Supply chain optimization method and system for cargo import and export

Abstract

The invention provides a supply chain optimization method and system for cargo import and export, and relates to the technical field of supply chain optimization, and the method comprises the steps: building a distributed account book based on block chain nodes; determining a trigger condition and execution logic, and generating a smart contract; installing an Internet of Things sensor, obtaining cargo environment parameters generated based on a monitored cargo environment, and carrying out information synchronous updating with the distributed account book to obtain whole-process monitoring data; carrying out transportation analysis according to the cargo demand prediction model to obtain predicted logistics data; carrying out transportation planning, and generating a supply chain strategy; and executing the supply chain strategy based on the intelligent contract, generating supply chain data, and performing visual display of the supply chain data. Through the method and the device, the technical problems of serious information island phenomenon and incapability of efficiently sharing data in the prior art can be solved, the technical targets of supply chain data transparency and automatic management are realized, and the technical effect of improving the overall efficiency and the strain capacity of the supply chain is achieved.

Description

Technical Field

[0001] The present application relates to the technical field of supply chain optimization, and in particular to a supply chain optimization method and system for the import and export of goods. Background Art

[0002] In current supply chain management, the combination of blockchain technology and the Internet of Things has become a key means to improve the transparency, efficiency and security of the supply chain. However, existing technologies still have obvious defects in data transparency, collaborative efficiency, adaptability and data processing. The traditional supply chain system has serious information island phenomenon, and the data between various links cannot be efficiently shared and updated in real time, resulting in delayed management decisions; too much manual intervention, low degree of automation, and inability to respond quickly to market changes and emergencies. In addition, the lack of effective data analysis and anomaly detection mechanisms makes it difficult to timely discover and deal with potential problems in the supply chain.

[0003] To sum up, there are technical problems in the existing technology due to serious information island phenomenon and inefficient data sharing, which lead to delayed supply chain management decision-making and insufficient response capabilities, further affecting the overall efficiency and security of the supply chain. Summary of the invention

[0004] The purpose of this application is to provide a supply chain optimization method and system for the import and export of goods, so as to solve the technical problems in the prior art that the serious information island phenomenon and the inability to efficiently share data lead to delayed supply chain management decisions and insufficient adaptability, further affecting the overall efficiency and security of the supply chain.

[0005] In view of the above problems, the present application provides a supply chain optimization method and system for the import and export of goods.

[0006] In the first aspect, the present application provides a supply chain optimization method for the import and export of goods, which is implemented through a supply chain optimization system for the import and export of goods, including: on a blockchain platform, deploying blockchain nodes in the supply chain link, and establishing a distributed ledger based on the blockchain nodes; extracting the business rules and business processes of the supply chain link, determining the trigger conditions and execution logic, and generating a smart contract; installing Internet of Things sensors on the goods and transportation tools, obtaining the cargo environment parameters generated based on monitoring the cargo environment, uploading the cargo environment parameters to the blockchain platform, and synchronizing the information with the distributed ledger to obtain the whole process monitoring data; according to the cargo demand prediction model, performing transportation analysis on the whole process monitoring data to obtain predicted logistics data; deploying the smart contract to the blockchain node, performing transportation planning according to the predicted logistics data, and generating a supply chain strategy; executing the supply chain strategy based on the smart contract, generating supply chain data, and visualizing the supply chain data.

[0007] In the second aspect, the present application also provides a supply chain optimization system for the import and export of goods, which is used to execute a supply chain optimization method for the import and export of goods as described in the first aspect, including: a distributed ledger establishment module, which is used to deploy blockchain nodes in the supply chain link on the blockchain platform, and establish a distributed ledger based on the blockchain node; a smart contract generation module, which is used to extract the business rules and business processes of the supply chain link, determine the trigger conditions and execution logic, and generate a smart contract; a full-process monitoring data acquisition module, which is used to install Internet of Things sensors on goods and transportation tools, obtain cargo environment parameters generated based on monitoring the cargo environment, upload the cargo environment parameters to the blockchain platform, synchronize information with the distributed ledger, and obtain full-process monitoring data; a predicted logistics data acquisition module, which is used to perform transportation analysis on the full-process monitoring data according to the cargo demand prediction model to obtain predicted logistics data; a supply chain strategy generation module, which is used to deploy the smart contract to the blockchain node, perform transportation planning according to the predicted logistics data, and generate a supply chain strategy; a visualization display module, which is used to execute the supply chain strategy based on the smart contract, generate supply chain data, and perform visualization of the supply chain data.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages: By deploying blockchain nodes in the supply chain link on the blockchain platform, a distributed ledger is established based on the blockchain nodes; the business rules and business processes of the supply chain link are extracted, the trigger conditions and execution logic are determined, and the smart contract is generated; the Internet of Things sensors are installed on the goods and transportation tools to obtain the cargo environment parameters generated based on the monitoring of the cargo environment, and the cargo environment parameters are uploaded to the blockchain platform, and the information is synchronized and updated with the distributed ledger to obtain the full-process monitoring data; according to the cargo demand prediction model, the transportation analysis of the full-process monitoring data is carried out to obtain the predicted logistics data; the smart contract is deployed to the blockchain node, and the transportation planning is carried out according to the predicted logistics data to generate the supply chain strategy; the supply chain strategy is executed based on the smart contract, the supply chain data is generated, and the supply chain data is visualized to achieve the technical goal of transparent and automated management of supply chain data, and achieve the technical effect of improving the overall efficiency and resilience of the supply chain.

[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0011] Figure 1 A schematic diagram of a flow chart of a supply chain optimization method for the import and export of goods in this application; Figure 2 This is a schematic diagram of the structure of a supply chain optimization system for the import and export of goods in this application.

[0012] Description of reference numerals: Distributed ledger establishment module 11, smart contract generation module 12, full-process monitoring data acquisition module 13, predicted logistics data acquisition module 14, supply chain strategy generation module 15, and visualization display module 16. DETAILED DESCRIPTION

[0013] This application provides a supply chain optimization method and system for the import and export of goods, which solves the technical problems in the prior art that the serious information island phenomenon and the inability to efficiently share data lead to delayed supply chain management decisions and insufficient resilience, further affecting the overall efficiency and security of the supply chain. It achieves the technical goal of transparent and automated management of supply chain data, and achieves the technical effect of improving the overall efficiency and resilience of the supply chain.

[0014] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0015] For example, please refer to the attached Figure 1 The present application provides a supply chain optimization method for the import and export of goods, which is applied to a supply chain optimization system for the import and export of goods, and specifically includes: Step 1: On the blockchain platform, deploy blockchain nodes in the supply chain and establish a distributed ledger based on the blockchain nodes.

[0016] Specifically, deploying blockchain nodes on a blockchain platform means installing and configuring blockchain nodes at various links in the supply chain, such as suppliers, manufacturers, logistics companies, customs, and retailers. Blockchain nodes are the basic units in a blockchain network. Each blockchain node has a complete copy of blockchain data and is responsible for recording and verifying transactions, ensuring that every participant in the supply chain can access and update the blockchain ledger in real time, thereby achieving data transparency and sharing. By deploying nodes in each link of the supply chain, the phenomenon of information islands can be effectively reduced and the overall collaborative efficiency of the supply chain can be improved. Establishing a distributed ledger based on blockchain nodes means using blockchain technology to integrate the transaction information recorded by each blockchain node into a distributed ledger. The distributed ledger is maintained and updated by all nodes in the blockchain network, and each node has the right to participate in the recording and verification of data. The biggest advantage of the distributed ledger is its decentralization and immutability, which ensures the security and reliability of the data. In supply chain management, the distributed ledger can effectively prevent data from being tampered with or lost, and improve the credibility and transparency of the data. At the same time, since all nodes participate in the maintenance and update of the ledger, the distributed ledger also has high fault tolerance and reliability. By deploying blockchain nodes and establishing distributed ledgers on the blockchain platform, each participant in the supply chain can share and verify transaction data in real time, thereby achieving transparent, collaborative and efficient supply chain management throughout the process. In practical applications, supply chain management systems based on blockchain technology can significantly improve the efficiency and security of the supply chain. For example, suppliers can understand the production and transportation status of orders in real time, manufacturers can keep abreast of the supply of raw materials, logistics companies can efficiently manage transportation routes, customs can quickly complete customs clearance procedures, and retailers can track inventory levels and sales in real time.

[0017] Step 2: Extract the business rules and business processes of the supply chain, determine the trigger conditions and execution logic, and generate a smart contract.

[0018] Specifically, extracting business rules and business processes of supply chain links is the basis for realizing supply chain automation. First, in-depth communication is conducted with various supply chain participants (such as suppliers, manufacturers, logistics companies, retailers, etc.) to understand the operation process and business rules of each link in detail. Business rules include order processing, inventory management, logistics tracking, and payment settlement. By identifying business rules, the operation standards and requirements of each link can be clarified, laying the foundation for subsequent process optimization and automation. Combined with specific business processes, a flowchart can be drawn to clarify the order and dependencies of each step. Determining trigger conditions and execution logic is a key step in smart contract design. In the business process diagram, the trigger conditions of each key step are identified. For example, order confirmation may require checking whether the inventory is sufficient, and payment settlement may require confirmation that the goods have been delivered. Each trigger condition corresponds to a specific business event, and the execution logic defines the operations that the system needs to perform when the trigger condition is met. The execution logic includes data verification, status update, notification sending, etc. By defining the trigger conditions and execution logic in detail, it can ensure that the smart contract performs the correct operation at the right time, avoid manual intervention, and improve efficiency and accuracy. Generating smart contracts is the last step in automating business rules and business processes. Smart contracts are self-executing codes that run on the blockchain and automatically run according to pre-set trigger conditions and execution logic. Each smart contract contains the specific implementation of business rules. Through smart contracts, various operations in the supply chain can be automatically processed, such as order confirmation, inventory management and payment settlement. After the contract is deployed to the blockchain network, it can automatically run between nodes to achieve decentralized business processing.

[0019] Step 3: Install IoT sensors on the cargo and the means of transport to obtain cargo environmental parameters generated based on monitoring the cargo environment, upload the cargo environmental parameters to the blockchain platform, synchronize information updates with the distributed ledger, and obtain full-process monitoring data.

[0020] Specifically, installing IoT sensors on goods and transportation vehicles is an important step to achieve full-process monitoring. IoT sensors can collect various environmental data in real time, such as temperature, humidity, vibration, location, etc., to ensure the safety and quality of goods during transportation. IoT sensors usually use wireless networks to transmit data to the central system, so that managers can understand the status of goods at any time. For example, in the transportation of food or medicine, temperature and humidity sensors can ensure that products are stored and transported under appropriate conditions, prevent deterioration or failure due to improper environmental conditions, and significantly improve the safety and reliability of cargo transportation. Uploading the collected cargo environmental parameters to the blockchain platform is an important link in achieving data transparency and sharing. The blockchain platform records and manages data in a decentralized manner to ensure that the data cannot be tampered with and has high security. After uploading the data collected by the IoT sensors to the blockchain platform, all nodes involved in the supply chain can access the data, thereby achieving full-process monitoring. For example, when the temperature sensor detects an abnormal situation, the data can be uploaded to the blockchain immediately, and the relevant parties can take timely measures to prevent the problem from expanding. It can achieve real-time sharing and efficient management of information, and improve the response speed and collaborative efficiency of the supply chain. On the blockchain platform, synchronizing and updating information with the distributed ledger is an important means to ensure data consistency and reliability. The distributed ledger is the core of blockchain technology. Each node saves a complete copy of the data, and all data changes are synchronized across the entire network. After the environmental parameters of the goods collected by the IoT sensors are uploaded to the blockchain platform, they will be automatically synchronized with the distributed ledger to ensure that the data of all nodes are consistent, which not only improves the transparency and credibility of the data, but also prevents the data from being tampered with or lost. For example, during the transportation of goods, all nodes can view the latest environmental parameters in real time to ensure that every link in the transportation process is under monitoring. Obtaining full-process monitoring data is the ultimate goal of realizing supply chain visualization and intelligent management. Through IoT sensors and blockchain technology, every link in the supply chain can achieve real-time monitoring and data sharing. Managers can view full-process monitoring data through the blockchain platform to understand the status of each link of the goods from production to delivery. For example, in logistics management, by viewing real-time data, transportation routes can be optimized and transportation efficiency can be improved; in quality control, environmental parameters can be monitored to ensure that products are stored and transported under optimal conditions, which can significantly improve the transparency, efficiency and security of the supply chain.

[0021] Step 4: According to the cargo demand forecasting model, the whole-process monitoring data is subjected to transportation analysis to obtain forecasted logistics data.

[0022] Specifically, according to the cargo demand forecasting model, the transportation analysis of the whole process monitoring data needs to be integrated with multiple data sources, including historical sales data, inventory data, transportation data and real-time monitoring data. The whole process monitoring data provides a comprehensive information basis for the forecasting model. The demand forecasting model usually uses machine learning algorithms (such as linear regression, decision tree, neural network, etc.) to analyze and predict future cargo demand. Through various algorithms, the trend and pattern of cargo demand can be identified, thus providing a basis for transportation planning. After integrating and cleaning the data, the data is input into the demand forecasting model for training and testing. By learning the patterns and trends in historical data, it is possible to predict the demand for cargo in the future. For example, if the demand for a certain type of cargo is predicted to increase significantly in a certain period of time, the transportation department needs to arrange transportation resources in advance to ensure that the cargo can be delivered in time. According to the forecast data provided by the demand forecasting model, the transportation analysis of the whole process monitoring data is carried out. The whole process monitoring data includes the real-time status of the cargo in each link, such as inventory level, transportation status, environmental conditions, etc. By combining the forecast data with the whole process monitoring data, it is possible to analyze whether the current transportation capacity can meet future demand. If the monitoring data shows that the current transportation capacity is insufficient, the transportation plan needs to be optimized, such as adding transportation vehicles, optimizing transportation routes, or adjusting transportation time to ensure that the goods are delivered on time. After obtaining the predicted logistics data, the transportation plan can be further refined. For example, based on the predicted data and actual monitoring data, a specific transportation plan can be formulated to determine the optimal transportation time and route for each batch of goods. If it is predicted that a certain transportation route may be congested, the route can be adjusted in advance to avoid transportation delays, which can improve transportation efficiency, reduce transportation costs, and ensure that the goods arrive at the destination on time and with quality.

[0023] Step 5: Deploy the smart contract to the blockchain node, perform transportation planning according to the predicted logistics data, and generate a supply chain strategy.

[0024] Specifically, deploying smart contracts to blockchain nodes is a key step in achieving automated and transparent supply chain management. Smart contracts are self-executing protocols that can automatically perform various operations in the supply chain based on predefined conditions. Before deploying smart contracts to blockchain nodes, you first need to ensure that the contract code has been rigorously tested and verified to ensure that the smart contract can be correctly executed in various situations. When deploying smart contracts, you need to upload the smart contracts to the blockchain platform so that the smart contracts can be synchronized and effective between various blockchain nodes, and each node can execute the same contract logic to ensure the consistency of supply chain operations and the reliability of data. Transportation planning based on predicted logistics data is the process of turning demand forecasts into actual actions. Predicted logistics data provides detailed information on the demand for goods in the future, including expected demand, demand time, destination, etc. Based on these predicted data, detailed transportation plans can be made. For example, determine the goods that need to be transported first, select the best transportation routes and transportation tools, and arrange transportation time and frequency. Through scientific and reasonable transportation planning, it can ensure that the goods can be delivered in time, meet market demand, reduce transportation costs, and improve transportation efficiency. Generating supply chain strategies is the process of optimizing and adjusting the entire supply chain based on transportation planning and the execution results of smart contracts. Supply chain strategies include inventory management strategies, production plans, and procurement plans, which can coordinate various links in the supply chain and improve the overall efficiency and flexibility of the supply chain. Specifically, inventory levels can be adjusted based on forecasted logistics data and transportation planning to ensure that inventory is sufficient but not excessive; production plans can be optimized to balance production capacity with market demand; and procurement plans can be formulated to ensure the timely supply of raw materials and parts. Through the implementation of multiple strategies, efficient operation of the supply chain can be achieved, and the competitiveness and market responsiveness of enterprises can be enhanced.

[0025] Step 6: Execute the supply chain strategy based on the smart contract, generate supply chain data, and visualize the supply chain data.

[0026] Specifically, to execute supply chain strategies based on smart contracts, it is first necessary to deploy and activate relevant smart contracts on the blockchain platform. Smart contracts automatically execute various operations in the supply chain according to predefined business rules and trigger conditions. For example, when the demand forecasting unit predicts that the demand for a certain type of goods will increase in the future, the smart contract will automatically trigger the corresponding production and transportation plan. The execution of supply chain strategies not only includes the scheduling of production and transportation, but also covers various links such as inventory management, order processing, and payment settlement. Through the automatic execution of smart contracts, the response speed and efficiency of the supply chain can be significantly improved, and human intervention and errors can be reduced. In the process of executing supply chain strategies, a large amount of supply chain data is generated, including production plans, transportation routes, inventory levels, order status, payment records, etc. Through the decentralization and transparency of blockchain, all data are recorded and shared in real time to ensure the integrity and immutability of the data. The generation process of supply chain data is not just a simple record of data, but also includes real-time updating and dynamic adjustment of data. For example, when there is a delay in transportation, the smart contract will automatically adjust the transportation plan and update the relevant data. The generation and update of data provides a basis for subsequent data analysis and visualization. Visualizing the generated supply chain data is an important means to achieve transparent and intelligent management of the supply chain. Through data visualization, the operating status, trends and potential problems of the supply chain can be intuitively displayed. For example, the changes in inventory levels can be displayed through line charts, the optimization of transportation routes can be displayed through heat maps, and the completion status of orders can be displayed through bar charts. Visualization not only helps managers quickly understand and analyze supply chain data, but also supports decision-making and optimization. The visualization platform provides a variety of data display tools, such as charts, reports, dashboards, etc. Users can choose the appropriate display method according to their needs to improve the efficiency and accuracy of data analysis.

[0027] The supply chain optimization method for the import and export of goods is applied to a supply chain optimization system for the import and export of goods, which can achieve the technical goals of supply chain data transparency and automated management, and achieve the technical effect of improving the overall efficiency and resilience of the supply chain.

[0028] Furthermore, the present application also includes: The node type of the blockchain node is selected according to the supply chain link to determine the blockchain node type; the blockchain network type is selected according to the participant requirements of the supply chain participants in the supply chain link; on the blockchain platform, based on the blockchain node type and the blockchain network type, the blockchain node is deployed at the supply chain participant in the supply chain link, and the blockchain network is obtained by communication connection with the blockchain node; the transaction information of the supply chain participants is recorded in the blockchain network to generate the distributed ledger.

[0029] Specifically, the node type of blockchain nodes is selected in the supply chain link, and the specific needs and functions of each supply chain link. Different supply chain links may require different types of blockchain nodes, such as full nodes, light nodes, or storage nodes. Full nodes store complete blockchain data and participate in the consensus process, which is suitable for links that require high data integrity and security; light nodes store blockchain information, which is suitable for links with limited resources or only need to verify transactions; storage nodes are mainly used for large-scale data storage, which is suitable for links that need to store a large amount of historical transaction data. By evaluating the needs of each supply chain link and selecting the most suitable node type, the efficient operation of the system and the rational use of resources can be ensured.

[0030] Then, select the type of blockchain network based on the participant needs of the supply chain participants in the supply chain link, and evaluate the specific requirements of each supply chain participant for data sharing, security, and transparency. Public blockchain is suitable for scenarios that require complete openness and transparency, but may sacrifice some privacy and performance; private blockchain is suitable for use within a single organization, with higher control and privacy protection; consortium blockchain is suitable for cooperation between multiple organizations, and can achieve data sharing while ensuring a certain degree of privacy. By analyzing the needs of each supply chain participant and selecting the most appropriate blockchain network type, a balance can be achieved between performance and security to meet the needs of all parties in the supply chain.

[0031] Next, the transaction information of supply chain participants is recorded in the blockchain network. Generating a distributed ledger is the core application of blockchain technology in supply chain management. When each supply chain participant conducts a transaction, the transaction information will be recorded in the blockchain network, which will be jointly verified and confirmed by all nodes in the network. The records form an unalterable distributed ledger to ensure the transparency and security of the transaction. All transaction data in the supply chain network can be shared and verified in real time, eliminating information asymmetry and data silos, and improving the overall efficiency and security of the supply chain.

[0032] The type of blockchain node is selected through the supply chain links, and the type of blockchain network is selected according to the needs of supply chain participants. Then, the blockchain nodes are deployed on the blockchain platform, and a blockchain network is formed through communication connections. Finally, transaction information is recorded on the blockchain to generate a distributed ledger, thereby improving the transparency, security and efficiency of the supply chain and providing a more reliable data sharing and collaborative management mechanism for all parties in the supply chain.

[0033] Furthermore, the present application also includes: Based on the deployment of the blockchain node, a public-private key pair is generated, including a public key and a private key; an access request from the supply chain participant is received, and the private key of the supply chain participant is verified according to the public key to obtain identity authentication; based on the identity authentication, an access permission control list is generated, and participant permissions are allocated; transaction information is transmitted and stored according to the participant permissions to generate the distributed ledger.

[0034] Specifically, in the process of deploying blockchain nodes, generating a public-private key pair, including a public key and a private key, is a key step to ensure the security of transactions and communications. Before joining the blockchain network, each blockchain node needs to generate a unique pair of public and private keys. The public key is public and is used to identify the node and encrypt data; the private key is confidential and is used to decrypt data and sign transactions. The generation of public-private key pairs usually uses secure cryptographic algorithms such as RSA or ECDSA to ensure that the key pairs cannot be easily cracked or tampered with. Communications and transactions between blockchain nodes can be effectively protected to prevent unauthorized access and data leakage.

[0035] Next, when a supply chain participant issues an access request, the private key of the supply chain participant is verified against the public key to confirm the authenticity of the identity. This is achieved through digital signature technology, that is, the participant signs the request with the private key, and the system uses the public key to verify the validity of the signature. Only when the signature verification is passed can the system confirm that the request is issued by a legitimate participant. The identity authentication mechanism not only ensures the security of the system, but also prevents forgery and impersonation, thereby protecting the integrity and credibility of the supply chain network.

[0036] Next, after identity authentication, the system will access the permission control list and assign corresponding permissions according to the roles and identities of the supply chain participants. The permission control list defines the operation permissions of each supply chain participant in the supply chain network, such as reading data, writing data, verifying transactions, etc. Through the refined control of participant permissions, it can be ensured that each participant can only access and operate the authorized part, preventing unauthorized operations and data abuse. The role-based access control mechanism improves the security and management efficiency of the system, ensuring that all links in the supply chain can operate efficiently and in a standardized manner.

[0037] Then, according to the rights of the participants, the transaction information is transmitted and stored to generate a distributed ledger. Whenever a supply chain participant initiates a transaction, the system will check the participant's rights to ensure that the supply chain participant has the right to perform the corresponding operation. Subsequently, the transaction information is transmitted through an encrypted channel and recorded in the distributed ledger of the blockchain. Each blockchain node keeps a complete copy of the ledger, and all transactions are jointly verified and confirmed by nodes across the entire network to ensure the transparency and immutability of the data. All transaction information in the supply chain can be shared and traced in real time, which improves the overall transparency and trust of the supply chain.

[0038] By generating public-private key pairs to achieve secure communications and transactions, the public key is used to verify the private key of the supply chain participants to ensure the authenticity of the identity. After the identity verification is passed, the participant permissions are assigned according to the permission control list. Finally, the transaction information is transmitted and stored according to the participant permissions, and a distributed ledger is generated, forming a secure, efficient and transparent blockchain supply chain management solution, which ensures the data security and operating specifications of all parties in the supply chain and effectively improves the overall management level and operational efficiency of the supply chain.

[0039] Furthermore, the present application also includes: Integrate the historical transaction information, historical logistics data and historical cargo environmental parameters of the blockchain platform and the IoT sensor to establish a cargo data management library; perform data training on the cargo data management library under time series to build a cargo transportation prediction model; input the full-process monitoring data into the cargo transportation prediction model to perform transportation analysis and obtain the predicted logistics data.

[0040] Specifically, integrating the historical transaction information, historical logistics data, and historical cargo environmental parameters of the blockchain platform and IoT sensors is an important step in establishing a cargo data management library. First, historical transaction information includes all past transaction records, such as orders, payments, shipments, etc.; historical logistics data includes past transportation records, such as transportation time, routes, delays, etc.; historical cargo environmental parameters include environmental conditions such as temperature, humidity, and vibration monitored during past transportation. Historical transaction information, historical logistics data, and historical cargo environmental parameters are collected and stored through the blockchain platform and IoT sensors, and then integrated into a unified cargo data management library. Integration can provide a comprehensive and accurate data foundation for subsequent data analysis and model training.

[0041] Next, training the cargo data management library with time series data is the key to building a cargo transportation forecasting model. Time series analysis is a statistical technique used to analyze time series data, identify patterns and trends in the data, and make predictions. Specifically, various machine learning and deep learning algorithms (such as ARIMA, LSTM, etc.) can be used to train the data and build a forecasting model. By analyzing past transaction, logistics, and environmental data, learning the laws and trends therein, it is possible to predict future transportation demand and possible anomalies. Through time series analysis, the accuracy of forecasts can be improved, providing more reliable decision support for supply chain management.

[0042] Then, inputting the full-process monitoring data into the cargo transportation prediction model for transportation analysis is the process of realizing the prediction of logistics data. The full-process monitoring data includes real-time cargo location, transportation status, environmental conditions, etc., which are collected in real time through IoT sensors and uploaded to the blockchain platform. By inputting real-time data into the previously constructed transportation prediction model, the current transportation situation can be analyzed and future transportation needs and possible problems can be predicted. Through real-time analysis, transportation plans can be adjusted in time, transportation routes can be optimized, transportation delays and cargo damage can be avoided, and cargo can be ensured to arrive at the destination on time and with quality.

[0043] By integrating the historical transaction information, historical logistics data and historical cargo environmental parameters of the blockchain platform and IoT sensors, a cargo data management library is established, and a cargo transportation forecasting model is constructed by time series analysis of the data. Then, the whole process monitoring data is input into the model for transportation analysis to obtain forecast logistics data. Through data integration, time series analysis and real-time monitoring, intelligent management of the supply chain is realized, which can improve the forecasting ability and response speed of the supply chain, optimize transportation plans, reduce operating costs, and improve the overall efficiency and reliability of the supply chain.

[0044] Furthermore, the present application also includes: Based on the cargo data management library, historical sales data and market trends are extracted for data training in time series to build a cargo demand forecasting unit; based on the cargo data management library, historical ordering nodes and historical ordering quantities are extracted for data training in time series to build an inventory optimization unit; based on the cargo data management library, historical transportation time and historical transportation routes are extracted for data training in time series to build a transportation route planning unit; the cargo demand forecasting unit, the inventory optimization unit and the transportation route planning unit are communicatively connected to obtain the cargo transportation forecasting model.

[0045] Specifically, based on the cargo data management library, historical sales data and market trends are extracted for data training under time series. First, the data needs to be cleaned and preprocessed to ensure the accuracy and consistency of the data. Historical sales data includes past sales records, sales quantities, sales time and other information, while market trends include industry reports, market analysis and consumer behavior data. Through time series analysis techniques such as ARIMA models and LSTM neural networks, patterns and rules in sales data and market trends can be identified to build a cargo demand forecasting unit. The cargo demand forecasting unit can predict cargo demand in the future and provide a basis for production and procurement plans of the supply chain.

[0046] Next, based on the cargo data management library, historical ordering nodes and historical ordering quantities are extracted for data training under time series in order to build an inventory optimization unit. Historical ordering data includes ordering records, ordering quantities, and ordering time for each ordering node (such as warehouses and retailers). Through time series analysis, the ordering patterns and seasonal changes in these data can be analyzed to predict future ordering needs. The inventory optimization unit uses forecast data, combined with the economic order quantity (EOQ) model, dynamic inventory management model, etc., to optimize inventory levels, avoid overstocking or shortages, and improve the efficiency and accuracy of inventory management.

[0047] Then, based on the cargo data management library, historical transportation time and historical transportation routes are extracted for data training under time series in order to construct a transportation route planning unit. Historical transportation data includes information such as the starting point, end point, transportation time, and transportation route used for each transportation. Through time series analysis, the best transportation route and time can be identified, and future transportation demand and possible transportation bottlenecks can be predicted. The transportation route planning unit combines these predicted data and uses optimization algorithms to plan the optimal transportation route, improve transportation efficiency, and reduce transportation costs and time.

[0048] Next, communicating and connecting the cargo demand forecasting unit, inventory optimization unit, and transportation route planning unit is a key step in building a cargo transportation forecasting model. By integrating the forecast results of the three units, a comprehensive cargo transportation forecasting model can be formed, which can not only predict future cargo demand, but also optimize inventory levels and transportation routes, thereby achieving overall optimization of the supply chain. For example, when the demand forecasting unit predicts high demand in a certain period in the future, the inventory optimization unit can arrange replenishment in advance, and the transportation route planning unit can plan the optimal transportation route in advance to ensure that the goods can be delivered in time.

[0049] By conducting time series analysis based on the cargo data management library, extracting historical sales data and market trends to build a cargo demand forecasting unit, extracting historical ordering data to build an inventory optimization unit, and extracting historical transportation data to build a transportation route planning unit, and connecting the three units for communication, a comprehensive cargo transportation forecasting model is formed, which realizes the intelligent and automated management of the supply chain, improves the accuracy and response speed of the forecast, optimizes the inventory and transportation plans, and significantly improves the overall efficiency and reliability of the supply chain.

[0050] Furthermore, the present application also includes: Extract cargo characteristics from the historical order quantity and construct a cargo interaction database, wherein the cargo interaction database includes independent cargo characteristics and mixed cargo characteristics; collect temperature, humidity and gas concentration from the historical order nodes and the historical transportation paths to obtain the transportation environment; perform characteristic degradation simulation on the independent cargo characteristics and the mixed cargo characteristics according to the transportation environment and the historical transportation time, and establish the cargo interaction prediction model; input the output data of the inventory optimization unit into the cargo interaction prediction model, perform dynamic cargo partition planning with minimum cargo characteristic degradation as the partitioning target through the output unit of the cargo interaction prediction model, and input the cargo planning data into the transportation path planning unit.

[0051] Specifically, the characteristics of goods are extracted from the historical order quantity, and the historical order data of each product is analyzed to understand the type of goods, demand patterns, turnover cycle and deterioration rate of each product under different storage conditions. A goods interaction database is established to record the independent characteristics of each product (i.e., the decay rate and humidity requirements when stored independently) and the mixed characteristics of multiple goods (i.e., the ripening or mutual influence characteristics when stored with other goods). For example, apples and bananas will ripen each other when stored together, so the mixed characteristics of apples and bananas will be reflected in the accelerated ripening speed.

[0052] Next, data on temperature, humidity, and gas concentrations are collected from historical ordering nodes and historical transportation routes to understand the specific environment that the goods experience during transportation, helping to predict the decay rate and deterioration of the goods, especially in the high temperature or low humidity that may be encountered in actual transportation. For example, in summer, the temperature in long-distance transportation often exceeds 30 degrees Celsius, and the ethylene concentration at this temperature is more likely to accelerate ripening.

[0053] Then, the degradation of the independent characteristics of the goods is simulated based on the environmental data and historical transportation time, and the degradation of the mixed characteristics of the goods is simulated based on the environmental data and historical transportation time. The simulation results are integrated to establish a cargo interaction prediction model. The cargo interaction prediction model predicts the decay or ripening during transportation by simulating the required transportation time of the goods and the degradation rate of the cargo characteristics under the required different temperature, humidity and gas conditions. Assuming that apples can remain unchanged for 10 days at 20 degrees Celsius and 60% humidity, but when stored with bananas that release ethylene, the deterioration rate is accelerated to 6 days, the degradation simulation can help optimize storage and transportation strategies in transportation environments.

[0054] Then, the cargo interaction prediction model is connected to the inventory optimization unit and the transportation route planning unit respectively, and the output data of the inventory optimization unit is input into the cargo interaction prediction model, and the cargo interaction prediction model is used to calculate the deterioration of the cargo in different partition environments. The output unit of the cargo interaction prediction model will partition the cargo according to the minimum deterioration of the cargo, and perform dynamic partition planning to determine the optimal cargo partitioning scheme, which can effectively reduce the deterioration and decay of the cargo and extend its shelf life. For example, apples and bananas will be planned in different areas to avoid ripening each other.

[0055] Finally, the cargo planning data after dynamic partitioning is input into the transportation path planning unit, and reasonable transportation routes and environmental conditions are designed according to the optimized partitioning to ensure that the quality of the goods is optimally maintained during the entire transportation process. For example, using cold chain transportation routes to avoid high temperature areas reduces the risk of apples and other fruits and vegetables rotting on the way.

[0056] By building a cargo interaction database and analyzing historical data of the transportation environment, combined with characteristic degradation simulation and dynamic zoning planning, the quality management of cargo during storage and transportation is improved. Through accurate prediction and zoning control, the decay and loss of cargo can be minimized, providing a more valuable optimization solution for supply chain management.

[0057] Furthermore, the present application also includes: The supply chain data is extracted for data normalization, and is centrally stored on a visualization platform to generate visualization platform data; the visualization platform data is extracted in multiple dimensions to generate demand forecasting data, inventory optimization data, and logistics path planning data; anomaly detection is performed on the demand forecasting data, inventory optimization data, and logistics path planning data to generate a visualization data table, and the visualization data table is displayed on the visualization platform.

[0058] Specifically, extracting supply chain data for data normalization is a key step to ensure data consistency and comparability. Data normalization involves standardizing data from different sources and formats, and comparing and analyzing them on the same scale. For example, it includes operations such as data cleaning, removing outliers, processing missing values, standardization, and normalization. Through data normalization, bias and noise in the data can be eliminated, and the quality of the data and the accuracy of the analysis can be improved. The normalized data is centrally stored on a visualization platform to facilitate subsequent multi-dimensional analysis and presentation.

[0059] Next, the normalized data is centrally stored on the visualization platform, and visualization platform data is generated. Visualization platform data is structured data that has been sorted and processed, which is convenient for various visualization analyses and displays. By centrally storing all data on one platform, unified management and access can be easily performed to ensure data consistency and integrity. The visualization platform provides a variety of data display and analysis tools. Users can intuitively view and analyze data through charts, reports, dashboards, etc., to support decision-making and optimization of supply chain management.

[0060] Next, multi-dimensional extraction of the visualization platform data to generate demand forecast data, inventory optimization data, and logistics path planning data is the key to realizing intelligent supply chain management. Multi-dimensional extraction refers to extracting data from multiple dimensions, such as time, location, and cargo type, from a data set for comprehensive analysis. Demand forecast data predicts future cargo demand by analyzing historical sales data and market trends; inventory optimization data optimizes inventory levels by analyzing historical ordering data and inventory data; and logistics path planning data plans the optimal transportation route by analyzing historical transportation data. Through multi-dimensional extraction, we can fully understand the operation of the supply chain and provide data support for supply chain optimization.

[0061] Then, anomaly detection of demand forecast data, inventory optimization data, and logistics routing data is an important means to ensure stable and efficient supply chain operation. Anomaly detection is to identify abnormal patterns and abnormal points in data through statistical analysis and machine learning algorithms. For example, if the demand forecast data for a certain period is significantly higher than the historical average, it may indicate potential market changes; if abnormal fluctuations in inventory optimization data are detected, it may indicate problems in inventory management; if abnormal delays in logistics routing data are detected, it may indicate problems in the transportation process. Through anomaly detection, potential problems in the supply chain can be discovered and handled in a timely manner to prevent the problems from expanding and affecting the overall operation of the supply chain.

[0062] Next, generating a visual data table on the visualization platform and displaying it is the process of converting data analysis results into intuitive information. Visual data tables are charts or reports that organize and display analysis results, and can intuitively display the patterns and trends in the data in a graphical way. The visualization platform provides a variety of data display tools, such as line charts, bar charts, pie charts, heat maps, etc. Users can choose the appropriate display method according to their needs. Through visual data tables, managers can quickly understand the operation status of the supply chain, support decision-making and optimization, and improve the efficiency and accuracy of supply chain management.

[0063] By extracting supply chain data, normalizing the data, and centrally storing it on a visualization platform, visualization platform data is generated; multi-dimensional extraction of visualization platform data is performed to generate demand forecasting data, inventory optimization data, and logistics path planning data; anomaly detection is performed, and visualization data tables are generated and displayed on the visualization platform, thereby achieving intelligent and efficient management of the supply chain, supporting decision-making and optimization through intuitive visualization data, and improving the overall efficiency and stability of the supply chain.

[0064] Furthermore, the present application also includes: An early warning mechanism is established to detect abnormal status of the supply chain data; if the supply chain data is judged to be normal, the visual data table is generated; if the supply chain data is judged to be abnormal, the early warning mechanism is triggered to alarm, generate alarm information, and add the alarm information to the visual data table.

[0065] Specifically, establishing an early warning mechanism and detecting abnormal status of supply chain data are important steps to ensure efficient operation of the supply chain and early detection of problems. The early warning mechanism identifies potential abnormalities by real-time monitoring of supply chain data, such as inventory levels, transportation status, order processing status, etc. For example, when the inventory level is lower than the preset warning line, the system will immediately detect this abnormality. Anomaly detection usually uses machine learning algorithms and statistical analysis methods, such as standard deviation analysis, time series analysis, cluster analysis, etc., to identify abnormal patterns and abnormal points in the data, which can promptly detect potential problems in the supply chain, prevent problems from expanding, and ensure the stable operation of the supply chain.

[0066] Next, if the supply chain data is judged to be normal, the system will generate a visual data table that displays the key indicators and operating status of the supply chain, and intuitively reflects the health of the supply chain in a graphical way. For example, the inventory level chart shows the trend of inventory changes, the transportation status chart shows the transportation progress of each batch of goods, and the order processing chart shows the completion status of the order. The visual data table not only helps managers understand the real-time status of the supply chain, but also supports data analysis and decision optimization to ensure the efficient operation of the supply chain.

[0067] Next, if the supply chain data is judged to be abnormal, the early warning mechanism will be triggered to alarm. The alarm information includes a detailed description of the abnormality, possible causes and recommended treatment measures. For example, when the inventory level is below the warning line, the alarm information will indicate the specific situation of insufficient inventory and recommend immediate replenishment or adjustment of production plans. The alarm information notifies relevant managers through various means, such as email, SMS, mobile application push, etc., to ensure that timely measures can be taken to deal with abnormal situations. The early warning mechanism improves the resilience and response speed of the supply chain and avoids supply chain interruptions or delays caused by abnormal situations.

[0068] Then, the alarm information is added to the visual data table, so that managers can view all data and alarm information on a unified platform. The visual data table not only shows the normal operation data of the supply chain, but also displays all alarm information, helping managers to fully understand the operation status and potential problems of the supply chain. For example, when viewing the inventory level chart, you can also see the alarm information triggered by insufficient inventory, which helps to make timely adjustment decisions. The integrated visual data display not only improves the transparency and readability of the data, but also enhances the overall control of the supply chain by managers.

[0069] By establishing an early warning mechanism, detecting abnormal status of supply chain data, judging whether the data is normal or abnormal, generating visual data tables and alarm information, and adding alarm information to the visual data table is an important means to achieve intelligent supply chain management. Through real-time monitoring and anomaly detection, potential problems in the supply chain can be discovered and handled in a timely manner to ensure the efficient operation and stability of the supply chain; through visual data display, managers can fully understand the operation status of the supply chain, make data-driven decisions and optimization, and improve the overall efficiency and competitiveness of the supply chain.

[0070] In summary, the supply chain optimization method for the import and export of goods provided in this application has the following technical effects: By deploying blockchain nodes in the supply chain link on the blockchain platform, a distributed ledger is established based on the blockchain nodes; the business rules and business processes of the supply chain link are extracted, the trigger conditions and execution logic are determined, and the smart contract is generated; the Internet of Things sensors are installed on the goods and transportation tools to obtain the cargo environment parameters generated based on the monitoring of the cargo environment, and the cargo environment parameters are uploaded to the blockchain platform, and the information is synchronized and updated with the distributed ledger to obtain the full-process monitoring data; according to the cargo demand prediction model, the transportation analysis of the full-process monitoring data is carried out to obtain the predicted logistics data; the smart contract is deployed to the blockchain node, and the transportation planning is carried out according to the predicted logistics data to generate the supply chain strategy; the supply chain strategy is executed based on the smart contract, the supply chain data is generated, and the supply chain data is visualized to achieve the technical goal of transparent and automated management of supply chain data, and achieve the technical effect of improving the overall efficiency and resilience of the supply chain.

[0071] Embodiment 2: Based on the supply chain optimization method for the import and export of goods in the above embodiment, and with the same inventive concept, this application also provides a supply chain optimization system for the import and export of goods, please refer to the attached Figure 2 ,include: A distributed ledger establishment module 11 is used to deploy blockchain nodes in the supply chain link on the blockchain platform and establish a distributed ledger based on the blockchain nodes; a smart contract generation module 12 is used to extract the business rules and business processes of the supply chain link, determine the trigger conditions and execution logic, and generate a smart contract; a full-process monitoring data acquisition module 13 is used to install Internet of Things sensors on goods and transportation tools, obtain cargo environmental parameters generated based on monitoring the cargo environment, upload the cargo environmental parameters to the blockchain platform, synchronize information with the distributed ledger, and obtain full-process monitoring data; a predicted logistics data acquisition module 14 is used to perform transportation analysis on the full-process monitoring data according to the cargo demand prediction model to obtain predicted logistics data; a supply chain strategy generation module 15 is used to deploy the smart contract to the blockchain node, perform transportation planning according to the predicted logistics data, and generate a supply chain strategy; a visualization display module 16 is used to execute the supply chain strategy based on the smart contract, generate supply chain data, and perform visualization of the supply chain data.

[0072] Furthermore, the distributed ledger establishment module 11 in the supply chain optimization system for goods import and export is also used for: The node type of the blockchain node is selected according to the supply chain link to determine the blockchain node type; the blockchain network type is selected according to the participant requirements of the supply chain participants in the supply chain link; on the blockchain platform, based on the blockchain node type and the blockchain network type, the blockchain node is deployed at the supply chain participant in the supply chain link, and the blockchain network is obtained by communication connection with the blockchain node; the transaction information of the supply chain participants is recorded in the blockchain network to generate the distributed ledger.

[0073] Furthermore, the distributed ledger establishment module 11 in the supply chain optimization system for goods import and export is also used for: Based on the deployment of the blockchain node, a public-private key pair is generated, including a public key and a private key; an access request from the supply chain participant is received, and the private key of the supply chain participant is verified according to the public key to obtain identity authentication; based on the identity authentication, an access permission control list is generated, and participant permissions are allocated; transaction information is transmitted and stored according to the participant permissions to generate the distributed ledger.

[0074] Furthermore, the predicted logistics data acquisition module 14 in the supply chain optimization system for the import and export of goods is also used for: Integrate the historical transaction information, historical logistics data and historical cargo environmental parameters of the blockchain platform and the IoT sensor to establish a cargo data management library; perform data training on the cargo data management library under time series to build a cargo transportation prediction model; input the full-process monitoring data into the cargo transportation prediction model to perform transportation analysis and obtain the predicted logistics data.

[0075] Furthermore, the predicted logistics data acquisition module 14 in the supply chain optimization system for the import and export of goods is also used for: Based on the cargo data management library, historical sales data and market trends are extracted for data training in time series to build a cargo demand forecasting unit; based on the cargo data management library, historical ordering nodes and historical ordering quantities are extracted for data training in time series to build an inventory optimization unit; based on the cargo data management library, historical transportation time and historical transportation routes are extracted for data training in time series to build a transportation route planning unit; the cargo demand forecasting unit, the inventory optimization unit and the transportation route planning unit are communicatively connected to obtain the cargo transportation forecasting model.

[0076] Furthermore, the predicted logistics data acquisition module 14 in the supply chain optimization system for the import and export of goods is also used for: Extract cargo characteristics from the historical order quantity and construct a cargo interaction database, wherein the cargo interaction database includes independent cargo characteristics and mixed cargo characteristics; collect temperature, humidity and gas concentration from the historical order nodes and the historical transportation paths to obtain the transportation environment; perform characteristic degradation simulation on the independent cargo characteristics and the mixed cargo characteristics according to the transportation environment and the historical transportation time, and establish the cargo interaction prediction model; input the output data of the inventory optimization unit into the cargo interaction prediction model, perform dynamic cargo partition planning with minimum cargo characteristic degradation as the partitioning target through the output unit of the cargo interaction prediction model, and input the cargo planning data into the transportation path planning unit.

[0077] Furthermore, the visual display module 16 in the supply chain optimization system for goods import and export is also used for: The supply chain data is extracted for data normalization, and is centrally stored on a visualization platform to generate visualization platform data; the visualization platform data is extracted in multiple dimensions to generate demand forecasting data, inventory optimization data, and logistics path planning data; anomaly detection is performed on the demand forecasting data, inventory optimization data, and logistics path planning data to generate a visualization data table, and the visualization data table is displayed on the visualization platform.

[0078] Furthermore, the visual display module 16 in the supply chain optimization system for goods import and export is also used for: An early warning mechanism is established to detect abnormal status of the supply chain data; if the supply chain data is judged to be normal, the visual data table is generated; if the supply chain data is judged to be abnormal, the early warning mechanism is triggered to alarm, generate alarm information, and add the alarm information to the visual data table.

[0079] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The supply chain optimization method for the import and export of goods and the specific examples in the aforementioned embodiment 1 are also applicable to the supply chain optimization system for the import and export of goods in this embodiment. Through the aforementioned detailed description of the supply chain optimization method for the import and export of goods, those skilled in the art can clearly know the supply chain optimization system for the import and export of goods in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0080] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0081] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A supply chain optimization method for the import and export of goods, characterized in that: include: On the blockchain platform, blockchain nodes are deployed in the supply chain, and a distributed ledger is established based on the blockchain nodes; Extract the business rules and business processes of the supply chain, determine the trigger conditions and execution logic, and generate smart contracts; Install IoT sensors on the cargo and the means of transport to obtain cargo environment parameters generated based on monitoring the cargo environment, upload the cargo environment parameters to the blockchain platform, synchronize information updates with the distributed ledger, and obtain full-process monitoring data; According to the cargo demand forecasting model, transport analysis is performed on the whole-process monitoring data to obtain forecast logistics data; Deploy the smart contract to the blockchain node, perform transportation planning according to the predicted logistics data, and generate a supply chain strategy; The supply chain strategy is executed based on the smart contract, supply chain data is generated, and a visual display of the supply chain data is performed.

2. A supply chain optimization method for the import and export of goods as claimed in claim 1, characterized in that: The blockchain platform deploys blockchain nodes in the supply chain link, and establishes a distributed ledger based on the blockchain nodes, including: Selecting the node type of the blockchain node according to the supply chain link to determine the blockchain node type; Selecting the type of blockchain network based on the participant needs of the supply chain participants in the supply chain link; On the blockchain platform, based on the blockchain node type and the blockchain network type, the blockchain node is deployed at the supply chain participant in the supply chain link, and the blockchain node is communicatively connected to obtain a blockchain network; The transaction information of the supply chain participants is recorded in the blockchain network to generate the distributed ledger.

3. A supply chain optimization method for the import and export of goods as claimed in claim 2, characterized in that: The step of recording the transaction information of the supply chain participants in the blockchain network and generating the distributed ledger includes: Based on the deployment of the blockchain node, generate a public-private key pair, including a public key and a private key; Receive an access request from the supply chain participant, verify the private key of the supply chain participant based on the public key, and obtain identity authentication; Based on the identity authentication and access control list, assigning the participant permissions; The transaction information is transmitted and stored according to the permissions of the participants to generate the distributed ledger.

4. A supply chain optimization method for the import and export of goods as claimed in claim 1, characterized in that: The method of performing transportation analysis on the whole-process monitoring data according to the cargo demand forecasting model to obtain forecasted logistics data includes: Integrate the historical transaction information, historical logistics data and historical cargo environmental parameters of the blockchain platform and the IoT sensor to establish a cargo data management library; Conducting time series data training on the cargo data management database to build a cargo transportation prediction model; The whole-process monitoring data is input into the cargo transportation prediction model for transportation analysis to obtain the predicted logistics data.

5. A supply chain optimization method for the import and export of goods as claimed in claim 4, characterized in that: The step of performing time series data training on the cargo data management library to construct a cargo transportation prediction model includes: Based on the cargo data management library, historical sales data and market trends are extracted to perform data training under time series, and a cargo demand forecasting unit is constructed; Based on the cargo data management library, historical ordering nodes and historical ordering quantities are extracted to perform data training under time series, and an inventory optimization unit is constructed; Based on the cargo data management library, historical transportation time and historical transportation routes are extracted to perform data training under time series, and a transportation route planning unit is constructed; The cargo demand forecasting unit, the inventory optimization unit and the transportation route planning unit are communicatively connected to obtain the cargo transportation forecasting model.

6. A method for optimizing the supply chain for the import and export of goods as claimed in claim 5, characterized in that: Also includes: Extracting cargo characteristics from the historical order quantity and constructing a cargo interaction database, wherein the cargo interaction database includes cargo independent characteristics and cargo mixed characteristics; Collect temperature, humidity and gas concentration from the historical ordering nodes and the historical transportation paths to obtain the transportation environment; According to the transportation environment and the historical transportation time, characteristic degradation simulation is performed on the independent characteristics of the goods and the mixed characteristics of the goods respectively, and the goods interaction prediction model is established; The output data of the inventory optimization unit is input into the cargo interaction prediction model, and dynamic cargo partitioning planning with minimum degradation of cargo characteristics as the partitioning target is performed through the output unit of the cargo interaction prediction model, and the cargo planning data is input into the transportation path planning unit.

7. A supply chain optimization method for the import and export of goods as claimed in claim 1, characterized in that: The visual display of the supply chain data includes: Extracting the supply chain data to perform data normalization, and centrally storing the data on the visualization platform to generate visualization platform data; Perform multi-dimensional extraction on the visualization platform data to generate demand forecasting data, inventory optimization data, and logistics path planning data; Anomaly detection is performed on the demand forecasting data, inventory optimization data, and logistics path planning data to generate a visualization data table, which is then displayed on the visualization platform.

8. A method for optimizing the supply chain for the import and export of goods as claimed in claim 7, characterized in that: The generating of the visual data table comprises: Establishing an early warning mechanism to detect abnormal status of the supply chain data; If the supply chain data is judged to be normal, the visual data table is generated; if the supply chain data is judged to be abnormal, the early warning mechanism is triggered to alarm, generate alarm information, and add the alarm information to the visual data table.

9. A supply chain optimization system for the import and export of goods, characterized in that: The steps for implementing a supply chain optimization method for the import and export of goods as described in any one of claims 1 to 8 include: A distributed ledger establishment module is used to deploy blockchain nodes in the supply chain on the blockchain platform and establish a distributed ledger based on the blockchain nodes; A smart contract generation module, used to extract the business rules and business processes of the supply chain link, determine the trigger conditions and execution logic, and generate a smart contract; A full-process monitoring data acquisition module is used to install IoT sensors on the cargo and the means of transport, obtain cargo environmental parameters generated based on monitoring the cargo environment, upload the cargo environmental parameters to the blockchain platform, synchronize information updates with the distributed ledger, and obtain full-process monitoring data; A predicted logistics data acquisition module is used to perform transportation analysis on the whole-process monitoring data according to a cargo demand prediction model to obtain predicted logistics data; A supply chain strategy generation module, used to deploy the smart contract to the blockchain node, perform transportation planning according to the predicted logistics data, and generate a supply chain strategy; A visualization module is used to execute the supply chain strategy based on the smart contract, generate supply chain data, and perform visualization of the supply chain data.

Images