Supply chain finance intelligent risk control management method and system

Abstract

The invention discloses a supply chain finance intelligent risk control management method and system, and relates to the technical field of risk control management. The method comprises the steps of obtaining supply chain financial multi-modal data in real time through a supply chain financial data perception analysis tool, constructing a virtual-real twin risk perception and conduction simulation center, obtaining an industry risk field domain factor, calculating a cross-domain coupling enterprise risk dynamic score based on the virtual-real twin risk perception and conduction simulation center, and obtaining an industry risk field domain factor. And based on the cross-domain coupling enterprise risk dynamic score, the virtual-real twin risk perception and conduction simulation center and a preset smart contract group, constructing a cross-chain co-processing network, issuing a risk control instruction, and based on historical risk control data, dynamically optimizing and updating the virtual-real twin risk perception and conduction simulation center and the cross-chain co-processing network. According to the method, the overall safety of supply chain financial services can be improved, efficient configuration of industry chain fund elements is promoted, the anti-disturbance capability of an industry chain is improved, and powerful guarantee is provided for high-quality development of entity economy.

Description

Technical Field

[0001] The present invention relates to the field of risk control management technology, and in particular to a supply chain finance intelligent risk control management method and system. Background Art

[0002] Current supply chain finance risk control management faces multi-dimensional technical bottlenecks. On the one hand, traditional risk control relies heavily on single-dimensional capital flow or business flow data, making it difficult to integrate the multimodal data of the four flows of supply chain "business flow, logistics flow, capital flow, and information flow." This leads to data fragmentation and low credibility, making it impossible to fully portray the company's true risk status. This is especially true for enterprise nodes that cooperate across the supply chain, where cross-chain data fragmentation can easily lead to risk monitoring blind spots. On the other hand, existing risk control systems mostly use static risk assessment models, which can only achieve "post-event risk identification." There is a lack of technical solutions that integrate the physical state simulation of digital twins with risk transmission analysis of dynamic graphs, making it difficult to predict risk evolution trends in advance. Risk management in cross-chain scenarios relies on manual coordination among multiple nodes such as banks, core enterprises, and suppliers, resulting in delayed response, low management efficiency, and poor coordination. At the same time, there is a lack of dynamic optimization mechanisms based on historical data, resulting in weak adaptability of risk control models and an inability to adjust assessment and management strategies as supply chain business models change. This makes it difficult to meet the risk control needs of complex supply chain scenarios such as new energy and cross-border trade. Summary of the Invention

[0003] The present invention provides a supply chain finance intelligent risk control management method, comprising: Step S1: Acquire supply chain finance multimodal data in real time through supply chain finance data perception and analysis tools; Step S2: Building a virtual-real twin risk perception and transmission simulation center based on supply chain finance multimodal data; Step S3: Obtain industry risk field factors and calculate cross-domain coupled enterprise risk dynamic scores based on the virtual-real twin risk perception and conduction simulation center; Step S4: Based on the cross-domain coupled enterprise risk dynamic scoring, the virtual-real twin risk perception and transmission simulation center, and the preset smart contract group, a cross-chain collaborative disposal network is constructed to issue risk control instructions; Step S5: Based on historical risk control data, dynamically optimize and update the virtual-real twin risk perception and transmission simulation center and cross-chain collaborative disposal network.

[0004] The intelligent risk control management method for supply chain finance described above, wherein obtaining supply chain finance multimodal data in real time through a supply chain finance data perception and analysis tool, includes the following sub-steps: Step S11: collecting supply chain finance multimodal data in real time through supply chain finance data perception and analysis tools; Step S12: Complete the fragmented data in the supply chain finance multimodal data.

[0005] In the above-mentioned intelligent risk control management method for supply chain finance, building a virtual-real twin risk perception and transmission simulation center based on multimodal data of supply chain finance includes the following sub-steps: Step S21: constructing a digital twin based on supply chain finance multimodal data; Step S22: construct a dual-track dynamic graph based on supply chain finance multimodal data; Step S23: Integrate the digital twin with the dual-track dynamic map to build a virtual-reality twin risk perception and conduction simulation center.

[0006] The intelligent risk control management method for supply chain finance described above, wherein obtaining industry risk domain factors and calculating cross-domain coupled enterprise risk dynamic scores based on a virtual-real twin risk perception and transmission simulation hub, includes the following sub-steps: Step S31: Obtain industry risk field factors based on industry characteristics; Step S32: Calculate the dynamic risk score of cross-domain coupled enterprises based on industry risk field factors and the virtual-real twin risk perception and conduction simulation center.

[0007] The intelligent risk control management method for supply chain finance described above includes the following sub-steps: constructing a cross-chain collaborative disposal network based on cross-domain coupled enterprise risk dynamic scoring, a virtual-real twin risk perception and transmission simulation hub, and a preset smart contract group; and issuing risk control instructions. Step S41: Based on the dynamic risk scoring of cross-domain coupled enterprises, risk prediction is performed through the virtual-real twin risk perception and transmission simulation center to generate risk prediction results; Step S42: Based on the risk prediction results and the preset smart contract group, a cross-chain collaborative disposal network is constructed and risk control instructions are issued.

[0008] The intelligent risk control management method for supply chain finance described above, wherein dynamically optimizing and updating the virtual-real twin risk perception and transmission simulation center and the cross-chain collaborative disposal network based on historical risk control data, includes the following sub-steps: Step S51: Generate a historical risk control database based on historical risk control data and real-time feedback data; Step S52: Based on the historical risk control database, dynamically optimize and update the virtual-real twin risk perception and transmission simulation center and the cross-chain collaborative disposal network.

[0009] The present invention also provides a supply chain finance intelligent risk control management system, comprising: Supply chain finance multimodal data acquisition module, which acquires supply chain finance multimodal data in real time through supply chain finance data perception and analysis tools; The central construction module builds a virtual-real twin risk perception and transmission simulation center based on the multimodal data of supply chain finance; The cross-domain coupled enterprise risk dynamic scoring module obtains industry risk field factors and calculates the cross-domain coupled enterprise risk dynamic scoring based on the virtual-real twin risk perception and transmission simulation center; The intelligent risk control module builds a cross-chain collaborative disposal network and issues risk control instructions based on cross-domain coupled enterprise risk dynamic scoring, virtual and real twin risk perception and transmission simulation center, and preset smart contract groups; The central network optimization module dynamically optimizes and updates the virtual-real twin risk perception and transmission simulation center and cross-chain collaborative disposal network based on historical risk control data.

[0010] In the above-mentioned intelligent risk control management system for supply chain finance, the supply chain finance multimodal data acquisition module specifically includes: The data collection submodule collects supply chain finance multimodal data in real time through supply chain finance data perception and analysis tools; The data completion submodule completes the fragmented data in the multimodal data of supply chain finance.

[0011] In the above-mentioned intelligent risk control management system for supply chain finance, the central building module specifically includes: The digital twin construction submodule builds a digital twin based on supply chain finance multimodal data; The dual-track system dynamic map construction submodule builds a dual-track system dynamic map based on supply chain finance multimodal data; The sub-module of the virtual-reality twin risk perception and transmission simulation center is constructed to integrate the digital twin with the dual-track dynamic map to build the virtual-reality twin risk perception and transmission simulation center.

[0012] The intelligent risk control management system for supply chain finance described above, wherein the cross-domain coupled enterprise risk dynamic scoring module specifically includes: Acquisition of industry risk field factors: based on industry characteristics, acquisition of industry risk field factors; The scoring calculation sub-module calculates the dynamic risk score of cross-domain coupled enterprises based on industry risk field factors and the virtual-real twin risk perception and transmission simulation center.

[0013] In the above-mentioned intelligent risk control management system for supply chain finance, the intelligent risk control module specifically includes: The risk prediction result generation submodule, based on the cross-domain coupled enterprise risk dynamic scoring, conducts risk prediction through the virtual-real twin risk perception and transmission simulation center to generate risk prediction results; The instruction issuance sub-module builds a cross-chain collaborative disposal network based on risk prediction results and preset smart contract groups to issue risk control instructions.

[0014] In the above-mentioned intelligent risk control management system for supply chain finance, the central network optimization module specifically includes: The historical risk control database generation submodule generates a historical risk control database based on historical risk control data and real-time feedback data; Optimize and update sub-modules, based on the historical risk control database, dynamically optimize and update the virtual and real twin risk perception and transmission simulation center and cross-chain collaborative disposal network.

[0015] The beneficial effects achieved by the present invention are as follows: the present invention can break the data barriers and static assessment limitations of traditional risk control, realize the upgrade of risk control mode from "post-risk remediation" to "pre-prediction and in-process intervention", reduce the credit risk and operational risk incidence rate of the entire industry, and improve the overall security of supply chain financial business; simplify the collaborative process of multiple parties such as banks, core enterprises, small and medium-sized suppliers, shorten the risk disposal response time, improve the efficiency of supply chain capital circulation, help solve the financing difficulties and slow financing problems of small and micro enterprises, and promote the efficient allocation of capital elements in the industrial chain; can adapt to the supply chain characteristics of different sub-sectors such as new energy, cross-border trade, and high-end manufacturing, enhance the universality and flexibility of industry risk control, and provide key support for the digital transformation of the industrial chain; reduce the risk of industrial chain rupture caused by local risk transmission, enhance the anti-disturbance ability of regional and even national industrial chains, and provide strong guarantees for the high-quality development of the real economy. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments described in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0017] Figure 1 This is a flow chart of a supply chain finance intelligent risk control management method provided in Example 1 of this application; Figure 2 This is a schematic diagram of a supply chain finance intelligent risk control management system provided in Example 2 of this application. DETAILED DESCRIPTION

[0018] The following is a clear and complete description of the technical solutions in the embodiments of the present invention, in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0019] Example 1 like Figure 1 As shown, the first embodiment of the present application provides a supply chain finance intelligent risk control management method, which includes the following steps: Step S1: Acquire supply chain finance multimodal data in real time through supply chain finance data perception and analysis tools; Furthermore, obtaining supply chain finance multimodal data in real time through supply chain finance data perception and analysis tools includes the following sub-steps: Step S11: collecting supply chain finance multimodal data in real time through supply chain finance data perception and analysis tools; Specifically, supply chain finance data perception and analysis tools such as IoT sensor devices, multi-source system interfaces, intelligent natural language processing tools, and blockchain oracles are used to collect supply chain finance multimodal data from core enterprises, upstream and downstream enterprises, financial institutions' payment systems, and government platforms in real time. Supply chain finance multimodal data includes business flow data, logistics data, capital flow data, and information flow data. Business flow data such as transaction amounts, payment periods, and performance requirements are collected through intelligent natural language processing tools. Real-time logistics data such as freight tracks, warehouse entry and exit records, and cargo status are collected through IoT sensor devices. Capital flow data such as corporate capital flow and account details are obtained through the financial institution payment system interface and verified in combination with blockchain oracles to verify the authenticity of capital transactions. Information flow data such as corporate tax records, credit ratings, and industry policy changes are collected through the government platform.

[0020] Step S12: completing the fragmented data in the supply chain finance multimodal data; Specifically, based on the complete data from each node in the multimodal data of supply chain finance, fragmented data on business flow, logistics, capital flow, and information flow is supplemented through integration and derivation techniques. For example, the start and end timestamps of the logistics chain, the prepayment payment nodes of the capital chain, and the customs clearance records of the high-speed port of the government chain are integrated. Through spatiotemporal interpolation and outlier correction models, discrete positioning points are supplemented into continuous transportation paths, synchronously correlating time series features to fill in the fragmented data in the logistics field. Network parsing fuzzy representations are reconstructed through intelligent natural language processing tools, combined with the industry general terms library and historical payment records of the capital chain, and mapped into structured parameters to supplement the fragmented contract data in the business flow field. Based on the agreed amount of the business flow contract and the freight frequency of the logistics chain, a complete capital flow ledger is derived to supplement the fragmented flow data in the capital flow field. All supplemented data is subjected to multi-chain hash verification through blockchain oracles to ensure the authenticity and credibility of the supplemented results, forming spatiotemporally continuous and logically self-consistent multimodal data of supply chain finance.

[0021] Step S2: Building a virtual-real twin risk perception and transmission simulation center based on supply chain finance multimodal data; Furthermore, building a virtual-real twin risk perception and transmission simulation center based on supply chain finance multimodal data includes the following sub-steps: Step S21: constructing a digital twin based on supply chain finance multimodal data; Specifically, physical status data such as logistics trajectory, warehouse inventory, production equipment status, and funds are extracted from the multimodal data of supply chain finance. Based on the physical status data, a digital twin with a one-to-one mapping with the real supply chain finance is built through a three-dimensional visualization engine. A physical rule engine is embedded in the digital twin to perform real-time mapping of the physical status and physical scene simulation.

[0022] Step S22: construct a dual-track dynamic graph based on supply chain finance multimodal data; Specifically, the dual-track dynamic map includes a hierarchical risk map and a cross-chain association map. The hierarchical risk map is constructed by extracting association data such as transaction relationships, capital transactions, and cross-chain cooperation records from the multimodal data of supply chain finance. Based on the association data, the supply chain enterprise level is divided, and the cross-domain credit penetration formula is used to calculate the risk level of the enterprise. Calculate the credit transmission coefficient of each level, where: For the Tier Enterprise The hierarchical credit transmission coefficient at the moment, The value range is , is the number of levels, For the Initial credit transmission benchmark value for hierarchical enterprises, is the number of core data domains, The value range is , For the The credit penetration weight coefficient of each data domain, For the Tier Enterprise Moment Real-time data indicators for each data domain, For the Industry average data indicators for each data domain, For the The industry data standards of each data domain are different. is the level credit transmission attenuation coefficient, For the Tier Enterprise The hierarchical credit transmission coefficient at each moment is used to draw a hierarchical risk map based on the supply chain enterprise level and the credit transmission coefficient of each level.

[0023] The cross-chain association graph is constructed by identifying the enterprise nodes of cross-supply chain cooperation based on the association relationship data, and Calculate the cross-chain risk transmission value of each cross-chain cooperative enterprise, where: For Moment Enterprise nodes from the source supply chain Towards target supply chain The cross-chain risk transmission value, The value range is , is the number of enterprise nodes, is the transaction coupling strength weight, For Moment Enterprise nodes and source supply chains The transaction amount, For Moment The total transaction amount of enterprise nodes, is the capital coupling intensity weight, For Moment Enterprise nodes from the source supply chain The flow of funds received, For Moment The total capital flow of enterprise nodes, is the cooperative coupling strength weight, For Moment Enterprise nodes and source supply chains business collaboration, For Shikeyuan Supply Chain Real-time risk index, is the correlation attenuation coefficient, For the Enterprise nodes and target supply chains The correlation distance, Target supply chain Maximum level distance.

[0024] Mark cross-chain transmission risks based on cross-chain risk transmission values ​​and draw risk association networks across supply chains; Step S23: Fusing the digital twin with the dual-track dynamic map to build a virtual-real twin risk perception and transmission simulation center; Specifically, the digital twin and the dual-track dynamic map are connected through the virtual-real mapping resonance formula To integrate and build a virtual and real risk perception and transmission simulation center, for A constant virtual and real risk perception and transmission simulation center, is the physical state weight coefficient, Digital Twin The physical state vector at time , It is the industry average physical state benchmark value, is the association weight coefficient, is the number of levels, is the number of enterprise nodes, is the hierarchical risk map perception coefficient, For the Tier Enterprise The hierarchical credit transmission coefficient at the moment, is the cross-chain association graph perception coefficient, For Moment Enterprise nodes from the source supply chain Towards target supply chain The cross-chain risk transmission value, is the virtual and real resonance coefficient, Predict physical state values ​​for spectra derivation.

[0025] Step S3: Obtain industry risk field factors and calculate cross-domain coupled enterprise risk dynamic scores based on the virtual-real twin risk perception and conduction simulation center; Furthermore, obtaining industry risk domain factors and calculating the cross-domain coupled enterprise risk dynamic score based on the virtual-real twin risk perception and transmission simulation center includes the following sub-steps: Step S31: Obtain industry risk field factors based on industry characteristics; Specifically, based on industry characteristics, industry risk factors are collected through government platforms, commodity trading platforms, industry association databases and other channels. Industry risk field factors are screened from industry risk factors based on factors such as the impact scope and impact intensity of each industry risk factor.

[0026] Step S32: Calculate the dynamic risk score of cross-domain coupled enterprises based on the industry risk field factors and the virtual-real twin risk perception and transmission simulation center; Specifically, the industry risk field factors are standardized, and weights are assigned to the industry risk field factors based on the sub-sectors to which the supply chain enterprises belong. Risk characteristics are extracted from the virtual and real twin risk perception and transmission simulation center. Based on the industry risk field factors and their weights and risk characteristics, a cross-domain coupling enterprise risk dynamic scoring formula is used. Calculate the cross-domain coupling enterprise risk dynamic score of each enterprise, where: For the Enterprises Dynamic scoring of cross-domain coupled enterprise risks at all times, is the weight of the industry risk field factor, is the number of industry risk field factors, The value range is , For the The distribution coefficient of the risk field factor of the same industry, For the Industry-related risk factors The real-time value at the moment, For the Industry safety thresholds for industry-related risk field factors, For the The industry volatility standard deviation of the industry-like risk field factor, is the central feature weight, It is a simulation center for the perception and transmission of virtual and real risks. The risk characteristic value at the moment, It is a simulation center for the perception and transmission of virtual and real risks. The theoretical maximum risk characteristic value at the moment, is the time decay coefficient.

[0027] Step S4: Based on the cross-domain coupled enterprise risk dynamic scoring, the virtual-real twin risk perception and transmission simulation center, and the preset smart contract group, a cross-chain collaborative disposal network is constructed to issue risk control instructions; Furthermore, based on the cross-domain coupled enterprise risk dynamic scoring, the virtual-real twin risk perception and transmission simulation center, and the preset smart contract group, a cross-chain collaborative disposal network is constructed. The issuance of risk control instructions includes the following sub-steps: Step S41: Based on the dynamic risk scoring of cross-domain coupled enterprises, risk prediction is performed through the virtual-real twin risk perception and transmission simulation center to generate risk prediction results; Specifically, based on the dynamic scoring of cross-domain coupled enterprise risks, preset extreme scenario parameters are generated, and the physical state evolution and risk transmission process of supply chain finance are simulated through the virtual-real twin risk perception and transmission simulation center to generate risk prediction results in multiple time dimensions, mark key risk transmission paths, and simultaneously output risk probability distribution.

[0028] Step S42: Based on the risk prediction results and the preset smart contract group, a cross-chain collaborative disposal network is constructed and risk control instructions are issued; Specifically, based on the risk prediction results, the corresponding smart response contract package is called from the preset smart contract group to extract key execution parameters; the supply chain finance participant nodes are automatically identified, and operation permissions are assigned to each node based on the permission rules in the smart response contract package to build a cross-chain collaborative disposal network; differentiated disposal rules are formulated based on the risk prediction results, and the differentiated disposal rules are integrated with the key execution parameters to generate an executable risk control instruction set, which is pushed to each node through the cross-chain collaborative disposal network. After each node executes the instruction, the execution result with a digital signature and timestamp is transmitted back to the virtual-reality twin risk perception and transmission simulation center. The center verifies the consistency through multi-node result hash comparison, updates the disposal status of the cross-chain collaborative disposal network, and packages the full process data for evidence storage in the alliance chain.

[0029] Step S5: Based on historical risk control data, dynamically optimize and update the virtual-real twin risk perception and transmission simulation center and the cross-chain collaborative disposal network; Furthermore, based on historical risk control data, the dynamic optimization and updating of the virtual-real twin risk perception and transmission simulation center and the cross-chain collaborative disposal network includes the following sub-steps: Step S51: Generate a historical risk control database based on historical risk control data and real-time feedback data; Specifically, historical data and real-time feedback data are extracted from the virtual-reality twin risk perception and transmission simulation center and the cross-chain collaborative disposal network, and the data are labeled according to data type, risk scenario, and disposal effect to build a historical risk control database.

[0030] Step S52: Based on the historical risk control database, dynamically optimize and update the virtual-real twin risk perception and transmission simulation center and the cross-chain collaborative disposal network; Specifically, based on the historical physical data in the historical risk control database, the physical rule engine in the virtual-reality twin risk perception and transmission simulation center is dynamically optimized and updated; based on the historical correlation data in the historical risk control database, the dual-track dynamic map in the virtual-reality twin risk perception and transmission simulation center is dynamically optimized and updated; based on the historical risk control database, the historical instruction execution efficiency and node response timeliness are analyzed, the triggering threshold and terms and conditions of the smart contract group are optimized, and the cross-chain collaborative disposal network parameters are dynamically optimized and updated.

[0031] Example 2 like Figure 2 As shown, the second embodiment of the present application provides a supply chain finance intelligent risk control management system, including: Supply chain finance multimodal data acquisition module 21, which acquires supply chain finance multimodal data in real time through supply chain finance data perception and analysis tools; Furthermore, the supply chain finance multimodal data acquisition module 21 includes the following submodules: The data collection submodule 211 collects supply chain finance multimodal data in real time through a supply chain finance data perception and analysis tool; The data completion submodule 212 completes the fragmented data in the supply chain finance multimodal data; Central construction module 22: constructs a virtual-real twin risk perception and transmission simulation center based on supply chain finance multimodal data; Furthermore, the central construction module 22 includes the following submodules: A digital twin construction submodule 221 constructs a digital twin based on supply chain finance multimodal data; A dual-track system dynamic map construction submodule 222 is used to construct a dual-track system dynamic map based on supply chain finance multimodal data; The virtual-real twin risk perception and transmission simulation center construction submodule 223 integrates the digital twin with the dual-track dynamic map to construct the virtual-real twin risk perception and transmission simulation center; The cross-domain coupling enterprise risk dynamic scoring module 23 obtains industry risk field factors and calculates the cross-domain coupling enterprise risk dynamic scoring based on the virtual-real twin risk perception and transmission simulation center; Furthermore, the cross-domain coupled enterprise risk dynamic scoring module 23 includes the following submodules: Industry risk field factor acquisition 231, based on industry characteristics, obtain industry risk field factors; The scoring calculation submodule 232 calculates the dynamic risk score of cross-domain coupled enterprises based on the industry risk field factors and the virtual-real twin risk perception and transmission simulation center; Intelligent risk control module 24, based on cross-domain coupled enterprise risk dynamic scoring, virtual and real twin risk perception and transmission simulation center and preset smart contract group, builds a cross-chain collaborative disposal network and issues risk control instructions; Furthermore, the intelligent risk control module 24 includes the following submodules: The risk prediction result generation submodule 241 performs risk prediction based on the cross-domain coupled enterprise risk dynamic scoring through the virtual-real twin risk perception and transmission simulation center to generate risk prediction results; The instruction issuing submodule 242 builds a cross-chain collaborative disposal network based on the risk prediction results and the preset smart contract group to issue risk control instructions; Central network optimization module 25, based on historical risk control data, dynamically optimizes and updates the virtual and real twin risk perception and transmission simulation center and cross-chain collaborative disposal network; Furthermore, the central network optimization module 25 includes the following submodules: The historical risk control database generation submodule 251 generates a historical risk control database based on the historical risk control data and the real-time feedback data; Optimize and update submodule 252, based on the historical risk control database, dynamically optimize and update the virtual and real twin risk perception and transmission simulation center and cross-chain collaborative disposal network; Corresponding to the above embodiment, an embodiment of the present invention provides a computer storage medium, comprising: at least one memory and at least one processor; The memory is used to store one or more program instructions; A processor is used to run one or more program instructions to execute a supply chain finance intelligent risk control management method.

[0032] Corresponding to the above embodiments, an embodiment of the present invention provides a computer-readable storage medium, which contains one or more program instructions, and the one or more program instructions are used by the processor to provide a supply chain financial intelligent risk control management method.

[0033] The embodiments disclosed in the present invention provide a computer-readable storage medium, in which computer program instructions are stored. When the computer program instructions are executed on a computer, the computer executes the above-mentioned supply chain financial intelligent risk control management method.

[0034] In the embodiments of the present invention, the processor may be an integrated circuit chip having signal processing capabilities. The processor may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0035] The methods, steps, and logic diagrams disclosed in the embodiments of the present invention can be implemented or executed. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of the present invention can be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules within the decoding processor. The software modules can be located in a storage medium well-established in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. The processor reads the information from the storage medium and, in conjunction with its hardware, completes the steps of the aforementioned methods.

[0036] The storage medium may be a memory and may be, for example, a volatile memory or a nonvolatile memory, or may include both volatile and nonvolatile memory.

[0037] Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory.

[0038] Volatile memory may be random access memory (RAM), which is used as an external cache memory. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM bus random access memory (DRRAM).

[0039] The storage media described in the embodiments of the present invention are intended to include, but are not limited to, these and any other suitable types of memory.

[0040] Those skilled in the art will appreciate that in one or more of the above examples, the functions described herein can be implemented using a combination of hardware and software. When software is used, the corresponding functions can be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein communication media includes any medium that facilitates the transmission of computer programs from one place to another. The storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0041] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent replacements, improvements, etc. made on the basis of the technical solution of the present invention should be included in the scope of protection of the present invention.

Claims

1. A supply chain finance intelligent risk control management method, characterized by: include: Step S1: Acquire supply chain finance multimodal data in real time through supply chain finance data perception and analysis tools; Step S2: Building a virtual-real twin risk perception and transmission simulation center based on supply chain finance multimodal data; Step S3: Obtain industry risk field factors and calculate cross-domain coupled enterprise risk dynamic scores based on the virtual-real twin risk perception and conduction simulation center; Step S4: Based on the cross-domain coupled enterprise risk dynamic scoring, the virtual-real twin risk perception and transmission simulation center, and the preset smart contract group, a cross-chain collaborative disposal network is constructed to issue risk control instructions; Step S5: Based on historical risk control data, dynamically optimize and update the virtual-real twin risk perception and transmission simulation center and cross-chain collaborative disposal network.

2. A supply chain finance intelligent risk management method according to claim 1, characterized in that: Acquiring supply chain finance multimodal data in real time through supply chain finance data perception and analysis tools includes the following sub-steps: Step S11: collecting supply chain finance multimodal data in real time through supply chain finance data perception and analysis tools; Step S12: Complete the fragmented data in the supply chain finance multimodal data.

3. The intelligent risk management method for supply chain finance according to claim 1, characterized in that: Building a virtual-real twin risk perception and transmission simulation center based on supply chain finance multimodal data includes the following sub-steps: Step S21: constructing a digital twin based on supply chain finance multimodal data; Step S22: constructing a dual-track dynamic graph based on supply chain finance multimodal data; Step S23: Integrate the digital twin with the dual-track dynamic map to build a virtual-reality twin risk perception and conduction simulation center.

4. The intelligent risk management method for supply chain finance according to claim 1, characterized in that: Obtaining industry risk domain factors and calculating cross-domain coupled enterprise risk dynamic scores based on the virtual-real twin risk perception and transmission simulation center includes the following sub-steps: Step S31: Obtain industry risk field factors based on industry characteristics; Step S32: Calculate the dynamic risk score of cross-domain coupled enterprises based on industry risk field factors and the virtual-real twin risk perception and conduction simulation center.

5. The intelligent risk management method for supply chain finance according to claim 1, characterized in that: Based on the cross-domain coupled enterprise risk dynamic scoring, virtual-real twin risk perception and transmission simulation center and preset smart contract group, a cross-chain collaborative disposal network is built. The issuance of risk control instructions includes the following sub-steps: Step S41: Based on the dynamic risk scoring of cross-domain coupled enterprises, risk prediction is performed through the virtual-real twin risk perception and transmission simulation center to generate risk prediction results; Step S42: Based on the risk prediction results and the preset smart contract group, a cross-chain collaborative disposal network is constructed and risk control instructions are issued.

6. A supply chain finance intelligent risk control management system, characterized by: include: Supply chain finance multimodal data acquisition module, which acquires supply chain finance multimodal data in real time through supply chain finance data perception and analysis tools; The central construction module builds a virtual-real twin risk perception and transmission simulation center based on the multimodal data of supply chain finance; The cross-domain coupled enterprise risk dynamic scoring module obtains industry risk field factors and calculates the cross-domain coupled enterprise risk dynamic scoring based on the virtual-real twin risk perception and transmission simulation center; The intelligent risk control module builds a cross-chain collaborative disposal network and issues risk control instructions based on cross-domain coupled enterprise risk dynamic scoring, virtual and real twin risk perception and transmission simulation center, and preset smart contract groups; The central network optimization module dynamically optimizes and updates the virtual-real twin risk perception and transmission simulation center and cross-chain collaborative disposal network based on historical risk control data.

7. A supply chain finance intelligent risk control management system according to claim 6, characterized in that: Supply chain finance multimodal data acquisition module, specifically including: The data collection submodule collects supply chain finance multimodal data in real time through supply chain finance data perception and analysis tools; The data completion submodule completes the fragmented data in the multimodal data of supply chain finance.

8. The intelligent risk control management system for supply chain finance according to claim 6, characterized in that: Central building blocks include: The digital twin construction submodule builds a digital twin based on supply chain finance multimodal data; The dual-track system dynamic map construction submodule builds a dual-track system dynamic map based on supply chain finance multimodal data; The sub-module of the virtual-reality twin risk perception and transmission simulation center is constructed to integrate the digital twin with the dual-track dynamic map to build the virtual-reality twin risk perception and transmission simulation center.

9. The intelligent risk control management system for supply chain finance according to claim 6, characterized in that: Cross-domain coupled enterprise risk dynamic scoring module, specifically including: Acquisition of industry risk field factors: based on industry characteristics, acquisition of industry risk field factors; The scoring calculation sub-module calculates the dynamic risk score of cross-domain coupled enterprises based on industry risk field factors and the virtual-real twin risk perception and transmission simulation center.

10. The intelligent risk control management system for supply chain finance according to claim 6, characterized in that: Intelligent risk control module, specifically including: The risk prediction result generation submodule, based on the cross-domain coupled enterprise risk dynamic scoring, conducts risk prediction through the virtual-real twin risk perception and transmission simulation center to generate risk prediction results; The instruction issuance sub-module builds a cross-chain collaborative disposal network based on risk prediction results and preset smart contract groups to issue risk control instructions.

Images