Block chain-driven supply chain collaborative management method

Abstract

The invention provides a blockchain-driven supply chain collaborative management method, and relates to the technical field of supply chain management. Sensing data of a plurality of nodes in a supply chain are collected; uploading the plurality of node sensing data in real time through a block chain to generate a plurality of blocks; performing optimization configuration on the plurality of blocks, generating a resource configuration result, performing sharing updating on the block chain based on the resource configuration result, and generating a platform sharing data set of the block chain; multi-party combination is carried out through a platform sharing data set, and a collaborative management decision is made; the collaborative management decision is simulated and executed to carry out risk monitoring on the supply chain, an early warning mechanism is activated to carry out feedback response on the collaborative management decision, and a collaborative management optimization strategy is generated. The technical problems of low data sharing efficiency and low collaborative decision-making efficiency among the nodes of the supply chain due to lack of reliable data sharing and collaborative decision-making mechanisms in the prior art are solved, and the real-time performance, transparency and collaborative decision-making efficiency of supply chain management are improved.

Description

Technical Field

[0001] The present application relates to the field of supply chain management technology, and specifically to a blockchain-driven supply chain collaborative management method. Background Art

[0002] Supply chain management is a key activity that coordinates resources and information between various nodes in the supply chain, such as suppliers, manufacturers, distributors, and retailers. The increasingly complex multi-node collaboration and dynamic market demand of the supply chain have put forward higher requirements for supply chain management.

[0003] Existing supply chain management methods usually rely on centralized systems or decentralized data processing, with each node collecting, storing and processing information separately. Due to the lack of a unified data sharing mechanism, the collaboration efficiency of upstream and downstream supply chains is low, and the problem of information islands is serious, resulting in increased communication costs between nodes. Secondly, existing methods mostly focus on static configuration and lack dynamic resource optimization capabilities, making it difficult to achieve real-time and secure data sharing. Data lags often lead to uneven resource allocation, slow supply chain response, and an inability to quickly adapt to demand fluctuations or emergencies. Summary of the invention

[0004] This application provides a blockchain-driven supply chain collaborative management method, which solves the technical problems in the prior art that the lack of a reliable data sharing and collaborative decision-making mechanism leads to low data sharing efficiency and low collaborative decision-making efficiency among supply chain nodes, and achieves the technical effect of improving the real-time, transparency and collaborative decision-making efficiency of supply chain management.

[0005] In view of the above problems, the present application provides a blockchain-driven supply chain collaborative management method, the method comprising: traversing multiple supply chain nodes in the supply chain to collect data and obtain multiple node sensor data; uploading the multiple node sensor data in real time through the blockchain to generate multiple blocks; optimizing the configuration of the multiple node sensor data of the supply chain according to the multiple blocks to generate resource configuration results, sharing and updating the blockchain based on the resource configuration results to generate a platform shared data set of the blockchain; conducting multi-party collaboration based on the platform shared data set of the blockchain through the multiple supply chain nodes to formulate collaborative management decisions; simulating the execution of the collaborative management decision to monitor the risk of the supply chain and generate an abnormal data set, activating the early warning mechanism according to the abnormal data set to provide feedback response to the collaborative management decision, and generating a collaborative management optimization strategy.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] By collecting sensor data from multiple nodes, the original information of each link in the supply chain can be obtained, providing the most basic data source for the management of the entire supply chain. The sensor data of the multiple nodes are uploaded in real time through the blockchain to generate multiple blocks, establishing a reliable infrastructure for data sharing and management. The sensor data of the multiple nodes in the supply chain are optimized and configured according to the multiple blocks to generate resource configuration results, thereby improving resource utilization efficiency. The blockchain is shared and updated based on the resource configuration results to generate a platform shared data set of the blockchain, so that the optimized resource configuration results can be shared among the nodes in the supply chain, further breaking the information island, promoting the collaborative cooperation between the nodes, and improving the synergy of the entire supply chain. Based on the platform shared data set of the blockchain, the multiple supply chain nodes are combined with multiple parties to make collaborative management decisions, which can integrate the interests and needs of each link in the supply chain, make the decision more scientific and reasonable, and improve the overall decision-making efficiency and quality of the supply chain. By simulating the execution of the collaborative management decision to monitor the risk of the supply chain, it is possible to timely discover abnormal situations in the operation of the supply chain and generate abnormal data sets. According to the abnormal data sets, the early warning mechanism is activated to provide feedback response to the collaborative management decision and generate collaborative management optimization strategies, thereby continuously improving collaborative management decisions and enhancing the supply chain's ability to cope with risks.

[0008] In summary, this application reduces information asymmetry and decision-making errors in the supply chain through data optimization configuration, collaborative decision-making and dynamic optimization mechanism, thereby improving the overall operational efficiency of the supply chain. The data security and dynamic optimization of decision-making ensured by blockchain technology enable the supply chain to adjust decisions in a timely manner when facing internal and external risks, ensuring the efficient and stable operation of the supply chain, enhancing the stability and reliability of the supply chain, and improving the overall competitiveness of the supply chain and its ability to cope with complex environments.

[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 in accordance with the contents of the specification. 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 listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A flowchart of a blockchain-driven supply chain collaborative management method provided in an embodiment of the present application.

[0011] Figure 2 A schematic diagram of a process for generating multiple blocks in a blockchain-driven supply chain collaborative management method provided in an embodiment of the present application.

[0012] Figure 3A schematic diagram of the process of making collaborative management decisions in the blockchain-driven supply chain collaborative management method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0013] The embodiments of the present application provide a blockchain-driven supply chain collaborative management method to solve the technical problems in the prior art, such as low data sharing efficiency and low collaborative decision-making efficiency among supply chain nodes due to the lack of a reliable data sharing and collaborative decision-making mechanism, thereby achieving the technical effect of improving the real-time, transparency and collaborative decision-making efficiency of supply chain management.

[0014] like Figure 1 As shown, the embodiment of the present application provides a blockchain-driven supply chain collaborative management method, the method comprising:

[0015] Step S1: traverse multiple supply chain nodes in the supply chain to collect data and obtain multiple node sensor data.

[0016] Specifically, supply chain nodes are all links in the supply chain that participate in information flow and resource interaction. For example, raw material suppliers, manufacturers, wholesalers, warehouse management, logistics companies, retailers, etc. are all supply chain nodes. Node sensor data refers to the data obtained by sensors or other data acquisition devices at various nodes in the supply chain. These data can reflect various status information of the node, such as production quantity, inventory level, location and speed of transport vehicles (if it is a transport node), etc.

[0017] Data is collected from each node through sensors or data acquisition devices deployed at each supply chain node. These sensors can be physical sensors, such as temperature sensors, humidity sensors, pressure sensors, etc., or they can be data acquisition tools at the software level, such as monitoring software for collecting production equipment operation data. For example, in a fresh food supply chain, there will be soil moisture sensors and weather stations (collecting temperature, humidity, rainfall and other data) at the farm node; GPS sensors (collecting vehicle location and driving speed) at the transportation node; and inventory management systems at the warehouse node to collect inventory quantity and other data. These different types of data acquisition devices collect node sensor data from each node.

[0018] By traversing multiple supply chain nodes in the supply chain to collect data, each link of the supply chain can be monitored in real time to ensure the accuracy and completeness of the data, provide basic data support for subsequent data upload, optimized configuration and collaborative management decision-making, and ensure that subsequent steps can be based on accurate and comprehensive data.

[0019] Step S2: Upload the sensor data of the multiple nodes in real time through the blockchain to generate multiple blocks.

[0020] Specifically, blockchain is a distributed ledger technology that stores data on multiple nodes (computers), each of which stores a complete or partial copy of the ledger. Data exists in the form of blocks, each of which contains certain transaction information or data and is linked together through cryptographic technology. Blocks are the basic data structure unit in blockchain. Each block contains certain data (node ​​sensor data in this supply chain management solution), timestamp, hash value of the previous block, and other information.

[0021] The collected sensor data from multiple nodes are first encrypted and then automatically triggered to be uploaded to the blockchain network through smart contracts. These data are packaged into new blocks, each of which contains a series of data records and is linked to the previous block through hash values ​​to form a growing blockchain. The blockchain ensures the security and reliability of the node sensor data and provides a decentralized, tamper-proof data recording system for the supply chain.

[0022] Step S3: Optimize and configure the sensor data of the multiple nodes in the supply chain according to the multiple blocks to generate a resource configuration result, and share and update the blockchain based on the resource configuration result to generate a platform shared data set of the blockchain.

[0023] Specifically, the resource allocation result is the result of a reasonable allocation of various resources (such as human, material, and financial resources) in the supply chain based on the sensor data of each node in the supply chain. The platform shared data set is a data set formed after shared updates on the blockchain. This data set contains supply chain-related data after optimized configuration and can be accessed and used by multiple nodes in the supply chain.

[0024] Analyze the node sensor data in each block, which reflects the status of each node in the supply chain. Use deep learning and optimization algorithms to optimize resource allocation according to factors such as demand and supply capacity of each node, and generate resource allocation results to improve resource utilization efficiency, reduce costs, and enhance the responsiveness of the supply chain. Then, update the optimized resource allocation results to the blockchain, so that the data set on the blockchain becomes a platform shared data set containing the latest resource configuration information, providing access and use to each node in the supply chain.

[0025] For example, in a furniture manufacturing supply chain, based on the inventory data of the wood supplier node (node ​​sensor data in the block), the production capacity and order demand data of each production workshop, the data analysis algorithm is used to determine the resource allocation results such as how much wood to allocate to each workshop and how many workers to arrange for overtime. This result is then updated on the blockchain, and supply chain nodes such as furniture manufacturers and sellers can obtain these shared data through the blockchain platform.

[0026] Step S4: Based on the multiple supply chain nodes, multiple parties are united through the shared data set of the blockchain platform to make collaborative management decisions.

[0027] Specifically, collaborative management decisions are decisions on supply chain management made by multiple nodes in the supply chain. This decision takes into account the interests of multiple nodes, resource conditions, market demand and other factors, and aims to achieve the overall optimization of the supply chain. Multiple supply chain nodes use shared data sets on the blockchain to conduct games and analysis through a multi-party joint model, generate joint game results, and make collaborative management decisions to promote cooperation among all parties in the supply chain and improve decision-making efficiency and synergy.

[0028] Step S5: simulate the execution of the collaborative management decision to monitor the risk of the supply chain, generate an abnormal data set, activate the early warning mechanism according to the abnormal data set to provide feedback response to the collaborative management decision, and generate a collaborative management optimization strategy.

[0029] Specifically, the abnormal data set is a set of data that is inconsistent with normal conditions, which is found by monitoring the supply chain risks during the simulation of collaborative management decision-making. These data may indicate risks in the supply chain, such as production delays, inventory shortages, transportation failures, etc. The collaborative management optimization strategy is a management strategy generated by adjusting and optimizing the collaborative management decision according to the abnormal situation. This strategy aims to eliminate or reduce the impact of risks on the supply chain and restore the supply chain to normal operation.

[0030] Use supply chain simulation software or establish a mathematical model of the supply chain, and input the formulated collaborative management decision into the model or software for simulation execution. During the simulation process, by comparing the actual node sensor data (obtained from the blockchain) and the simulated expected data, the differences are found, and these difference data (i.e., abnormal data sets) are collected as abnormal data sets. After the abnormal data set is found, the early warning mechanism is activated to notify the relevant supply chain nodes to take temporary measures. The early warning mechanism can be to automatically send text messages, emails, or pop up a prompt box in the management system to notify relevant personnel. At the same time, the abnormal data and early warning results are transmitted to the collaborative management decision-making system through the feedback mechanism. Based on the abnormal analysis results, the supply chain strategy is dynamically adjusted, such as reconfiguring resources, modifying transportation routes, updating production schedules, etc., to deal with risks and restore the supply chain to normal operation.

[0031] By simulating the execution of decisions and monitoring risks, potential risks in the supply chain operation process can be discovered in advance, abnormal data sets can be generated, and early warning mechanisms can be activated in a timely manner. Feedback responses to collaborative management decisions can be made based on early warning information, and optimization strategies can be generated, which can continuously adjust and improve decisions, ensure the stable and efficient operation of the supply chain, and reduce the impact of risks on the supply chain.

[0032] Further, such as Figure 2 As shown, step S2 of the embodiment of the present application includes:

[0033] Step S21: construct a smart contract, automatically trigger a transmission instruction through the smart contract, synchronize the sensor data of the multiple nodes to the blockchain for packaging through the transmission instruction, and generate multiple data packets.

[0034] Step S22: using a hash function to perform mapping calculations on the multiple data packets to generate multiple hash values, where the multiple hash values ​​correspond to the multiple data packets.

[0035] Step S23: Aggregate the multiple data packets according to the multiple hash values ​​to generate multiple initial blocks.

[0036] Step S24: verify the multiple initial blocks through a consensus mechanism to obtain a block verification result.

[0037] Step S25: storing the multiple initial blocks in chain form in chronological order according to the block verification result to generate the multiple blocks.

[0038] Specifically, a smart contract is an automatically executed contract clause that exists in the form of code on the blockchain. The contract defines the conditions and process for uploading data to the blockchain. First, deploy the smart contract on the blockchain and set the trigger conditions, such as uploading data at a certain interval or triggering when sensor data is updated. When the trigger conditions are met, the smart contract automatically generates transmission instructions and synchronizes the data to the blockchain network. The data is encapsulated into multiple data packets and prepared for the next step of processing. Through smart contracts, data upload can be automated, reducing manual intervention and improving efficiency and accuracy.

[0039] A hash function is a function that maps data of any length to a hash value of a fixed length. Each data packet is processed using a hash function to generate a unique hash value. This hash value is an encrypted representation of the contents of the data packet and can be used to verify the integrity and authenticity of the data. Each data packet has a corresponding hash value, which ensures the correspondence between the data and also provides a secure identity for the data packet to prevent data tampering during transmission.

[0040] Multiple data packets are aggregated according to multiple hash values ​​to generate multiple initial blocks. Each initial block contains a certain number of data packets and their corresponding hash values. By aggregating data packets, storage efficiency is improved, allowing more data to be stored on the blockchain.

[0041] The consensus mechanism is an algorithm in the blockchain that ensures that all nodes agree on the order and content of blockchain data. Consensus mechanisms include proof of work (PoW), proof of stake (PoS), etc. Multiple nodes in the network use the consensus mechanism to verify the initial block, including checking the hash value of the block, verifying the legitimacy of the data packet, etc. After each verification, a corresponding verification result is generated to indicate whether the block has passed the verification. Only when the block passes the verification will it be accepted and added to the blockchain. The verification and verification of multiple initial blocks through the consensus mechanism ensures the security and reliability of the blockchain and prevents invalid or malicious data from being added to the chain.

[0042] According to the block verification results, multiple initial blocks are chained and stored in chronological order to generate multiple new blocks. Each new block contains the hash value of the previous block, forming a chain structure, ensuring the immutability of the data in the blockchain and providing a reliable data record for the supply chain.

[0043] Through the above data storage, the security and integrity of data in the supply chain can be ensured on the blockchain, while real-time updating and sharing of data can also be achieved, thereby improving the efficiency and transparency of supply chain management.

[0044] Furthermore, in step S3 of the embodiment of the present application, the sensor data of the multiple nodes of the supply chain are optimized and configured according to the multiple blocks to generate a resource configuration result, including:

[0045] Step S31: introducing the resource and environmental parameters of the supply chain, performing traversal configuration analysis on the sensor data of the multiple nodes based on the multiple blocks in combination with the resource and environmental parameters, and generating a pre-configuration solution.

[0046] Step S32: performing expected optimization analysis based on the sensor data of the multiple nodes and setting optimization configuration targets.

[0047] Step S33: performing resource allocation calculation on the pre-configuration scheme according to the optimization configuration target, performing configuration feasibility analysis based on the allocation result, and generating resource configuration feasibility information.

[0048] Step S34: Perform deep reinforcement learning based on the feasible resource configuration information combined with the resource environment parameters to generate the resource configuration result.

[0049] Specifically, resource environment parameters refer to external environmental factors that affect resource allocation and configuration in the supply chain, such as production capacity, transportation capacity, market demand, inventory level, etc. The pre-configuration plan is a preliminary plan generated through the analysis results, which describes the preliminary resource allocation and configuration plan.

[0050] First, resource and environmental parameters that affect the operation of the supply chain are introduced, such as market demand forecasts, warehouse capacity limitations, and transportation costs. Then, combined with the sensor data of multiple nodes in the blockchain, multiple nodes in the supply chain are traversed and configured for analysis. The sensor data of each node is evaluated using data analysis software to determine how to allocate resources to meet current and expected needs, and a preliminary resource allocation plan, namely the pre-configuration plan, is generated based on the analysis results. This plan is the basis for subsequent optimization and provides a feasible framework for the preliminary allocation of resources. For example, in the electronic equipment supply chain, if resource and environmental parameters show that the supply of rare metals in a certain area may be limited, combined with the equipment production capacity and raw material inventory data in the sensor data of each production workshop node, a preliminary plan for adjusting the allocation of rare metals between different workshops is analyzed.

[0051] The optimization configuration target refers to the performance indicator of resource configuration optimization, such as minimizing costs and maximizing service levels. The setting of the optimization configuration target is to guide the subsequent resource allocation calculation and ensure that the final resource allocation result can meet the business needs of the supply chain. Based on the real-time sensor data of each node in the supply chain, the current status is analyzed and the desired optimization target is set. For example, in the clothing supply chain, the production progress of each production workshop and the inventory data of the warehouse are analyzed, and it is found that the production progress is lagging and the inventory is overstocked. The optimization configuration target set after the optimization analysis may be to increase production efficiency by 20% within a month and reduce inventory levels by 30%.

[0052] According to the pre-configuration scheme and the optimization configuration target, the resource allocation calculation is performed. Mathematical models (such as linear programming models) can be used to perform resource allocation calculations, and various resources in the pre-configuration scheme are quantitatively allocated according to the optimization configuration target. For example, according to the set goal of improving production efficiency, calculate how many workers and raw materials should be allocated to each workshop. Then, through simulation operation or actual experience evaluation, the allocation result is analyzed for configuration feasibility, and whether the configuration meets the actual constraints, such as inventory, production capacity, logistics restrictions, etc., is checked, and resource configuration feasibility information is generated to determine whether the configuration scheme is actually executable. This resource configuration feasibility information is feedback information generated by feasibility analysis to confirm the operability and effect of the resource allocation scheme. For example, if the allocation result causes the number of workers in a workshop to exceed its space capacity (not in line with the actual operating conditions), it is considered infeasible. Through resource allocation calculation and feasibility analysis, the feasibility and effectiveness of the resource allocation scheme in actual operation are ensured.

[0053] The generated feasible information on resource allocation is combined with resource and environmental parameters as input for deep reinforcement learning. The resource allocation scheme is continuously optimized through a deep reinforcement learning model (such as a deep Q network or a deep reinforcement learning algorithm). Through a trial-and-error process, the model learns how to reasonably allocate resources in different environments to achieve maximum benefits or meet optimization goals, and generates the final resource allocation result. This resource allocation result is a scheme optimized by deep reinforcement learning and can be effectively implemented in practice. The introduction of deep reinforcement learning improves the intelligence and adaptability of resource allocation schemes, allowing supply chain resource allocation to not only be optimized based on static data, but also to self-adjust according to dynamic changes.

[0054] The above steps combine sensor data, resource and environmental parameters, and deep reinforcement learning to systematically optimize the resource allocation of the supply chain, ensure the rational allocation of resources, improve the efficiency and flexibility of supply chain management, and meet the dynamically changing market needs.

[0055] Furthermore, in step S3 of the embodiment of the present application, the blockchain is shared and updated based on the resource configuration result to generate a platform shared data set of the blockchain, including:

[0056] Step S35: encrypt the plurality of node sensing data to generate a plurality of encrypted data.

[0057] Step S36: Synchronize the multiple encrypted data with the blockchain according to the resource configuration result to generate chain synchronization data.

[0058] Step S37: Determine whether the chain synchronization data meets the expected synchronization threshold.

[0059] Step S38: When the chain synchronization data does not meet the expected synchronization threshold, a first prompt is generated, the priority of the chain synchronization data is set to 0 according to the first prompt, and the chain synchronization data is added to the data column to be processed.

[0060] Step S39: When the chain synchronization data meets the expected synchronization threshold, a second prompt is generated, the priority of the chain synchronization data is set to 1 according to the second prompt, and the platform shared data set of the blockchain is generated.

[0061] Specifically, the sensor data of each node is encrypted using an encryption algorithm (such as AES, RSA or blockchain-specific encryption technology) to generate corresponding encrypted data. The encrypted data is stored as ciphertext to ensure that it will not be tampered with or leaked during data transmission and storage.

[0062] The storage location and update order of each encrypted data in the blockchain are determined based on the resource allocation results, and then the encrypted data is distributed to different blocks in the blockchain. The encrypted data is synchronized through the distributed ledger mechanism of the blockchain to ensure data consistency. The synchronized encrypted data constitutes chain synchronization data, which is structured and stored on the blockchain, becoming the basis for subsequent sharing and verification.

[0063] The expected synchronization threshold refers to a value preset during the data synchronization process, which is used to determine whether the data synchronization has achieved the expected effect. This threshold can be set according to different supply chain requirements, such as quantitative indicators such as the data integrity ratio and the timeliness requirements for data updates. According to the specific indicators of the expected synchronization threshold set, a data verification algorithm (such as a Merkle tree or a hash function) is used to check the chain synchronization data to verify the integrity and consistency of the chain synchronization data. The verification result of the synchronization data is compared with the expected synchronization threshold. The judgment result of compliance or non-compliance is output to determine the next step.

[0064] The first prompt is a notification message used to inform the relevant system or personnel that the chain synchronization data has not reached the expected synchronization threshold. The pending data column is a data storage area for storing chain synchronization data that temporarily does not meet the processing requirements (i.e., does not meet the expected synchronization threshold) and needs further processing. When it is determined that the chain synchronization data does not meet the expected synchronization threshold, the first prompt is generated to inform the relevant personnel of the cause of the problem (such as missing data or incorrect data format). This prompt can be a log record, a system message, or a notification sent to the administrator. Then, the priority of the chain synchronization data is set to 0, and further operations on the blockchain are suspended. The abnormal data is added to the pending data column, which is added to a special pending data column and waits for subsequent correction or re-verification. In data processing, priority is an attribute that determines the order of data processing. Setting the priority to 0 means that the chain synchronization data is given the lowest priority in the current processing queue, which means that these data will not be processed until other data with higher priority are processed.

[0065] The second prompt is similar to the first prompt, which is a notification information used to inform relevant systems or personnel that the chain synchronization data has reached the expected synchronization threshold. When the chain synchronization data meets the expected synchronization threshold, a second prompt is generated, which can also be a log record, system message or notification. Then, the priority of the data is set to 1, giving it the right to store and share in the blockchain. These chain synchronization data that meet the requirements are integrated to form a platform shared data set of the blockchain, providing access and use to each node in the supply chain. Setting the priority of the chain synchronization data to 1 means that the data has a higher priority in the processing queue and can be used for subsequent operations such as generating platform shared data sets.

[0066] The above steps ensure the security and privacy of data during transmission and storage by encrypting node sensor data, preventing unauthorized access and tampering of data; through expected synchronization threshold verification, abnormal data can be prevented from entering the blockchain, ensuring that only high-quality data is stored and shared, improving the credibility and reliability of supply chain data, and providing a high-quality data foundation for subsequent collaborative management.

[0067] Further, step S35 includes:

[0068] Step S351: traverse the plurality of node sensing data to perform sensitivity analysis and obtain a plurality of data sensitivities.

[0069] Step S352: Arrange the plurality of node sensing data in descending order according to the plurality of data sensitivities to generate a sensing data sequence.

[0070] Step S353: Divide the plurality of node sensing data based on the sensing data sequence to determine a plurality of data to be encrypted.

[0071] Step S354: Perform homomorphic encryption calculation on the multiple data to be encrypted to generate the multiple encrypted data.

[0072] Specifically, the sensor data uploaded by the supply chain nodes are traversed and sensitivity analysis is performed to identify and classify the sensitivity of the data. The sensitivity level of each node sensor data is determined based on the sensitivity analysis results, and a data sensitivity is generated for it. This data sensitivity is a measure of the importance and security requirements of the data, which can be expressed in scores or grades. Sensitivity analysis can be completed by judging through preset rules or by establishing a sensitivity assessment model using machine learning algorithms. Exemplarily, different sensitivity levels can be assigned to data of different types, different data volumes, and different sources in the preset rules. The sensor data of each node is matched according to the preset rules to generate the corresponding data sensitivity. The sensitivity assessment model can collect the labeled historical node sensor data and use machine learning algorithms such as decision trees, random forests, neural networks, etc. for training, so that the model can continuously learn the characteristics of sensitive data in the historical node sensor data. The model is evaluated using a test data set, and indicators such as accuracy, recall rate, and F1 score are calculated. The internal parameters of the model are adjusted using an optimizer based on the evaluation results, so that the model can generate corresponding data sensitivity values ​​based on the input node sensor data.

[0073] The calculated sensitivity value is bound to the corresponding node sensor data, and a sorting algorithm (such as bubble sort, quick sort, etc.) is used to arrange the sensor data of multiple nodes in order of sensitivity from high to low to generate a sensor data sequence.

[0074] According to the pre-set division rules, node sensor data is divided based on the sensor data sequence, and multiple node sensor data are divided into "data to be encrypted" and "data that does not need to be encrypted", the data range that needs to be encrypted is determined, and organized into a list of data to be encrypted. Data that is not within the encryption range can be stored in a normal format or lightly encrypted. For example, a sensitivity threshold can be set, and data above the threshold is determined as data to be encrypted, and the rest of the data is data that does not need to be encrypted. Or according to a certain ratio, such as the top 50% of the most sensitive data is determined as data to be encrypted. Data division optimizes the allocation of encryption resources, ensuring priority protection of important data while reducing overall computing costs.

[0075] Apply homomorphic encryption algorithms to the encrypted data list one by one. Use homomorphic encryption tools (such as PyCrypto, SEAL library) to encrypt the data, generate encrypted data in ciphertext format, and store or transmit it to the blockchain. While protecting data privacy, homomorphic encryption allows encrypted data to be processed directly, achieving a balance between privacy protection and data utilization.

[0076] The above steps gradually realize the priority division and secure encrypted storage of supply chain node sensor data through sensitive analysis, data sorting, partitioning and homomorphic encryption, maintaining data availability while protecting data privacy.

[0077] Further, such as Figure 3 As shown, step S4 of the embodiment of the present application includes:

[0078] Step S41: construct a multi-party joint model, synchronize the platform shared data set of the blockchain to the multi-party joint model according to the multiple supply chain nodes, and generate a joint game result.

[0079] Step S42: performing correlation analysis on the multiple supply chain nodes based on the joint game results to generate multiple correlation coefficients.

[0080] Step S43: performing data tracing on the multiple supply chain nodes according to the multiple association coefficients, identifying the multiple supply chain nodes according to the tracing results, and generating multiple association identification information.

[0081] Step S44: collaboratively divide the multiple supply chain nodes according to the multiple association identification information to generate multiple collaborative node groups.

[0082] Step S45: formulating the collaborative management decision according to the multiple collaborative node groups and the joint game result.

[0083] Specifically, the multi-party joint model is a mathematical model used to simulate and analyze the interactive behaviors between multiple supply chain nodes. The joint game results refer to the results of the strategic interactions of the participants in the multi-party joint model, which are used to guide actual decision-making. A multi-party joint model is constructed using the cooperative game model in game theory, and multiple supply chain nodes are defined as game participants. Then, the platform shared data set on the blockchain is synchronized to this model to reflect the status and behavior of each node. The model uses game theory methods (such as Nash equilibrium) for analysis, and generates joint game results by simulating the strategy selection and interaction of each node. These results reflect the benefits and risks of each node under different strategies, providing decision support for the collaborative management of the supply chain.

[0084] Based on the generated joint game results, evaluate the collaboration patterns and interdependencies between various supply chain nodes. Use statistical analysis or correlation algorithms (such as Pearson correlation coefficient or mutual information) to calculate the correlation coefficients between various nodes in the supply chain to quantify the cooperation potential and synergy between the nodes. For example, if the correlation coefficient between two warehouse nodes is high, it means that they have a close cooperation relationship in the delivery task, and collaborative optimization needs to be given priority.

[0085] According to the calculated correlation coefficient, data traceability is performed on supply chain nodes to track and record the source, transmission path and change process of the data to determine the specific connection and impact path between the nodes. Then, based on the traceability results, the role and responsibility of each node in the supply chain are marked, such as key nodes, collaborative nodes, etc., and the corresponding correlation identification information of each node is generated. This information can be used to identify key nodes and optimize the supply chain structure.

[0086] According to the associated identification information, the supply chain nodes are grouped according to similarity and association to form collaborative node groups. Each collaborative node group contains multiple nodes with common goals or cooperative relationships in the supply chain. Through collaborative division, effective cooperation between supply chain nodes is promoted and the overall collaborative efficiency of the supply chain is improved.

[0087] Based on the characteristics of the collaborative node group and the results of the joint game, specific management decisions are made for each collaborative group, namely collaborative management decisions. These collaborative management decisions include specific management measures in resource allocation, task allocation, risk management, etc., aiming to maximize the overall efficiency of the supply chain.

[0088] Further, step S41 includes:

[0089] Step S411: Perform strategy selection based on the multiple supply chain nodes in combination with the platform shared data set of the blockchain to generate multiple strategy sets.

[0090] Step S412: introducing a payment function, calculating the multiple strategy sets through the payment function, and generating a strategy payment matrix.

[0091] Step S413: Using the Nash equilibrium method in combination with the strategy payment matrix to derive the platform shared data set, and generate multiple equilibrium solution sets.

[0092] Step S414: performing a game on the multiple supply chain nodes according to the multiple equilibrium solution sets to generate the joint game result.

[0093] Specifically, for each supply chain node, relevant data is first obtained from the platform shared data set of the blockchain. For example, manufacturers may obtain data such as raw material prices and market demand forecasts; retailers may obtain data such as product supply and consumer preferences. Then, based on this data, combined with historical behavior and expected goals, all possible strategy options are listed to form a strategy set for the node. Taking the manufacturer as an example, if its goal is to maximize profits, and it is known from the platform shared data set that the market demand is strong and the price of raw materials is stable, it may choose a strategy to increase production quantity and appropriately increase pricing. Finally, the strategies selected by each supply chain node are combined to form multiple strategy sets.

[0094] The payment function is a function used to measure the benefits or costs of each participant (supply chain node) when choosing a specific strategy. The payment function of each participant is determined according to its own characteristics. For example, the payment function of the manufacturer includes parameters such as sales quantity, cost, market demand, etc., and the payment function of the retailer includes parameters such as product pricing, inventory cost, and order quantity. The strategy payment matrix is ​​a two-dimensional array calculated based on the payment function, which represents the benefits of each node under different strategy combinations. The rows represent the strategy choices of different participants, and the columns also represent the strategy choices of different participants. Each element in the matrix represents the benefits or costs of each participant under the corresponding strategy combination. Determine the payment function of each supply chain node. Exemplarily, the payment function of the manufacturer can be set to S = (PC) × Q, where P is the product price, C is the unit cost, and Q is the sales quantity. The payment function of the retailer can be set to S = (RP) x-hx, where R is the retail price, P is the purchase price, x is the sales quantity, and h is the unit inventory cost. For each strategy set, the strategy of each supply chain node is substituted into the corresponding payment function for calculation. The payment results under all possible strategy combinations are organized into a strategy payment matrix.

[0095] Using the strategy payoff matrix as input, analyze the changes in the revenue of each node under different strategy combinations. Through the Nash equilibrium method, find the Nash equilibrium point, derive the strategy combination that satisfies the Nash equilibrium conditions for all nodes, and generate the equilibrium solution set. Each equilibrium solution represents a stable strategy combination, and the strategies between nodes will not change easily. For each participant, find the strategy that maximizes its payment given the strategies of other participants. For example, for manufacturers, find the production quantity and pricing strategy that can maximize their payment (profit) when retailers choose specific pricing and inventory management strategies; for retailers, find the pricing and inventory management strategy that can maximize their payment when manufacturers choose specific production quantity and pricing strategies. Through iterative calculation, determine all strategy combinations that meet the Nash equilibrium conditions, and these combinations constitute multiple equilibrium solution sets. The equilibrium solution set provides a variety of possible cooperation or competition results for each node in the supply chain, which is convenient for selecting a strategy combination that meets the overall optimization goal.

[0096] Each supply chain node conducts actual game according to the strategy in the equilibrium solution. During the game, each node adjusts its own strategy according to market dynamics and the behavior of other nodes, records each node’s revenue, cost and other data, as well as the impact on the overall efficiency and stability of the supply chain. These data together constitute the result of the joint game.

[0097] The above steps, from strategy selection to game derivation, comprehensively analyze the interactive behaviors and optimal cooperation methods of supply chain nodes. The joint game results finally generated provide a clear cooperation model and stable strategy combination for the supply chain, optimize resource utilization efficiency, and enhance the overall supply chain's coordination ability and operational stability.

[0098] Further, step S45 includes:

[0099] Step S451: performing matching analysis based on the multiple collaborative node groups according to the strategy payment matrix to generate a matching result.

[0100] Step S452: Screening and verifying the multiple equilibrium solution sets based on the matching results to determine multiple coordination strategies, where the multiple coordination strategies correspond to the multiple coordination node groups.

[0101] Step S453: Mapping the multiple collaborative strategies according to the joint game result to formulate the collaborative management decision.

[0102] Specifically, for multiple collaborative node groups, the strategy payment matrix is ​​used to perform matching analysis on each node group to evaluate the cooperation potential of different nodes after selecting strategies. Through calculation and comparison, matching results are generated, that is, the performance of each collaborative node group under different strategy combinations.

[0103] Based on the generated matching results, multiple equilibrium solution sets are combined for screening and verification. By comparison, it is determined which strategy combinations can ensure the maximum benefit of each collaborative node group and be consistent with the equilibrium solution set. These screened strategies are collaborative strategies, and each collaborative node group has an optimal strategy corresponding to it. Through screening and verification, it is ensured that the final collaborative strategy can achieve resource optimization and benefit maximization between nodes, thereby improving the overall efficiency of the supply chain.

[0104] Based on the selected multiple collaborative strategies, these strategies are mapped to the joint game results to ensure that the decision follows the optimal solution in game theory. The final collaborative management decision is made to transform these optimal strategies into actual supply chain operation decisions, such as inventory management, transportation arrangements, order processing, etc. By mapping the collaborative strategy to the game results, a stable and optimal collaborative management decision is finally made to ensure that each node in the supply chain can collaborate efficiently, thereby improving overall operational efficiency, reducing costs, and improving service quality.

[0105] In summary, the blockchain-driven supply chain collaborative management method provided in the embodiments of the present application has the following technical effects:

[0106] The embodiment of the present application realizes real-time data sharing, resource optimization configuration and collaborative decision-making in supply chain management by combining blockchain with a multi-party collaborative model, using distributed data collection, encrypted storage, game analysis and risk warning. First, the sensor data of the supply chain nodes are encrypted, hash mapped and chained through blockchain technology to ensure the security and integrity of data transmission; then, the collected data is optimized and configured based on resource environment parameters and deep reinforcement learning methods, and the resource configuration results are generated and updated to the blockchain synchronously to form a shared data set. Subsequently, the joint game model is used to screen and verify the collaborative strategies between nodes through the strategy payment matrix and the equilibrium solution set, make collaborative management decisions, and generate feedback optimization strategies through simulated execution and abnormal monitoring. Finally, information transparency, maximum resource utilization and intelligent risk management between supply chain nodes are achieved, the overall response efficiency and collaborative capabilities of the supply chain are improved, and the security and stability of the supply chain are enhanced.

[0107] 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.

Claims

1. The blockchain-driven supply chain collaborative management method is characterized by: The method comprises: Traverse multiple supply chain nodes in the supply chain to collect data and obtain sensor data from multiple nodes; Uploading the sensor data of the multiple nodes in real time through the blockchain to generate multiple blocks; Optimizing and configuring the sensor data of the multiple nodes of the supply chain according to the multiple blocks to generate a resource configuration result, and sharing and updating the blockchain based on the resource configuration result to generate a platform shared data set of the blockchain; Based on the multiple supply chain nodes sharing the data set through the blockchain platform, multiple parties are united to make collaborative management decisions; The collaborative management decision is simulated and executed to monitor the risk of the supply chain, an abnormal data set is generated, an early warning mechanism is activated according to the abnormal data set to provide feedback response to the collaborative management decision, and a collaborative management optimization strategy is generated.

2. The blockchain-driven supply chain collaborative management method according to claim 1, characterized in that: The plurality of node sensor data are uploaded in real time through the blockchain to generate a plurality of blocks, the method comprising: Constructing a smart contract, automatically triggering a transmission instruction through the smart contract, synchronizing the sensor data of the multiple nodes to the blockchain for packaging through the transmission instruction, and generating multiple data packets; Using a hash function to perform mapping calculation on the multiple data packets to generate multiple hash values, where the multiple hash values ​​correspond to the multiple data packets; Aggregating the multiple data packets according to the multiple hash values ​​to generate multiple initial blocks; Verifying and checking the multiple initial blocks through a consensus mechanism to obtain a block verification result; According to the block verification result, the multiple initial blocks are chain-stored in chronological order to generate the multiple blocks.

3. The blockchain-driven supply chain collaborative management method according to claim 1, characterized in that: Optimizing and configuring the plurality of node sensor data of the supply chain according to the plurality of blocks to generate a resource configuration result, the method comprising: Introducing the resource and environmental parameters of the supply chain, performing traversal configuration analysis on the sensor data of the multiple nodes based on the multiple blocks combined with the resource and environmental parameters, and generating a pre-configuration solution; Performing expected optimization analysis based on the sensor data of the multiple nodes and setting an optimization configuration target; Perform resource allocation calculation on the pre-configuration scheme according to the optimization configuration target, perform configuration feasibility analysis based on the allocation result, and generate resource configuration feasibility information; Deep reinforcement learning is performed based on the feasible resource configuration information combined with the resource environment parameters to generate the resource configuration result.

4. The blockchain-driven supply chain collaborative management method according to claim 1, characterized in that: Based on the resource configuration result, the blockchain is shared and updated to generate a platform shared data set of the blockchain, the method comprising: Encrypting the plurality of node sensing data to generate a plurality of encrypted data; Synchronize the multiple encrypted data with the blockchain according to the resource configuration result to generate chain synchronization data; Determining whether the chain synchronization data meets the expected synchronization threshold; When the chain synchronization data does not meet the expected synchronization threshold, a first prompt is generated, the priority of the chain synchronization data is set to 0 according to the first prompt, and the chain synchronization data is added to the data column to be processed; When the chain synchronization data meets the expected synchronization threshold, a second prompt is generated, the priority of the chain synchronization data is set to 1 according to the second prompt, and the platform shared data set of the blockchain is generated.

5. The blockchain-driven supply chain collaborative management method according to claim 4, characterized in that: Encrypting the plurality of node sensing data to generate a plurality of encrypted data, the method comprising: Traversing the plurality of node sensing data to perform sensitivity analysis and obtain a plurality of data sensitivities; Arrange the plurality of node sensor data in descending order according to the plurality of data sensitivities to generate a sensor data sequence; Dividing the plurality of node sensor data based on the sensor data sequence to determine a plurality of data to be encrypted; Perform homomorphic encryption calculation on the multiple data to be encrypted to generate the multiple encrypted data.

6. The blockchain-driven supply chain collaborative management method according to claim 1, characterized in that: Based on the multiple supply chain nodes sharing the data set through the platform of the blockchain, multiple parties are united to make collaborative management decisions, and the method includes: Constructing a multi-party joint model, synchronizing the platform shared data set of the blockchain to the multi-party joint model according to the multiple supply chain nodes, and generating a joint game result; Based on the joint game result, a correlation analysis is performed on the multiple supply chain nodes to generate multiple correlation coefficients; Performing data tracing on the multiple supply chain nodes according to the multiple association coefficients, identifying the multiple supply chain nodes according to the tracing results, and generating multiple association identification information; Collaboratively dividing the multiple supply chain nodes according to the multiple association identification information to generate multiple collaborative node groups; The collaborative management decision is formulated according to the multiple collaborative node groups in combination with the joint game result.

7. The blockchain-driven supply chain collaborative management method according to claim 6, characterized in that: The platform shared data set of the blockchain is synchronized to the multi-party joint model according to the multiple supply chain nodes to generate a joint game result, the method comprising: Performing strategy selection based on the plurality of supply chain nodes combined with the platform shared data set of the blockchain to generate a plurality of strategy sets; Introducing a payment function, calculating the multiple strategy sets through the payment function, and generating a strategy payment matrix; The platform shared data set is derived by combining the Nash equilibrium method with the strategy payment matrix to generate multiple equilibrium solution sets; The multiple supply chain nodes are gamed according to the multiple equilibrium solution sets to generate the joint game result.

8. The blockchain-driven supply chain collaborative management method according to claim 7, characterized in that: The collaborative management decision is formulated according to the multiple collaborative node groups in combination with the joint game result, and the method includes: Performing matching analysis based on the multiple collaborative node groups according to the strategy payment matrix to generate a matching result; Based on the matching result, screening and verification are performed according to the multiple equilibrium solution sets to determine multiple coordination strategies, where the multiple coordination strategies correspond to the multiple coordination node groups; The multiple collaborative strategies are mapped according to the joint game results to formulate the collaborative management decision.

Images