Blockchain-based Trade Data Processing Method and System

Abstract

The present invention relates to the field of blockchain technology, and in particular, to a method and system for processing trade data based on blockchain. The method includes the following steps: obtaining real-time trade data and historical trade data; performing standardization processing on the real-time trade data to obtain standard trade data; constructing a trade blockchain network based on the standard trade data; identifying the flow of trade products based on the trade blockchain network to obtain circulation link data; generating dynamic demand data based on the circulation link data; performing supply-demand perception modeling on the dynamic demand data to construct a dynamic supply-demand perception model; using the dynamic supply-demand perception model to calculate the production capacity bottleneck of nodes in the trade blockchain network to generate production capacity bottleneck data of nodes; generating delivery efficiency data based on the production capacity bottleneck data of nodes; performing risk propagation analysis on the delivery efficiency data to generate risk transmission path data. This realizes efficient processing of trade data.

Description

Technical Field

[0001] The present invention relates to the technical field of blockchain, and in particular, to a method and system for processing trade data based on blockchain. Background Art

[0002] With the continuous growth of global trade and the advancement of digitization, the processing and management of trade data have become increasingly important. Trade data processing is an important data source for macroeconomic analysis and prediction. By statistically analyzing trade data, it helps to understand the development trend of the economy, discover potential opportunities and challenges, and provide references for decision-makers. However, traditional trade data processing methods mainly rely on manual means for data processing, often suffering from low data processing efficiency. To improve the efficiency and reliability of trade data processing, an intelligent trade data processing method is needed. Summary of the Invention

[0003] To solve the above technical problems, the present invention proposes a method and system for processing trade data based on blockchain to solve at least one of the above technical problems.

[0004] To achieve the above object, the present invention provides a method for processing trade data based on blockchain, including the following steps:

[0005] Step S1: Obtain real-time trade data and historical trade data; perform standardization processing on the real-time trade data to obtain standard trade data; construct a trade blockchain network based on the standard trade data;

[0006] Step S2: Identify the flow direction of trade products based on the trade blockchain network to obtain circulation link data; generate dynamic demand data based on the circulation link data; perform supply-demand perception modeling on the dynamic demand data to construct a dynamic supply-demand perception model;

[0007] Step S3: Use the dynamic supply-demand perception model to calculate the production capacity bottleneck of nodes in the trade blockchain network to generate production capacity bottleneck data of nodes; generate delivery efficiency data based on the production capacity bottleneck data of nodes; perform risk propagation analysis on the delivery efficiency data to generate risk transmission path data;

[0008] Step S4: Obtain a multi-dimensional matrix of trade data based on the real-time trade data; perform dynamic plane reconstruction on the multi-dimensional matrix of trade data to construct a multi-dimensional plane space of trade;

[0009] Step S5: Generate risk trend data based on the risk transmission path data and the multi-dimensional plane space of trade; perform trade risk prediction on the risk trend data based on the historical trade data to generate risk trend prediction data;

[0010] Step S6: Obtain node resource scheduling data based on risk trend prediction data; perform supply-demand optimization scheduling decision on the node resource scheduling data, and construct a trade supply-demand optimization scheduling model.

[0011] The present invention obtains real-time trade data and historical trade data to establish a comprehensive trade data set for subsequent analysis and modeling. Standardize the real-time trade data to ensure data consistency and comparability. Construct a trade blockchain network to provide a decentralized and traceable trade data storage and exchange platform, enhancing data security and transparency. Through the trade blockchain network, track and identify the flow of trade products, understand the situation of trade in different links, and generate dynamic demand data to reflect the changing trends and volatility of market demand. Through supply-demand perception modeling and constructing a dynamic supply-demand perception model, deeply analyze the supply-demand relationship, identify supply-demand shortages or surpluses, and provide a basis for supply chain decision-making. Through the dynamic supply-demand perception model, calculate the production capacity bottlenecks of each node in the trade blockchain network, identify bottleneck links and bottleneck risks, and generate delivery efficiency data to evaluate the delivery speed and efficiency of trade. Through risk propagation analysis and generating risk transmission path data, identify potential risk factors and their transmission paths, predict and manage trade risks. Construct a multi-dimensional matrix of trade data from real-time trade data, classify and organize trade data according to different dimensions, providing a more comprehensive data perspective. Dynamically reconstruct the plane to adjust and update the multi-dimensional matrix of trade data according to demand and time changes to reflect the dynamic changes of trade and provide a basis for further analysis and modeling. Through risk transmission path data and the multi-dimensional plane space of trade, analyze the propagation methods and paths of trade risks, identify risk factors, and generate risk trend data to reveal the changing trends and potential risk situations of trade risks. Through analyzing and modeling historical trade data, conduct trade risk prediction, identify potential risk events and impacts in advance, and provide early warnings and decision-making basis for decision-makers. Based on risk trend prediction data, perform node resource scheduling, optimize the resource allocation and scheduling of each node in the trade network, and through supply-demand optimization scheduling decision, reasonably allocate resources between different nodes to improve the efficiency and flexibility of trade. Construct a trade supply-demand optimization scheduling model to help decision-makers make the best resource scheduling decisions to cope with different market demands and risk situations.

[0012] Preferably, step S1 includes the following steps:

[0013] Step S11: Obtain real-time trade data and historical trade data;

[0014] Step S12: Standardize the real-time trade data to obtain standard trade data;

[0015] Step S13: Design a distributed contract architecture for the standard trade data to generate a distributed contract structure;

[0016] Step S14: Perform intelligent contract analysis on the standard trade data to obtain a trade intelligent contract;

[0017] Step S15: Use the trade intelligent contract to construct a topological network for the distributed contract structure to build a trade blockchain network.

[0018] The present invention obtains real-time trade data and historical trade data to establish a comprehensive trade data set, including current trade activities and past transaction records. Such a data set is used to analyze market trends, predict changes in demand and supply, and identify potential trade opportunities and risks. Standardizing the real-time trade data ensures the consistency and comparability of the data. By converting the data according to a unified format, unit, and standard, the heterogeneity of the data is eliminated, making the data easier to analyze and compare. The standardized trade data set provides more accurate and reliable basic data, providing a reliable basis for subsequent analysis and modeling. By designing a distributed contract architecture for the standard trade data, a distributed contract structure is established for managing and executing trade transactions. The distributed contract is an intelligent contract based on blockchain technology, with characteristics such as decentralization, transparency, and immutability. Through the distributed contract structure, the automation, traceability, and security of trade transactions are realized, reducing the participation of intermediate links and the risks of transactions. By performing intelligent contract analysis on the standard trade data, trade rules and conditions are encoded into intelligent contracts. The trade intelligent contract automatically executes trade transactions, verifies the legality and validity of transactions, and ensures the security and credibility of transactions. Through the intelligent contract, automatic settlement of transactions is achieved, disputes and illegal acts are reduced, and the efficiency and trust of trade are improved. By using the trade intelligent contract to construct a topological network for the distributed contract structure, a trade blockchain network is established. The trade blockchain network is a decentralized network, where the nodes are trading participants, regulatory agencies, etc. Through the trade blockchain network, the sharing and exchange of trade data are realized, ensuring the security and transparency of the data. The trade blockchain network also provides a traceable trade history record and transaction verification, reducing the occurrence of fraud and dishonest behavior.

[0019] Preferably, step S2 includes the following steps:

[0020] Step S21: Identify the flow direction of trade products based on the trade blockchain network to generate trade product flow direction data;

[0021] Step S22: Perform supply chain circulation analysis on the trade product flow direction data to obtain circulation link data;

[0022] Step S23: Perform node production capacity analysis on the circulation link data to generate node production capacity data;

[0023] Step S24: Conduct dynamic demand analysis on real-time trade data to generate dynamic demand data;

[0024] Step S25: Based on the node production capacity data, perform supply-demand perception modeling on the dynamic demand data to construct a dynamic supply-demand perception model.

[0025] The present invention identifies the flow of trade products based on a trade blockchain network, tracks and records the flow of trade products in the supply chain, thereby generating trade product flow data, including the source, transfer process, and final destination of the products. The trade product flow data is of great significance to regulatory agencies and participants for verifying product compliance, tracing product quality and safety, and supporting anti-fraud and anti-evasion measures. By conducting supply chain circulation analysis on the trade product flow data, it is possible to identify and understand each circulation link of the product in the supply chain, which includes production, transportation, warehousing, sales, etc. By analyzing the data of these circulation links, it is possible to gain an in-depth understanding of the supply chain path of the product, the time efficiency and cost-effectiveness of each link, and identify potential bottlenecks and improvement opportunities, which will help improve the visibility, efficiency, and sustainability of the supply chain. By conducting node production capacity analysis on the data of the circulation links, it is possible to evaluate the production capacity of each node in the supply chain. Nodes are production factories, logistics centers, warehouses, etc. By analyzing the node production capacity data, it is possible to understand the production capacity, storage capacity, and distribution capacity of each node, as well as the associations and dependencies between nodes, which will help optimize the resource allocation of the supply chain, improve the accuracy of production planning, and support the flexibility and scalability of the supply chain. By conducting dynamic demand analysis on real-time trade data, it is possible to identify and predict market demand trends and changes. The dynamic demand data reflects the fluctuations, seasonality, and trend changes in market demand. By analyzing the dynamic demand data, it is possible to more accurately predict the demand quantity and demand distribution of products, provide decision-making support for the production planning, inventory management, and logistics scheduling of the supply chain, and reduce the risks of supply-demand imbalance and inventory backlog. By performing supply-demand perception modeling on the dynamic demand data based on the node production capacity data, a dynamic supply-demand perception model is established. This model matches and coordinates the node production capacity and dynamic demand to achieve supply-demand balance and resource optimization. Through the dynamic supply-demand perception model, it is possible to predict shortages and surpluses in the supply chain, make adjustments and decisions in advance to maximize market demand satisfaction, reduce costs, and improve customer satisfaction.

[0026] Preferably, the specific steps of step S23 are as follows:

[0027] Step S231: Conduct regional demand difference analysis on real-time trade data to generate regional demand difference data;

[0028] Step S232: Based on the regional demand difference data, perform demand fluctuation calculation to generate demand fluctuation data;

[0029] Step S233: Conduct a demand trend analysis on the demand fluctuation data to generate demand trend data;

[0030] Step S234: Conduct a demand change elasticity analysis on the demand trend data based on historical trade data to generate demand change elasticity data;

[0031] Step S235: Conduct a dynamic demand analysis on the demand change elasticity data to generate dynamic demand data.

[0032] Through the regional demand difference analysis of real-time trade data, the present invention identifies the demand differences between different regions, including those between different geographical regions, countries or cities. The generated regional demand difference data helps to understand the demand characteristics and trends of each market, so as to better formulate regional market strategies, optimize product positioning and marketing. By calculating the demand fluctuation based on the regional demand difference data, the volatility and instability of demand are evaluated. The generated demand fluctuation data reflects the change range and frequency of market demand, helping to understand the uncertainty and risks of the market. This is helpful for supply chain planning, inventory management and production scheduling to adapt to demand fluctuations, reduce inventory risks and improve resource utilization rate. By conducting a demand trend analysis on the demand fluctuation data, the long-term trend and change pattern of market demand are understood. The generated demand trend data helps to predict the development direction and trend of the market, providing a basis for strategic decision-making. This is helpful for formulating long-term supply chain strategies, product development plans and market expansion strategies to better meet market demand and maintain a competitive advantage. By conducting a demand change elasticity analysis on the demand trend data based on historical trade data, the sensitivity and elasticity of demand to different factors are evaluated. The generated demand change elasticity data helps to understand the response degree of demand to prices, promotional activities, seasons and other factors. This is helpful for formulating pricing strategies, marketing strategies and product portfolio strategies to better meet consumer needs and optimize sales performance. By conducting a dynamic demand analysis on the demand change elasticity data, the demand changes in different market scenarios are predicted and simulated. The generated dynamic demand data helps to conduct supply chain planning, production scheduling and inventory management to cope with the changes and fluctuations of market demand. This is helpful for achieving rapid response, flexible adjustment and accurate prediction, and improving the agility of the supply chain and customer satisfaction.

[0033] Preferably, the specific steps of Step S3 are as follows:

[0034] Step S31: Use the dynamic supply and demand perception model to calculate the node production capacity bottleneck of the trade blockchain network to generate node production capacity bottleneck data;

[0035] Step S32: Conduct an analysis of the node inventory change of the trade blockchain network to generate node inventory change data;

[0036] Step S33: Calculate the delivery efficiency based on the node inventory change data to generate delivery efficiency data;

[0037] Step S34: Conduct risk propagation analysis on the delivery efficiency data according to the node production capacity bottleneck data to generate risk transmission path data.

[0038] The present invention calculates the node production capacity bottleneck of the trade blockchain network by using a dynamic supply and demand perception model, determines the existing node production capacity bottlenecks in the network. The node production capacity bottleneck refers to the key nodes that restrict the supply chain process in the trade network, resulting in delivery delays or resource waste. The generated node production capacity bottleneck data helps identify and optimize the bottleneck links in the supply chain, improve delivery efficiency, reduce costs and resource utilization rate. By analyzing the node inventory changes in the trade blockchain network, the inventory change situations of different nodes are understood. Node inventory refers to the inventory quantity of materials or products at each node in the supply chain network. The generated node inventory change data helps monitor and analyze the changing trends of inventory levels, so as to better conduct inventory planning, order management and supply chain coordination. This helps reduce inventory holding costs, avoid the risks of overstocking or out-of-stock, and improve the agility and responsiveness of the supply chain. By calculating the delivery efficiency based on the node inventory change data, the delivery efficiency of the supply chain is evaluated. Delivery efficiency refers to the ability of the supply chain to complete orders and deliver them on time. The generated delivery efficiency data helps measure the operation effect of the supply chain, identify potential delivery delay problems, and optimize the supply chain process. By conducting risk propagation analysis on the delivery efficiency data according to the node production capacity bottleneck data, the risk transmission paths in the supply chain are identified. The risk transmission path refers to the transmission path and influence scope of potential risks caused by node production capacity bottlenecks in the supply chain network. The generated risk transmission path data helps understand the vulnerable links and potential risk sources in the supply chain, and take corresponding risk management and response measures. This helps reduce supply chain risks, enhance the risk resistance ability, and ensure the sustainability and stability of the supply chain.

[0039] Preferably, the specific steps of step S34 are as follows:

[0040] Step S341: Detect inventory anomalies in the node inventory change data to obtain node inventory anomaly data;

[0041] Step S342: Calculate the delivery delay probability of the delivery efficiency data to generate node delivery delay probability data;

[0042] Step S343: Conduct supply and demand balance analysis on the node inventory anomaly data and the node delivery delay probability data according to the node production capacity bottleneck data to generate node supply and demand balance data;

[0043] Step S344: Perform smooth curve fitting on the node supply and demand balance data to construct a node supply and demand balance curve;

[0044] Step S345: Conduct potential risk analysis on the topological network diagram between nodes through the node supply-demand balance curve to generate node risk data;

[0045] Step S346: Conduct risk propagation analysis on the node risk data to generate risk transmission path data.

[0046] Through inventory anomaly detection of the node inventory change data, the present invention identifies the abnormal node inventory situations in the supply chain network. The generated node inventory anomaly data helps to timely discover and solve inventory anomaly problems, such as excessive inventory backlog or inventory shortage, so as to avoid negative impacts on the supply chain and improve the accuracy and efficiency of inventory management. By calculating the delivery delay probability of the delivery efficiency data, the probability of delivery delay occurring in the supply chain network is evaluated. The generated node delivery delay probability data helps to understand the delivery delay risks existing in the supply chain, predict potential delivery delay events, and take corresponding preventive and response measures to improve the delivery on-time rate and customer satisfaction. By conducting supply-demand balance analysis on the node inventory anomaly data and the node delivery delay probability data according to the node production capacity bottleneck data, the supply-demand balance situation of the nodes in the supply chain is evaluated. The generated node supply-demand balance data helps to identify the nodes with supply-demand imbalance, predict supply-demand conflicts and contradictions, and take corresponding adjustment measures to achieve supply-demand balance and improve the efficiency and flexibility of the supply chain. By performing smooth curve fitting on the node supply-demand balance data, a node supply-demand balance curve is established. The node supply-demand balance curve helps to visualize the change trend of the supply-demand balance situation, better understand the dynamic changes of the supply-demand relationship, and provide a reference basis for supply chain planning and decision-making. By using the node supply-demand balance curve to conduct potential risk analysis on the topological network diagram between nodes, the potential risk points existing in the supply chain network are identified. The generated node risk data helps to determine potential risk sources, vulnerable links and risk transmission paths, so as to take corresponding risk management and control measures to reduce the impact of risks on the supply chain. By conducting risk propagation analysis on the node risk data, the transmission paths and influence scopes of risks in the supply chain are identified. The generated risk transmission path data helps to understand how risks spread in the supply chain network and prioritize the risk sources, so as to take corresponding risk response measures. This helps to enhance the ability to respond to supply chain risks, reduce the impact of potential risks on the business, and ensure the sustainability and stability of the supply chain.

[0047] Preferably, the specific steps of Step S4 are as follows:

[0048] Step S41: Conduct multi-dimensional plane decomposition on the real-time trade data to generate trade multi-dimensional plane data;

[0049] Step S42: Perform spatial mapping on the multi-dimensional trade plane data to generate a multi-dimensional trade data matrix;

[0050] Step S43: Perform implicit feature analysis on the multi-dimensional trade data matrix to generate plane implicit feature data;

[0051] Step S44: Perform dynamic plane reconstruction on the multi-dimensional trade data matrix according to the plane implicit feature data to construct a multi-dimensional trade plane space.

[0052] In the present invention, through multi-dimensional plane decomposition of real-time trade data, the original data is decomposed and combined according to different dimensions to generate multi-dimensional trade plane data. This decomposition transforms the trade data from a whole into multiple independent dimensions, making the data structure clearer and more understandable. By performing spatial mapping on the multi-dimensional trade plane data, the plane data is transformed into a multi-dimensional matrix. The spatial mapping organizes and displays the data in multiple dimensions, providing a more intuitive and operable data representation method. The generated multi-dimensional trade data matrix helps to view and analyze trade data in the form of a matrix, thereby discovering patterns, trends, and correlations in the data, providing a basis for subsequent data analysis and mining. By performing implicit feature analysis on the multi-dimensional trade data matrix, implicit feature information in the data is extracted. Implicit feature analysis is a statistical and machine learning technique that discovers potential patterns and structures in the data and reveals the underlying laws behind the data. The generated plane implicit feature data helps to understand the essential features of trade data, discover important factors and key influencing factors in the data, and provide a basis for subsequent data modeling and prediction. By performing dynamic plane reconstruction on the multi-dimensional trade data matrix according to the plane implicit feature data, the dimensions and structure of the trade data are reorganized and adjusted to construct a multi-dimensional trade plane space. The dynamic plane reconstruction optimizes and adjusts the trade data according to the analysis results of the implicit feature data to better represent and utilize the information of the data. The constructed multi-dimensional trade plane space provides a more comprehensive and accurate data view, helps to deeply understand the internal relationships and evolution trends of trade data, and provides a more reliable basis for decision-making.

[0053] Preferably, the specific steps of Step S5 are as follows:

[0054] Step S51: Perform risk decision factor analysis on the risk transmission path data to generate risk decision factor data;

[0055] Step S52: Perform trend analysis on the risk decision factor data through the multi-dimensional trade plane space to generate risk trend data;

[0056] Step S53: Perform trend reverse inference on the historical trade data to generate time-series trend reverse inference data;

[0057] Step S54: Perform trade risk prediction on the risk trend data through time series trend reverse extrapolation data to generate risk trend prediction data.

[0058] The present invention analyzes risk decision-making factors for risk transmission path data, identifies and extracts key factors affecting risk decision-making. The risk decision-making factor analysis is based on historical data, market trends, and relevant factors to determine factors that have an important impact on trade risks, and the generated risk decision-making factor data helps to understand the driving factors of risk decision-making, providing a basis for subsequent risk assessment and decision-making. Through trend analysis of risk decision-making factor data in the trade multi-dimensional plane space, the development trends and change laws of risk factors are revealed. The trade multi-dimensional plane space provides a comprehensive perspective to display and analyze risk decision-making factor data in multiple dimensions. The generated risk trend data helps to identify the evolution trends of risks, discover potential risk threats and opportunities, and provide early warnings and references for risk management and decision-making. By performing trend reverse extrapolation on historical trade data, the possibility that past trends continue into the future is inferred. The trend reverse extrapolation analysis is based on the trends and patterns of historical data to predict future development directions and trends. The generated time series trend reverse extrapolation data helps to understand the historical change trends of trade data and provides references and predictions for future decision-making and planning. Through the time series trend reverse extrapolation data, trade risk prediction is performed on the risk trend data to predict the future development trends of trade risks and risk events. The trade risk prediction is based on historical data and trend reverse extrapolation results, combined with risk decision-making factors and risk trend data, to evaluate and predict future trade risks. The generated risk trend prediction data helps to formulate risk management strategies and timely respond to potential trade risks.

[0059] Preferably, the specific steps of step S6 are as follows:

[0060] Step S61: Perform node resource scheduling analysis on the trade blockchain network according to the risk trend prediction data to generate node resource scheduling data;

[0061] Step S62: Make a supply-demand optimization scheduling decision on the node resource scheduling data to construct a supply-demand optimization scheduling decision engine;

[0062] Step S63: Perform dilated convolution on the supply-demand optimization scheduling decision engine to construct a trade supply-demand optimization scheduling model.

[0063] The present invention optimizes the allocation and utilization of node resources by performing node resource scheduling analysis on a trade blockchain network based on risk trend prediction data. The node resource scheduling analysis is based on risk trend prediction data to identify high-risk regions or nodes, and adjusts the resource allocation and scheduling strategy according to the prediction results. The generated node resource scheduling data helps the trade blockchain network achieve reasonable resource allocation, improve the security and efficiency of the network. Through the supply-demand optimization scheduling decision-making for the node resource scheduling data, the balance and optimization of resources in the trade network are realized. The supply-demand optimization scheduling decision-making analysis is based on the node resource scheduling data to evaluate the supply-demand situation of resources and formulate an optimized scheduling strategy. By constructing a supply-demand optimization scheduling decision-making engine, the supply and demand of node resources are monitored and adjusted in real time in an automated and intelligent manner to improve the efficiency and reliability of the trade network. By performing dilated convolution on the supply-demand optimization scheduling decision-making engine, a trade supply-demand optimization scheduling model is constructed to further improve the accuracy and effect of resource scheduling. Dilated convolution is a technology of convolutional neural network that performs multi-level and multi-scale feature extraction and analysis on data. The trade supply-demand optimization scheduling model is constructed based on dilated convolution technology to perform deep learning and pattern recognition on the supply-demand data, extract potential supply-demand laws and trends, and provide more accurate guidance and prediction for resource scheduling decisions.

[0064] In this specification, a blockchain-based trade data processing system is provided for performing the blockchain-based trade data processing method as described above, including:

[0065] A blockchain network module for obtaining real-time trade data and historical trade data; performing standardization processing on the real-time trade data to obtain standard trade data; constructing a trade blockchain network based on the standard trade data;

[0066] A dynamic demand module for identifying the flow direction of trade products based on the trade blockchain network to obtain circulation link data; generating dynamic demand data based on the circulation link data; performing supply-demand perception modeling on the dynamic demand data to construct a dynamic supply-demand perception model;

[0067] A risk path module for calculating the node production capacity bottleneck of the trade blockchain network using the dynamic supply-demand perception model to generate node production capacity bottleneck data; generating delivery efficiency data based on the node production capacity bottleneck data; performing risk propagation analysis on the delivery efficiency data to generate risk transmission path data;

[0068] A plane reconstruction module for obtaining a multi-dimensional matrix of trade data based on real-time trade data; performing dynamic plane reconstruction on the multi-dimensional matrix of trade data to construct a trade multi-dimensional plane space;

[0069] A risk prediction module, configured to generate risk trend data based on risk transmission path data and the trade multi-dimensional plane space; perform trade risk prediction on the risk trend data based on historical trade data to generate risk trend prediction data;

[0070] A supply and demand scheduling module, configured to obtain node resource scheduling data based on the risk trend prediction data; perform supply and demand optimization scheduling decision on the node resource scheduling data to construct a trade supply and demand optimization scheduling model.

[0071] The present invention obtains real-time trade data through a blockchain network module, enabling trade participants to timely understand market dynamics and make more accurate decisions, standardizes the format and structure of unified trade data, improves the consistency and comparability of data, constructs a trade blockchain network to ensure the security and immutability of trade data, enhances the trust between participants, a dynamic demand module identifies and tracks the flow of trade products and records the circulation path of trade products, revealing the supply chain information of the products, helping to monitor the compliance and traceability of trade activities, the generation of dynamic demand data reflects the changes in market demand in real time, assisting the supplier to make timely adjustments and decisions, a dynamic supply and demand perception model analyzes the changing trends of the supply and demand relationship based on real-time data and historical data, provides in-depth insights into the market, supports decision-making and resource allocation, a risk path module identifies the bottlenecks in the production and circulation links in the trade blockchain network, providing a basis for optimizing the supply chain and resource allocation, the generation of delivery efficiency data evaluates the speed and accuracy of delivery, helping participants to optimize the delivery process and improve customer satisfaction, the analysis of risk transmission path data identifies potential risk propagation paths, issues early warnings and takes risk management measures to reduce the impact of risks on trade activities, a plane reconstruction module sorts and classifies trade data according to different dimensions, facilitating data analysis and mining, dynamic plane reconstruction dynamically adjusts the dimensions and correlation relationships of trade data according to requirements and changing situations, improving the visualization and interpretability of data, the construction of the trade multi-dimensional plane space provides a basis for data exploration and decision support, helping to discover potential associations and rules in trade activities, the generation of risk trend data by the risk prediction module analyzes and predicts the risk trends in trade activities based on the risk transmission path and the trade multi-dimensional plane space, helping participants to formulate risk management strategies, the application of historical trade data draws on past experiences and lessons to predict and evaluate future trade risks, improving the accuracy and effectiveness of decision-making, the supply and demand scheduling module analyzes and plans the resource allocation and scheduling of nodes based on the risk trend prediction data to ensure the efficient operation of the supply chain, the supply and demand optimization scheduling decision optimizes the matching relationship between supply and demand based on the node resource scheduling data to improve resource utilization rate and delivery efficiency, the construction of the trade supply and demand optimization scheduling model establishes a dynamic scheduling system to achieve the reasonable allocation and coordination of resources and optimize the overall efficiency of trade activities. Description of the Drawings

[0072] Figure 1 It is a schematic diagram of the step flow of a method for processing trade data based on blockchain according to the present invention;

[0073] Figure 2 It is a schematic diagram of the detailed implementation steps of step S1;

[0074] Figure 3 It is a schematic diagram of the detailed implementation steps of step S2;

[0075] Figure 4 It is a schematic diagram of the detailed implementation steps of step S3. Specific implementation manner

[0076] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0077] The embodiments of the present application provide a method for processing trade data based on blockchain. The execution subjects of the method and system for processing trade data based on blockchain include but are not limited to: mechanical equipment, data processing platforms, cloud server nodes, network upload devices, etc. that can be regarded as general computing nodes of the present application. The data processing platform includes but is not limited to at least one of: audio and image management systems, information management systems, and cloud data management systems.

[0078] Please refer to Figures 1 to 4 , the present invention provides a method for processing trade data based on blockchain, and the method for processing trade data based on blockchain includes the following steps:

[0079] Step S1: Obtain real-time trade data and historical trade data; perform standardization processing on the real-time trade data to obtain standard trade data; construct a trade blockchain network based on the standard trade data;

[0080] Step S2: Identify the flow direction of trade products based on the trade blockchain network to obtain circulation link data; generate dynamic demand data based on the circulation link data; perform supply and demand perception modeling on the dynamic demand data to construct a dynamic supply and demand perception model;

[0081] Step S3: Use the dynamic supply and demand perception model to calculate the node production capacity bottleneck of the trade blockchain network to generate node production capacity bottleneck data; generate delivery efficiency data based on the node production capacity bottleneck data; perform risk propagation analysis on the delivery efficiency data to generate risk transmission path data;

[0082] Step S4: Obtain a trade data multi-dimensional matrix based on the real-time trade data; perform dynamic plane reconstruction on the trade data multi-dimensional matrix to construct a trade multi-dimensional plane space;

[0083] Step S5: Generate risk trend data based on risk transmission path data and the multi-dimensional trade plane space; conduct trade risk prediction on the risk trend data based on historical trade data to generate risk trend prediction data;

[0084] Step S6: Obtain node resource scheduling data based on the risk trend prediction data; conduct supply-demand optimization scheduling decision on the node resource scheduling data to construct a trade supply-demand optimization scheduling model.

[0085] The present invention obtains real-time trade data and historical trade data to establish a comprehensive trade data set for subsequent analysis and modeling. Standardize the real-time trade data to ensure data consistency and comparability. Construct a trade blockchain network to provide a decentralized and traceable trade data storage and exchange platform, enhancing data security and transparency. Through the trade blockchain network, track and identify the flow of trade products, understand the situation of trade in different links, and generate dynamic demand data to reflect the changing trends and volatility of market demand. Through supply-demand perception modeling and constructing a dynamic supply-demand perception model, deeply analyze the supply-demand relationship, identify supply-demand shortages or surpluses, and provide a basis for supply chain decision-making. Through the dynamic supply-demand perception model, calculate the production capacity bottlenecks of each node in the trade blockchain network, identify bottleneck links and bottleneck risks, generate delivery efficiency data to evaluate the delivery speed and efficiency of trade. Through risk propagation analysis and generating risk transmission path data, identify potential risk factors and their transmission paths, predict and manage trade risks. Construct a multi-dimensional matrix of trade data based on real-time trade data, classify and organize trade data according to different dimensions, providing a more comprehensive data perspective. Dynamically reconstruct the plane according to demand and time changes to adjust and update the multi-dimensional matrix of trade data to reflect the dynamic changes of trade, providing a basis for further analysis and modeling. Through risk transmission path data and the multi-dimensional trade plane space, analyze the propagation methods and paths of trade risks, identify risk factors, generate risk trend data to reveal the changing trends of trade risks and potential risk situations. Through analyzing and modeling historical trade data, conduct trade risk prediction, identify risk events and impacts in advance, and provide early warnings and decision-making bases for decision-makers. Based on the risk trend prediction data, conduct node resource scheduling, optimize the resource allocation and scheduling of each node in the trade network, and through supply-demand optimization scheduling decision, reasonably allocate resources between different nodes to improve the efficiency and flexibility of trade. Construct a trade supply-demand optimization scheduling model to help decision-makers make the best resource scheduling decisions to cope with different market demands and risk situations.

[0086] In the embodiment of the present invention, refer to Figure 1 , which is a schematic diagram of the step flow of a trade data processing method based on blockchain of the present invention. In this example, the steps of the trade data processing method based on blockchain include:

[0087] Step S1: Obtain real-time trade data and historical trade data; perform standardization processing on the real-time trade data to obtain standard trade data; build a trade blockchain network based on the standard trade data;

[0088] In this embodiment, after obtaining user and platform authorization, real-time trade data is obtained from various trade data sources, including e-trading platforms, logistics systems, customs data, etc. By establishing connections with these data sources or using corresponding APIs, the latest trade data is obtained. Historical trade data is obtained from reliable historical data storage or databases, including transaction records, logistics information, supply chain data, etc. over a past period of time. The acquisition of historical data is completed by querying databases, accessing storage systems, or using the services of data providers. Define the standard format and standard fields of trade data, and perform standardization processing on the real-time trade data, which is achieved by formulating data standard specifications, establishing data dictionaries, etc. Standardization processing helps with data docking and comparative analysis between different data sources. Select an appropriate data storage and management solution, and store the standardized trade data in a database or distributed storage system, including technologies such as relational databases, NoSQL databases, or blockchains, to ensure the security, reliability, and scalability of the data. Based on the standardized trade data, build a trade blockchain network, select a suitable blockchain platform or customize a blockchain solution, and perform network configuration and deployment according to requirements. Define and implement functions such as data storage, data verification, and smart contracts to ensure the credibility and traceability of trade data in the blockchain network.

[0089] Step S2: Identify the flow of trade products based on the trade blockchain network to obtain circulation link data; generate dynamic demand data based on the circulation link data; perform supply-demand perception modeling on the dynamic demand data to construct a dynamic supply-demand perception model;

[0090] In this embodiment, the obtained transaction records are analyzed to identify the flow of trade products. By analyzing the buyer and seller information, logistics data, trade amounts, etc. in the transaction records, the flow path of trade products is traced. Relevant circulation link data is extracted from the identified flow of trade products, which includes supplier information, manufacturer information, logistics company information, retailer information, etc. The circulation link data is associated with other relevant data sources, such as market research data, consumer behavior data, etc. Through association analysis, more comprehensive demand data is obtained. According to the characteristics of the demand data and the goals of demand forecasting, a suitable data modeling method is selected, and statistical models, machine learning models, deep learning models, etc. are used for demand data modeling. Using the constructed data model, the identified circulation link data is predicted and dynamic demand data is generated. These data include predicted market demand, sales trends, product popularity, etc. Feature extraction and transformation are performed on the data so that supply- and demand-related features can be understood and utilized by the model, including operations such as feature selection, feature scaling, and feature combination. According to specific requirements, a suitable supply-demand perception model is selected, such as a regression model, a time series model, a neural network model, etc. The model is trained and optimized using training data, and the trained model is evaluated using validation data. The parameters and structure of the model are adjusted to improve the performance and accuracy of the model.

[0091] Step S3: Use the dynamic supply-demand perception model to calculate the node production capacity bottleneck of the trade blockchain network to generate node production capacity bottleneck data; generate delivery efficiency data based on the node production capacity bottleneck data; perform risk propagation analysis on the delivery efficiency data to generate risk transmission path data;

[0092] In this embodiment, relevant data of each node in the trade blockchain network is collected, such as transaction records, trade partner information, node resource status, etc., to establish a dynamic supply and demand perception model. This model evaluates and predicts the supply and demand situation of the trade blockchain network based on real-time data. The model is constructed using machine learning algorithms or other relevant methods. The dynamic supply and demand perception model is used to calculate the production capacity bottleneck of each node in the trade blockchain network. The production capacity bottleneck refers to the maximum transaction volume that a node can process or the service capacity it can provide within a specific time period. According to the output result of the model, the production capacity bottleneck situation of each node is determined and expressed as a quantity or other relevant metrics. Based on the node production capacity bottleneck data, the delivery efficiency of each node is calculated. The delivery efficiency refers to the ability of a node to complete delivery on time in actual transactions. According to the production capacity bottleneck and actual transaction situation of the node, the delivery efficiency of each node is calculated and expressed as a percentage or other relevant metrics. The generated delivery efficiency data is used as input for risk propagation analysis. Risk propagation analysis evaluates the risk transmission path based on the network topology structure and transaction relationships between nodes. Appropriate methods (such as graph theory, network analysis, etc.) are used to perform risk propagation analysis on the delivery efficiency data to identify the risk transmission path and key nodes. According to the results of the risk propagation analysis, risk transmission path data is generated. The risk transmission path data is represented as a relationship graph between nodes, a path matrix, or other forms of data structures. The risk transmission path data helps trade participants understand the risk transmission paths existing in the trade blockchain network, so as to take corresponding risk management measures.

[0093] Step S4: Obtain a multi-dimensional matrix of trade data based on real-time trade data; perform dynamic plane reconstruction on the multi-dimensional matrix of trade data to construct a multi-dimensional trade plane space;

[0094] In this embodiment, a multi-dimensional matrix of trade data is constructed according to real-time trade data. The multi-dimensional matrix is a data structure that describes trade data in multiple dimensions and is constructed using data analysis tools or programming languages. According to the characteristics and requirements of the trade data, appropriate dimensions are selected, such as time, geographical location, product category, trade partner, etc., and corresponding measurement metrics, such as transaction volume, amount, price, etc. The real-time trade data is mapped to the corresponding dimensions and measurement metrics of the multi-dimensional matrix to form a multi-dimensional trade matrix based on real-time data. Perform dynamic plane reconstruction on the multi-dimensional matrix of trade data. Dynamic plane reconstruction is to dynamically update and adjust the structure and attributes of the multi-dimensional trade plane space according to the changes in real-time trade data, monitor the changes in real-time trade data, and make corresponding adjustments to the multi-dimensional trade plane space according to the changes. This includes adding new dimensions, deleting dimensions that are no longer needed, updating the attributes and measurement metrics of dimensions, etc. Through dynamic plane reconstruction, the consistency between the multi-dimensional trade plane space and the actual trade data is maintained, so that it can accurately reflect the changes and characteristics of the trade data.

[0095] Step S5: Generate risk trend data based on risk transmission path data and the multi-dimensional trade plane space; conduct trade risk prediction on the risk trend data based on historical trade data to generate risk trend prediction data;

[0096] In this embodiment, map the risk transmission path data to the corresponding dimensions or attributes in the multi-dimensional trade plane space, associate the risk transmission path data with the multi-dimensional trade plane space, and generate risk trend data by using data analysis techniques or algorithms based on the association between the risk transmission path data and the multi-dimensional trade plane space. The risk trend data represents the change trend of risk indicators with respect to time and other relevant dimensions. According to the risk transmission paths and key nodes identified in the risk transmission path data, calculate the corresponding risk indicators or other relevant indicators, and associate them with the time dimension to form risk trend data. Conduct trade risk prediction on the risk trend data by using historical trade data, and use various prediction models and algorithms, such as time series analysis, machine learning algorithms, etc. Based on the patterns and trends of historical trade data, train the prediction model and use this model to predict the risk trend data. The prediction result is the predicted value or probability distribution of trade risks within a future time period. Generate risk trend prediction data according to the output of the trade risk prediction model. These data are represented as the predicted values or probability distributions of risk indicators or relevant indicators within a future time period. The risk trend prediction data is used to help trade participants identify potential risk trends and risk events, so as to make corresponding decisions and risk management strategies.

[0097] Step S6: Obtain node resource scheduling data based on the risk trend prediction data; conduct supply-demand optimization scheduling decision on the node resource scheduling data to construct a trade supply-demand optimization scheduling model.

[0098] In this embodiment, based on the risk trend prediction data, a model or algorithm is used to generate node resource scheduling data, which describes the resources required and supply situation of each node (such as ports, warehouses, transportation tools, etc.) within a specific time period. The node resource scheduling data includes information such as resource demand, resource supply, resource availability, and resource flow between nodes, so as to reflect the supply and demand situation of trade activities. Based on the node resource scheduling data, a supply-demand optimization scheduling decision is made, which involves determining how to reasonably allocate and schedule between resource demand and supply to meet the needs of trade activities and optimize resource utilization. Using a supply-demand optimization scheduling algorithm or model, considering factors such as the availability, priority, timing relationship, and cost of node resources, a scheduling decision is formulated. This is an optimization problem that requires matching and scheduling the resource demand and supply of each node to achieve overall supply-demand balance and maximize benefits. Based on the methods and results of the supply-demand optimization scheduling decision, a trade supply-demand optimization scheduling model is constructed. This model is a mathematical model, optimization model, or simulation model used to describe the supply-demand relationship and resource scheduling strategy in trade activities. When constructing the trade supply-demand optimization scheduling model, factors such as the characteristics of trade activities, the interaction relationship between nodes, resource constraints, and time windows are considered to establish an accurate, feasible, and optimizable model.

[0099] In this embodiment, refer to Figure 2 , which is a schematic diagram of the detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include:

[0100] Step S11: Obtain real-time trade data and historical trade data;

[0101] Step S12: Standardize the real-time trade data to obtain standard trade data;

[0102] Step S13: Design a distributed contract architecture for the standard trade data to generate a distributed contract structure;

[0103] Step S14: Analyze the standard trade data with a smart contract to obtain a trade smart contract;

[0104] Step S15: Use the trade smart contract to construct a topological network for the distributed contract structure to construct a trade blockchain network.

[0105] In this embodiment, after obtaining the authorization of the user and the platform, real-time trade data is obtained from various trade data sources, including e-commerce platforms, logistics systems, customs data, etc. By establishing connections with these data sources or using corresponding APIs, the latest trade data is obtained. Historical trade data is obtained from reliable historical data storage or databases, including transaction records, logistics information, supply chain data, etc. over a past period of time. The acquisition of historical data is completed by querying databases, accessing storage systems, or using the services of data providers. The real-time trade data is cleaned to remove invalid data, duplicate data, missing data, etc., including data format conversion, data format correction, outlier handling, etc. Through data cleaning and denoising, the quality and consistency of the real-time trade data are ensured. The data model and data structure of the standard trade data are determined, which defines a set of standard formats, fields, and specifications for trade data. The cleaned real-time trade data is standardized to conform to the format and specifications of the standard trade data, including field mapping, unit unification, data type conversion, etc. Understand and analyze the trade business requirements, determine the functions and logics to be implemented in the distributed contract, and determine the requirements in aspects such as contract participants, contract execution conditions, contract trigger events, etc. Design the architecture of the distributed contract, including the organizational structure, data model, contract methods, and events of the contract. Consider the requirements in aspects such as the scalability, security, and performance of the distributed contract, and select a suitable distributed contract platform or framework. Based on the results of the distributed contract architecture design, use contract programming languages or tools to implement the distributed contract structure. Analyze the trade business requirements, determine the business logics and rules to be implemented in the smart contract, understand the interactions between contract participants and the contract execution conditions, and design the structure and functions of the smart contract to meet the trade business requirements, which involves defining the state, methods, events, participant roles, permissions, etc. of the contract. Consider the requirements in aspects such as the security, scalability, and reliability of the smart contract, and select a suitable smart contract platform or framework. Based on the results of the smart contract design, use smart contract programming languages or tools to implement the trade smart contract, and write the code logic of the contract, including data processing, transaction verification, event triggering, etc. Analyze the trade business requirements, determine the functions and features of the trade blockchain network to be constructed, and determine the requirements in aspects such as network participants, network topology, consensus mechanism, data storage, etc. Design the structure and architecture of the trade blockchain network, including network nodes, blockchain data structure, communication protocol, consensus algorithm, etc. Consider the requirements in aspects such as the scalability, security, and performance of the trade blockchain network, and select a suitable blockchain platform or framework. Based on the trade smart contract and the distributed contract structure, deploy the nodes and chain codes of the trade blockchain network, configure and connect the network nodes to ensure the normal operation and communication of the network.

[0106] In this embodiment, refer to Figure 3, which is a schematic diagram of the detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of step S2 include:

[0107] Step S21: Identify the flow of trade products based on the trade blockchain network to generate trade product flow data;

[0108] Step S22: Conduct a supply chain circulation analysis on the trade product flow data to obtain circulation link data;

[0109] Step S23: Conduct a node production capacity analysis on the circulation link data to generate node production capacity data;

[0110] Step S24: Conduct a dynamic demand analysis on the real-time trade data to generate dynamic demand data;

[0111] Step S25: Based on the node production capacity data, conduct a supply-demand perception modeling on the dynamic demand data to construct a dynamic supply-demand perception model.

[0112] In this embodiment, based on the business logic and rules defined in the smart contract, trace the flow of trade products, which is achieved by tracking the transaction records, logistics information, and confirmation operations of the parties involved. Record the identified trade product flow information, including product source, transfer path, destination, and parties involved, etc. Analyze the circulation path of trade products in the supply chain, including production, warehousing, transportation, sales, etc. Identify the various parties involved in the circulation of trade products, such as manufacturers, wholesalers, retailers, logistics companies, etc. Associate the trade product flow data with the parties and circulation links to establish a complete link of product circulation. Identify the various nodes in the trade product circulation link, such as production factories, warehouses, transportation nodes, etc. Evaluate the production capacity of each node, including factors such as production capacity, production efficiency, and inventory management. Record the node production capacity data, including node name, production capacity indicators, time period, etc. Analyze the real-time trade data to identify the changing trends and periodicity of demand, such as seasonal demand, market trends, etc. Record the dynamic demand data, including demand period, demand quantity, demand change trend, etc. Analyze the supply-demand relationship between node production capacity and dynamic demand, identify the supply-demand matching degree, supply-demand gap, etc. Based on the analysis results of the supply-demand relationship, construct a dynamic supply-demand perception model using methods such as statistical analysis, machine learning, or optimization algorithms.

[0113] In this embodiment, the specific steps of step S23 are as follows:

[0114] Step S231: Conduct a regional demand difference analysis on the real-time trade data to generate regional demand difference data;

[0115] Step S232: Based on the regional demand difference data, conduct a demand fluctuation calculation to generate demand fluctuation data;

[0116] Step S233: Conduct a demand trend analysis on the demand fluctuation data to generate demand trend data;

[0117] Step S234: Conduct a demand change elasticity analysis on the demand trend data based on historical trade data to generate demand change elasticity data;

[0118] Step S235: Conduct a dynamic demand analysis on the demand change elasticity data to generate dynamic demand data.

[0119] In this embodiment, statistical analysis methods (such as variance analysis) or machine learning algorithms (such as clustering analysis) are used to compare and analyze the trade data of different regions, identify the demand differences between regions. For example, calculate the average order volume or transaction amount of each region, and then compare the differences between regions. Use mathematical or statistical methods to calculate the volatility of demand in different regions. Commonly used indicators include standard deviation, variance, etc., to measure the degree of demand volatility. Use time series analysis methods or trend prediction models to analyze the demand fluctuation data, identify the long-term trend and periodic changes of demand. According to the results of the trend analysis, generate demand trend data, including information such as the growth trend and periodic changes of demand. Use the demand elasticity theory in economics or statistical methods to analyze the historical trade data, calculate the change elasticity of demand to different factors, and apply the results of the elasticity analysis to the demand trend data to generate demand change elasticity data, indicating the sensitivity and elasticity range of demand to different factors. Based on the demand change elasticity data, construct a dynamic demand prediction model to predict the future change trend and scale of demand. Apply the dynamic demand prediction model to the real-time trade data to generate dynamic demand data, reflecting the current and future demand situations of each region.

[0120] In this embodiment, refer to Figure 4 , which is a schematic diagram of the detailed implementation steps of Step S3. In this embodiment, the detailed implementation steps of Step S3 include:

[0121] Step S31: Use the dynamic supply and demand perception model to calculate the node production capacity bottleneck of the trade blockchain network to generate node production capacity bottleneck data;

[0122] Step S32: Conduct a node inventory change analysis on the trade blockchain network to generate node inventory change data;

[0123] Step S33: Calculate the delivery efficiency of the node inventory change data to generate delivery efficiency data;

[0124] Step S34: Conduct a risk propagation analysis on the delivery efficiency data based on the node production capacity bottleneck data to generate risk transmission path data.

[0125] In this embodiment, a dynamic supply-demand perception model is used to calculate with node data as the input. Based on the supply-demand relationship and dynamic changes of the data, this model evaluates the production capacity utilization rate of each node, determines the nodes where production capacity bottlenecks exist, generates node production capacity bottleneck data according to the results of the model calculation. These data indicate the degree of production capacity bottlenecks of each node, help enterprises understand the bottleneck problems in the supply chain, and take corresponding optimization measures. Analyze the inventory data of the nodes to understand the changes in inventory, calculate indicators such as the increase or decrease in inventory and inventory turnover rate, evaluate the inventory change trend and efficiency of the nodes, and generate node inventory change data according to the results of the inventory change analysis. These data reflect the inventory changes of different nodes and provide basic data for subsequent calculation of delivery efficiency. Define the indicators and measurement methods of delivery efficiency according to demand and business scenarios. For example, use indicators such as delivery time and delivery accuracy to measure delivery efficiency. Use node inventory change data and other relevant data to calculate the delivery efficiency of each node, analyze the relationship between the inventory changes of the nodes and the actual delivery situation, calculate indicators such as delivery time and out-of-stock rate, and generate delivery efficiency data according to the calculated delivery efficiency results. These data reflect the delivery efficiency levels of different nodes and can be used for subsequent risk propagation analysis. Define the indicators and paths of risk transmission. The decline in delivery efficiency, the impact of node production capacity bottlenecks, etc. are used as indicators of risk transmission. Analyze the risk transmission paths between nodes, use node production capacity bottleneck data and delivery efficiency data to analyze the risk transmission paths between nodes, and use methods such as network analysis and propagation models to study the laws of risk transmission in the trade network.

[0126] In this embodiment, the specific steps of step S34 are as follows:

[0127] Step S341: Perform inventory anomaly detection on the node inventory change data to obtain node inventory anomaly data;

[0128] Step S342: Calculate the delivery delay probability for the delivery efficiency data to generate node delivery delay probability data;

[0129] Step S343: Perform supply-demand balance analysis on the node inventory anomaly data and node delivery delay probability data according to the node production capacity bottleneck data to generate node supply-demand balance data;

[0130] Step S344: Perform smooth curve fitting on the node supply-demand balance data to construct a node supply-demand balance curve;

[0131] Step S345: Perform potential risk analysis on the node-to-node topological network diagram through the node supply-demand balance curve to generate node risk data;

[0132] Step S346: Conduct risk propagation analysis on the node risk data to generate risk transmission path data.

[0133] In this embodiment, a suitable inventory anomaly detection method is selected, such as a statistical method, a machine learning method, or an outlier detection algorithm, etc. The selected inventory anomaly detection method is applied to analyze and calculate the node inventory change data. This method identifies the nodes that deviate significantly from the normal inventory change pattern and regards them as inventory anomalies. According to the results of the inventory anomaly detection, node inventory anomaly data is generated. These data identify the nodes with abnormal inventory changes and provide basic data for subsequent supply-demand balance analysis and risk propagation analysis. Define the calculation method of the delivery delay probability. For example, based on historical delivery data or model prediction and other methods, calculate the delivery delay probability of the nodes. Use the selected calculation method to analyze and calculate the delivery efficiency data. This calculation evaluates the probability that each node will experience a delay during the delivery process. According to the calculated delivery delay probability, generate node delivery delay probability data. These data reflect the delivery delay risk level of each node and provide basic data for supply-demand balance analysis and risk propagation analysis. According to the comprehensive data set, conduct supply-demand balance analysis, considering factors such as the production capacity bottleneck, inventory anomaly situation, and delivery delay probability of the nodes, and evaluate the supply-demand balance status of the nodes. Select a suitable smoothing curve fitting method, such as polynomial fitting, spline interpolation, etc. Apply the selected fitting method to fit the node supply-demand balance data and generate a smooth supply-demand balance curve. According to the fitting results, construct the node supply-demand balance curve. This curve reflects the change trend of the node supply-demand balance and provides a reference basis for supply chain management decisions. Based on the node supply-demand balance curve, analyze the supply-demand situation of each node and identify potential risk nodes. These risk nodes have problems such as supply shortages and demand fluctuations, which affect the entire supply chain system. Define the calculation method of the risk transmission path. For example, consider factors such as the dependency relationship and supply-demand relationship between nodes to determine the risk transmission path. Use the selected calculation method to analyze and calculate the node risk data and evaluate the propagation path and propagation degree of the risk in the supply chain.

[0134] In this embodiment, the specific steps of Step S4 are as follows:

[0135] Step S41: Conduct multi-dimensional plane decomposition on the real-time trade data to generate trade multi-dimensional plane data;

[0136] Step S42: Conduct spatial mapping on the trade multi-dimensional plane data to generate a trade data multi-dimensional matrix;

[0137] Step S43: Conduct implicit feature analysis on the trade data multi-dimensional matrix to generate plane implicit feature data;

[0138] Step S44: Dynamically reconstruct the multi-dimensional plane of the trade data based on the plane implicit feature data to construct a multi-dimensional trade plane space.

[0139] In this embodiment, the standardized trade data is decomposed into multiple dimensions or features, and each dimension or feature represents a potential structure or pattern in the data. The specific process of the multi-dimensional plane decomposition is as follows: Based on the standardized data, calculate the covariance matrix between the indicators. The covariance matrix reflects the correlation between different indicators, and each of its elements represents the covariance between the corresponding indicators. Perform eigenvalue decomposition or singular value decomposition on the covariance matrix. The eigenvalues represent the importance of each eigenvector, and the eigenvectors represent the directions of each principal component or factor. According to the magnitudes of the eigenvalues, determine how many principal components or factors to retain. Sort the eigenvectors according to the magnitudes of the eigenvalues. The principal components or factors corresponding to the eigenvectors with larger eigenvalues have higher explanatory power and capture more variance in the data. Select the eigenvectors corresponding to the largest eigenvalues to retain. These eigenvectors are also called principal components or factors, and they form the new dimensions of the data. Each dimension represents a principal component or factor. Project the original trade data onto the selected principal components or factors to obtain the projection values of each sample on the new dimensions. In this way, the original data is represented as a linear combination of the principal components or factors. Calculate the contribution degree of each principal component or factor to the total variance, which is measured by the ratio of the eigenvalue to the total eigenvalues. The larger the ratio, the more variance the principal component or factor explains. Select a suitable space mapping method to map the plane data to the multi-dimensional matrix. Commonly used methods include matrix transpose, matrix rotation, etc. According to the selected space mapping method, map the multi-dimensional trade plane data to construct the multi-dimensional matrix of the trade data, which will make the data easier to understand and process in the multi-dimensional space. Perform implicit feature analysis on the multi-dimensional matrix of the trade data to identify the potential structures and correlations therein, and help discover the interactions and important features between different dimensions. Reconstruct the multi-dimensional matrix of the trade data to construct the multi-dimensional plane space of the trade, which will consider the weights and correlations in the plane implicit feature data, making the reconstructed plane space better reflect the characteristics of the original trade data.

[0140] In this embodiment, the specific steps of Step S5 are as follows:

[0141] Step S51: Analyze the risk decision factors of the risk transmission path data to generate risk decision factor data;

[0142] Step S52: Perform trend analysis on the risk decision factor data through the multi-dimensional trade plane space to generate risk trend data;

[0143] Step S53: Perform trend reverse inference on the historical trade data to generate time-series trend reverse inference data;

[0144] Step S54: Perform trade risk prediction on the risk trend data through time series trend reverse extrapolation data to generate risk trend prediction data.

[0145] In this embodiment, analyze the risk transmission path data to identify key risk decision factors, that is, the factors with the greatest impact on trade risks, analyze the associations and mutual influences among risk factors, understand their dependencies, evaluate the importance and potential impacts of each risk factor, determine its contribution degree to supply chain risks, observe the change trends of risk decision factors in different dimensions according to the plane space data, use time series analysis methods such as moving average and exponential smoothing to identify the long-term trends, seasonal variations, etc. of risk decision factors, comprehensively consider the plane space and time dimensions, analyze the dynamic changes and trends of risk decision factors in the trade link, check the time attributes of the data to ensure that the data is arranged in chronological order, apply time series analysis methods such as stationarity test, autocorrelation analysis, and trend analysis to understand the time characteristics and laws of the data, identify the periodic changes, trends, seasons, etc. in the trade link according to the results of time series analysis, apply the selected reverse extrapolation method to perform trend reverse extrapolation on historical trade data. This process aims to restore the trend of the data and predict the future trend direction. According to the results of the reverse extrapolation, generate time series trend reverse extrapolation data. These data reflect the trend restoration of historical trade data and the prediction of future trends. Select a suitable risk prediction method, such as time series prediction, machine learning algorithms, etc., apply the selected prediction method to predict the risk trend data. This process aims to predict the future risk trend based on past trends and trend reverse extrapolation data. According to the prediction results, generate risk trend prediction data. These data reflect the prediction of future risk trends and provide a reference for risk management and decision-making.

[0146] In this embodiment, the specific steps of Step S6 are as follows:

[0147] Step S61: Perform node resource scheduling analysis on the trade blockchain network according to the risk trend prediction data to generate node resource scheduling data;

[0148] Step S62: Make a supply-demand optimization scheduling decision on the node resource scheduling data to construct a supply-demand optimization scheduling decision engine;

[0149] Step S63: Perform dilated convolution on the supply-demand optimization scheduling decision engine to construct a trade supply-demand optimization scheduling model.

[0150] In this embodiment, the trade blockchain network and related node resources for node resource scheduling analysis are determined, and the objectives of node resource scheduling analysis are determined, such as optimizing resource utilization, balancing network load, etc. Different node resource scheduling analysis methods are studied, such as priority scheduling, dynamic allocation algorithms, etc. A suitable analysis method is selected according to the characteristics of the trade blockchain network and business requirements. The risk trend prediction data and node resources are input into the selected analysis method, the analysis method is run, the node resources of the trade blockchain network are scheduled and analyzed, the rationality and efficiency of resource allocation are evaluated, the node resource scheduling data and related indicators for supply-demand optimization scheduling decision-making are determined, and the objectives of supply-demand optimization scheduling decision-making are determined, such as improving resource utilization efficiency, reducing costs, improving network performance, etc. Different supply-demand optimization scheduling decision-making methods are studied, such as linear programming, genetic algorithms, simulated annealing, etc. A suitable decision-making method is selected according to the characteristics of resource scheduling and optimization objectives. The node resource scheduling data and related indicators are input into the selected decision-making method, the decision-making method is run, the supply-demand optimization scheduling decision-making is performed on the node resource scheduling data, and an optimized scheduling plan is generated. The decision-making method and the optimized scheduling plan are integrated into a supply-demand optimization scheduling decision-making engine. The engine includes a decision-making model, algorithm implementation, decision-making rules, etc. to support real-time resource scheduling decision-making. The data of the supply-demand optimization scheduling decision-making engine is preprocessed, such as normalization, noise reduction, etc. A convolutional neural network model is constructed, including a convolutional layer, a pooling layer, a fully connected layer, etc. The supply-demand optimization scheduling decision-making engine is input into the convolutional neural network model, and dilated convolution operations are performed. According to the output of the convolutional neural network model, the results of the supply-demand optimization scheduling model are obtained.

[0151] In this embodiment, a blockchain-based trade data processing system is provided for performing the blockchain-based trade data processing method as described above, including:

[0152] A blockchain network module for obtaining real-time trade data and historical trade data; performing standardization processing on the real-time trade data to obtain standard trade data; constructing a trade blockchain network based on the standard trade data;

[0153] A dynamic demand module for identifying the flow direction of trade products based on the trade blockchain network to obtain circulation link data; generating dynamic demand data based on the circulation link data; performing supply-demand perception modeling on the dynamic demand data to construct a dynamic supply-demand perception model;

[0154] A risk path module for calculating the node production capacity bottleneck of the trade blockchain network using the dynamic supply-demand perception model to generate node production capacity bottleneck data; generating delivery efficiency data based on the node production capacity bottleneck data; performing risk propagation analysis on the delivery efficiency data to generate risk transmission path data;

[0155] A plane reconstruction module is used to obtain a multidimensional matrix of trade data based on real-time trade data; dynamically reconstruct the multidimensional matrix of trade data to construct a multidimensional plane space of trade;

[0156] The risk prediction module is used to generate risk trend data based on risk transmission path data and trade multi-dimensional space; to predict trade risks based on risk trend data based on historical trade data and generate risk trend prediction data;

[0157] The supply and demand scheduling module is used to obtain node resource scheduling data based on risk trend prediction data; make supply and demand optimization scheduling decisions on the node resource scheduling data, and build a trade supply and demand optimization scheduling model.

[0158] The present invention obtains real-time trade data through the blockchain network module, so that trade participants can timely understand market dynamics and make more accurate decisions. The format and structure of unified trade data are standardized and processed to improve the consistency and comparability of data. A trade blockchain network is constructed to ensure the security and immutability of trade data and enhance the trust between participants. The dynamic demand module identifies the flow of trade products, tracks and records the circulation path of trade products, reveals the supply chain information of products, and helps to monitor the compliance and traceability of trade activities. The generation of dynamic demand data reflects the changes in market demand in real time and helps suppliers make timely adjustments and decisions. The dynamic supply and demand perception model analyzes the changing trend of supply and demand relationships based on real-time data and historical data, provides in-depth insights into the market, and supports decision-making and resource allocation. The risk path module identifies the bottlenecks in the production and circulation links in the trade blockchain network, and provides a basis for optimizing the supply chain and resource allocation. The generation of delivery efficiency data evaluates the speed and accuracy of delivery, helping participants optimize the delivery process and improve customer satisfaction. The analysis of risk transmission path data identifies potential risk transmission paths, warns in advance and takes risk management measures to reduce risks. The impact of trade activities, the plane reconstruction module organizes and classifies trade data according to different dimensions to facilitate data analysis and mining. The dynamic plane reconstruction dynamically adjusts the dimensions and correlations of trade data according to demand and changes, and improves data visualization and interpretability. The construction of the multi-dimensional plane space of trade provides a basis for data exploration and decision support, which helps to discover potential correlations and laws in trade activities. The risk prediction module generates risk trend data based on the risk transmission path and the multi-dimensional plane space of trade, analyzes and predicts risk trends in trade activities, and helps participants formulate risk management strategies. The application of historical trade data draws on past experiences and lessons to predict and evaluate future trade risks and improve the accuracy and effectiveness of decision-making. The supply and demand scheduling module analyzes and plans the resource allocation and scheduling of nodes based on risk trend prediction data to ensure the efficient operation of the supply chain. The supply and demand optimization scheduling decision is based on the node resource scheduling data. By optimizing the matching relationship between supply and demand, it improves resource utilization and delivery efficiency. The construction of the trade supply and demand optimization scheduling model establishes a dynamic scheduling system to achieve reasonable allocation and coordination of resources and optimize the overall benefits of trade activities.

[0159] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0160] The above are only specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but rather will conform to the broadest scope consistent with the principles and novel features invented herein.

Claims

1. A trade data processing method based on blockchain, characterized in that: The following steps are involved: Step S1: obtaining real-time trade data and historical trade data; standardizing the real-time trade data to obtain standard trade data; Build a trade blockchain network based on standard trade data; Step S2: Identify the flow of trade products based on the trade blockchain network to obtain circulation link data; Generate dynamic demand data based on circulation link data; perform supply and demand perception modeling on dynamic demand data and build a dynamic supply and demand perception model; Step S3: Calculate the node capacity bottleneck of the trade blockchain network using the dynamic supply and demand perception model to generate node capacity bottleneck data; Generate delivery efficiency data based on node capacity bottleneck data; Conduct risk propagation analysis on delivery efficiency data to generate risk transfer path data; Step S4: obtaining a multidimensional matrix of trade data based on real-time trade data; Dynamically reconstruct the multidimensional matrix of trade data to construct a multidimensional trade space; Step S5: Generate risk trend data based on risk transmission path data and trade multidimensional space; Conduct trade risk forecasting on risk trend data based on historical trade data to generate risk trend forecast data; Step S6: Obtaining node resource scheduling data based on risk trend prediction data; Make supply and demand optimization scheduling decisions for node resource scheduling data and build a trade supply and demand optimization scheduling model; The specific steps of step S3 are: Step S31: Calculate the node capacity bottleneck of the trade blockchain network using a dynamic supply and demand perception model to generate node capacity bottleneck data; Step S32: Analyze the node inventory changes of the trade blockchain network to generate node inventory change data; Step S33: Calculate the delivery efficiency of the node inventory change data to generate delivery efficiency data; Step S34: Perform risk propagation analysis on the delivery efficiency data according to the node capacity bottleneck data to generate risk transmission path data; the specific steps of step S34 are: Step S341: performing inventory anomaly detection on the node inventory change data to obtain node inventory anomaly data; Step S342: Calculate the delivery delay probability based on the delivery efficiency data to generate node delivery delay probability data; Step S343: performing supply and demand balance analysis on the node inventory abnormality data and the node delivery delay probability data according to the node capacity bottleneck data to generate node supply and demand balance data; Step S344: performing smooth curve fitting on the node supply and demand balance data to construct a node supply and demand balance curve; Step S345: performing potential risk analysis on the node topology network diagram through the node supply and demand balance curve to generate node risk data; Step S346: performing risk propagation analysis on the node risk data to generate risk transmission path data; The specific steps of step S4 are: Step S41: performing multi-dimensional plane decomposition on the real-time trade data to generate trade multi-dimensional plane data; Step S42: spatially mapping the trade multi-dimensional plane data to generate a trade data multi-dimensional matrix; Step S43: performing implicit feature analysis on the multidimensional matrix of trade data to generate plane implicit feature data; Step S44: Dynamically reconstruct the multidimensional matrix of trade data according to the implicit feature data of the plane to construct a multidimensional plane space of trade; the dynamic plane reconstruction is specifically: dynamically update and adjust the structure and attributes of the multidimensional plane space of trade according to the changes of real-time trade data, monitor the changes of real-time trade data, and make corresponding adjustments to the multidimensional plane space of trade according to the changes, including adding new dimensions, deleting dimensions that are no longer needed, and updating the attributes and measurement indicators of dimensions.

2. The blockchain-based trade data processing method according to claim 1 is characterized in that: The specific steps of step S1 are: Step S11: Obtaining real-time trade data and historical trade data; Step S12: standardizing the real-time trade data to obtain standard trade data; Step S13: Designing a distributed contract architecture for standard trade data to generate a distributed contract structure; Step S14: Perform smart contract analysis on standard trade data to obtain a trade smart contract; Step S15: Use the trade smart contract to construct a topological network for the distributed contract structure to build a trade blockchain network.

3. The blockchain-based trade data processing method according to claim 1 is characterized in that: The specific steps of step S2 are: Step S21: Identify the flow of trade products based on the trade blockchain network and generate trade product flow data; Step S22: performing supply chain circulation analysis on the trade product flow data to obtain circulation link data; Step S23: performing node capacity analysis on the circulation link data to generate node capacity data; Step S24: performing dynamic demand analysis on the real-time trade data to generate dynamic demand data; Step S25: Perform supply and demand perception modeling on the dynamic demand data according to the node capacity data to construct a dynamic supply and demand perception model.

4. The blockchain-based trade data processing method according to claim 3 is characterized in that: The specific steps of step S23 are: Step S231: performing regional demand difference analysis on real-time trade data to generate regional demand difference data; Step S232: Calculate demand fluctuation based on regional demand difference data to generate demand fluctuation data; Step S233: performing demand trend analysis on the demand fluctuation data to generate demand trend data; Step S234: performing demand change elasticity analysis on the demand trend data based on the historical trade data to generate demand change elasticity data; Step S235: Perform dynamic demand analysis on the demand change elasticity data to generate dynamic demand data.

5. The blockchain-based trade data processing method according to claim 1 is characterized in that: The specific steps of step S5 are: Step S51: performing risk decision factor analysis on the risk transfer path data to generate risk decision factor data; Step S52: performing trend analysis on risk decision factor data through the trade multi-dimensional plane space to generate risk trend data; Step S53: reverse the trend of historical trade data to generate time series trend reverse data; Step S54: predicting trade risks on risk trend data through time series trend inversion data to generate risk trend prediction data.

6. The blockchain-based trade data processing method according to claim 1, characterized in that: The specific steps of step S6 are: Step S61: performing node resource scheduling analysis on the trade blockchain network according to the risk trend prediction data to generate node resource scheduling data; Step S62: performing supply and demand optimization scheduling decision on the node resource scheduling data to build a supply and demand optimization scheduling decision engine; Step S63: Perform dilation convolution on the supply and demand optimization scheduling decision engine to build a trade supply and demand optimization scheduling model.

7. A trade data processing system based on blockchain, characterized in that: Used to execute the blockchain-based trade data processing method as claimed in claim 1, comprising: The blockchain network module is used to obtain real-time trade data and historical trade data; standardize the real-time trade data to obtain standard trade data; and build a trade blockchain network based on standard trade data; The dynamic demand module is used to identify the flow of trade products based on the trade blockchain network to obtain circulation link data; generate dynamic demand data based on circulation link data; perform supply and demand perception modeling on dynamic demand data to build a dynamic supply and demand perception model; The risk path module is used to calculate the node capacity bottleneck of the trade blockchain network using a dynamic supply and demand perception model to generate node capacity bottleneck data; generate delivery efficiency data based on the node capacity bottleneck data; and perform risk propagation analysis on the delivery efficiency data to generate risk transmission path data; A plane reconstruction module is used to obtain a multidimensional matrix of trade data based on real-time trade data; dynamically reconstruct the multidimensional matrix of trade data to construct a multidimensional plane space of trade; The risk prediction module is used to generate risk trend data based on risk transmission path data and trade multi-dimensional space; to predict trade risks based on risk trend data based on historical trade data and generate risk trend prediction data; The supply and demand scheduling module is used to obtain node resource scheduling data based on risk trend prediction data; make supply and demand optimization scheduling decisions on the node resource scheduling data, and build a trade supply and demand optimization scheduling model.

Images