Blockchain-based product logistics management scheduling method, medium and device

Abstract

The application discloses a product logistics management scheduling method based on a block chain, a medium and equipment, and generates an initial transportation path scheme by collecting logistics transportation demand information and supply chain node data; a decentralized logistics resource pool is constructed, transportation fluctuation parameters are collected and verified to generate a credible state matrix; the initial transportation path scheme and the logistics resource credible state matrix are input into a graph neural network scheduling model to output a dynamic scheduling scheme; the compliance verification of task allocation and scheduling instructions is automatically executed through a smart contract; finally, the scheduling execution result and the logistics resource credible state matrix are updated to a distributed ledger, and a logistics management report is output. Through the deep cooperation of the smart contract and the dynamic path optimization, the application realizes real-time and credible scheduling of the transportation process, solves the problems of insufficient dynamic response and lack of multi-party cooperation trust in the existing logistics system, and improves the reliability and efficiency of sensitive goods transportation such as cold chain.

Description

Technical Field

[0001] This invention relates to the field of blockchain smart logistics technology, and in particular to a product logistics management and scheduling method, medium and equipment based on blockchain. Background Technology

[0002] In the field of modern logistics management, especially in the transportation of temperature-sensitive goods, achieving dynamic optimization of the transportation process and reliable multi-party collaboration has always been a focus of industry attention. Current logistics systems typically employ a centralized scheduling model, relying on preset rules or historical data for route planning, which struggles to adapt to real-time changes during transportation. While the application of IoT technology has made basic data collection, such as vehicle positioning and environmental monitoring, possible, the data silos formed at each stage make it difficult to effectively integrate and utilize information.

[0003] In recent years, blockchain technology has been introduced into the logistics field to enhance data credibility. Some solutions attempt to automate the execution of transportation agreements through smart contracts, while other studies employ machine learning algorithms to optimize route planning. However, these methods still have limitations in terms of dynamic response and system coordination: on the one hand, static data recording mechanisms struggle to support real-time decision-making needs; on the other hand, algorithm optimization and blockchain verification are often disconnected, failing to form a closed-loop management system. Particularly in high-value scenarios such as cross-border logistics and pharmaceutical cold chain logistics, the contradiction between the dynamic changes in the transportation environment and the static nature of scheduling strategies leads to delayed responses to anomalies. Furthermore, the lack of a reliable automated evaluation mechanism still necessitates manual intervention for coordination during multi-party collaboration. These issues constrain the potential of logistics systems in terms of efficiency improvement and cost control, and also affect the overall reliability of complex supply chain networks. Summary of the Invention

[0004] In view of this, the purpose of this invention is to propose a product logistics management and scheduling method, medium and equipment based on blockchain, which realizes real-time reliable adjustment of transportation routes through deep coupling of smart contracts and dynamic routing optimization, and solves the problems of insufficient dynamic response capability and lack of trust in multi-party collaboration in existing logistics systems.

[0005] To achieve the aforementioned technical objectives, in a first aspect, this application provides a blockchain-based product logistics management and scheduling method, comprising:

[0006] Collect product logistics and transportation demand information and supply chain node data. The logistics and transportation demand information includes product type, transportation priority, temperature control requirements and target delivery area. The supply chain node data includes warehouse location, transportation vehicle status and carrier qualifications.

[0007] The logistics transportation demand information is dynamically decomposed, and a multi-objective optimization algorithm is used to generate an initial transportation route plan. The route feasibility score of the initial transportation route plan is calculated by combining historical transportation data.

[0008] A decentralized logistics resource pool is built based on supply chain node data. Transportation fluctuation parameters are collected in real time through edge computing nodes. These parameters include vehicle GPS trajectory, temperature and humidity sensor data, and electronic lock status. A spatiotemporal consistency verification algorithm is used to filter abnormal data, and the verified transportation fluctuation parameters are stored on the blockchain to generate a reliable logistics resource status matrix.

[0009] The initial transportation route plan and the logistics resource reliability state matrix are input into the graph neural network scheduling model. The spatiotemporal dependencies between transportation nodes are modeled through the graph attention mechanism, the path weights are dynamically adjusted, and the dynamic scheduling plan containing real-time path optimization suggestions, emergency scheduling instructions and resource allocation strategies is output.

[0010] The smart contract is triggered by a dynamic scheduling scheme. The smart contract automatically allocates transportation tasks, freezes abnormal batch transaction permissions and calculates carrier incentive tokens according to preset rules. At the same time, it verifies the compliance of scheduling instructions through zero-knowledge proof and obtains the scheduling execution result.

[0011] Based on the blockchain consensus mechanism, the scheduling execution results and the trusted status matrix of logistics resources are updated to the distributed ledger, generating and outputting a logistics management report that includes the completion rate of transportation tasks, the temperature control compliance rate, and statistics on violations.

[0012] In some embodiments, the logistics transportation demand information is dynamically decomposed into tasks, an initial transportation route plan is generated using a multi-objective optimization algorithm, and a route feasibility score for the initial transportation route plan is calculated by combining historical transportation data, including:

[0013] Based on product type, transportation priority, and temperature control requirements in logistics and transportation demand information, a transportation constraint weight matrix is ​​constructed using the analytic hierarchy process. The transportation constraint weight matrix is ​​used to quantify the differentiated requirements of different product categories for timeliness, temperature stability, and safety.

[0014] The transportation constraint weight matrix is ​​spatiotemporally aligned with historical transportation data, and an improved non-dominated sorting genetic algorithm is used to solve multi-objective optimization problems, generating a set of candidate path schemes containing Pareto optimal solutions.

[0015] A dynamic risk assessment is performed on each candidate route in the candidate route solution set. The potential traffic congestion probability and temperature control deviation risk of each candidate route in the target delivery area are predicted by the long short-term memory network. Combined with the real-time vehicle status data in the logistics resource trust state matrix, the comprehensive feasibility score of each candidate route solution is calculated.

[0016] Based on the comprehensive feasibility score, the candidate route schemes in the candidate route scheme set are sorted and filtered, and the candidate route schemes with comprehensive feasibility scores lower than the preset feasibility score threshold are eliminated. The remaining candidate route schemes are matched with the carrier qualifications in the supply chain node data to generate the initial transportation route scheme and the corresponding route feasibility score.

[0017] In some embodiments, a decentralized logistics resource pool is constructed based on supply chain node data, including:

[0018] The edge computing nodes in the blockchain network collect dynamic resource data of each supply chain node in real time. The dynamic resource data includes the real-time inventory status of the warehousing node, the load capacity of the transport vehicle and the information on available refrigerated units, and the current task load status of the carrier.

[0019] A fast verification algorithm based on Bloom filters is used to initially screen the dynamic resource data, removing invalid or duplicate data records to obtain verified dynamic resource data.

[0020] The verified dynamic resource data is correlated and mapped with the static qualification information in the supply chain node data to construct a multi-dimensional resource feature vector, which includes spatial availability, equipment compatibility and serviceability.

[0021] Multidimensional resource feature vectors are classified and integrated according to preset rules to generate a decentralized logistics resource pool with timestamps. Each resource unit in the decentralized logistics resource pool is accompanied by a verifiable credit score and historical service records.

[0022] In some embodiments, transportation fluctuation parameters are collected in real time via edge computing nodes, including:

[0023] Real-time acquisition of raw sensor data, including vehicle GPS positioning coordinates, multi-area temperature and humidity sensor readings, and electronic lock switch status signals;

[0024] An adaptive sampling strategy is adopted to dynamically acquire raw sensor data. When the rate of change of temperature and humidity exceeds a preset threshold or the GPS signal is lost, the sampling frequency is automatically increased.

[0025] The collected data is denoised in real time using a lightweight filtering algorithm, and digital signatures and timestamps of edge nodes are added to generate transportation fluctuation parameters with identity authentication.

[0026] In some embodiments, a spatiotemporal consistency verification algorithm is used to filter out abnormal data, and the verified transportation fluctuation parameters are stored on the blockchain to generate a reliable state matrix of logistics resources, including:

[0027] Receive transportation fluctuation parameters, parse and obtain vehicle GPS trajectory sequence, temperature and humidity time series data and electronic lock status change records, and record them as the first processed data;

[0028] A spatiotemporal correlation analysis model is constructed. The first processed data is input into the spatiotemporal correlation analysis model. The matching degree between GPS trajectory and temperature and humidity changes is identified through a multi-dimensional clustering algorithm. The model detects whether there is human tampering or equipment failure, and then obtains the second processed data.

[0029] A differential privacy protection algorithm is used to anonymize the second-processed data, generating standard data units that meet the storage requirements of blockchain.

[0030] The processed standard data units are written into the blockchain via smart contracts to generate a trusted state matrix of logistics resources, and to update the real-time state records in the decentralized logistics resource pool.

[0031] In some embodiments, an initial transportation route plan and a logistics resource reliability state matrix are input into a graph neural network scheduling model. A graph attention mechanism is used to model the spatiotemporal dependencies between transportation nodes, dynamically adjusting path weights and outputting a dynamic scheduling scheme that includes real-time route optimization suggestions, emergency scheduling instructions, and resource allocation strategies.

[0032] Construct a transportation network topology graph, converting warehousing nodes, transportation vehicles, and transfer stations into graph nodes. Based on the spatiotemporal characteristics and resource availability indicators in the logistics resource trust state matrix, establish node feature vectors corresponding to the graph nodes, and construct edge features according to the actual transportation route connection relationships.

[0033] A multi-layer graph attention network is used to learn features of the transportation network topology graph. The spatial dependency weights between graph nodes are calculated through a multi-head attention mechanism, and a temporal convolutional network is combined to capture the dynamic change patterns of transportation resources, thereby obtaining the path weights of the optimized initial transportation path.

[0034] The priority scores of each initial transportation path are iteratively updated using the message passing mechanism of a graph neural network to generate a set of candidate optimized paths;

[0035] Based on the candidate optimization path set, real-time path optimization suggestions are dynamically generated through reinforcement learning strategies. When abnormal fluctuations are detected in the logistics resource trust state matrix, emergency dispatch instructions containing backup routes and emergency resource allocation are automatically triggered.

[0036] The optimized path weights are integrated with the initial transportation path plan to output a dynamic scheduling plan that includes optimal path recommendations, resource reallocation plans, and risk warning information.

[0037] In some embodiments, smart contract execution is triggered based on a dynamic scheduling scheme. The smart contract automatically allocates transportation tasks, freezes transaction permissions for abnormal batches, and calculates carrier incentive tokens according to preset rules. Simultaneously, it verifies the compliance of scheduling instructions using zero-knowledge proofs to obtain the scheduling execution result, including:

[0038] The algorithm analyzes the path optimization suggestions and resource allocation strategies in the dynamic scheduling scheme, and uses smart contracts to allocate transportation tasks to the optimal carrier node, generating task allocation results. The allocation process is based on multi-dimensional optimization selection based on the real-time available resources in the logistics resource trust status matrix and the carrier credit score.

[0039] When the detected transportation fluctuation parameters exceed the preset safety threshold, the anomaly handling smart contract is triggered, automatically freezing the transaction permissions of the relevant batch of products and generating an immutable violation record on the blockchain. At the same time, an encrypted alarm is sent to the regulatory node, and an anomaly handling record is generated.

[0040] The number of incentive tokens is dynamically calculated based on the carrier's task completion quality, timeliness, and temperature control compliance rate. External market data is obtained through a decentralized oracle to adjust the token value anchoring coefficient, resulting in a detailed token incentive list.

[0041] A zero-knowledge proof verification module is constructed to generate a validity proof that the scheduling instructions comply with the product sales rules, which is then used by regulators for compliance spot checks to obtain compliance proof.

[0042] The task allocation results, exception handling records, token incentive details, and compliance proofs are packaged to generate the scheduling execution results.

[0043] In some embodiments, the scheduling execution results and the trusted state matrix of logistics resources are updated to the distributed ledger according to the blockchain consensus mechanism, generating and outputting a logistics management report that includes statistics on transportation task completion, temperature control compliance rate, and violations, including:

[0044] Based on the scheduling execution results, the task completion indicators for each transportation batch are automatically calculated through smart contracts. The task completion indicators include timeliness achievement rate, path deviation, and resource utilization efficiency.

[0045] Historical temperature control sensor data from the logistics resource trust status matrix is ​​extracted, and the temperature control compliance rate at each transportation stage is calculated using a sliding window algorithm. The frequency and duration of abnormal temperature fluctuation events are also identified.

[0046] By using smart contracts that record violations on the blockchain, the distribution and spatial characteristics of violation event types within a preset period are statistically analyzed to generate analysis results of violation hotspot areas.

[0047] By weighting and integrating task completion indicators, temperature control compliance rate, and analysis results of violation hotspots, suggestions for updating carrier credit scores and supply chain optimization solutions are generated.

[0048] The logistics management report integrates carrier credit score update suggestions and supply chain optimization plans with task completion indicators, temperature control compliance rate and violation hotspot area analysis results into a logistics management report. The logistics management report includes a transportation performance trend chart, a temperature control quality heat map and violation risk warning prompts.

[0049] In a second aspect, the present invention also provides a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, implement the method described in the first aspect.

[0050] In a third aspect, the present invention also provides an electronic device including a memory and a processor, the memory being used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method described in the first aspect.

[0051] By adopting the above technical solution, the present invention has the following beneficial effects compared with the prior art: It generates an initial transportation route plan by collecting logistics transportation demand information and supply chain node data; it constructs a decentralized logistics resource pool, collects and verifies transportation fluctuation parameters to generate a reliable state matrix; it inputs the initial transportation route plan and the reliable state matrix of logistics resources into a graph neural network scheduling model to output a dynamic scheduling plan; it automatically executes task allocation and compliance verification of scheduling instructions through smart contracts; and finally, it updates the scheduling execution results and the reliable state matrix of logistics resources to a distributed ledger and outputs a logistics management report. The present invention achieves real-time reliable scheduling of the transportation process through deep collaboration between smart contracts and dynamic route optimization, solving the problems of insufficient dynamic response and lack of trust in multi-party collaboration in existing logistics systems, and improving the reliability and efficiency of transportation of sensitive goods such as cold chain logistics. Attached Figure Description

[0052] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0053] Figure 1 This is a flowchart illustrating steps S101 to S106 of the method described in the specific implementation embodiment;

[0054] Figure 2This is a flowchart illustrating steps S201 to S204 of the method described in the specific implementation embodiment;

[0055] Figure 3 This is a schematic diagram of the structure of the electronic device described in a specific embodiment.

[0056] The reference numerals used in the above figures are explained as follows:

[0057] 1. Electronic equipment;

[0058] 11. Memory;

[0059] 12. Processor. Detailed Implementation

[0060] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be particularly noted that the following embodiments are for illustrative purposes only and do not limit the scope of the invention. Similarly, the following embodiments are only some, not all, embodiments of the present invention, and all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0061] Please see Figure 1 In a first aspect, this embodiment provides a product logistics management and scheduling method based on blockchain, including:

[0062] S101. Collect product logistics and transportation demand information and supply chain node data. Logistics and transportation demand information includes product type, transportation priority, temperature control requirements and target delivery area. Supply chain node data includes warehouse location, transportation vehicle status and carrier qualifications.

[0063] S102. Dynamically decompose the logistics transportation demand information, use a multi-objective optimization algorithm to generate an initial transportation route plan, and calculate the route feasibility score of the initial transportation route plan in combination with historical transportation data.

[0064] S103. Construct a decentralized logistics resource pool based on supply chain node data. Collect transportation fluctuation parameters in real time through edge computing nodes. The transportation fluctuation parameters include vehicle GPS trajectory, temperature and humidity sensor data and electronic lock status. Use a spatiotemporal consistency verification algorithm to filter abnormal data and store the verified transportation fluctuation parameters on the blockchain to generate a logistics resource trusted status matrix.

[0065] S104. Input the initial transportation route plan and the logistics resource trust state matrix into the graph neural network scheduling model. Model the spatiotemporal dependency between transportation nodes through the graph attention mechanism, dynamically adjust the path weights, and output a dynamic scheduling plan that includes real-time path optimization suggestions, emergency scheduling instructions and resource allocation strategies.

[0066] S105. Based on the dynamic scheduling scheme, the smart contract is triggered to execute. The smart contract automatically allocates transportation tasks, freezes abnormal batch transaction permissions and calculates carrier incentive tokens according to preset rules. At the same time, it verifies the compliance of the scheduling instructions through zero-knowledge proof and obtains the scheduling execution result.

[0067] S106. Based on the blockchain consensus mechanism, update the scheduling execution results and the trusted status matrix of logistics resources to the distributed ledger, generate and output a logistics management report that includes the completion rate of transportation tasks, the temperature control compliance rate and statistics of violations.

[0068] In step S101, logistics transportation demand information serves as the raw input to the scheduling system. Its product type field distinguishes between regular goods and special categories such as pharmaceutical cold chain products. Transportation priority can adopt the industry-standard T1-T4 grading system. Temperature control requirements record the allowable temperature fluctuation range of the product. The target delivery area is defined using geographic information system coordinates. Preferably, supply chain node data is collected through IoT terminals deployed in warehouses and transportation vehicles. Warehouse location information is linked to inventory data from the enterprise resource planning system. Vehicle status includes real-time monitoring parameters such as engine condition and fuel level. Carrier qualification information requires verification of its digital certificate validity via blockchain nodes. Furthermore, the data collection process employs an encrypted transmission protocol to ensure information security, establishing a reliable data foundation for subsequent intelligent scheduling.

[0069] Step S102 employs dynamic task decomposition technology to break down complex logistics orders into a set of sub-tasks with spatiotemporal constraints. The multi-objective optimization algorithm simultaneously considers transportation costs, timeliness, and carbon emission indicators during path generation, resulting in an initial transportation route plan that includes a detailed sequence of transit nodes and time window arrangements. Preferably, the path feasibility score is calculated by analyzing the frequency and resolution efficiency of abnormal events in historical transportation records. This scoring mechanism can effectively identify potentially high-risk path segments, providing a basis for subsequent dynamic adjustments.

[0070] The decentralized logistics resource pool constructed in step S103 realizes a digital twin of physical transportation resources. Preferably, edge computing nodes are deployed at key logistics facilities, which can reduce the impact of network transmission latency through local preprocessing. The vehicle GPS trajectory data collected by these nodes needs to be cross-verified through multi-base station positioning. Temperature and humidity sensor readings meet the requirements of national metrological verification regulations, and electronic lock status information includes encrypted user identity identifiers. The spatiotemporal consistency verification algorithm identifies anomalies by analyzing the time-series characteristics and spatial correlations of device data, such as vehicle signals appearing in different locations at the same time or abnormal temperature change records. The generated logistics resource trusted status matrix adopts a multi-dimensional data structure, which includes key dimensions such as resource availability, environmental compliance, and operational trustworthiness. Furthermore, the logistics resource trusted status matrix is ​​distributed and synchronized in real time through a blockchain network, providing the system with the latest logistics status snapshot.

[0071] The graph neural network scheduling model in step S104 captures the implicit spatiotemporal correlation patterns in the transportation network through a graph attention mechanism. When the logistics resource reliability state matrix indicates an anomaly in a certain route segment, the model adaptively adjusts the weight coefficients of relevant paths and generates an optimization scheme by comprehensively considering the distribution of remaining transport capacity. The three types of instructions output by the dynamic scheduling scheme have a synergistic relationship: real-time route optimization suggestions focus on geographical route adjustments, emergency scheduling instructions handle sudden equipment failures, and resource allocation strategies optimize the matching scheme between vehicles and goods. This multi-layered response mechanism enables the system to effectively cope with various uncertainties in the logistics process.

[0072] During the execution of the smart contract in step S105, based on the verified path optimization suggestions and resource allocation strategies in the dynamic scheduling scheme, the transportation task allocation mechanism is automatically triggered through pre-set contract logic. The smart contract first verifies the real-time vehicle status and carrier qualifications recorded in the logistics resource trust status matrix. When transportation fluctuation parameters exceed a preset safety threshold, the on-chain transaction permissions for the relevant batch of products are immediately frozen, and an immutable violation record is generated. The task allocation process strictly follows the resource priority ranking in the dynamic scheduling scheme, while also selecting the best match based on the real-time updated carrier credit score. For each successfully allocated transportation task, the smart contract automatically calculates the corresponding incentive token base, which is bound to core parameters such as the task's timeliness and temperature control standards.

[0073] All scheduling instructions must undergo compliance verification using zero-knowledge proofs before taking effect to ensure that the instructions comply with the basic rules and requirements for product transportation. Data generated during execution, including task allocation records, anomaly handling results, and token calculation details, collectively constitute the scheduling execution result and generate corresponding blockchain transaction vouchers. This step, through the automated execution of smart contracts, transforms the dynamic scheduling scheme into a binding on-chain operation, ensuring the executability of scheduling decisions while providing structured input data for subsequent blockchain consensus verification.

[0074] Step S106 ensures that all participants reach a consensus on the scheduling result through the blockchain consensus mechanism. The distributed ledger records the scheduling execution result, containing a complete chain of operational evidence. The generated logistics management report uses structured data to display key indicators of the transportation process. Among them, the transportation task completion rate reflects the degree of conformity between actual execution and plan, the temperature control compliance rate reflects the stability of environmental control, and the violation event statistics reveal abnormal situations in system operation. This data provides an objective basis for the continuous improvement of logistics enterprises.

[0075] This embodiment maps the status of transportation resources in real time using a trusted state matrix of logistics resources, and dynamically models the spatiotemporal correlation characteristics in the transportation network using a graph neural network scheduling model, forming a closed-loop feedback mechanism from data collection to scheme optimization. The multi-objective optimization algorithm comprehensively considers transportation costs, timeliness, and environmental indicators during the path planning stage. Edge computing nodes ensure data real-time performance through localized processing, and a spatiotemporal consistency verification algorithm effectively eliminates abnormal data interference. Smart contracts automatically execute task allocation and anomaly handling based on preset business rules, a zero-knowledge proof mechanism ensures compliance verification of scheduling instructions, and blockchain consensus ensures reliable storage of execution results. This method achieves the organic unity of resource status perception, dynamic decision optimization, and automated execution in the logistics scheduling process, improving transportation efficiency while ensuring temperature control compliance and operational traceability, providing reliable technical support for intelligent scheduling in complex supply chain environments.

[0076] Please see Figure 2 In some embodiments, the logistics transportation demand information is dynamically decomposed, an initial transportation route plan is generated using a multi-objective optimization algorithm, and a route feasibility score for the initial transportation route plan is calculated by combining historical transportation data, including:

[0077] S201. Based on the product type, transportation priority and temperature control requirements in the logistics transportation demand information, a transportation constraint weight matrix is ​​constructed using the analytic hierarchy process. The transportation constraint weight matrix is ​​used to quantify the differentiated requirements of different product categories for timeliness, temperature stability and safety.

[0078] S202. Align the transportation constraint weight matrix with historical transportation data in time and space, and use an improved non-dominated sorting genetic algorithm to solve multi-objective optimization problems, generating a set of candidate path schemes containing Pareto optimal solutions.

[0079] S203. Perform dynamic risk assessment on each candidate route in the candidate route solution set. Predict the potential traffic congestion probability and temperature control deviation risk of each candidate route in the target delivery area through a long short-term memory network. Combine the real-time vehicle status data in the logistics resource trust state matrix to calculate the comprehensive feasibility score of each candidate route solution.

[0080] S204. Based on the comprehensive feasibility score, sort and filter the candidate route schemes in the candidate route scheme set, remove the candidate route schemes whose comprehensive feasibility score is lower than the preset feasibility score threshold, and perform a matching degree analysis between the remaining candidate route schemes and the carrier qualifications in the supply chain node data to generate an initial transportation route scheme and the corresponding route feasibility score.

[0081] In step S201, the transportation constraint weight matrix transforms product transportation demand into quantifiable decision parameters through the analytic hierarchy process. The product type field is mapped to the temperature stability coefficient, the transportation priority corresponds to the timeliness weight, and the temperature control requirements are converted into safety tolerance values ​​for the allowable fluctuation range.

[0082] Step S202's spatiotemporal alignment operation establishes a mapping relationship between spatiotemporal features such as route time and temperature control records in historical transportation data and current transportation constraints. The improved non-dominated sorting genetic algorithm introduces a transportation resource occupancy penalty factor based on the traditional NSGA-II, enabling the generated Pareto optimal solution set to simultaneously satisfy the triple objectives of cost minimization, timeliness optimization, and carbon emission control. Each solution in the candidate route scheme set contains a complete node sequence, time window arrangement, and expected resource consumption details.

[0083] In the dynamic risk assessment model adopted in step S203, the Long Short-Term Memory (LSTM) network establishes a mapping relationship between spatiotemporal characteristics and congestion probability by analyzing historical traffic flow data and meteorological records. Preferably, its network structure includes an attention mechanism layer to capture the impact patterns of special periods such as holidays. The temperature control deviation risk prediction module integrates product characteristic curves and route environmental parameters, and establishes a risk prediction model by analyzing temperature fluctuation patterns in historical abnormal events. The comprehensive feasibility score calculation process can introduce a real-time vehicle status correction factor. When the logistics resource credibility state matrix shows a warning signal for a vehicle's refrigeration system, the temperature control risk coefficient of the relevant route plan will be dynamically adjusted upwards.

[0084] In step S204, the preset feasibility scoring threshold is dynamically adjusted using a sliding window mechanism. The window size is determined based on the moving average of historical scoring errors, ensuring that the screening criteria are adapted to the current logistics network status. The final initial transportation route generation process considers the carrier's qualification matching degree, and its credit score data comes from the immutable historical performance records on the blockchain, forming a precise match between transportation capacity and task requirements.

[0085] This embodiment constructs a dynamically evolving evaluation system that combines static route planning with real-time risk prediction. It employs the analytic hierarchy process (AHP) to transform subjective business rules into a computable transportation constraint weight matrix, introduces a long short-term memory network time-series model to enhance the predictability of candidate route evaluation, and establishes a preset feasibility score threshold adaptive adjustment mechanism to improve system robustness. This allows the route feasibility score to dynamically respond to changes in the logistics network state, ensuring both the feasibility of the solution and multi-objective optimization requirements. It provides high-quality initial input for subsequent graph neural network scheduling models. The decision evidence chain formed throughout the evaluation process will be automatically recorded on the blockchain via smart contracts, providing data support for logistics companies to optimize their transportation strategies.

[0086] In some embodiments, a decentralized logistics resource pool is constructed based on supply chain node data, including:

[0087] The edge computing nodes in the blockchain network collect dynamic resource data of each supply chain node in real time. The dynamic resource data includes the real-time inventory status of the warehousing node, the load capacity of the transport vehicle and the information on available refrigerated units, and the current task load status of the carrier.

[0088] A fast verification algorithm based on Bloom filters is used to initially screen the dynamic resource data, removing invalid or duplicate data records to obtain verified dynamic resource data.

[0089] The verified dynamic resource data is correlated and mapped with the static qualification information in the supply chain node data to construct a multi-dimensional resource feature vector, which includes spatial availability, equipment compatibility and serviceability.

[0090] Multidimensional resource feature vectors are classified and integrated according to preset rules to generate a decentralized logistics resource pool with timestamps. Each resource unit in the decentralized logistics resource pool is accompanied by a verifiable credit score and historical service records.

[0091] In this embodiment, a decentralized logistics resource pool built based on supply chain node data achieves dynamic aggregation and management of logistics resources through edge computing nodes in the blockchain network. Edge computing nodes collect dynamic resource data from each supply chain node in real time. This data can be automatically obtained through interfaces between IoT devices and enterprise information systems, ensuring the real-time nature and integrity of the data source.

[0092] The initial screening of dynamic resource data employs a fast verification algorithm based on a Bloom filter. This algorithm maps key data fields to a bit array structure using a pre-defined set of hash functions, achieving efficient duplicate data detection. Preferably, the storage space configuration of the Bloom filter needs to balance the false positive rate and computational overhead; in engineering practice, the bit array size is typically dynamically adjusted based on the resource update frequency. Dynamic resource data exhibits significant spatiotemporal locality, meaning that most resource status updates are concentrated within the jurisdiction of adjacent edge nodes. Therefore, a two-layer mechanism combining local and global verification is adopted to optimize network transmission efficiency while ensuring data accuracy.

[0093] Verified dynamic resource data is mapped to static qualification information in the supply chain node data, constructing a multi-dimensional resource feature vector encompassing three dimensions: spatial availability, equipment compatibility, and serviceability. Spatial availability is calculated using the topological relationship between geographic coordinates and the task area; equipment compatibility depends on the matching degree between transportation tools and cargo characteristics; and serviceability is derived by combining credit scores and real-time load status assessments. The classification and integration of these feature vectors employs a timestamped sliding window mechanism to ensure the timeliness of information in the resource pool. In the final decentralized logistics resource pool, each resource unit is accompanied by a credit score automatically calculated by a smart contract and traceable historical service records.

[0094] This embodiment achieves real-time acquisition of resource data through edge computing nodes, utilizes Bloom filters for efficient data verification, and combines blockchain technology to ensure data immutability. The multi-dimensional feature vector construction method transforms heterogeneous logistics resources into standardized computable units, providing a reliable data foundation for path feasibility scoring and graph neural network scheduling. The utilization of spatiotemporal locality features further optimizes the allocation of computing resources at the edge layer, improving the overall system response efficiency.

[0095] In some embodiments, transportation fluctuation parameters are collected in real time via edge computing nodes, including:

[0096] Real-time acquisition of raw sensor data, including vehicle GPS positioning coordinates, multi-area temperature and humidity sensor readings, and electronic lock switch status signals;

[0097] An adaptive sampling strategy is adopted to dynamically acquire raw sensor data. When the rate of change of temperature and humidity exceeds a preset threshold or the GPS signal is lost, the sampling frequency is automatically increased.

[0098] The collected data is denoised in real time using a lightweight filtering algorithm, and digital signatures and timestamps of edge nodes are added to generate transportation fluctuation parameters with identity authentication.

[0099] In this embodiment, the transportation fluctuation parameter refers to a set of key indicators reflecting dynamic changes during the logistics transportation process, which consists of raw sensor data collected in real time by edge computing nodes. In the raw sensor data, GPS positioning coordinates are used to track the continuity of the transportation route, temperature and humidity sensor readings monitor the stability of the cargo storage environment, and electronic lock switch status signals characterize the security of cargo packaging during transportation.

[0100] The adaptive sampling strategy balances monitoring accuracy and resource consumption by dynamically adjusting the data acquisition frequency. When the rate of change in temperature and humidity exceeds a preset threshold or GPS signal is lost, the system automatically increases the sampling frequency. This preset threshold is determined based on cargo characteristics (such as the thermal sensitivity coefficient of cold chain pharmaceuticals) and historical transportation environment data. The lightweight filtering algorithm uses an improved moving average method to perform real-time denoising on the acquired data. Different filter window sizes are set for GPS coordinate fluctuations and instantaneous drift of temperature and humidity sensors to ensure that the denoised data retains effective fluctuation characteristics.

[0101] Preferably, the process of attaching digital signatures and timestamps to edge nodes is implemented through a hardware security module. An asymmetric encryption algorithm is used to sign the filtered data, ensuring the immutability of transportation fluctuation parameters. The generated, authenticated transportation fluctuation parameters will be used for subsequent anomaly detection, with GPS trajectory jumps, temperature and humidity anomalies, and electronic lock status anomalies forming the basis for multi-dimensional correlation detection. For multi-sensor data conflicts, a cross-modal arbitration strategy based on Kalman filtering is adopted. By establishing a state-space model of each sensor's data, the anomaly probabilities of different modes are dynamically weighted and fused, ultimately outputting a comprehensive anomaly score. For example, when the temperature and humidity sensor readings are abnormal but the electronic lock status is normal, the system will combine GPS trajectory continuity to determine whether the environmental parameter fluctuations are caused by temporary vehicle stops.

[0102] This embodiment achieves multi-dimensional dynamic monitoring of the transportation process through edge computing nodes. Adaptive sampling and lightweight filtering ensure the real-time performance and reliability of data acquisition. The identity authentication mechanism based on the hardware security module provides a trusted data source for subsequent anomaly detection, while the cross-modal arbitration strategy supported by Kalman filtering effectively resolves the data conflict problem from multiple sensors, overcoming the limitations of single-temperature detection. Through multi-dimensional sensor data fusion and edge intelligent processing, this embodiment achieves efficient and reliable monitoring of the transportation process, significantly improving the accuracy of anomaly detection and system reliability.

[0103] In some embodiments, a spatiotemporal consistency verification algorithm is used to filter out abnormal data, and the verified transportation fluctuation parameters are stored on the blockchain to generate a reliable state matrix of logistics resources, including:

[0104] Receive transportation fluctuation parameters, parse and obtain vehicle GPS trajectory sequence, temperature and humidity time series data and electronic lock status change records, and record them as the first processed data;

[0105] A spatiotemporal correlation analysis model is constructed. The first processed data is input into the spatiotemporal correlation analysis model. The matching degree between GPS trajectory and temperature and humidity changes is identified through a multi-dimensional clustering algorithm. The model detects whether there is human tampering or equipment failure, and then obtains the second processed data.

[0106] A differential privacy protection algorithm is used to anonymize the second-processed data, generating standard data units that meet the storage requirements of blockchain.

[0107] The processed standard data units are written into the blockchain via smart contracts to generate a trusted state matrix of logistics resources, and to update the real-time state records in the decentralized logistics resource pool.

[0108] In this embodiment, the spatiotemporal consistency verification algorithm is a technical means of identifying anomalies by analyzing the correlation between transportation data in the time and space dimensions, used to verify the physical rationality of GPS trajectory sequences and temperature and humidity time-series data. Specifically, the GPS trajectory sequence in the first processed data is spatiotemporally aligned with the electronic lock status change record. For example, when the electronic lock is opened in a non-preset geofence area, an anomaly marker is triggered. At the same time, if a sudden change in temperature and humidity is not accompanied by a vehicle stop (GPS stationary), it is determined to be a possible equipment failure. Preferably, the multi-dimensional clustering algorithm adopts the density-based DBSCAN method, which clusters GPS coordinate points and temperature and humidity readings according to spatiotemporal windows, and identifies outliers (such as sudden temperature and humidity readings that do not match the smooth driving trajectory) through the intra-cluster distance threshold, thereby detecting human tampering or sensor failure.

[0109] For differential privacy protection algorithms, the preferred method is to use... - Differential privacy parameters control the strength of data anonymization, where the privacy budget allocation strategy is graded according to data sensitivity: GPS trajectory privacy budget is higher ( To prevent location re-identification; temperature and humidity data privacy budget is low ( Due to its relatively low sensitivity, differential privacy protection algorithms can be implemented by adding Laplace noise. The noise scale is inversely proportional to the privacy budget, ensuring a balance between data availability (such as the preservation of temperature and humidity trends) and privacy protection. The standard data unit after differential privacy processing includes anonymized trajectory segments, aggregated temperature and humidity ranges, and encrypted electronic lock events. Its data structure conforms to the key-value storage requirements of blockchain.

[0110] Smart contracts perform dual verification when writing to the blockchain: first, they check whether the hash value of the data unit is consistent with the spatiotemporal verification result; second, they verify whether the differential privacy parameters meet preset standards. The logistics resource trust state matrix records the data trust score of each edge node and updates the resource pool in conjunction with the transportation fluctuation parameters of the aforementioned embodiment. Preferably, the data trust score of each edge node is dynamically adjusted based on anomaly detection results. For example, when a node frequently triggers abnormal temperature and humidity but its GPS trajectory is normal, its trust score decreases, and the resource pool will reduce the task allocation to that node.

[0111] This embodiment achieves trusted processing and secure storage of logistics transportation data through the synergy of a spatiotemporal consistency verification algorithm and differential privacy protection. The spatiotemporal correlation analysis model utilizes a multi-dimensional clustering algorithm to identify physical discrepancies between GPS trajectories and temperature / humidity data, effectively detecting human tampering and equipment malfunctions. The differential privacy protection algorithm, through sensitivity-graded noise injection, prevents location re-identification while preserving data trends. A dual verification mechanism of hash consistency verification and privacy parameter review in smart contracts ensures the integrity and compliance of on-chain data. The generated trusted state matrix of logistics resources dynamically updates the trusted scores of edge nodes, providing accurate state information for the decentralized resource pool. This embodiment achieves privacy security while ensuring data authenticity, providing a reliable basis for trusted scheduling of logistics resources.

[0112] In some embodiments, an initial transportation route plan and a logistics resource reliability state matrix are input into a graph neural network scheduling model. A graph attention mechanism is used to model the spatiotemporal dependencies between transportation nodes, dynamically adjusting path weights and outputting a dynamic scheduling scheme that includes real-time route optimization suggestions, emergency scheduling instructions, and resource allocation strategies.

[0113] Construct a transportation network topology graph, converting warehousing nodes, transportation vehicles, and transfer stations into graph nodes. Based on the spatiotemporal characteristics and resource availability indicators in the logistics resource trust state matrix, establish node feature vectors corresponding to the graph nodes, and construct edge features according to the actual transportation route connection relationships.

[0114] A multi-layer graph attention network is used to learn features of the transportation network topology graph. The spatial dependency weights between graph nodes are calculated through a multi-head attention mechanism, and a temporal convolutional network is combined to capture the dynamic change patterns of transportation resources, thereby obtaining the path weights of the optimized initial transportation path.

[0115] The priority scores of each initial transportation path are iteratively updated using the message passing mechanism of a graph neural network to generate a set of candidate optimized paths;

[0116] Based on the candidate optimization path set, real-time path optimization suggestions are dynamically generated through reinforcement learning strategies. When abnormal fluctuations are detected in the logistics resource trust state matrix, emergency dispatch instructions containing backup routes and emergency resource allocation are automatically triggered.

[0117] The optimized path weights are integrated with the initial transportation path plan to output a dynamic scheduling plan that includes optimal path recommendations, resource reallocation plans, and risk warning information.

[0118] In this embodiment, the transportation network topology graph is a network representation method that abstracts warehousing nodes, transportation vehicles, and transfer stations in the logistics system as graph nodes, and constructs edge features based on the actual transportation route connections. The node feature vectors are jointly generated from the spatiotemporal features and resource availability indicators in the logistics resource reliability state matrix. The spatiotemporal features include GPS trajectory verification results and temperature and humidity data reliability scores, while the resource availability indicators cover parameters such as vehicle cargo capacity and temperature and humidity compliance status. Edge features are quantified and constructed using historical transportation route travel times and road grade data.

[0119] The graph attention mechanism employs a multi-head attention structure to calculate the spatial dependency weights between nodes, while combining it with a temporal convolutional network to analyze the dynamic changes in transportation resources. The spatial dependency weight calculation considers the physical distance and transportation capacity matching degree between nodes, while the temporal convolutional network captures the temporal patterns of vehicle speed and cargo status changes. This spatiotemporal joint modeling approach can more accurately reflect the actual degree of correlation between nodes in the transportation network.

[0120] The message passing mechanism updates path priority scores through multiple iterative layers. The first layer aggregates real-time resource status information of adjacent nodes; the second layer adjusts the connection strength between nodes based on spatiotemporal dependency weights; and the third layer introduces a time-sensitive factor to prioritize transportation tasks nearing their deadlines. This mechanism ensures that the path optimization process considers both static network topology and dynamic resource changes.

[0121] The reinforcement learning strategy generates scheduling decisions based on real-time transportation status. Its state space includes priority scores and resource availability data for candidate routes, while the action space is defined as operations such as route adjustment and resource reallocation. When the logistics resource reliability state matrix detects anomalies, such as abnormal temperature and humidity data at a node but normal GPS trajectory, an alternative route bypassing that node is automatically generated, and relevant warehousing nodes are coordinated to allocate emergency resources. The final dynamic scheduling scheme output includes optimal route recommendations, resource allocation adjustment suggestions, and anomaly risk warning information.

[0122] This embodiment combines the temporal characteristics of GPS trajectories with spatial correlation analysis using graph attention mechanisms to construct a spatiotemporal joint representation that accurately reflects the actual state of the transportation network. This ensures both the spatial rationality of the path optimization scheme and the timely response of scheduling decisions to dynamic changes during transportation. Furthermore, through real-time interaction with the reliable state matrix of logistics resources, it achieves efficient scheduling of transportation resources and rapid handling of abnormal situations.

[0123] In some embodiments, smart contract execution is triggered based on a dynamic scheduling scheme. The smart contract automatically allocates transportation tasks, freezes transaction permissions for abnormal batches, and calculates carrier incentive tokens according to preset rules. Simultaneously, it verifies the compliance of scheduling instructions using zero-knowledge proofs to obtain the scheduling execution result, including:

[0124] The algorithm analyzes the path optimization suggestions and resource allocation strategies in the dynamic scheduling scheme, and uses smart contracts to allocate transportation tasks to the optimal carrier node, generating task allocation results. The allocation process is based on multi-dimensional optimization selection based on the real-time available resources in the logistics resource trust status matrix and the carrier credit score.

[0125] When the detected transportation fluctuation parameters exceed the preset safety threshold, the anomaly handling smart contract is triggered, automatically freezing the transaction permissions of the relevant batch of products and generating an immutable violation record on the blockchain. At the same time, an encrypted alarm is sent to the regulatory node, and an anomaly handling record is generated.

[0126] The number of incentive tokens is dynamically calculated based on the carrier's task completion quality, timeliness, and temperature control compliance rate. External market data is obtained through a decentralized oracle to adjust the token value anchoring coefficient, resulting in a detailed token incentive list.

[0127] A zero-knowledge proof verification module is constructed to generate a validity proof that the scheduling instructions comply with the product sales rules, which is then used by regulators for compliance spot checks to obtain compliance proof.

[0128] The task allocation results, exception handling records, token incentive details, and compliance proofs are packaged to generate the scheduling execution results.

[0129] In this embodiment, the selection process for the optimal carrier node is implemented through a smart contract. This contract performs multi-dimensional selection based on real-time available resources in the logistics resource trust status matrix and carrier credit scores. Real-time available resources include the current location of transport vehicles, load capacity, and refrigerated unit status, which are continuously updated through edge computing nodes. Carrier credit scores are derived from historical performance records stored on the blockchain, including task completion rate, temperature control compliance rate, and statistics on violations, ensuring the immutability and objectivity of the score data. A weighted scoring mechanism is used in the allocation process, prioritizing carriers with high resource matching and excellent credit scores, thereby reducing operational risks while ensuring transportation efficiency.

[0130] When transportation fluctuation parameters exceed a preset safety threshold, the system automatically triggers anomaly handling smart contracts. Preferably, the preset safety thresholds are dynamically adjusted based on product characteristics (such as the temperature control range of pharmaceuticals) and historical transportation data (such as equipment failure rates) to ensure the accuracy of anomaly detection. The smart contract first freezes the on-chain transaction permissions of the relevant batch of products to prevent abnormal batches from entering subsequent circulation stages. Simultaneously, it generates a violation record on the blockchain, including a timestamp, anomaly type, and handling measures. The violation record uses distributed storage to ensure immutability and sends encrypted alerts to regulatory nodes for timely intervention. The generation process of the anomaly handling record strictly follows preset rules to ensure the standardization and traceability of handling measures.

[0131] The calculation of incentive tokens comprehensively considers the carrier's task completion quality, timeliness, and temperature control compliance rate. External market data obtained through a decentralized oracle dynamically adjusts the token value anchoring coefficient, linking the incentives to actual market conditions. Preferably, token allocation employs a contribution algorithm based on Shapley values ​​to quantify the actual contributions of multiple carriers in collaborative tasks, avoiding the unfairness caused by simple average distribution. Simultaneously, a deflationary mechanism is introduced: when a carrier's credit score falls below a set threshold, a portion of its tokens will be burned to maintain the long-term stability and incentive effectiveness of the token economy system.

[0132] Preferably, the zero-knowledge proof verification module is implemented using zk-SNARKs technology. The smart contract compiles scheduling instructions and preset rules into a verifiable circuit, generating compliance proofs without disclosing the original data. This ensures the compliance of scheduling instructions without revealing their specific content. The module proves that the scheduling instructions conform to preset product transportation rules, allowing regulators to conduct random checks. The final generated scheduling execution result includes task allocation results, anomaly handling records, token incentive details, and compliance proofs. All data is stored on the blockchain to ensure integrity and auditability.

[0133] This embodiment achieves full-process automation and trustworthiness of dynamic logistics scheduling through a collaborative mechanism of smart contracts and zero-knowledge proofs. Rules for route optimization, resource allocation, anomaly handling, and incentive calculation are encoded into executable logic, and the immutability of blockchain ensures data transparency and auditability at each stage. In the resource allocation phase, smart contracts perform multi-dimensional optimization based on a real-time updated logistics resource trust status matrix and carrier historical credit scores, dynamically matching the optimal carrier node. In the anomaly handling phase, a dynamic threshold adjustment mechanism precisely triggers the freezing of transaction permissions and the recording of violations on the blockchain. Incentive tokens are anchored to market data through a decentralized oracle and incorporate a contribution algorithm to achieve a strong correlation between value allocation and credit scores. The zero-knowledge proof module verifies scheduling compliance without exposing the original data, forming a closed-loop regulatory system. This embodiment significantly improves the resource allocation efficiency of cold chain logistics, reduces the risk of human intervention through automatic execution of on-chain rules, and ensures a balance between commercial privacy and regulatory compliance through cryptographic technology, providing a trustworthy and efficient scheduling paradigm for the transportation of high-value products.

[0134] In some embodiments, the scheduling execution results and the trusted state matrix of logistics resources are updated to the distributed ledger according to the blockchain consensus mechanism, generating and outputting a logistics management report that includes statistics on transportation task completion, temperature control compliance rate, and violations, including:

[0135] Based on the scheduling execution results, the task completion indicators for each transportation batch are automatically calculated through smart contracts. The task completion indicators include timeliness achievement rate, path deviation, and resource utilization efficiency.

[0136] Historical temperature control sensor data from the logistics resource trust status matrix is ​​extracted, and the temperature control compliance rate at each transportation stage is calculated using a sliding window algorithm. The frequency and duration of abnormal temperature fluctuation events are also identified.

[0137] By using smart contracts that record violations on the blockchain, the distribution and spatial characteristics of violation event types within a preset period are statistically analyzed to generate analysis results of violation hotspot areas.

[0138] By weighting and integrating task completion indicators, temperature control compliance rate, and analysis results of violation hotspots, suggestions for updating carrier credit scores and supply chain optimization solutions are generated.

[0139] The logistics management report integrates carrier credit score update suggestions and supply chain optimization plans with task completion indicators, temperature control compliance rate and violation hotspot area analysis results into a logistics management report. The logistics management report includes a transportation performance trend chart, a temperature control quality heat map and violation risk warning prompts.

[0140] In this embodiment, the immutability of the blockchain ensures the authenticity and reliability of the transportation data, providing a solid data foundation for subsequent analysis. The distributed ledger feature enables all participants to access the latest data in real time, facilitating collaborative management.

[0141] In calculating task completion metrics, the timeliness achievement rate is determined by comparing the actual completion time of the transportation task with the time threshold preset by the smart contract. If the actual time is earlier than or equal to the threshold, it is considered fully achieved. Route deviation is calculated based on the standard deviation of the spatial distance between the vehicle's GPS trajectory and the planned route, reflecting the degree of route adherence during transportation. Resource utilization efficiency is comprehensively evaluated based on the ratio of load capacity to actual load, combined with the operating power consumption of the refrigeration unit. These three metrics are converted to a unified dimension using a normalization algorithm built into the smart contract, and then the weight of each metric is determined using the entropy weight method. Finally, a weighted sum is obtained to obtain the overall task completion score. This scoring mechanism avoids the excessive influence of a single metric deviation on the overall evaluation, providing an objective basis for subsequent credit score updates.

[0142] The temperature control compliance rate is calculated using a sliding window algorithm to process historical sensor data. The window size is set considering the time span of the transportation phase and the data sampling frequency to ensure that the statistical results reflect both the overall trend and capture local fluctuations. Temperature anomaly event identification is based on a preset threshold range, recording the duration and frequency of events exceeding the threshold. This provides a quantitative basis for cold chain quality control. The preset threshold range can be dynamically set according to industry standards and product characteristics, and can be automatically loaded by smart contracts.

[0143] The analysis of violations relies on the immutable records stored on the blockchain. Smart contracts categorize and statistically analyze violations within a preset period, examining the temporal distribution patterns of different types of violations. Spatial distribution characteristics are visualized using Geographic Information System (GIS) technology, and high-risk areas are identified by combining this with the transportation network topology.

[0144] The credit score update recommendations employ a multi-indicator fusion approach. The weights of each indicator are dynamically adjusted based on its impact on transportation quality, ensuring the fairness and guidance of the scoring results. Supply chain optimization solutions are proposed based on historical data and current problem analysis, suggesting targeted improvement measures.

[0145] The final logistics management report integrates various analytical results. The transportation performance trend chart visually displays changes in carrier performance, the temperature control quality heatmap reflects key control points in cold chain transportation, and the violation risk warning alerts help managers proactively prevent potential risks. The report's output format supports viewing on multiple terminal devices, facilitating access to the information needed by users in different roles.

[0146] This embodiment synchronizes scheduling execution results and the trusted state matrix of logistics resources to a distributed ledger through a blockchain consensus mechanism. It utilizes smart contracts to automatically calculate transportation task completion indicators and combines a sliding window algorithm to analyze temperature control compliance rates and abnormal events. Simultaneously, it statistically analyzes the spatial distribution characteristics of violations based on the immutability of blockchain. By dynamically weighting and fusing multi-dimensional indicators using the entropy weight method, it generates carrier credit score update suggestions and supply chain optimization solutions. Finally, it integrates these into a logistics management report that includes a transportation performance trend chart, a temperature control quality heatmap, and violation risk warnings.

[0147] This embodiment realizes full-chain reliable traceability and multi-dimensional quantitative evaluation of the transportation process. The automated execution of smart contracts ensures the authenticity of data and the objectivity of calculations. The spatiotemporal feature fusion analysis improves the accuracy of risk identification and provides closed-loop support for cold chain logistics management from real-time monitoring to decision optimization, significantly enhancing the systematicness and collaborative efficiency of transportation quality control.

[0148] In a second aspect, this embodiment also provides a computer-readable storage medium storing computer program instructions thereon, which, when executed by a processor, implement the method described in the first aspect.

[0149] The computer program involved in this embodiment can be stored in a computer device readable storage medium, which includes, but is not limited to, disks, magnetic tapes, magnetic cards, floppy disks, flash memory, optical disks, optical cards, read-only memory (ROM), random access memory (RAM), erasable programmable ROM (EPROM), and electrically erasable programmable ROM (EEPROM), etc. It also includes other biological, physical, or chemical structures capable of performing similar or equivalent functions to the storage media listed above, such as DNA, RNA, proteins, and other units with information storage capabilities. In specific embodiments, the storage medium involved can be one of the above-mentioned media types or a combination of the above media types. In different embodiments, the computer program involved in the embodiment can be centrally stored in a single medium or distributed across multiple media. The memory containing the computer device readable storage medium can be non-volatile memory or random access memory. These computer device readable storage media can be built into the device or connected to the device involved in the embodiment as an external device or part of an external device. In some embodiments, the memory having a computer device readable storage medium is deployed locally; in other embodiments, the memory may be deployed remotely from the processor, for example, as a network-attached memory accessed via RF circuitry or an external port and a communication network, wherein the communication network may be the Internet, one or more intranets, a local area network (LAN), a wide area network (WLAN), a storage area network (SAN), or a suitable combination thereof, as long as computer device access to the memory is enabled. Furthermore, the computer program involved in the embodiments may be stored in plaintext / ciphertext form, or it may be designed as training data, integrated and recombined through model training and implicitly stored in the parameter states of a deep neural network or other machine learning model.

[0150] Please see Figure 3 In a third aspect, this embodiment also provides an electronic device 1, including a memory 11 and a processor 12, wherein the memory 11 is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor 12 to implement the method described in the first aspect.

[0151] The processor described in this embodiment can be implemented by hardware, firmware, software, or a combination thereof. It can be a circuit, one or more of an application-specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field-programmable gate array (FPGA), a central processing unit (CPU), a controller, a microcontroller, or a microprocessor. It also includes other physical, biological, or chemical structures that can implement the same or equivalent functions as the processors listed above, such as biological neurons, quantum computing units, DNA computing units, etc., so that the processor can execute some or all of the steps in the computer program or method involved in the various embodiments of this application, or any combination of the steps mentioned therein.

[0152] Unlike existing technologies, the above technical solution has the following advantages: by constructing a reliable state matrix of logistics resources, dynamic digital mapping of transportation resources is achieved; by combining the spatiotemporal attention mechanism of the graph neural network scheduling model, the transportation network is modeled in real time, forming a closed-loop management from demand collection and route optimization to dynamic scheduling; a blockchain consensus mechanism is adopted to ensure reliable synchronization between scheduling execution results and resource status; and smart contracts are used to automatically calculate task completion indicators, temperature control compliance rate, and statistics of violations, and generate a logistics management report that includes credit score update suggestions and optimization schemes.

[0153] The above technical solution combines real-time data acquisition from edge computing nodes, spatiotemporal consistency verification algorithms, and differential privacy protection to solve the problems of insufficient data authenticity and delayed response in traditional logistics management. Through the collaborative optimization of graph attention networks and reinforcement learning, dynamic weight adjustment of transportation paths and rapid response to anomalies are achieved. Zero-knowledge proofs are used to verify scheduling compliance, ensuring commercial privacy while meeting regulatory requirements. Ultimately, this achieves reliable traceability and optimized resource allocation throughout the entire product logistics process, significantly improving transportation efficiency, temperature control compliance, and anomaly handling capabilities, providing a safe and reliable intelligent scheduling solution for high-value product supply chains, especially cold chain logistics.

[0154] The above description is only a part of the embodiments of the present invention and does not limit the scope of protection of the present invention. Any equivalent device or equivalent process transformation made based on the content of the present invention specification and drawings, or direct or indirect application in other related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. A blockchain-based product logistics management scheduling method, characterized by, Comprise: Collecting product logistics transportation demand information and supply chain node data, the logistics transportation demand information includes product type, transportation priority, temperature control requirement and target distribution area, the supply chain node data includes warehouse location, transportation vehicle state and carrier qualification; Dynamic task decomposition is performed on the logistics transportation demand information, a multi-objective optimization algorithm is used to generate an initial transportation path scheme, and the path feasibility score of the initial transportation path scheme is calculated combined with historical transportation data; Based on the supply chain node data, a decentralized logistics resource pool is constructed, transportation fluctuation parameters are collected in real time through edge computing nodes, the transportation fluctuation parameters include vehicle GPS trajectory, temperature and humidity sensor data and electronic lock state, abnormal data is filtered by spatiotemporal consistency verification algorithm, and verified transportation fluctuation parameters are stored on chain to generate logistics resource trust state matrix; The initial transportation path scheme and the logistics resource trust state matrix are input into a graph neural network scheduling model, the spatiotemporal dependence relationship between transportation nodes is modeled through graph attention mechanism, the path weight is dynamically adjusted, and a dynamic scheduling scheme containing real-time path optimization suggestion, emergency scheduling instruction and resource allocation strategy is output, including: Constructing a transportation network topology graph, converting warehouse nodes, transportation vehicles and transfer stations into graph nodes, establishing node feature vectors corresponding to graph nodes based on spatiotemporal features and resource availability indexes in the logistics resource trust state matrix, and constructing edge features according to actual transportation route connection relationship; Feature learning of the transportation network topology graph is performed by using multi-layer graph attention network, spatial dependence weight between graph nodes is calculated through multi-head attention mechanism, and dynamic change mode of transportation resources is captured combined with time convolution network to obtain path weight of optimized initial transportation path; The priority score of each initial transportation path is iteratively updated by using message passing mechanism of graph neural network to generate candidate optimization path set; Based on the candidate optimization path set, real-time path optimization suggestion is dynamically generated by reinforcement learning strategy, when abnormal fluctuation appears in the logistics resource trust state matrix, emergency scheduling instruction containing backup route and emergency resource allocation is automatically triggered; The optimized path weight is fused with the initial transportation path scheme to output a dynamic scheduling scheme containing optimal path recommendation, resource reallocation scheme and risk warning information; Triggering smart contract execution based on the dynamic scheduling scheme, the smart contract automatically allocates transportation tasks, freezes abnormal batch transaction authority and calculates carrier incentive Token according to preset rules, and verifies the compliance of scheduling instruction through zero-knowledge proof to obtain scheduling execution result, including: Analyzing path optimization suggestion and resource allocation strategy in the dynamic scheduling scheme, assigning transportation tasks to optimal carrier nodes through smart contract to generate task allocation result, the allocation process is based on real-time available resources and carrier credit score in the logistics resource trust state matrix for multi-dimensional optimal selection; When detecting that the transportation fluctuation parameter exceeds the preset safety threshold, triggering the exception handling smart contract, automatically freezing the transaction permission of the related batch product and generating an unforgeable violation record on the blockchain, at the same time sending an encrypted alarm to the regulatory node, and generating an exception handling record; According to the task completion quality, timeliness and temperature control compliance rate of the carrier, dynamically calculate the number of incentive tokens, adjust the token value anchor coefficient through the decentralized oracle to obtain the token incentive details; Build a zero-knowledge proof verification module to generate an effectiveness proof that the dispatching instruction meets the product sales rules, which is provided to the regulatory party for compliance sampling to obtain a compliance proof; Packaging the task allocation result, exception handling record, token incentive details and compliance proof to generate the dispatch execution result; According to the blockchain consensus mechanism, update the dispatch execution result and the logistics resource credible state matrix to the distributed ledger, and generate a logistics management report containing transportation task completion, temperature control compliance rate and violation event statistics and output. 2.The blockchain-based product logistics management scheduling method of claim 1, wherein, Dynamically decompose the logistics transportation demand information, generate an initial transportation path scheme using a multi-objective optimization algorithm, and calculate the path feasibility score of the initial transportation path scheme based on historical transportation data, including: Based on the product type, transportation priority and temperature control requirement in the logistics transportation demand information, construct a transportation constraint weight matrix by AHP, which is used to quantify the differentiated demand of different product categories for timeliness, temperature stability and safety; Align the transportation constraint weight matrix with historical transportation data in space and time, and use an improved non-dominated sorting genetic algorithm for multi-objective optimization to generate a candidate path scheme set containing a Pareto optimal solution set; Perform dynamic risk assessment on each candidate path scheme in the candidate path scheme set, predict the potential traffic congestion probability and temperature control deviation risk of each candidate path scheme in the target distribution area through a long short-term memory network, and calculate the comprehensive feasibility score of each candidate path scheme based on real-time vehicle state data in the logistics resource credible state matrix; Based on the comprehensive feasibility score, sort and filter the candidate path schemes in the candidate path scheme set, remove candidate path schemes with a comprehensive feasibility score below a preset feasibility score threshold, and perform matching degree analysis on the remaining candidate path schemes and the carrier qualifications in the supply chain node data to generate the initial transportation path scheme and the corresponding path feasibility score. 3.The blockchain-based product logistics management scheduling method of claim 1, wherein, Based on the supply chain node data, build a decentralized logistics resource pool, including: Collect real-time resource data of each supply chain node through edge computing nodes in the blockchain network, including real-time inventory status of warehouse nodes, load capacity and available refrigeration unit information of transportation vehicles, and current task load status of carriers; Use a fast verification algorithm based on Bloom filter to preliminarily filter the dynamic resource data, remove invalid or duplicate data records, and obtain verified dynamic resource data; The verified dynamic resource data is associated and mapped with static qualification information in the supply chain node data to construct a multi-dimensional resource feature vector, and the multi-dimensional resource feature vector includes spatial availability, device compatibility and serviceability; The multi-dimensional resource feature vector is classified and integrated according to a preset rule to generate a decentralized logistics resource pool with a timestamp mark, and each resource unit in the decentralized logistics resource pool is attached with a verifiable credit score and a historical service record. 4.The blockchain-based product logistics management scheduling method of claim 1, wherein, Through the edge computing node, transportation fluctuation parameters are collected in real time, including: Real-time collection of original sensing data, including vehicle GPS positioning coordinates, multi-region temperature and humidity sensor readings, and electronic lock switch state signals; An adaptive sampling strategy is used to dynamically collect the original sensing data, and the sampling frequency is automatically increased when the temperature and humidity change rate exceeds a preset threshold or the GPS signal is lost; Real-time denoising processing of the collected data is performed through a lightweight filtering algorithm, and an edge node digital signature and a timestamp are attached to generate transportation fluctuation parameters with identity authentication. 5.The blockchain-based product logistics management scheduling method of claim 4, wherein, An spatiotemporal consistency verification algorithm is used to filter abnormal data, and the verified transportation fluctuation parameters are stored on a chain to generate a logistics resource trust state matrix, including: Receiving transportation fluctuation parameters, analyzing vehicle GPS trajectory sequences, temperature and humidity time series data, and electronic lock state change records, denoted as first processing data; A spatiotemporal correlation analysis model is constructed, the first processing data is input into the spatiotemporal correlation analysis model, the matching degree of GPS trajectory and temperature and humidity change is identified through a multi-dimensional clustering algorithm, and whether there is human tampering or device failure is detected to obtain second processing data; A differential privacy protection algorithm is used to anonymize the second processing data to generate standard data units that meet the requirements of blockchain storage; The processed standard data units are written into the blockchain through a smart contract to generate a logistics resource trust state matrix and update the real-time state record in the decentralized logistics resource pool. 6.The blockchain-based product logistics management scheduling method of claim 1, wherein, According to the blockchain consensus mechanism, the scheduling execution result and the logistics resource trust state matrix are updated to a distributed ledger to generate a logistics management report containing transportation task completion, temperature control compliance rate and violation event statistics and output, including: Based on the scheduling execution result, the task completion degree index of each transportation batch is automatically calculated through a smart contract, including time limit achievement rate, path deviation degree and resource utilization efficiency; The temperature control sensor historical data in the logistics resource trust state matrix is extracted, a sliding window algorithm is used to calculate the temperature control compliance rate of each transportation stage, and the occurrence frequency and duration of temperature abnormal fluctuation events are identified; Through the violation record smart contract on the blockchain, the type distribution and spatial distribution characteristics of the violation events in a preset period are counted to generate a violation hotspot area analysis result; The task completion degree index, temperature control compliance rate and violation hotspot area analysis result are weighted and fused to generate a carrier credit score update suggestion and a supply chain optimization scheme; The carrier credit score update suggestion and the supply chain optimization scheme are integrated with the task completion degree index, the temperature control compliance rate and the illegal hotspot area analysis result into a logistics management report and output, and the logistics management report includes a transportation performance trend chart, a temperature control quality heat map and an illegal risk early warning prompt.

7. A computer readable storage medium having stored thereon computer program instructions, wherein, The computer program instructions, when executed by a processor, implement the method of any one of claims 1 to 6.

8. An electronic device comprising a memory and a processor, characterized in that, The memory is configured to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method of any one of claims 1 to 6.

Images