Cross-border supply chain intelligent matching and collaborative management system

Abstract

The invention discloses a cross-border supply chain intelligent matching and collaborative management system, and relates to the technical field of cross-border supply chain management. The system comprises a matching parameter acquisition module, a matching dimension adjustment module and a supply chain matching module, wherein the matching parameter acquisition module acquires demand data of a demand side and supply data of each supply side; dynamically acquiring a first dimension matching parameter and a second dimension matching parameter of each cross-border supply chain based on the demand data and supply data of a supply side; a matching dimension adjustment module executes matching dimension dynamic adjustment based on transportation strategy driving parameters in the demand data; and the supply chain matching module performs first dimension matching and second dimension matching according to the first dimension matching parameter and the second dimension matching parameter of each cross-border supply chain, and performs screening based on a matching dimension weight dynamic adjustment result and a dimension matching result of each matched supply chain to obtain a final cross-border supply chain.

Description

Technical Field

[0001] This invention relates to the field of cross-border supply chain management technology, and in particular to a cross-border supply chain intelligent matching and collaborative management system. Background Technology

[0002] Cross-border supply chains are underpinned by digitalization, integrating key technologies such as blockchain, IoT, big data, AI, and cloud computing, supplemented by digital twins, electronic customs clearance, and the International Trade Single Window system to build a highly efficient and collaborative system across the entire chain. Blockchain ensures product traceability and data immutability; IoT enables real-time monitoring of cargo location and environment; big data and AI optimize demand forecasting, inventory management, and logistics route planning; cloud computing provides cross-entity data sharing and elastic computing power support; digital twins optimize physical supply chain operations through virtual simulation; and the Single Window system breaks down data barriers between multiple departments, significantly improving customs clearance efficiency. These technologies work together to break down geographical and information silos, achieving closed-loop interconnection of information, logistics, and capital flows. This enhances the transparency, resilience, and compliance of the supply chain while effectively reducing operating costs and shortening delivery cycles, adapting to the dual needs of globalization and regionalization.

[0003] Existing cross-border supply chain collaborative management methods mainly rely on cross-border supply chain collaborative platforms as carriers, integrating technologies such as big data, artificial intelligence, blockchain, and the Internet of Things. By collecting multi-dimensional data from both supply and demand sides, including order requirements, transportation resources, warehousing capacity, customs clearance policies, and logistics timeliness, AI algorithms are used to achieve intelligent matching of goods with transportation and warehousing resources. At the same time, blockchain technology is used to build a reliable data sharing system, breaking down information barriers between multiple entities such as suppliers, logistics service providers, customs, and distributors. This enables collaborative linkage throughout the entire process, including order placement, logistics scheduling, customs declaration, inventory management, and fund settlement. With the support of real-time monitoring and dynamic optimization mechanisms, matching strategies and collaborative solutions are adjusted in a timely manner, ultimately achieving the goal of optimizing resource allocation and maximizing process efficiency in all aspects of the cross-border supply chain.

[0004] For example, a cross-border supply chain data management system and method, as announced in patent application CN118780733B, includes: identifying all relevant nodes in the cross-border supply chain as data sources; extracting data from each data source based on a set collection period to obtain a multidimensional dataset of the cross-border supply chain; preprocessing the multidimensional dataset of the cross-border supply chain; using minimizing total cost and maintaining a set standard inventory level as the optimization objective, while defining a first constraint, a second constraint, and a third constraint, calculating the multidimensional dataset of the cross-border supply chain using the ASGD algorithm to solve for the optimal reorder point and optimal order quantity, and generating a future inventory level prediction result based on the optimal reorder point and optimal order quantity.

[0005] For example, patent application CN119809072A discloses a supply chain management system and method for cross-border trade, comprising: a blockchain network for storing and managing all data related to the supply chain; a compliance code generation module for generating unique product codes based on product type and information for each product, and generating compliance numbers for each region based on the compliance conditions of the current product in each region; a data acquisition module for collecting logistics status and environmental data in real time through sensors and IoT devices, and uploading the data to the blockchain network; a route optimization module for calculating the optimal logistics route using dynamic optimization algorithms based on compliance codes and real-time data analysis; and a user interface module for providing a user interface for participants to query information and perform operations.

[0006] However, in the process of implementing the inventive technical solution in the embodiments of this application, it was found that the above-mentioned technology has at least the following technical problems: In existing technologies, the cross-border supply chain matching process typically employs static, fixed evaluation models and weight parameters. This results in the system's inability to adaptively adjust to changing transportation strategies, real-time scenario requirements, and dynamic fluctuations in supply chain resources. Consequently, the matching results are often rigid and simplistic, lacking the ability to accurately adapt to complex business scenarios. Furthermore, it lacks a closed-loop mechanism for self-learning and iterative optimization when matching fails. This leads to problems such as a disconnect between matching standards and actual business operations, insufficient system robustness and fault tolerance, and difficulty in achieving an intelligent balance between efficiency and collaborative quality. Summary of the Invention

[0007] This application provides an intelligent matching and collaborative management system for cross-border supply chains. It addresses the shortcomings of existing technologies where the matching process typically employs static, fixed evaluation models and weight parameters. This results in systems unable to adapt to changing transportation strategies, real-time scenario demands, and dynamic fluctuations in supply chain resources, leading to rigid and simplistic matching results. Such systems lack the ability to accurately adapt to complex business scenarios and lack a closed-loop mechanism for self-learning and iterative optimization when matching fails. Furthermore, existing systems suffer from a disconnect between matching standards and actual business needs, insufficient system robustness and fault tolerance, and difficulty in achieving an intelligent balance between efficiency and collaborative quality. This new system enables cross-border supply chain matching to dynamically adjust evaluation standards and decision preferences based on changing transportation strategies and real-time scenario demands, and to optimize parameters through adaptive learning when matching fails, thereby achieving an intelligent balance between efficiency and collaborative quality.

[0008] This application provides a cross-border supply chain intelligent matching and collaborative management system, including: a matching parameter acquisition module, a matching dimension adjustment module, and a supply chain matching module. The matching parameter acquisition module acquires demand data from the demand side and supply data from each supply side, and dynamically acquires first-dimensional matching parameters and second-dimensional matching parameters for each cross-border supply chain based on the demand data and supply data. Each cross-border supply chain is an independent supply chain route constructed based on a point-to-point correspondence between the demand side and each supply side. The first-dimensional matching parameter represents the static fit of key nodes in cross-border product transportation, and the second-dimensional matching parameter represents the dynamic fit of key nodes in cross-border product transportation. The matching dimension adjustment module is used to adjust the matching parameters based on the demand data... The transportation strategy drives the dynamic adjustment of matching dimensions. Dynamic adjustment of matching dimensions means dynamically adjusting the allocation ratio of dimension weight parameters to adapt to different emphases on the static and dynamic efficiency of transportation under different demand scenarios. Dimension weight parameters include the first dimension weight and the second dimension weight. The supply chain matching module is used to perform first dimension matching based on the first dimension matching parameters of each cross-border supply chain, output each candidate matching supply chain, and perform second dimension matching based on the second dimension matching parameters of the candidate matching supply chains, output each matching supply chain, and filter the final cross-border supply chain based on the dynamic adjustment results of matching dimension weights and the dimension matching results of each matching supply chain. The dimension matching results include the first dimension matching results and the second dimension matching results.

[0009] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages: 1. By decoupling cross-border supply chain matching into two dimensions of static structure and dynamic collaboration, and introducing a weight adaptive adjustment mechanism based on transportation strategy and a parameter relaxation self-learning mechanism based on failure attribution, the system can dynamically calibrate evaluation standards and decision preferences according to real-time business scenarios. It can also intelligently lower non-core thresholds to discover feasible solutions when matching fails. This achieves a synergistic improvement in matching accuracy, system robustness, and business scenario adaptability, ensuring the reliable output of supply chain solutions with optimal efficiency and collaboration quality in complex and ever-changing cross-border environments.

[0010] 2. By standardizing demand and supply data into target parameters and driving the construction of point-to-point supply chains, and then extracting static structural features from network topology and dynamic collaborative features from flow logs, we can independently and quantitatively characterize the static robustness and dynamic collaborative efficiency of each potential supply chain. This provides calculable and comparable precise inputs for subsequent multi-scenario adaptive weight adjustment and intelligent screening, laying the foundation for moving from fuzzy experience matching to data-driven precise evaluation.

[0011] 3. By quantifying and coupling high-level business strategies such as the granularity of transportation data, update frequency, and intensity of collaborative needs with preset benchmarks, and mapping them to specific weight adjustment ratios, the evaluation weights of the first dimension (static structure) and the second dimension (dynamic collaboration) are dynamically allocated in real time and in a quantitative manner. This achieves precise alignment between the system's matching logic and the ever-changing actual transportation strategies and scenario preferences, enabling the matching results to intelligently achieve the optimal balance between the structural efficiency and collaborative quality of the supply chain, which aligns with the current business intent.

[0012] 4. By quantitatively weighting and evaluating the static structural parameters of the supply chain and setting unified thresholds for screening, and by initiating a local repair mechanism based on dual verification of the location and path of replacement nodes for non-compliant supply chains, intelligent optimization opportunities are provided for some supply chains that are rejected due to single-point defects, while ensuring the robustness of the basic structure. This achieves a balance between screening efficiency and resource utilization in the first round of screening, effectively expanding the candidate range of high-quality supply chains and laying a better static structural foundation for subsequent dynamic collaborative matching.

[0013] 5. By applying preset dynamic efficiency standards to conduct secondary quantitative evaluation and weighted integration of transportation timeliness, node connection and collaboration quality on the supply chain that has passed static screening, a multi-level and refined consideration from structural robustness to real-time collaboration efficiency is achieved. This allows for the selection of a high-quality matching supply chain pool that also meets the standards at the dynamic operation level, providing a high-quality candidate set with both static reliability and dynamic execution for the final intelligent decision-making, ensuring the collaboration quality and efficiency of the recommended solution in actual operation.

[0014] 6. By applying dynamically adjusted dimensional weights to comprehensively score and rank candidate supply chains, and implementing a final quality threshold verification for the best candidate, a parameter relaxation learning mechanism based on historical failure attribution is automatically initiated when matching fails. This ensures that the final decision reflects both scenario-based preferences and absolute quality. When the system faces challenges of universally high standards, it can intelligently and purposefully relax secondary constraints to seek feasible solutions. Thus, while pursuing matching accuracy, the system's business usability, fault tolerance, and continuous self-optimization capabilities are significantly improved, ensuring the reliable operation and long-term effectiveness of the intelligent matching system in complex real-world environments. Attached Figure Description

[0015] Figure 1 A schematic diagram of the structure of the cross-border supply chain intelligent matching and collaborative management system provided in the embodiments of this application; Figure 2 The first dimension matching flowchart of the cross-border supply chain intelligent matching and collaborative management system provided in the embodiments of this application. Detailed Implementation

[0016] This application provides an intelligent matching and collaborative management system for cross-border supply chains. It addresses the shortcomings of existing technologies where the matching process typically employs static, fixed evaluation models and weight parameters. This results in systems unable to adapt to changing transportation strategies, real-time scenario demands, and dynamic fluctuations in supply chain resources, leading to rigid and simplistic matching results. Such systems lack the ability to accurately adapt to complex business scenarios and lack a closed-loop mechanism for self-learning and iterative optimization when matching fails. Other issues include a disconnect between matching standards and actual business operations, insufficient system robustness and fault tolerance, and difficulty in achieving an intelligent balance between efficiency and collaborative quality. The overall approach is as follows: First, the matching parameter acquisition module collects demand-side and supply-side data and dynamically calculates two types of core parameters for each potential point-to-point supply chain route: first-dimensional matching parameters (quantifying the static structural fit of key nodes, such as network depth, location, and path matching) and second-dimensional matching parameters (quantifying the dynamic collaborative efficiency of key nodes, such as transportation timeliness, node connectivity, and collaborative matching). Then, the matching dimension adjustment module dynamically adjusts the weight allocation of these two dimensions in the final decision based on the specific transportation strategy of the demand side (such as data granularity, update frequency, and collaborative demand intensity), enabling the system to flexibly adapt to different business scenarios with varying emphases on static efficiency and dynamic collaboration. Finally, the supply chain matching module performs two levels of matching and filtering: first, static structure filtering based on the first-dimensional parameters, and then dynamic collaboration filtering based on the second-dimensional parameters. The adjusted dimension weights are then comprehensively applied to evaluate and rank the candidate supply chains, outputting the optimal matching result. When the optimal candidate still fails to meet the final quality threshold, the system will analyze historical matching failure data, intelligently determine whether there is a systematic deviation between the static structural standard or the dynamic collaborative standard and the current resource pool, and adjust the corresponding matching reference parameters accordingly, and then automatically re-execute the matching process.

[0017] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.

[0018] like Figure 1The diagram shown is a structural schematic of the cross-border supply chain intelligent matching and collaborative management system provided in this application embodiment. The cross-border supply chain intelligent matching and collaborative management system provided in this application embodiment includes: a matching parameter acquisition module, a matching dimension adjustment module, and a supply chain matching module. The matching parameter acquisition module is used to acquire demand data from the demand side and supply data from each supply side. The demand data from the demand side includes, but is not limited to, order attributes (such as product type, quantity, and value), logistics requirements (such as origin / destination, warehouse location, expected delivery time and cost range), operational strategies (such as data granularity and update frequency requirements), and collaborative preference data (such as preferences for suppliers). To meet the demand for information sharing and collaboration among all nodes in the supply chain, the supply data of each supply side includes, but is not limited to, static resource networks (such as warehouse / port / transportation route layout), dynamic operational capabilities (such as historical transportation timeliness, node connection efficiency, cost structure), and collaboration interface levels (such as data exchange protocols, anomaly response mechanisms, and collaboration rule compatibility). For example, the demand side provides "to transport 500 boxes of electronic products from a bonded warehouse in Shenzhen to Frankfurt, Germany, requiring delivery within 30 days, a cost of less than 100,000 yuan, and hourly updates to freight coordinates"; the supply side needs to provide "five hub warehouses in Europe, an average delivery time of 25 days on the China-Europe route, and automated customs clearance at ports." The system supports real-time data integration and other data. Based on this, the system constructs point-to-point supply chains and calculates dynamic and static matching parameters. It dynamically acquires the first and second dimension matching parameters for each cross-border supply chain based on demand data and supply-side data. Each cross-border supply chain is an independent supply chain route constructed based on a point-to-point correspondence between the demand side and each supply side. The first dimension matching parameter represents the static fit of key nodes in cross-border product transportation, while the second dimension matching parameter represents the dynamic fit of key nodes in cross-border product transportation. The matching dimension adjustment module is used to dynamically adjust the matching dimension based on the transportation strategy-driven parameters in the demand data. Dynamic adjustment of the matching dimension means dynamically adjusting the allocation ratio of dimension weight parameters to adapt to different emphases on the static and dynamic efficiency of transportation under different demand scenarios. The dimension weight parameters include the first dimension weight and the second dimension weight. The supply chain matching module performs first-dimensional matching based on the first-dimensional matching parameters of each cross-border supply chain, outputting each candidate matching supply chain. It also performs second-dimensional matching based on the second-dimensional matching parameters, outputting each matched supply chain. Finally, based on the dynamic adjustment results of the matching dimension weights and the dimension matching results of each matched supply chain, the final cross-border supply chain is obtained. The dimension matching results include both the first and second dimension matching results.

[0019] In this embodiment, the present invention achieves multiple core technical effects through the coordinated operation of the matching parameter acquisition module, the matching dimension adjustment module, and the supply chain matching module. The system relies on the matching parameter acquisition module to accurately capture demand data from the demand side and supply data from each supply side. Based on these two types of data, it constructs independent cross-border supply chain paths point-to-point between the demand side and each supply side. It extracts a first-dimensional matching parameter representing the static fit of key nodes in cross-border product transportation and a second-dimensional matching parameter representing the dynamic fit of key nodes. This breaks the dependence of traditional cross-border supply chain matching on single-dimensional data, providing comprehensive, layered, and accurate data support for subsequent matching work, effectively avoiding matching deviations caused by incomplete parameters. The matching dimension adjustment module dynamically adjusts the allocation ratio of the first-dimensional and second-dimensional weights based on the transportation strategy-driven parameters in the demand data, achieving scenario-based adaptive matching rules. It can adjust the static matching parameters of transportation according to different demand scenarios. The differentiated approach to efficiency and dynamic efficiency emphasizes flexible adjustment of the matching logic, completely abandoning the one-size-fits-all matching model with fixed weights. This significantly improves the adaptability of the matching solution to diverse transportation needs. The supply chain matching module uses a hierarchical and progressive matching logic: the first dimension initially screens out candidate supply chains, the second dimension further screens out matching supply chains, and dynamic weights are combined to select the final cross-border supply chain. This logic not only uses the first dimension matching to quickly narrow down the candidate range and ensure matching efficiency, but also relies on the second dimension matching to deeply explore the dynamic fit of key nodes and ensure matching accuracy. The final cross-border supply chain solution can take into account both the static reliability and dynamic timeliness of transportation, effectively reducing the risks of node connection and resource waste in the cross-border transportation process, and significantly improving the overall collaborative operation efficiency and demand response speed of the cross-border supply chain.

[0020] Furthermore, the steps for dynamically acquiring the first-dimensional matching parameters and second-dimensional matching parameters of each cross-border supply chain based on demand data and supply-side data include: obtaining target basic parameters of the demand side based on demand data, including but not limited to the basic attributes of the demanded goods, target warehousing location, target transportation destination, target cost range, target timeliness requirements, and order priority identifier; performing initial screening of each supply side based on the target basic parameters to obtain candidate supply sides; linking each candidate supply side to the demand side point-to-point to generate the corresponding cross-border supply chain; for each cross-border supply chain, extracting its corresponding key node network data, and calculating and generating the first-dimensional matching parameters based on the key node network data, including network depth matching degree, location matching degree of each key node, and average path matching degree of each key node; for each cross-border supply chain, extracting its corresponding key node flow data, and calculating and generating the second-dimensional matching parameters based on the key node flow data, including transportation timeliness matching degree, node connection matching degree, and node collaboration matching degree of each key node.

[0021] In this embodiment, the present invention achieves significant and layered technical effects by refining the specific process of dynamically acquiring the first and second dimension matching parameters based on demand and supply data. By first extracting multi-dimensional target basic parameters covering the basic attributes of the demanded goods, target warehousing location, transportation destination, cost range, timeliness requirements, and order priority identifiers, comprehensive and accurate demand-oriented criteria can be provided for supply-side screening, effectively avoiding the problem of ineffective supply-side inclusion due to missing or incomplete demand parameters. The initial supply-side screening based on these target basic parameters can quickly filter out suppliers that do not meet core needs, significantly narrowing the scope of subsequent supply chain construction and parameter calculation, and improving the overall efficiency of the matching process. By linking candidate suppliers and demand sides point-to-point to generate independent cross-border supply chain paths, it can ensure that each matching link forms a precise correspondence with the demand side, avoiding link confusion and matching interference in many-to-many association models. Furthermore, for each supply chain path, key node network data is extracted, and calculations are performed including network depth matching degree, node location matching degree, and average path matching degree. The first dimension matching parameter accurately measures the static layout fit of key nodes in cross-border transportation, ensuring the basic rationality and stability of the supply chain in terms of node distribution and route planning. Simultaneously, extracting key node flow data and calculating the second dimension matching parameter, which includes transportation timeliness matching, node connection matching, and node collaboration matching, effectively captures the dynamic adaptability of cargo flow between nodes during cross-border transportation. This reflects the timeliness guarantee level and collaborative response efficiency of the link in actual operation. Finally, through the refined and hierarchical extraction of both static and dynamic matching parameters, comprehensive, accurate, and clearly targeted data support is provided for subsequent matching dimension weight adjustment and final supply chain selection. This completely solves the problems of low matching accuracy and poor scenario adaptability caused by general parameter extraction and confusion between static and dynamic dimensions in traditional cross-border supply chain matching, significantly improving the targeting, reliability, and collaborative management efficiency of cross-border supply chain matching.

[0022] Furthermore, the transportation strategy driving parameters include transportation data granularity, transportation data update frequency, and collaborative demand intensity. The steps for dynamically adjusting the matching dimensions based on the transportation strategy driving parameters in the demand data include: obtaining preset dimension weight reference parameters, which include a first dimension reference coefficient and a second dimension weight reference coefficient; comparing the transportation strategy driving parameters with the preset transportation strategy driving reference parameters to perform influence calculations, and then using preset transportation strategy weight parameters to weight and couple the comparison influence calculation results to obtain transportation strategy driving influence parameters. The transportation strategy driving reference parameters include granularity benchmark values, update frequency benchmark values, and collaborative strength benchmark values. The transportation strategy weight parameters include granularity... The following parameters are considered: degree of influence coefficient, update frequency influence coefficient, and synergy strength influence coefficient. Based on the transportation strategy-driven influence parameters, a pre-defined weight coefficient adjustment relationship table is used to obtain the corresponding weight coefficient adjustment ratio. This table defines the mapping relationship between different ranges of transportation strategy-driven influence parameters and their corresponding weight coefficient adjustment amounts. The weight coefficient adjustment ratio is used to multiply the second-dimensional weight reference coefficient to obtain the second-dimensional base coefficient. Then, the second-dimensional base coefficient is coupled with the first-dimensional reference coefficient to obtain the comprehensive matching base coefficient. The ratios of the first-dimensional reference coefficient, the second-dimensional base coefficient, and the comprehensive matching base coefficient are calculated to obtain the adjusted first-dimensional weight and the adjusted second-dimensional weight.

[0023] The scores for the parameters influencing transportation strategy are as follows: ; In the formula, This indicates the parameters that drive the transportation strategy. , and These represent the granularity influence coefficient, update frequency influence coefficient, and synergy strength influence coefficient, respectively. , and These represent the granularity of transportation data, the frequency of transportation data updates, and the intensity of collaborative demand, respectively. , and These represent the granularity benchmark value, update frequency benchmark value, and synergistic strength benchmark value, respectively.

[0024] In this embodiment, the present invention achieves precise and standardized weight adaptation by clearly defining the specific types of transportation strategy driving parameters and the dynamic adjustment steps for matching dimension weights. It selects transportation data granularity, transportation data update frequency, and the intensity of collaborative demand as transportation strategy driving parameters, comprehensively covering the data-level granularity requirements, timeliness-level update requirements, and collaboration-level linkage requirements in the cross-border supply chain matching process. This provides a targeted core basis for dimension weight adjustment, effectively avoiding the blindness and one-sidedness of weight adjustment. By pre-setting dimension weight reference parameters and transportation strategy driving reference parameters, a standardized benchmark framework is established for weight adjustment, eliminating the adjustment deviation problem caused by the lack of a unified reference. By comparing the transportation strategy driving parameters with the corresponding benchmark values ​​and performing influence calculations, and combining them with preset transportation strategy weight parameters for weighting coupling processing, the invention can accurately quantify the differentiated influence of different driving parameters on weight adjustment, ensuring that the weight adjustment direction is highly consistent with the transportation strategy requirements. By querying the preset weight coefficient adjustment relationship table to obtain the corresponding adjustment ratio, the weight adjustment rules are solidified and reused, significantly improving the execution efficiency and consistency of weight adjustment results. The second dimension base coefficient is obtained by multiplying the second dimension weight reference coefficient, and then coupled with the first dimension reference coefficient to calculate the comprehensive matching base coefficient. Finally, the adjusted first and second dimension weights are obtained through ratio calculation, which can ensure the normalized allocation of the two types of dimension weights. This ensures that the weight ratio can accurately reflect the core needs of the transportation strategy and achieve an organic balance between static dimension matching and dynamic dimension matching. This completely solves the pain point that the traditional fixed weight mode cannot adapt to diverse transportation strategy scenarios, significantly improving the scientific nature, accuracy, and scenario adaptability of matching dimension weight adjustment, and laying a reliable weight basis for the efficient screening of the subsequent supply chain.

[0025] like Figure 2The diagram shown illustrates the first-dimensional matching flowchart of the cross-border supply chain intelligent matching and collaborative management system provided in this application embodiment. The steps for performing first-dimensional matching based on the first-dimensional matching parameters of each cross-border supply chain and outputting each candidate matching supply chain include: comparing the first-dimensional matching parameters of each cross-border supply chain with preset first-dimensional matching reference parameters for influence calculation; then, using preset first-dimensional weight parameters, weighting and coupling the comparison influence calculation results to obtain the first-dimensional matching parameters of each cross-border supply chain. The first-dimensional matching reference parameters include network depth matching reference, location matching reference, and path matching reference. The first-dimensional weight... The key parameters include the network depth matching degree influence coefficient, the location matching degree influence coefficient, and the path matching degree influence coefficient. The first dimension matching parameter of each cross-border supply chain is compared with the preset first dimension matching threshold. If the first dimension matching parameter of any cross-border supply chain is lower than the first dimension matching threshold, it is marked as a supply chain to be matched. The first dimension matching is then performed based on the replacement nodes corresponding to the key nodes of the supply chain to be matched, and candidate matching supply chains and non-candidate matching supply chains are selected. If the first dimension matching parameter of any cross-border supply chain is not lower than the first dimension matching threshold, it is marked as a candidate matching supply chain. The candidate matching supply chains are counted and output.

[0026] The methods for obtaining the first dimension matching parameters for each cross-border supply chain are as follows: ; In the formula, This represents the first dimension matching parameter of the i-th cross-border supply chain. , and These represent the influence coefficients of network depth matching degree, location matching degree, and path matching degree, respectively. This represents the network depth matching degree of the i-th cross-border supply chain. and Let these represent the location matching degree and average path matching degree of the j-th key node in the i-th cross-border supply chain, respectively. , and These represent the network depth matching reference value, location matching reference value, and path matching reference value, respectively. Here, i is the cross-border supply chain number, i=1,2,3,...,N, where N is the total number of cross-border supply chains, and j is the key node number, j=1,2,3,...,M, where M is the total number of key nodes.

[0027] In this embodiment, the present invention achieves accurate and efficient initial screening of cross-border supply chains by constructing a standardized and hierarchical first-dimensional matching process. It compares and calculates the impact of the first-dimensional matching parameters of each cross-border supply chain with preset reference values ​​for network depth, location, and path matching, and performs weighted coupling processing based on corresponding weight parameters. This allows for the quantitative integration of core indicators characterizing the static fit of key nodes in cross-border transportation, generating first-dimensional matching parameters with clear directionality. This effectively avoids the problems of high subjectivity and low accuracy in traditional static matching processes, which rely on manual judgment and arbitrary allocation of indicator weights. By setting a first-dimensional matching threshold and performing comparison and classification, supply chains with matching parameters not lower than the threshold are directly marked as candidate matching supply chains. This quickly filters out links whose static layout meets core requirements, significantly improving the execution efficiency of first-dimensional matching. Simultaneously, it addresses supply chains with parameters lower than the threshold. The threshold-based matching of supply chains involves re-matching the first dimension based on the replacement nodes corresponding to their key nodes. This approach can uncover cross-border supply chains with overall optimization potential due to local node layout deviations, avoiding the direct exclusion of an entire high-quality link due to a single node defect. This significantly improves the comprehensiveness and coverage of static dimension matching. Finally, by statistically outputting each candidate matching supply chain, a precise and reasonable candidate range is defined for the subsequent dynamic matching in the second dimension. This also ensures the basic reliability of the candidate links in terms of node network layout, path planning, and other static aspects. This completely solves the pain points of traditional cross-border supply chain initial screening, such as the difficulty in balancing efficiency and accuracy and the high rate of missing high-quality links. It lays a solid foundation for static dimension screening in the overall supply chain matching and collaborative management.

[0028] Furthermore, the first-dimensional matching step based on the replacement nodes corresponding to each key node of the supply chain to be matched includes: if the position matching degree of any key node in the supply chain to be matched is lower than the position matching degree reference value, then obtain the replacement node corresponding to the key node; determine whether the position matching degree of the replacement node reaches the position matching degree reference value, otherwise no additional processing is performed; if it reaches the reference value, determine whether the average path matching degree of the path associated with the replacement node reaches the path matching degree reference value, if so, replace the key stage with the replacement node; otherwise no additional processing is performed; re-execute the first-dimensional matching based on the first-dimensional matching parameters of each supply chain to be matched after replacement, generate the first-dimensional matching parameters of each supply chain to be matched after replacement, if the first-dimensional matching parameter of any supply chain to be matched after replacement is not lower than the first-dimensional matching parameter, then mark it as a candidate supply chain; if the first-dimensional matching parameter of any supply chain to be matched after replacement is still lower than the first-dimensional matching parameter, then mark it as a non-candidate supply chain.

[0029] In this embodiment, the present invention constructs a targeted node replacement, dual verification, and re-matching supply chain optimization mechanism to achieve precise completion and efficiency upgrade of the first-dimensional matching process. It targets specific key nodes in the supply chain whose positional matching degree is lower than the reference value, selectively acquiring replacement nodes. This abandons the traditional extensive processing mode of directly eliminating or indiscriminately replacing nodes throughout the entire supply chain, achieving targeted repair of local node defects and significantly improving the accuracy and pertinence of the supply chain optimization process. Through a dual verification logic—first verifying whether the replacement node's own positional matching degree meets the standard, and then verifying whether the average path matching degree of its associated paths meets the requirements—it effectively avoids the path adaptability imbalance caused by replacing a single node, ensuring the overall rationality and stability of the cross-border supply chain's key node network layout after replacement. Based on the first-dimensional matching parameters of the replaced supply chain... By recalculating matching parameters and executing the judgment process, cross-border supply chains that were originally classified as pending due to defects in local nodes were given the opportunity to advance to the candidate matching supply chain. This maximized the exploration of potential high-quality supply chain resources and significantly reduced the missed screening rate of high-quality cross-border supply chains. Ultimately, by effectively revitalizing links with local defects, this mechanism not only improved the comprehensiveness and accuracy of the first-dimensional matching results, but also provided a pool of candidate links with better quality and wider coverage for the subsequent second-dimensional dynamic matching stage. This fundamentally strengthened the reliability and effectiveness of the entire intelligent matching process for cross-border supply chains, and completely solved the industry pain point of misscreening or missing high-quality links due to local node problems in traditional first-dimensional matching.

[0030] Furthermore, the steps for performing second-dimensional matching on the candidate supply chains based on the second-dimensional matching parameters and outputting each matching supply chain include: comparing the second-dimensional matching parameters of each candidate supply chain with preset second-dimensional matching reference parameters for influence calculation; then using preset second-dimensional weight parameters to weight and couple the comparison influence calculation results to obtain the second-dimensional matching parameters of each candidate supply chain. The second-dimensional matching reference parameters include the reference values ​​for transportation timeliness matching degree, node connection matching degree, and node collaboration matching degree; the second-dimensional weight parameters include the influence coefficients for transportation timeliness matching degree, node connection matching degree, and node collaboration matching degree. The second-dimensional matching parameters of each candidate supply chain are compared with preset second-dimensional matching thresholds. If the second-dimensional matching parameter of any candidate supply chain is lower than the second-dimensional matching threshold, it is marked as a non-matching supply chain; if the second-dimensional matching parameter of any candidate supply chain is not lower than the second-dimensional matching threshold, it is marked as a matching supply chain. Finally, the matching supply chains are statistically analyzed and output.

[0031] The second dimension matching parameters for each candidate supply chain are obtained as follows: ; In the formula, This represents the second dimension matching parameter of the k-th candidate supply chain. , and These represent the influence coefficients of transportation timeliness matching degree, node connection matching degree, and node coordination matching degree, respectively. , and Let $\mathbf{k}$ represent the transportation timeliness matching degree, node connectivity matching degree, and node collaboration matching degree of the $j$-th key node in the $k$-th candidate matching supply chain, respectively. , and These represent the reference values ​​for transportation timeliness matching, node connection matching, and node collaboration matching, respectively. k is the number of each candidate matching supply chain, k=1,2,3,...,K, and K is the total number of candidate matching supply chains.

[0032] In this embodiment, the present invention achieves precise screening of the dynamic adaptability of cross-border supply chains by constructing a standardized and indexed second-dimensional matching process. It compares the second-dimensional matching parameters of each candidate matching supply chain with preset reference values ​​for transportation timeliness, node connectivity, and node collaboration matching, and performs weighted coupling processing based on corresponding weight parameters. This allows for the quantitative integration of core indicators characterizing the dynamic fit of key nodes in cross-border transportation, generating second-dimensional matching parameters that can be directly used for judgment. This effectively avoids the problem of distorted matching results caused by vague indicator evaluation standards and lack of basis for weight allocation in traditional dynamic matching processes. By setting clear second-dimensional matching thresholds and performing comparison judgments, matching supply chains that meet the dynamic flow efficiency standards can be quickly screened out, while accurately eliminating those with static layout requirements but insufficient dynamic timeliness guarantees and node... The selection of candidate links with poor connectivity and weak collaboration capabilities not only ensures the accuracy of matching results but also improves the execution efficiency of the second-dimensional matching. As a key fine-tuning step after the first-dimensional static initial screening, this second-dimensional matching process effectively complements the first-dimensional matching, achieving a dual verification of the rationality of the static layout and the efficiency of dynamic flow of the cross-border supply chain. This provides a high-quality candidate link pool with both basic reliability and practical operational adaptability for the subsequent selection of the final cross-border supply chain based on dynamic weights. It completely solves the industry pain point of traditional cross-border supply chain matching, which emphasizes static aspects over dynamic aspects, resulting in the link's actual operational efficiency falling short of expectations. This significantly improves the overall quality and collaborative management level of intelligent matching of cross-border supply chains.

[0033] Furthermore, the steps for obtaining the final cross-border supply chain based on the dynamic adjustment results of the matching dimension weights and the dimension matching results of each matching supply chain include: weighting and coupling the first and second dimension matching parameters of each matching supply chain based on the adjusted dimension weight parameters to obtain the comprehensive matching parameters of each matching supply chain; sorting the matching supply chains in reverse order according to the comprehensive matching parameters, and marking the first matching supply chain as the cross-border supply chain to be judged; comparing the comprehensive matching parameters of the cross-border supply chain to be judged with a preset comprehensive matching threshold; if the comprehensive matching parameters of the cross-border supply chain to be judged are lower than the comprehensive matching threshold, a matching anomaly prompt is output, and an adaptive parameter relaxation adjustment mechanism based on matching failure attribution is executed; if the comprehensive matching parameters of the cross-border supply chain to be judged are not lower than the comprehensive matching threshold, the cross-border supply chain to be judged is marked as the final cross-border supply chain.

[0034] In this embodiment, the present invention constructs a full-process final supply chain screening mechanism involving weight coupling, sorting and filtering, threshold verification, and adaptive adjustment, enabling precise control and dynamic optimization of cross-border supply chain matching results. Based on the adjusted dimensional weight parameters, the first and second dimension matching parameters of each matched supply chain are weighted and coupled. This scientifically integrates the static node layout fit and dynamic node flow efficiency according to the actual weight proportion of the demand scenario, generating comprehensive matching parameters that combine scenario adaptability and comprehensive reference value. This effectively avoids the problem of misjudgment of comprehensive efficiency caused by the separation of static and dynamic dimension evaluation and fixed weight allocation in traditional screening processes. By reversing the order of the comprehensive matching parameters and marking the first one as the cross-border supply chain to be judged, the candidate link with the best comprehensive fit can be quickly identified, significantly improving the execution efficiency of the final screening process. Simultaneously, the core comparison object is clearly defined to ensure the targeting of the screening. Comparing the comprehensive matching parameters of the cross-border supply chain to be judged with the preset comprehensive matching threshold can define a clear performance benchmark for the final supply chain, ensuring that the marked final cross-border supply chain has both static reliability and... Dynamic efficiency meets the actual needs of cross-border transportation. When the comprehensive matching parameters are below the threshold, the system outputs a matching anomaly alert and executes an adaptive parameter relaxation adjustment mechanism based on matching failure attribution. This abandons the traditional crude mode of terminating the process upon matching failure, instead using dynamic relaxation of parameter thresholds to uncover potential matching links, significantly improving the success rate and fault tolerance of supply chain matching and forming a closed-loop management logic of screening, verification, and optimization. This mechanism, as the final gatekeeper in the entire intelligent matching process of the cross-border supply chain, connects the initial static screening and dynamic fine screening. Through scientific comprehensive evaluation and flexible adaptive adjustment, it thoroughly solves industry pain points such as the lack of weighted dynamic adaptation comprehensive evaluation standards in traditional supply chain screening, the lack of effective remedial measures after matching failure leading to low supply chain matching rates and poor adaptability. This significantly improves the overall operational efficiency and practical application value of the intelligent matching and collaborative management system for cross-border supply chains.

[0035] Furthermore, the specific steps for implementing the adaptive parameter relaxation adjustment mechanism based on matching failure attribution include: obtaining a set of historical matching tasks that triggered matching anomaly alerts within a preset statistical period, and calculating the matching failure rate of the historical matching task set; if the matching failure rate is greater than or equal to a preset failure rate warning threshold, it is determined that there is a systematic deviation between the current system matching standard and the available resource pool, triggering parameter relaxation adjustment; respectively calculating the average difference between the first-dimensional matching parameter and the first-dimensional matching threshold of each cross-border supply chain to be judged in the historical matching task set, denoted as the static deviation mean, and the average difference between the second-dimensional matching parameter and the second-dimensional matching threshold, denoted as the dynamic deviation mean; based on the static deviation mean and the dynamic deviation mean, adjusting the first-dimensional matching... The reference parameters and the second-dimensional matching reference parameters are adjusted collaboratively for relaxation: if the mean static deviation is greater than or equal to the mean dynamic deviation, it indicates that the static structural requirements are the main bottleneck, and the network depth matching degree reference, location matching degree reference, and path matching degree reference in the first-dimensional matching reference parameters are lowered to their corresponding relaxation lower limits; if the mean static deviation is less than the mean dynamic deviation, it indicates that the dynamic coordination requirements are the main bottleneck, and the transportation timeliness matching degree reference, node connection matching degree reference, and node coordination matching degree reference in the second-dimensional matching reference parameters are lowered to their corresponding relaxation lower limits; after the reference parameters are adjusted, the supply chain matching process for the current demand data is re-executed based on the updated matching reference parameters.

[0036] In this embodiment, the present invention constructs an adaptive parameter relaxation adjustment closed-loop mechanism based on historical data attribution analysis, which enables dynamic fault tolerance and intelligent optimization of the cross-border supply chain matching process. By acquiring a set of historical matching tasks that trigger matching anomaly alerts within a preset statistical period and calculating the matching failure rate, scientific data support can be provided for triggering parameter relaxation adjustment. Only when the matching failure rate reaches a preset warning threshold is it determined that there is a systematic deviation between the current system matching standard and the available supply resource pool, effectively avoiding the problem of uncontrolled system matching accuracy caused by blindly triggering parameter adjustments due to occasional matching failures, and ensuring the necessity and rationality of parameter adjustment. By separately statistically analyzing the static deviation average and dynamic deviation average of the cross-border supply chain to be judged in historical matching tasks, it is possible to accurately distinguish whether the core bottleneck causing the matching failure stems from excessively high node layout requirements at the static structural level or from excessively strict node flow standards at the dynamic collaboration level, achieving precise positioning of the cause of matching failure and completely abandoning the one-size-fits-all, extensive adjustment mode in traditional parameter adjustment. Targeted parameters are executed based on the comparison results of the deviation averages. The relaxation strategy involves lowering the indicators of the first dimension matching reference parameters to the relaxation lower limit if the static deviation mean is dominant, and lowering the indicators of the second dimension matching reference parameters to the relaxation lower limit if the dynamic deviation mean is dominant. This achieves precise matching between the matching standard and the actual carrying capacity of the supply resource pool, effectively solving the matching failure problem caused by the mismatch between the standard and resources. After completing the parameter relaxation adjustment, the supply chain matching process is re-executed, forming a complete closed loop of matching failure, attribution analysis, precise adjustment, and retrying matching. This significantly improves the system's adaptability and fault tolerance in the face of dynamic changes in the supply resource pool. It completely solves the industry pain points of traditional cross-border supply chain matching systems, such as the lack of effective remedial measures after matching failure, the lack of precise attribution basis for parameter adjustment leading to low matching success rate, and insufficient resource utilization. This greatly enhances the practical application stability and scenario adaptability flexibility of the cross-border supply chain intelligent matching and collaborative management system.

[0037] This application also provides a computing device, characterized in that it includes: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the system as described in any one of claims 1 to 8.

[0038] One embodiment of this application also provides a computer-readable storage medium for storing a program, which, when executed by a processor, enables a cross-border supply chain intelligent matching and collaborative management system.

[0039] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0040] This invention is described with reference to flowchart illustrations and / or block diagrams of systems, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0041] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0042] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0043] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0044] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A cross-border supply chain intelligent matching and collaborative management system, characterized in that, This includes a matching parameter acquisition module, a matching dimension adjustment module, and a supply chain matching module. The matching parameter acquisition module is used to acquire demand data from the demand side and supply data from each supply side, and dynamically acquire first-dimensional matching parameters and second-dimensional matching parameters for each cross-border supply chain based on the demand data and supply data. Each cross-border supply chain is an independent supply chain route constructed by the demand side and each supply side based on a point-to-point correspondence. The first-dimensional matching parameter represents the static fit of key nodes in cross-border product transportation, and the second-dimensional matching parameter represents the dynamic fit of key nodes in cross-border product transportation. The matching dimension adjustment module is used to perform dynamic adjustment of the matching dimension based on the transportation strategy driving parameters in the demand data. The dynamic adjustment of the matching dimension means dynamically adjusting the allocation ratio of the dimension weight parameters to adapt to the different emphasis on the static and dynamic efficiency of transportation under different demand scenarios. The dimension weight parameters include the first dimension weight and the second dimension weight. The supply chain matching module is used to perform first-dimensional matching based on the first-dimensional matching parameters of each cross-border supply chain, output each candidate matching supply chain, and perform second-dimensional matching based on the second-dimensional matching parameters of the candidate matching supply chains, output each matching supply chain, and filter to obtain the final cross-border supply chain based on the dynamic adjustment results of the matching dimension weights and the dimension matching results of each matching supply chain. The dimension matching results include the first-dimensional matching results and the second-dimensional matching results.

2. The cross-border supply chain intelligent matching and collaborative management system as described in claim 1, characterized in that, The steps for dynamically obtaining the first-dimensional matching parameters and the second-dimensional matching parameters of each cross-border supply chain based on the demand data and the supply data on the supply side include: Based on the demand data, the target basic parameters on the demand side are obtained. The target basic parameters include, but are not limited to, the basic attributes of the demanded goods, the target warehousing location, the target transportation destination, the target cost range, the target timeliness requirements, and the order priority identifier. Based on the target basic parameters, each supply side is initially screened to obtain each candidate supply side; Each candidate supply side is linked to the demand side on a point-to-point basis to generate a corresponding cross-border supply chain; For each of the aforementioned cross-border supply chains, the corresponding key node network data is extracted, and a first dimension matching parameter is calculated and generated based on the key node network data. The first dimension matching parameter includes network depth matching degree, location matching degree of each key node, and average path matching degree of each key node. For each of the aforementioned cross-border supply chains, the corresponding key node flow data is extracted, and a second-dimensional matching parameter is calculated and generated based on the key node flow data. The second-dimensional matching parameter includes the transportation timeliness matching degree, node connection matching degree, and node collaboration matching degree of each key node.

3. The cross-border supply chain intelligent matching and collaborative management system as described in claim 1, characterized in that, The transportation strategy driving parameters include transportation data granularity, transportation data update frequency, and intensity of collaborative demand. The step of dynamically adjusting the matching dimension based on the transportation strategy-driven parameters in the demand data includes: Obtain preset dimension weight reference parameters, which include a first dimension reference coefficient and a second dimension weight reference coefficient; The transportation strategy driving parameters are compared and their impact is calculated with preset transportation strategy driving reference parameters. Then, the comparison and impact calculation results are weighted and coupled using preset transportation strategy weight parameters to obtain transportation strategy driving impact parameters. The transportation strategy driving reference parameters include granularity benchmark value, update frequency benchmark value and cooperation strength benchmark value. The transportation strategy weight parameters include granularity impact coefficient, update frequency impact coefficient and cooperation strength impact coefficient. According to the transportation strategy-driven impact parameters, a preset weight coefficient adjustment relationship table is queried to obtain the corresponding weight coefficient adjustment ratio. The weight coefficient adjustment relationship table defines the mapping relationship between different ranges of transportation strategy-driven impact parameters and their corresponding weight coefficient adjustment amounts. The weight reference coefficient of the second dimension is processed using the weight coefficient adjustment ratio to obtain the basic coefficient of the second dimension. Then, the basic coefficient of the second dimension is coupled with the reference coefficient of the first dimension to obtain the comprehensive matching basic coefficient. The ratios of the first dimension reference coefficient and the second dimension base coefficient to the comprehensive matching base coefficient are calculated respectively to obtain the adjusted first dimension weight and the adjusted second dimension weight.

4. The cross-border supply chain intelligent matching and collaborative management system as described in claim 1, characterized in that, The step of performing first-dimensional matching based on the first-dimensional matching parameters of each cross-border supply chain and outputting each candidate matching supply chain includes: The first dimension matching parameters of each cross-border supply chain are compared with the preset first dimension matching reference parameters to calculate the impact. Then, the results of the comparison and impact calculation are weighted and coupled using the preset first dimension weight parameters to obtain the first dimension matching parameters of each cross-border supply chain. The first dimension matching reference parameters include network depth matching degree reference, location matching degree reference and path matching degree reference. The first dimension weight parameters include network depth matching degree influence coefficient, location matching degree influence coefficient and path matching degree influence coefficient. The first dimension matching parameter of each cross-border supply chain is compared with the preset first dimension matching threshold. If the first dimension matching parameter of any cross-border supply chain is lower than the first dimension matching threshold, it is marked as a supply chain to be matched. The first dimension matching is performed based on the replacement nodes corresponding to each key node of the supply chain to be matched, and the candidate matching supply chain and the non-candidate matching supply chain are selected. If the first dimension matching parameter of any cross-border supply chain is not lower than the first dimension matching threshold, it is marked as a candidate matching supply chain; Statistics are compiled and output for each candidate matching supply chain.

5. The cross-border supply chain intelligent matching and collaborative management system as described in claim 4, characterized in that, The steps for first-dimensional matching based on the replacement nodes corresponding to each key node in the supply chain to be matched include: If the location matching degree of any key node in the supply chain to be matched is lower than the location matching degree reference value, then obtain the replacement node corresponding to the key node; determine whether the location matching degree of the replacement node reaches the location matching degree reference value, otherwise no additional processing is performed; If the target is reached, determine whether the average path matching degree of the path associated with the replacement node reaches the path matching degree reference value. If it does, replace the key stage with the replacement node; otherwise, no additional processing is performed. Based on the first dimension matching parameters of each supply chain to be matched after replacement, the first dimension matching is re-executed to generate the first dimension matching parameters of each supply chain to be matched after replacement. If the first dimension matching parameter of any supply chain to be matched after replacement is not lower than the first dimension matching parameter, it is marked as a candidate supply chain. If the first dimension matching parameter of any supply chain to be matched after replacement is still lower than the first dimension matching parameter, it is marked as a non-candidate supply chain.

6. The cross-border supply chain intelligent matching and collaborative management system as described in claim 1, characterized in that, The step of performing second-dimensional matching on the candidate matching supply chains based on the second-dimensional matching parameters and outputting each matching supply chain includes: The second-dimensional matching parameters of each candidate matching supply chain are compared with the preset second-dimensional matching reference parameters to calculate their impact. Then, the results of the comparison and impact calculation are weighted and coupled using the preset second-dimensional weight parameters to obtain the second-dimensional matching parameters of each candidate matching supply chain. The second-dimensional matching reference parameters include the reference quantity of transportation timeliness matching degree, the reference quantity of node connection matching degree, and the reference quantity of node collaboration matching degree. The second-dimensional weight parameters include the influence coefficient of transportation timeliness matching degree, the influence coefficient of node connection matching degree, and the influence coefficient of node collaboration matching degree. The second dimension matching parameter of each candidate matching supply chain is compared with the preset second dimension matching threshold. If the second dimension matching parameter of any candidate matching supply chain is lower than the second dimension matching parameter, it is marked as a mismatched supply chain. If the second dimension matching parameter of any candidate matching supply chain is not lower than the second dimension matching parameter, it is marked as a matched supply chain. Statistics are compiled and output for each matching supply chain.

7. The cross-border supply chain intelligent matching and collaborative management system as described in claim 1, characterized in that, The steps for obtaining the final cross-border supply chain based on the dynamic adjustment results of matching dimension weights and the dimension matching results of each matching supply chain include: Based on the adjusted dimensional weight parameters, the first and second dimension matching parameters of each matching supply chain are weighted and coupled to obtain the comprehensive matching parameters of each matching supply chain. Based on the comprehensive matching parameters, the matching supply chains are sorted in reverse order, and the matching supply chain ranked first is marked as a cross-border supply chain to be judged. The comprehensive matching parameters of the cross-border supply chain to be judged are compared with the preset comprehensive matching threshold. If the comprehensive matching parameters of the cross-border supply chain to be judged are lower than the comprehensive matching threshold, a matching anomaly prompt is output, and an adaptive parameter relaxation adjustment mechanism based on matching failure attribution is executed. If the comprehensive matching parameters of the cross-border supply chain to be judged are not lower than the comprehensive matching threshold, the cross-border supply chain to be judged is marked as the final cross-border supply chain.

8. The cross-border supply chain intelligent matching and collaborative management system as described in claim 7, characterized in that, The specific steps for implementing the adaptive parameter relaxation adjustment mechanism based on matching failure attribution include: Obtain a set of historical matching tasks that triggered the matching anomaly prompt within a preset statistical period, and calculate the matching failure rate of the set of historical matching tasks; If the matching failure rate is greater than or equal to the preset failure rate warning threshold, parameter relaxation adjustment is triggered. The average difference between the first dimension matching parameter and the first dimension matching threshold of each cross-border supply chain to be judged in the historical matching task set is calculated and recorded as the static deviation mean, and the average difference between the second dimension matching parameter and the second dimension matching threshold is recorded as the dynamic deviation mean. Based on the mean static deviation and the mean dynamic deviation, the first dimension matching reference parameter and the second dimension matching reference parameter are adjusted by coordinated relaxation: If the mean static deviation is greater than or equal to the mean dynamic deviation, then the network depth matching reference value, the location matching reference value, and the path matching reference value in the first dimension matching reference parameters are respectively lowered to their corresponding relaxation lower limit values. If the mean static deviation is less than the mean dynamic deviation, then the reference values ​​for transportation timeliness matching, node connection matching, and node coordination matching in the second dimension matching reference parameters will be lowered to their corresponding relaxation lower limits. After the reference parameters are adjusted, the supply chain matching process for the current demand data is re-executed based on the updated matching reference parameters.

9. A computing device, characterized in that, include: One or more processors; A storage device for storing one or more programs, which, when executed by one or more processors, cause the one or more processors to implement the system as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program or instructions that, when executed, cause the system according to any one of claims 1 to 8 to be executed.

Images