprising: receiving the transport request of freight forwarder, when judging that the air cargo to be transported has security risk, obtaining its full life cycle business data;Call freight forwarder, ground service agent, training institution and operator's credit score and historical record as participant credit data;Full life cycle business data and participant credit data are input into pre-trained risk prediction model, and transport risk prediction result is generated;And full life cycle business data, participant credit data and risk prediction result are stored to blockchain, realize the credible evidence of transport data and whole-process traceability;After the completion of cargo transport, the business data generated in the transport process and the transport result are stored on chain.This method combines blockchain and risk prediction model, improves the safety, traceability and regulatory credibility of air cargo transport.

Description

Technical Field

[0001] This application relates to the field of shipping management technology, and in particular to a blockchain-based method and system for managing air cargo transportation. Background Technology

[0002] Air cargo transportation is one of the most security-critical links in the international logistics system, and its transportation process involves collaboration among multiple entities, including freight forwarders, ground service agents, airlines, training institutions, and operators.

[0003] In actual transportation, there are many types of goods, including a certain proportion of goods with safety risks, such as substances with flammable, corrosive, radioactive, or energy-releasing properties. These types of goods pose potential threats to personnel safety and aircraft operational safety during transportation, loading and unloading, storage, and handover.

[0004] The existing air cargo transport security management system generally suffers from the following problems:

[0005] Data fragmentation and lack of traceability: Data records among freight forwarders, ground service agents, and regulatory authorities are distributed across different systems, lacking a unified evidence storage mechanism, making it difficult to trace data at key points in the transportation process.

[0006] Insufficient transportation risk prediction capabilities: Traditional systems rely heavily on manual review or fixed rules to assess cargo risks, failing to combine historical data and behavioral patterns for dynamic prediction, resulting in lagging accident prevention and control. Summary of the Invention

[0007] To overcome, to some extent, the problems of data dispersion and lack of traceability, as well as insufficient transportation risk prediction capabilities in the existing air cargo transportation safety management system, this application provides an air cargo transportation management method and system based on blockchain.

[0008] The proposed solution is as follows: According to a first aspect of the embodiments of this application, a blockchain-based air cargo transportation management method is provided, comprising: Receive air cargo transportation requests from freight forwarders; When it is determined that there is a safety risk to the air cargo to be transported, obtain the full lifecycle business data of the air cargo to be transported. Credit scores and historical business records of freight forwarders, ground service agents, cargo transportation training institutions, and cargo operators are retrieved as credit data of the participating entities for the air cargo to be transported. The entire lifecycle business data of the air cargo to be transported and the credit data of the participating entities are input into a pre-trained risk prediction model, which outputs the transportation risk prediction results of the air cargo to be transported. Store the entire lifecycle business data of air cargo to be transported, the credit data of participating entities, and the results of transportation risk prediction on the blockchain; During transportation, multi-source sensing devices installed in the transport carrier and cargo packaging collect environmental parameters of the cargo and the cargo's own status parameters. Determine whether a transportation accident has occurred based on environmental parameters and the cargo's own condition parameters; When a transportation accident occurs, the type of the accident is determined and the accident is stored in the blockchain; After the goods arrive at their destination, the business data, transportation results, and all monitoring data generated during the transportation process will be stored in the blockchain.

[0009] Preferably, the full lifecycle business data includes at least: transportation contracts, transportation appraisal reports, cargo delivery lists from the freight forwarder's side, cargo collection lists from the ground service agent's side, cargo transportation status, qualifications of cargo transportation training institutions, qualifications of cargo operators, cargo operation logs, and violations of regulations. The environmental parameters include at least: temperature, humidity, air pressure, vibration intensity, and spatial location data; the cargo's own status parameters include: packaging integrity, cabin orientation, sealing status, and storage status.

[0010] Preferably, the presence or absence of a transportation accident is determined based on environmental parameters and the cargo's own condition parameters. If a transportation accident occurs, the type of accident is determined, and the accident is stored on the blockchain, including: Synchronize and preprocess environmental parameters and cargo status parameters over time; The processed environmental parameters and cargo status parameters are input into a pre-trained anomaly recognition model; Perform trend prediction on the time series of processed environmental parameters and cargo status parameters to generate predicted values ​​for the next time step; Calculate the residual sequence and its rolling statistics; Generate adaptive thresholds based on cargo category, flight segment type, and cargo space attributes; Residuals whose absolute value exceeds the adaptive threshold are considered as candidates for trend anomalies; Based on the strength and duration of the trend anomaly candidates, the trend anomaly candidates are classified into different levels: When the level of any candidate for abnormal trend reaches the preset warning level, or when multiple monitoring parameters show consistent abnormalities in time and space, it is determined that a transportation accident has occurred; the types of transportation accidents include at least: environmental limit violation accidents, packaging damage accidents, abnormal loading and unloading posture accidents, and energy safety accidents; The system outputs the accident type, trigger time, anomaly intensity, and impact range of the judgment results, and generates accident identification information. The accident identification information, together with the monitoring data, residual rolling statistics, and adaptive threshold used for judgment, are signed and hashed to obtain the judgment result of the transportation accident. The results of the transportation accident determination will be stored on the blockchain.

[0011] Preferably, the method further includes: In the event of a transportation accident, the system retrieves full lifecycle business data, credit data of participating entities, transportation risk prediction results, and current monitoring data for source tracing analysis to generate liability determination results.

[0012] Preferably, the process involves retrieving full lifecycle business data, credit data of participating entities, transportation risk prediction results, and current monitoring data for source tracing analysis to generate liability determination results, including: In the event of a transportation accident, full lifecycle business data, credit data of participating entities, transportation risk prediction results, and current monitoring data are retrieved as traceability data. The integrity and temporal consistency of the traceability data are verified based on the timestamps, signature information and data hash values ​​recorded in the blockchain. When the verification is successful, the key transportation node data in the traceability data are reconstructed according to the business process sequence to form a time series of the cargo transportation process; Based on the transportation contracts, cargo delivery lists, cargo receipt lists, cargo handling logs, and current monitoring data in the traceability data, an operational chain for the cargo transportation process is constructed. Input the time series and operation chain of the cargo transportation process into the accident tracing analysis model, and identify the accident triggering link and responsible party through the causal correlation analysis algorithm; Based on the identified responsible parties and their corresponding credit scores, violation records, and operational behaviors, a liability determination result for the transportation accident is generated. The liability determination results and related data will be stored in the blockchain.

[0013] Preferably, the method further includes: Data stored on the blockchain will be subject to layered encryption and access control based on security levels. Among them, high-security-level data uses homomorphic encryption or multi-key fragmentation encryption, and can only be decrypted and accessed by nodes with regulatory authority; Medium-security level data uses symmetric encryption and implements hierarchical authorization based on role-based access control policies; Low-security-level data is stored in plaintext or hash indexes for data consistency verification.

[0014] Preferably, the method further includes: Retrieve historical transportation datasets from the blockchain; the historical transportation datasets include full lifecycle business data of historical transported goods, credit data of participating entities, and labeled transportation risk event data; The historical transportation dataset is cleaned and risk features are extracted. The risk features include at least: cargo category, transportation environment parameters, transportation duration, violation event characteristics, freight forwarder credit score, ground service agent credit score, cargo transportation training institution credit score, cargo operator credit score, cargo transportation training institution qualification, and cargo operator qualification. The extracted risk features are input into a pre-defined deep learning model for training; the deep learning model includes a time series prediction sub-model and a multi-dimensional feature fusion sub-model. The loss function is optimized through iterative training, and the model parameters are updated until the prediction error meets the set convergence condition. After the deep learning model is trained, a risk prediction model for online risk assessment is generated, and the model parameter summary and training version information of the risk prediction model are stored in the blockchain.

[0015] Preferably, the method further includes: Based on the transportation risk prediction results, the transportation risks of the air cargo to be transported are classified. When the transportation risk of the air cargo to be transported is higher than the set risk level, a corresponding risk warning is generated and the corresponding regulatory handling strategy is invoked; the regulatory handling strategy includes at least: temporarily suspending the loading of the air cargo to be transported and re-inspecting it, reviewing the credit of the participating entities, and reviewing the qualifications of cargo transportation training institutions and cargo operators; The generated risk warning information, regulatory handling strategies, and execution results will be stored on the blockchain.

[0016] Preferably, the method further includes: After the goods arrive at their destination, the credit data of the participating entities will be updated based on the business data and transportation results generated during the transportation process.

[0017] According to a second aspect of the embodiments of this application, a blockchain-based air cargo transportation management system is provided, comprising: Processor and memory; The processor and memory are connected via a communication bus: The processor is used to call and execute the program stored in the memory; The memory is used to store a program, which is at least used to execute a blockchain-based air cargo transportation management method as described in any of the above.

[0018] The technical solution provided in this application may include the following beneficial effects: This technical solution stores the entire lifecycle business data of air cargo to be transported (transportation contracts, transportation appraisal reports, cargo delivery lists from freight forwarders, cargo receipt lists from ground service agents, cargo transportation status, qualifications of cargo transportation training institutions, qualifications of cargo operators, cargo operation logs, and multi-source business data such as violations) on the blockchain. Utilizing the blockchain's distributed consensus mechanism, timestamps, and hash chain structure, the authenticity, integrity, and immutability of the data records are guaranteed, providing a reliable data foundation for subsequent risk assessment and incident tracing. Business data generated by different participants (freight forwarders, ground service agents, training institutions, and operators) are uniformly aggregated and verified on the blockchain, solving the problems of data fragmentation, lack of unified standards, and difficulty in sharing among entities in traditional systems. This achieves secure data trust and collaborative management across organizations.

[0019] By incorporating credit scores and historical business records of freight forwarders, ground service agents, training institutions, and operators as credit data for participating entities, the system can comprehensively assess the compliance and reliability of the participating entities' behavior, providing quantitative basis for subsequent risk model training and regulatory decisions, and establishing a credit-based safety management system.

[0020] By combining full lifecycle business data with the credit data of participating entities and inputting them into a pre-trained risk prediction model, potential transportation risks of air cargo to be transported can be automatically identified, thereby enabling dynamic risk assessment and early warning before transportation and significantly improving transportation safety.

[0021] Credit data of participating entities and transportation risk prediction results are stored as hash credentials on the blockchain. After the goods arrive at their destination, business data and transportation results generated during the transportation process are also stored on the blockchain. In the event of a transportation accident, the transportation process can be quickly reconstructed based on the on-chain records, the authenticity of data can be verified, and the responsible party can be identified, improving the accuracy of accident tracing and regulatory transparency. Accident tracing analysis is built on the blockchain, eliminating the possibility of human intervention and post-event data tampering.

[0022] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0023] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0024] Figure 1 This is a schematic flowchart of a blockchain-based air cargo transportation management method provided in one embodiment of this application; Figure 2 This is a schematic diagram of the structure of a blockchain-based air cargo transportation management system provided in one embodiment of this application.

[0025] Reference numerals: Processor-21; Memory-22. Detailed Implementation

[0026] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0027] Example 1 Figure 1 This is a flowchart illustrating a blockchain-based air cargo transportation management method according to one embodiment of this application. (Refer to...) Figure 1 A blockchain-based method for managing air cargo transportation includes: S11: Receive air cargo transportation requests from freight forwarders; S12: When it is determined that there is a safety risk to be transported by air cargo, obtain the full life cycle business data of the air cargo to be transported; the full life cycle business data shall include at least: transportation contract, transportation appraisal report, cargo delivery list on the side of freight forwarder, cargo collection list on the side of ground service agent, cargo transportation status, cargo transportation training institution qualification, cargo operator qualification, cargo operation log and violation operation events; Cargo transportation status data is used to describe the real-time location, environmental parameters, and status indicators of cargo at different stages of transportation.

[0028] The qualification data of cargo transportation training institutions is used to identify the legality and validity of institutions responsible for training in the handling, packaging or declaration of dangerous goods. Typical data items include: the name and registration number of the training institution, the certification document number of the competent authority, the type of training course, the validity period and issuance date of the certificate, and historical review and violation records.

[0029] Cargo handler qualification data describes the competence and licensing status of personnel engaged in the handling, declaration, or loading and unloading of dangerous goods. Typical data items include: operator's name and unique identification code, affiliated organization and job category (freight forwarding, ground loading and unloading, security inspection, etc.), training records and certificate numbers, certificate type and validity period, and historical violation or assessment results records.

[0030] Cargo operation logs are used to record the specific operation events and time sequence performed manually or automatically throughout the entire cargo transportation process. Typical data items include: operation event type: loading, transshipment, handover, inspection, sealing, unsealing, etc.; identity of the operation executor and equipment number; operation timestamp and geographical location; operation result and remarks.

[0031] Violation event data is used to record safety violations, operational anomalies, or system alarm events that occur during transportation. Typical data items include: violation event number and type (illegal loading, damaged packaging, temperature exceeding limits, unauthorized unsealing, etc.); trigger source (manual reporting or system detection); involved entities (operators, organizations, or flight numbers); event description and risk level; handling measures and rectification results.

[0032] S13: Retrieve the credit scores and historical business records of freight forwarders, ground service agents, cargo transportation training institutions, and cargo operators as credit data of the participating entities for the air cargo to be transported; In this embodiment, the credit scores and historical business records of freight forwarders, ground service agents, cargo transportation training institutions, and cargo operators together constitute the "participating entity credit data" in the air cargo transportation lifecycle data model.

[0033] This data reflects the compliance, performance, and safe operation records of all entities involved in the transportation business, and is used for risk prediction, accident tracing, and credit management. Specifically, it includes, but is not limited to, the following: 1. Freight forwarder credit data reflects the historical performance of the agency in cargo declaration, packaging, and transportation organization. Typical fields include: Company identity information: Agent company name, registration number, license number; Business performance record: annual transportation volume, on-time delivery rate, violation rate, and delay rate; Compliance review records: accuracy rate of cargo declarations, number of errors in dangerous goods classification; Credit scoring metrics: Agent credit score calculated based on historical business data on the blockchain; Risk event log: including incidents, violation warnings, and rectification results.

[0034] 2. Ground service agent credit data reflects their operational safety and performance quality in cargo loading, unloading, receiving, inspection, and transshipment. Typical fields include: Operation records: number of loading and unloading operations, overtime rate, and cargo damage rate; Safety inspection results: Ground safety inspection pass rate, number of potential hazards found; Violation records: unauthorized operation, equipment malfunction, misinstallation incidents; Credit Score: A service credit value calculated based on a comprehensive assessment of historical operational quality and incident records; Regulatory feedback: Review results and opinions from regulatory authorities.

[0035] 3. Credit data of training institutions reflects their training compliance and student quality. Typical fields include: Organization registration information: organization name, registration number, certification type; Training quality indicators: trainee pass rate, course update frequency; Violation records: unauthorized training, forged certificates, expired courses; Credit score: A credit score calculated based on training quality, violations, and regulatory feedback; Audit results: Records of regular reviews and on-site inspections by the competent authority.

[0036] 4. Operator credit data reflects an individual's compliance and historical performance in actual operations. Typical fields include: Identity and job information: Operator ID, affiliated unit, job category; Training and Qualifications: Training institution, certificate number, validity period, skill level; Operational behavior records: number of loading / unloading tasks, number of violations, and accident-related records; Performance and evaluation: task completion rate, system security score; Credit Score: An automatically generated personal security credit score based on the above indicators.

[0037] S14: Input the full lifecycle business data of the air cargo to be transported and the credit data of the participating entities into the pre-trained risk prediction model, and output the transportation risk prediction results of the air cargo to be transported. S15: Store the entire lifecycle business data of the air cargo to be transported, the credit data of the participating entities, and the transportation risk prediction results on the blockchain; S16: During transportation, environmental parameters of the goods and the state parameters of the goods themselves are collected by multi-source sensing devices installed in the transport carrier and the packaging of the goods. S17: Determine whether a transportation accident has occurred based on environmental parameters and the cargo's own condition parameters; S18: When a transportation accident occurs, determine the type of the transportation accident and store the transportation accident in the blockchain; S19: After the goods are transported to their destination, the business data, transportation results, and all monitoring data generated during the transportation process will be stored in the blockchain.

[0038] In practice, multi-source sensing devices can be embedded wireless temperature and humidity sensors, accelerometers, barometric pressure sensors, tilt sensors, RFID modules, or GPS positioning modules, etc. Each sensing device uploads the collected data to the transportation monitoring node or the blockchain sidechain database via a wireless communication module.

[0039] After receiving the monitoring data, the system determines whether a transportation accident has occurred based on environmental parameters and the cargo's own status parameters.

[0040] When an abnormal fluctuation or exceeding a set threshold is detected in a parameter, the system triggers the accident identification process. In the accident identification process, the system determines the type of transportation accident based on abnormal characteristics. After determining the type of accident, the system signs and hashes the transportation accident information (including accident type, trigger time, involved flight segment, equipment number, and parameter snapshot, etc.) and stores it in the blockchain.

[0041] After being confirmed by a consensus algorithm, blockchain nodes write their data into the ledger, enabling tamper-proof evidence storage and full-process traceability management of transportation accidents.

[0042] After the goods arrive at their destination, the system will package all monitoring data (including normal and abnormal data) generated during the transportation process and write it into the blockchain to form a complete transportation data archive, providing basic data support for subsequent risk analysis and accountability.

[0043] In one possible implementation of this embodiment, a transportation accident is determined based on environmental parameters and the cargo's own state parameters. If a transportation accident occurs, the type of the accident is determined, and the accident is stored in the blockchain. This includes: Synchronize and preprocess environmental parameters and cargo status parameters over time; The processed environmental parameters and cargo status parameters are input into a pre-trained anomaly recognition model; Perform trend prediction on the time series of processed environmental parameters and cargo status parameters to generate predicted values ​​for the next time step; Calculate the residual sequence and its rolling statistics; Generate adaptive thresholds based on cargo category, flight segment type, and cargo space attributes; Residuals whose absolute value exceeds the adaptive threshold are considered as candidates for trend anomalies; Based on the strength and duration of the trend anomaly candidates, the trend anomaly candidates are classified into different levels: When the level of any candidate for abnormal trend reaches the preset warning level, or when multiple monitoring parameters show consistent abnormalities in time and space, it is determined that a transportation accident has occurred; the types of transportation accidents include at least: environmental over-limit accidents, packaging damage accidents, abnormal loading and unloading posture accidents, and energy safety accidents; The system outputs the accident type, trigger time, anomaly intensity, and impact range of the judgment results, and generates accident identification information. The accident identification information, along with the monitoring data, residual rolling statistics, and adaptive thresholds used for the determination, are signed and hashed to serve as the determination result for the transportation accident. The results of the transportation accident determination will be stored on the blockchain.

[0044] The process of determining whether a transportation accident has occurred based on environmental parameters and the cargo's own condition parameters includes the following steps: 1. Time synchronization and preprocessing: The system performs time synchronization, outlier removal, and interpolation smoothing on the collected environmental parameters and cargo status parameters to ensure that the data from different sensor channels are aligned on the time axis.

[0045] 2. Data Input and Model Recognition: The pre-processed environmental parameters and cargo status parameters are input into a pre-trained anomaly recognition model.

[0046] 3. Trend forecasting and residual calculation: The model predicts the parameter values ​​for the next moment based on historical window data, generates a prediction sequence, and calculates the residual sequence between the actual and predicted values.

[0047] The system further calculates rolling statistics of the residuals (mean, variance, skewness, etc.) to reflect the trend of parameter changes.

[0048] 4. Adaptive threshold generation: Adaptive thresholds are dynamically generated based on cargo category, flight segment type, and cargo space attributes.

[0049] For example, stricter temperature fluctuation thresholds are set for temperature-controlled goods, while more lenient environmental tolerances are set for ordinary goods.

[0050] 5. Identification and classification of trend anomaly candidates: When the absolute value of the residual exceeds the adaptive threshold, the system marks the parameter as a candidate for trend anomaly.

[0051] Based on the intensity (residual amplitude) and duration (continuous exceedance period) of the candidate anomalies, the system classifies the candidate anomalies into multiple risk levels.

[0052] 6. Accident Determination and Type Mapping: When the level of any candidate for abnormal trend reaches the preset warning level, or when multiple monitoring parameters show consistent abnormalities in time and space, it is determined that a transportation accident has occurred.

[0053] The system automatically identifies the type of incident based on the source of the anomaly, including but not limited to: Environmental limit violations (e.g., temperature, humidity, or air pressure exceeding the set range); Packaging damage incidents (sudden changes in packaging structural integrity or a decrease in sealing pressure); Accidents involving abnormal loading and unloading postures (excessive tilt angle of cargo or excessive vibration amplitude); Energy safety incidents (such as abnormal temperature rise in energized goods or chemical energy storage devices).

[0054] 7. Generation and on-chain evidence storage of incident results: The system outputs the accident type, trigger time, anomaly intensity, and scope of impact, and generates accident identification information.

[0055] The accident identification information, along with key monitoring data, residual statistics, and threshold parameters used for judgment, is digitally signed and hashed before being stored on the blockchain.

[0056] By leveraging the consensus mechanism of blockchain, accident records can be verified and preserved in an immutable manner.

[0057] Through the above steps, the system can achieve real-time risk identification and accident determination during transportation, forming a closed-loop technical path of "sensor monitoring - model recognition - trend analysis - accident determination - on-chain evidence storage", which greatly improves the intelligent monitoring capabilities and safety assurance level of air cargo transportation.

[0058] This technical solution stores the entire lifecycle business data of air cargo to be transported (transportation contracts, transportation appraisal reports, cargo delivery lists from freight forwarders, cargo receipt lists from ground service agents, cargo transportation status, qualifications of cargo transportation training institutions, qualifications of cargo operators, cargo operation logs, and multi-source business data such as violations) on the blockchain. Utilizing the blockchain's distributed consensus mechanism, timestamps, and hash chain structure, the authenticity, integrity, and immutability of the data records are guaranteed, providing a reliable data foundation for subsequent risk assessment and incident tracing. Business data generated by different participants (freight forwarders, ground service agents, training institutions, and operators) are uniformly aggregated and verified on the blockchain, solving the problems of data fragmentation, lack of unified standards, and difficulty in sharing among entities in traditional systems. This achieves secure data trust and collaborative management across organizations.

[0059] By incorporating credit scores and historical business records of freight forwarders, ground service agents, training institutions, and operators as credit data for participating entities, the system can comprehensively assess the compliance and reliability of the participating entities' behavior, providing quantitative basis for subsequent risk model training and regulatory decisions, and establishing a credit-based safety management system.

[0060] By combining full lifecycle business data with the credit data of participating entities and inputting them into a pre-trained risk prediction model, potential transportation risks of air cargo to be transported can be automatically identified, thereby enabling dynamic risk assessment and early warning before transportation and significantly improving transportation safety.

[0061] Credit data of participating entities and transportation risk prediction results are stored as hash credentials on the blockchain. After the goods arrive at their destination, business data and transportation results generated during the transportation process are also stored on the blockchain. In the event of a transportation accident, the transportation process can be quickly reconstructed based on the on-chain records, the authenticity of data can be verified, and the responsible party can be identified, improving the accuracy of accident tracing and regulatory transparency. Accident tracing analysis is built on the blockchain, eliminating the possibility of human intervention and post-event data tampering.

[0062] Example 2 It should be noted that the method also includes: In the event of a transportation accident, the system retrieves full lifecycle business data, credit data of participating entities, transportation risk prediction results, and current monitoring data for source tracing analysis to generate liability determination results.

[0063] The process involves retrieving full lifecycle business data, credit data of participating entities, transportation risk prediction results, and current monitoring data for source tracing analysis to generate liability determination results, specifically including: In the event of a transportation accident, full lifecycle business data, credit data of participating entities, transportation risk prediction results, and current monitoring data are retrieved as traceability data. Based on the timestamps, signature information and data hash values ​​recorded in the blockchain, the integrity and temporal consistency of the traceability data are verified. When the verification is successful, the key transportation node data in the traceability data are reconstructed according to the business process sequence to form a time series of the cargo transportation process; Based on the transportation contracts, cargo delivery lists, cargo receipt lists, cargo handling logs, and current monitoring data in the traceability data, an operational chain for the cargo transportation process is constructed. Input the time series and operation chain of the cargo transportation process into the accident tracing analysis model, and identify the accident triggering link and responsible party through the causal correlation analysis algorithm; Based on the identified responsible parties and their corresponding credit scores, violation records, and operational behaviors, a liability determination result for the transportation accident is generated. The results of liability determination and related data will be stored on the blockchain.

[0064] After accessing the aforementioned traceability data, the system first verifies the integrity and temporal consistency of the data based on the timestamp, signature information, and data hash value recorded in the blockchain.

[0065] When the hash value of the data matches the recorded value in the blockchain ledger, and the time series is continuous without any missing data, it is confirmed that the data has not been tampered with and is trustworthy. If the verification fails, an anomaly report is generated and submitted to the supervisory node for review.

[0066] After the data verification is passed, the system reconstructs the key transportation node data in the traceability data according to the business process sequence, forming a time-series structured dataset of the cargo transportation process.

[0067] This time series includes, but is not limited to, the following node information: Cargo delivery time, ground collection time, loading time, etc.; Operator ID, equipment ID, and environmental monitoring data snapshot for each node; Inter-node time intervals and state change trends.

[0068] By reconstructing time-series data, the changes in the status and operation of goods throughout the entire transportation process can be intuitively reflected, providing a temporal basis for accident cause analysis.

[0069] The system further constructs an operational chain for the cargo transportation process based on the transportation contracts, cargo delivery lists, cargo receipt lists, cargo operation logs, and monitoring data in the traceability data.

[0070] This operation chain is used to describe the behavioral logic and operational dependencies of each participating entity during the transportation process.

[0071] The time series and operation chain are used as joint inputs and fed into the pre-set accident tracing analysis model.

[0072] The model can use graph neural networks (GNNs) or causal reasoning algorithms (such as structural equation modeling (SEM), Granger causal analysis, or Bayesian causal networks) to model the event dependencies between nodes and identify possible accident triggering links and their corresponding responsible parties.

[0073] By comparing the changing trends of state variables before and after an accident, operational behavior characteristics, and the credit scores and violation records of the responsible parties, the model can output the probability distribution of accident liability.

[0074] When the probability of liability of a certain responsible party exceeds a preset threshold, the system automatically generates a liability determination result.

[0075] Based on the responsible parties, accident-triggered events, and corresponding credit data identified by the source tracing model, the system generates a transportation accident liability determination result, which includes: Accident number and type; triggering point and responsible party; weight of responsibility or level of responsibility; Relevant credit scores, violation records and judgment criteria; judgment time and signature node information.

[0076] The generated liability determination results are stored in the blockchain after being digitally signed and hashed.

[0077] After the blockchain network confirms the result through the consensus mechanism, it solidifies the result into the ledger, realizing the tamper-proof, traceable, and multi-party verifiable sharing of accident responsibility data.

[0078] Regulatory nodes can query the accident liability results through the on-chain interface and file or impose penalties based on the actual review opinions.

[0079] Example 3 It should be noted that the method also includes: Data stored on the blockchain will be subject to layered encryption and access control based on security levels. Among them, high-security-level data uses homomorphic encryption or multi-key fragmentation encryption, and can only be decrypted and accessed by nodes with regulatory authority; Medium-security level data uses symmetric encryption and implements hierarchical authorization based on role-based access control policies; Low-security-level data is stored in plaintext or hash indexes for data consistency verification.

[0080] High-security data includes, but is not limited to: Information on dangerous goods categories, transport routes, flight numbers, identification information of freight forwarders and operators, packaging structure parameters, and raw sensor data for transport monitoring, etc.

[0081] This type of data involves commercial privacy and security sensitive content, and access is restricted to nodes with regulatory authority.

[0082] In this embodiment, high-security data is protected using homomorphic encryption or multi-key fragmentation encryption.

[0083] Under homomorphic encryption, regulatory nodes can perform statistical, comparative, or risk analysis operations without decrypting the data content, ensuring both data computability and privacy security. In the multi-key fragmentation encryption method, the system divides the encryption key into several key fragments and stores them in different monitoring nodes. The key can only be reconstructed and decrypted for access when the preset number of joint authorizations (such as three-party or multi-party joint authorizations) is reached.

[0084] The above methods achieve the goal of ensuring regulatory visibility while maintaining enterprise data confidentiality, preventing the leakage of highly sensitive information from a single node.

[0085] The medium-level safety data includes business contracts, delivery lists, collection lists, training qualifications, credit scores, and accident determination results.

[0086] This type of data is related to business operations, but does not directly involve sensitive personal or security route information.

[0087] The system uses a symmetric encryption algorithm to encrypt and store data with medium security level.

[0088] To ensure access controllability during multi-party collaboration, this embodiment introduces a role-based access control policy, which implements hierarchical authorization by defining access permissions for different roles (such as regulatory nodes, airline nodes, agent nodes, and training institution nodes).

[0089] When an access request is made, the system matches and verifies the calling node's digital certificate against the role and permission table, allowing only nodes that meet the authorization level to perform data reading or calling operations.

[0090] This mechanism enables secure data sharing through multi-party collaboration, ensuring that "data is available but not visible," and avoiding the risk of unauthorized access across entities.

[0091] Low-security-level data includes non-sensitive public information such as hash indexes, timestamps, node identifiers, model version information, and credit score summaries.

[0092] The system stores this type of data in plaintext or hash indexes to enable fast ledger lookup and consistency verification.

[0093] When the system performs regulatory audits or model training, it can verify data integrity by comparing hash indexes without accessing the original sensitive content, thus balancing performance and privacy protection.

[0094] Example 4 It should be noted that the method also includes: Retrieve historical transportation datasets from the blockchain; historical transportation datasets include full lifecycle business data of historical transported goods, credit data of participating entities, and labeled transportation risk event data; Data cleaning and risk feature extraction are performed on historical transportation datasets. Risk features include at least: cargo category, transportation environment parameters, transportation duration, violation event characteristics, freight forwarder credit score, ground service agent credit score, freight transportation training institution credit score, freight operator credit score, freight transportation training institution qualification, and freight operator qualification. The extracted risk features are input into a pre-defined deep learning model for training; the deep learning model includes a time series prediction sub-model and a multi-dimensional feature fusion sub-model. The loss function is optimized through iterative training, and the model parameters are updated until the prediction error meets the set convergence condition. After the deep learning model is trained, a risk prediction model for online risk assessment is generated, and the model parameter summary and training version information of the risk prediction model are stored in the blockchain.

[0095] In this embodiment, historical transportation datasets are first retrieved from the blockchain. These datasets include full lifecycle business data generated during past air cargo transportation missions, credit data of participating entities, and transportation risk event data confirmed by regulatory authorities. Since all of the above data is stored through a blockchain notarization mechanism, it possesses the characteristics of being tamper-proof and traceable, and can be used as trusted training samples.

[0096] The system performs data cleaning and feature extraction operations on historical transportation datasets.

[0097] Data cleaning includes removing missing items, duplicates, and abnormal records, and standardizing timestamps.

[0098] The extracted multidimensional features are input into a pre-defined deep learning model for training.

[0099] Deep learning models include time series prediction sub-models and multi-dimensional feature fusion sub-models: The time series prediction sub-model is used to capture the dynamic characteristics of parameter changes over time during transportation; The multidimensional feature fusion sub-model is used to integrate cargo features, credit features, and historical risk features to achieve global risk modeling.

[0100] During training, the system iteratively optimizes the loss function (such as mean squared error or cross-entropy loss) to update the model parameters until the prediction error converges to a set threshold.

[0101] After training is completed, the system generates a risk prediction model that can be used for online risk assessment. The model parameter summary, training version information and performance indicators (such as accuracy and recall) are signed and hashed and then stored in the blockchain to achieve traceability and tamper-proof management of the model version.

[0102] Example 5 It should be noted that the method also includes: Based on the transportation risk prediction results, the transportation risks of the air cargo to be transported are classified. When the transportation risk of air cargo to be transported exceeds the set risk level, corresponding risk warning information is generated and corresponding regulatory handling strategies are invoked. The regulatory handling strategies include at least: temporarily suspending loading and re-inspecting the air cargo to be transported, reviewing the credit of the participating entities, and reviewing the qualifications of cargo transportation training institutions and cargo operators. The generated risk warning information, regulatory handling strategies, and execution results will be stored on the blockchain.

[0103] After completing the evaluation of the risk prediction model, the system classifies the transportation risks of the air cargo to be transported based on the output values ​​of the risk prediction results.

[0104] The classification can include multiple risk levels, such as low risk, moderate risk, high risk and very high risk. The specific classification can be automatically determined based on the risk probability range output by the model or the set confidence threshold.

[0105] When the transportation risk of air cargo to be transported exceeds the set risk level threshold, the system automatically generates risk warning information.

[0106] The risk warning information includes: cargo number, risk level, risk source, trigger time, and related participating entities.

[0107] The system invokes the corresponding regulatory response strategy based on the risk level, and the regulatory response strategy includes at least the following steps: 1. For air cargo, a temporary suspension of loading shall be implemented, and a re-inspection shall be carried out before loading, including the integrity of the cargo packaging, the accuracy of the declared category, and the compliance of safety markings; 2. Review the credit data of related freight forwarders, ground service agents and other participating entities, and assess their compliance and performance records in recent transportation tasks; 3. Automatically verify the qualifications of the training institutions and operators responsible for this batch of operations, and confirm whether the certificates are valid and whether the training type matches the current goods category.

[0108] The system will sign and hash the risk warning information, the execution process of the regulatory disposal strategy, and the final execution result together before writing them into the blockchain ledger.

[0109] Once the blockchain nodes are confirmed through consensus, they form an immutable record for early warning and supervision, providing data support for subsequent regulatory audits and risk statistics.

[0110] Example 6 It should be noted that the method also includes: After the goods arrive at their destination, the credit data of the participating entities will be updated based on the business data and transportation results generated during the transportation process.

[0111] After the goods arrive at their destination, the system updates the credit data of freight forwarders, ground service agents, training institutions, and operators based on the business data and transportation results generated during the transportation process.

[0112] Business data includes transportation time, anomaly records, number of accidents, regulatory handling status, and compliance inspection results; The transportation results include indicators such as whether the goods are intact, whether any warnings have been triggered, and whether there have been any delays or violations.

[0113] The system performs credit updates in the following ways: If no abnormalities or accidents occur during this transportation mission and the operation complies with regulations, the credit score of the corresponding entity will be increased by a preset increment. If a minor violation occurs (such as a slight delay or missing procedure), the credit score will remain unchanged or decrease slightly. In the event of a serious violation or incident of liability, the credit score will be automatically reduced based on the incident determination results, and the type of violation and penalty information will be recorded.

[0114] The updated credit data is stored on the blockchain after being hashed and verified by signature, forming a long-term traceable credit evolution chain.

[0115] Regulatory nodes can conduct credit rating, blacklist management, or risk-based access for each entity based on on-chain credit records, thereby achieving a closed-loop mechanism of "promoting security with credit and strengthening regulation with data".

[0116] Example 7 Figure 2 This is a schematic diagram of the structure of a blockchain-based air cargo transportation management system provided in one embodiment of this application, with reference to... Figure 2 A blockchain-based air cargo transportation management system includes: Processor 21 and memory 22; Processor 21 and memory 22 are connected via a communication bus: The processor 21 is used to call and execute the program stored in the memory 22; The memory 22 is used to store a program, which is used to execute at least one of the blockchain-based air cargo transportation management methods described in the above embodiments.

[0117] It is understood that the same or similar parts in the above embodiments can be referred to each other, and the contents not described in detail in some embodiments can be referred to the same or similar contents in other embodiments.

[0118] It should be noted that in the description of this application, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. Furthermore, in the description of this application, unless otherwise stated, "a plurality of" means at least two.

[0119] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the function involved, as will be understood by those skilled in the art to which embodiments of this application pertain.

[0120] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0121] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0122] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0123] The storage media mentioned above can be read-only memory, disk, or optical disk, etc.

[0124] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0125] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A blockchain-based air cargo transportation management method, characterized in that, include: Receive air cargo transportation requests from freight forwarders; When it is determined that there is a safety risk to the air cargo to be transported, obtain the full lifecycle business data of the air cargo to be transported. Credit scores and historical business records of freight forwarders, ground service agents, cargo transportation training institutions, and cargo operators are retrieved as credit data of the participating entities for the air cargo to be transported. The entire lifecycle business data of the air cargo to be transported and the credit data of the participating entities are input into a pre-trained risk prediction model, which outputs the transportation risk prediction results of the air cargo to be transported. Store the entire lifecycle business data of air cargo to be transported, the credit data of participating entities, and the results of transportation risk prediction on the blockchain; During transportation, multi-source sensing devices installed in the transport carrier and cargo packaging collect environmental parameters of the cargo and the cargo's own status parameters. Determine whether a transportation accident has occurred based on environmental parameters and the cargo's own condition parameters; When a transportation accident occurs, the type of the accident is determined and the accident is stored in the blockchain; After the goods arrive at their destination, the business data, transportation results, and all monitoring data generated during the transportation process will be stored in the blockchain.

2. The method according to claim 1, characterized in that, The full lifecycle business data includes at least: transportation contracts, transportation appraisal reports, cargo delivery lists from the freight forwarder's side, cargo collection lists from the ground service agent's side, cargo transportation status, qualifications of cargo transportation training institutions, qualifications of cargo operators, cargo operation logs, and violations of operation events; The environmental parameters include at least: temperature, humidity, air pressure, vibration intensity, and spatial location data; the cargo's own status parameters include: packaging integrity, cabin orientation, sealing status, and storage status.

3. The method according to claim 1, characterized in that, Based on environmental parameters and the cargo's own condition parameters, it is determined whether a transportation accident has occurred. If a transportation accident occurs, the type of accident is determined, and the accident is stored on the blockchain, including: Synchronize and preprocess environmental parameters and cargo status parameters over time; The processed environmental parameters and cargo status parameters are input into a pre-trained anomaly recognition model; Perform trend prediction on the time series of processed environmental parameters and cargo status parameters to generate predicted values ​​for the next time step; Calculate the residual sequence and its rolling statistics; Generate adaptive thresholds based on cargo category, flight segment type, and cargo space attributes; Residuals whose absolute value exceeds the adaptive threshold are considered as candidates for trend anomalies; Based on the strength and duration of the trend anomaly candidates, the trend anomaly candidates are classified into different levels: When the level of any candidate for abnormal trend reaches the preset warning level, or when multiple monitoring parameters show consistent abnormalities in time and space, it is determined that a transportation accident has occurred; the types of transportation accidents include at least: environmental limit violation accidents, packaging damage accidents, abnormal loading and unloading posture accidents, and energy safety accidents; The system outputs the accident type, trigger time, anomaly intensity, and impact range of the judgment results, and generates accident identification information. The accident identification information, together with the monitoring data, residual rolling statistics, and adaptive threshold used for judgment, are signed and hashed to obtain the judgment result of the transportation accident. The results of the transportation accident determination will be stored on the blockchain.

4. The method according to claim 3, characterized in that, The method further includes: In the event of a transportation accident, the system retrieves full lifecycle business data, credit data of participating entities, transportation risk prediction results, and current monitoring data for source tracing analysis to generate liability determination results.

5. The method according to claim 4, characterized in that, Retrieve full lifecycle business data, credit data of participating entities, transportation risk prediction results, and current monitoring data for source tracing analysis to generate liability determination results, including: In the event of a transportation accident, full lifecycle business data, credit data of participating entities, transportation risk prediction results, and current monitoring data are retrieved as traceability data. The integrity and temporal consistency of the traceability data are verified based on the timestamps, signature information and data hash values ​​recorded in the blockchain. When the verification is successful, the key transportation node data in the traceability data are reconstructed according to the business process sequence to form a time series of the cargo transportation process; Based on the transportation contracts, cargo delivery lists, cargo receipt lists, cargo handling logs, and current monitoring data in the traceability data, an operational chain for the cargo transportation process is constructed. Input the time series and operation chain of the cargo transportation process into the accident tracing analysis model, and identify the accident triggering link and responsible party through the causal correlation analysis algorithm; Based on the identified responsible parties and their corresponding credit scores, violation records, and operational behaviors, a liability determination result for the transportation accident is generated. The liability determination results and related data will be stored in the blockchain.

6. The method according to claim 1, characterized in that, The method further includes: Data stored on the blockchain will be subject to layered encryption and access control based on security levels. Among them, high-security-level data uses homomorphic encryption or multi-key fragmentation encryption, and can only be decrypted and accessed by nodes with regulatory authority; Medium-security level data uses symmetric encryption and implements hierarchical authorization based on role-based access control policies; Low-security-level data is stored in plaintext or hash indexes for data consistency verification.

7. The method according to claim 1, characterized in that, The method further includes: Retrieve historical transportation datasets from the blockchain; the historical transportation datasets include full lifecycle business data of historical transported goods, credit data of participating entities, and labeled transportation risk event data; The historical transportation dataset is cleaned and risk features are extracted. The risk features include at least: cargo category, transportation environment parameters, transportation duration, violation event characteristics, freight forwarder credit score, ground service agent credit score, cargo transportation training institution credit score, cargo operator credit score, cargo transportation training institution qualification, and cargo operator qualification. The extracted risk features are input into a pre-defined deep learning model for training; the deep learning model includes a time series prediction sub-model and a multi-dimensional feature fusion sub-model. The loss function is optimized through iterative training, and the model parameters are updated until the prediction error meets the set convergence condition. After the deep learning model is trained, a risk prediction model for online risk assessment is generated, and the model parameter summary and training version information of the risk prediction model are stored in the blockchain.

8. The method according to claim 1, characterized in that, The method further includes: Based on the transportation risk prediction results, the transportation risks of the air cargo to be transported are classified. When the transportation risk of the air cargo to be transported is higher than the set risk level, a corresponding risk warning is generated and the corresponding regulatory handling strategy is invoked; the regulatory handling strategy includes at least: temporarily suspending the loading of the air cargo to be transported and re-inspecting it, reviewing the credit of the participating entities, and reviewing the qualifications of cargo transportation training institutions and cargo operators; The generated risk warning information, regulatory handling strategies, and execution results will be stored on the blockchain.

9. The method according to claim 1, characterized in that, The method further includes: After the goods arrive at their destination, the credit data of the participating entities will be updated based on the business data and transportation results generated during the transportation process.

10. A blockchain-based air cargo transportation management system, characterized in that, include: Processor and memory; The processor and memory are connected via a communication bus: The processor is used to call and execute the program stored in the memory; The memory is used to store a program, which is at least used to execute the blockchain-based air cargo transportation management method according to any one of claims 1-9.

Images