Financial supply chain risk identification method, device, equipment and medium

Abstract

The application discloses a financial supply chain risk identification method and device, equipment and medium, and relates to the field of information technology. The method comprises the following steps: acquiring multi-source heterogeneous data corresponding to a financial supply chain; determining risk features based on the multi-source heterogeneous data; aligning the risk features to obtain standardized entities and standardized relationships; constructing a risk knowledge graph based on the standardized entities and the standardized relationships, wherein the risk knowledge graph at least comprises the following nodes: an enterprise entity node, a contract flow node, a cargo flow node, a bill flow node and a fund flow node; and identifying risks of the financial supply chain based on the risk knowledge graph. In this way, the risk identification efficiency is improved.

Description

Technical Field

[0001] This application relates to the field of information technology, and in particular to a method, apparatus, equipment and medium for identifying financial supply chain risks. Background Technology

[0002] Commodity supply chain finance is characterized by large transaction amounts, numerous participants, long trade chains, and volatile commodity prices. Many SMEs often face cash flow difficulties, and platforms provide financing services to SMEs within the supply chain. Before providing financing services, SMEs need to prove the authenticity of their business transactions. However, proving the authenticity of business transactions often relies on a large number of documents such as contracts, VAT invoices, and bank statements. These documents are from diverse sources and have different formats, making manual verification inefficient, prone to omissions, and difficult to detect inconsistencies between documents. Summary of the Invention

[0003] The purpose of this application is to provide a method, apparatus, equipment, and medium for identifying financial supply chain risks, so as to improve the efficiency of risk identification.

[0004] To achieve the above objectives, this application provides the following solution: Firstly, this application provides a method for identifying financial supply chain risks, including: Acquire multi-source heterogeneous data corresponding to the financial supply chain; Risk characteristics are determined based on multi-source heterogeneous data; Aligning risk characteristics yields standardized entities and standardized relationships; A risk knowledge graph is constructed based on standardized entities and standardized relationships. The risk knowledge graph includes at least the following nodes: enterprise entity nodes, contract flow nodes, goods flow nodes, bill flow nodes, and capital flow nodes. Risk identification in the financial supply chain based on risk knowledge graph.

[0005] In one optional embodiment, risk identification in the financial supply chain based on a risk knowledge graph includes: Based on risk knowledge graphs, identify whether the financial supply chain exhibits at least one of the following anomalies: There are mismatches in risk characteristics, missing risk characteristics, and temporal contradictions among risk characteristics.

[0006] In one optional embodiment, risk identification in the financial supply chain based on a risk knowledge graph includes: Directed loop detection is performed on the financial supply chain based on risk knowledge graph to obtain a closed loop; Determine whether there are related parties among the enterprises in the closed loop, whether there is a real flow of goods between the enterprises, and whether the transaction prices between the enterprises deviate from the market price. If the companies in the closed loop are related, there is no actual flow of goods between them, and the transaction prices between them deviate from market prices, then the supply chain is identified as having financing trade risks.

[0007] In one optional embodiment, risk identification in the financial supply chain based on a risk knowledge graph includes: Identify the risk of double pledging in the financial supply chain based on risk knowledge graphs.

[0008] In one optional embodiment, the financial supply chain risk identification method further includes: Obtain real-time market prices, quantities, discount rates, and financing balances of the pledged assets; The pledge ratio is determined based on the real-time market price of the pledged assets, the quantity of the pledged assets, the discount factor, and the outstanding financing balance. If the pledge ratio exceeds the preset pledge ratio threshold, it is determined that there is a pledge ratio risk in the financial supply chain.

[0009] In one optional embodiment, the financial supply chain risk identification method further includes: To obtain the price fluctuation amount of a commodity; If the price fluctuation of a commodity exceeds a preset price fluctuation threshold, all companies holding the commodity will be identified in the risk knowledge graph. The direct exposure loss of each firm holding the goods is determined based on the quantity of goods held by the firm and the price fluctuation of the goods. The weight of inter-enterprise transmission is determined based on the proportion of inter-enterprise transaction volume. Determine the transmission exposure loss of each firm based on the inter-firm transmission weight. The sum of direct exposure loss and transmitted exposure loss is determined as the firm's total exposure loss, which is used to quantify the impact of market price fluctuations on the firm.

[0010] In one optional embodiment, the financial supply chain risk identification method further includes: Determine the network centrality and bridging centrality of enterprises based on risk knowledge graphs; Determine an enterprise's network importance score based on network centrality and bridging centrality; The product of the network importance score and the total exposure loss is determined as the risk amplification effect value; Target risk companies are identified based on the risk amplification effect value.

[0011] Secondly, this application provides a financial supply chain risk identification device, comprising: The acquisition module is used to acquire multi-source heterogeneous data corresponding to the financial supply chain; The determination module is used to identify risk characteristics based on multi-source heterogeneous data; The alignment module is used to align risk features to obtain standardized entities and standardized relationships; The module is used to build a risk knowledge graph based on standardized entities and standardized relationships. The risk knowledge graph includes at least the following nodes: enterprise entity nodes, contract flow nodes, goods flow nodes, bill flow nodes, and capital flow nodes. The risk identification module is used to identify risks in the financial supply chain based on a risk knowledge graph.

[0012] In one optional embodiment, the risk identification module is used for: Based on risk knowledge graphs, identify whether the financial supply chain exhibits at least one of the following anomalies: There are mismatches in risk characteristics, missing risk characteristics, and temporal contradictions among risk characteristics.

[0013] In one optional embodiment, the risk identification module is used for: Directed loop detection is performed on the financial supply chain based on risk knowledge graph to obtain a closed loop; Determine whether there are related parties among the enterprises in the closed loop, whether there is a real flow of goods between the enterprises, and whether the transaction prices between the enterprises deviate from the market price. If there are related parties among the enterprises in the closed loop, no real goods are transferred between the enterprises, and the transaction prices between the enterprises deviate from the market price, then the supply chain is identified as having financing trade risks.

[0014] In one optional embodiment, the risk identification module is used for: Identify the risk of double pledging in the financial supply chain based on risk knowledge graphs.

[0015] In an optional embodiment, the financial supply chain risk identification device further includes a module for performing the following operations: Obtain real-time market prices, quantities, discount rates, and financing balances of the pledged assets; The pledge ratio is determined based on the real-time market price of the pledged assets, the quantity of the pledged assets, the discount factor, and the outstanding financing balance. If the pledge ratio exceeds the preset pledge ratio threshold, it is determined that there is a pledge ratio risk in the financial supply chain.

[0016] In an optional embodiment, the financial supply chain risk identification device further includes a module for performing the following operations: To obtain the price fluctuation amount of a commodity; If the price fluctuation of a commodity exceeds a preset price fluctuation threshold, all companies holding the commodity will be identified in the risk knowledge graph. The direct exposure loss of each firm holding the goods is determined based on the quantity of goods held by the firm and the price fluctuation of the goods. The weight of inter-enterprise transmission is determined based on the proportion of inter-enterprise transaction volume. Determine the transmission exposure loss of each firm based on the inter-firm transmission weight. The sum of direct exposure loss and transmitted exposure loss is determined as the firm's total exposure loss, which is used to quantify the impact of market price fluctuations on the firm.

[0017] In an optional embodiment, the financial supply chain risk identification device further includes a module for performing the following operations: Determine the network centrality and bridging centrality of enterprises based on risk knowledge graphs; Determine an enterprise's network importance score based on network centrality and bridging centrality; The product of the network importance score and the total exposure loss is determined as the risk amplification effect value; Target risk companies are identified based on the risk amplification effect value.

[0018] Thirdly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the financial supply chain risk identification method described above.

[0019] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the financial supply chain risk identification method described above.

[0020] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the financial supply chain risk identification method described above.

[0021] According to the specific embodiments provided in this application, the following technical effects are disclosed: This application provides a method, apparatus, equipment, and medium for identifying risks in the financial supply chain. It acquires multi-source heterogeneous data corresponding to the financial supply chain; determines risk characteristics based on the multi-source heterogeneous data; aligns the risk characteristics to obtain standardized entities and standardized relationships; constructs a risk knowledge graph based on the standardized entities and standardized relationships, the risk knowledge graph including at least the following nodes: enterprise entity nodes, contract flow nodes, goods flow nodes, document flow nodes, and capital flow nodes; and identifies risks in the financial supply chain based on the risk knowledge graph. By centralizing documents with heterogeneous formats and dispersed sources, modeling based on document-level elements, and performing risk identification based on the constructed risk knowledge graph, the efficiency of risk identification is improved. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a diagram illustrating the application environment of a financial supply chain risk identification method according to an embodiment of this application. Figure 2 A flowchart illustrating a financial supply chain risk identification method provided in an embodiment of this application; Figure 3 A functional module diagram of a financial supply chain risk identification device provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0024] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0025] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0026] The financial supply chain risk identification method provided in this application embodiment can be applied to, for example, Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be set up independently, integrated into server 104, or placed in the cloud or on other servers. Terminal 102 can send multi-source heterogeneous data corresponding to the financial supply chain to server 104. After receiving the multi-source heterogeneous data, server 104 determines risk characteristics based on the multi-source heterogeneous data; aligns the risk characteristics to obtain standardized entities and standardized relationships; constructs a risk knowledge graph based on the standardized entities and standardized relationships, the risk knowledge graph including at least the following nodes: enterprise entity nodes, contract flow nodes, goods flow nodes, bill flow nodes, and capital flow nodes; and identifies risks in the financial supply chain based on the risk knowledge graph. Server 104 can feed back the risk identification results obtained after risk identification to terminal 102. In addition, in some embodiments, the financial supply chain risk identification method can also be implemented by the server 104 or the terminal 102 separately. For example, the terminal 102 can directly identify risks based on the multi-source heterogeneous data corresponding to the financial supply chain, or the server 104 can obtain the multi-source heterogeneous data corresponding to the financial supply chain from the data storage system and identify risks based on the multi-source heterogeneous data corresponding to the financial supply chain.

[0027] The terminal 102 can be, but is not limited to, various desktop computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, and smart in-vehicle devices. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted devices. The server 104 can be implemented using a standalone server or a server cluster composed of multiple servers, or it can be a cloud server.

[0028] In one exemplary embodiment, such as Figure 2 As shown, a method for identifying financial supply chain risks is provided. This method is executed by computer equipment, specifically by a terminal or server alone, or by both a terminal and a server. In this embodiment, the method is applied to... Figure 1 Taking server 104 as an example, the explanation includes the following steps S201 to S205. Wherein: Step S201: Obtain multi-source heterogeneous data corresponding to the financial supply chain.

[0029] In one optional embodiment, multi-source heterogeneous data is categorized into the following types: contracts, goods, bills of exchange, funds, and intelligence. Contract data includes purchase and sale contracts, framework agreements, and supplementary agreements, which are unstructured data. Goods data includes bills of lading, warehouse receipts, inbound and outbound slips, quality inspection reports, logistics tracking data, and weighbridge slips, which are typically semi-structured and unstructured data. Bills of exchange data includes VAT invoices, drafts, and bank acceptances, which are semi-structured data. Funds data includes bank statements, payment vouchers, and margin records, which are structured time-series data. Intelligence data includes corporate sentiment, industry policies, and market announcements, which are unstructured data.

[0030] Step S202: Determine risk characteristics based on multi-source heterogeneous data.

[0031] In one optional embodiment, after acquiring the multi-source heterogeneous data corresponding to the supply chain, the method further includes: Layout analysis and text recognition are performed on multi-source heterogeneous data to obtain text blocks with location information.

[0032] Accordingly, risk characteristics are determined based on multi-source heterogeneous data, including: By inputting text blocks containing location information into a pre-built large language model, risk features are obtained.

[0033] It should be noted that the pre-built large language model used in this application is a general large language model that has already been trained in the prior art, and no additional training is required for this application.

[0034] In one specific embodiment, the risk characteristics include at least one of the following fields: document type, contract number, buyer and seller, product information, amount, payment period, guarantee information, and extracted confidence level.

[0035] In another optional embodiment, risk features whose confidence levels output by the large language model are lower than a preset confidence threshold are marked as requiring review, and can then be manually reviewed. This prevents the large language model from unnecessarily contaminating the risk knowledge graph. It should be noted that the preset confidence threshold can be set according to actual needs, and this application does not limit its implementation.

[0036] Step S203: Align the risk characteristics to obtain standardized entities and standardized relationships.

[0037] In one alternative embodiment, entities in different documents that point to the same real-world object are aligned and unified to obtain standardized entities and standardized relationships.

[0038] In one specific embodiment, entities pointing to the same real-world object in different documents can be the same company whose company name is spelled differently in different documents, or the same batch of goods whose numbers are used in different documents, etc.

[0039] In a more specific embodiment, enterprises can be aligned using the unified social credit code, and goods batches can be aligned using a combination of "product specifications + product quantity + storage warehouse + time window".

[0040] Step S204: Construct a risk knowledge graph based on standardized entities and standardized relationships.

[0041] It should be noted that the risk knowledge graph includes at least the following nodes: enterprise entity node, contract flow node, goods flow node, bill flow node, and capital flow node.

[0042] In one optional embodiment, nodes in the risk knowledge graph can be categorized into the following types: entity type, document type, asset type, and account type. Entity type includes enterprises, legal representatives, actual controllers, shareholders, and guarantors; document type includes purchase and sale contracts, VAT invoices, warehouse receipts / bill of lading, warehousing records, and cash flow statements; asset type includes goods batches, accounts receivable, and pledged assets; and account type includes bank accounts and margin accounts. Edge types can be categorized according to nodes. For example, for contract nodes, edge types include signing, buyer, and seller; for goods nodes, edge types include delivery, warehousing, delivery, and pledge; for bill type nodes, edge types include issuance and correspondence; for fund type nodes, edge types include payment and settlement; and for entity relationship type nodes, edge types include guarantee, holding, and association. It should be noted that the above node and edge types can be adaptively expanded according to actual needs, and this application does not limit this.

[0043] In this step, a risk knowledge graph is established to form a transparent and searchable trade network.

[0044] Step S205: Identify risks in the financial supply chain based on risk knowledge graph.

[0045] In one optional embodiment, risk identification in the financial supply chain based on a risk knowledge graph includes: Based on risk knowledge graphs, identify whether the financial supply chain exhibits at least one of the following anomalies: There are mismatches in risk characteristics, missing risk characteristics, and temporal contradictions among risk characteristics.

[0046] In one specific embodiment, a mismatch in risk characteristics can be a mismatch between the contract amount and the invoice amount, a mismatch between the agreed quantity and the quantity received, or a mismatch between the buyer and seller and the party receiving or paying funds. A lack of risk characteristics can be a situation where there is a contract and an invoice but the corresponding inbound / outbound records or fund flow is missing. A temporal contradiction between risk characteristics can be a situation where the payment time is earlier than the contract signing time or the outbound time is earlier than the inbound time.

[0047] In another optional embodiment, considering the possibility of several companies signing purchase and sale contracts without actual goods transfer in order to obtain financing funds, risk identification of the financial supply chain is performed based on a risk knowledge graph, including: Directed loop detection is performed on the financial supply chain based on risk knowledge graph to obtain a closed loop; it is then determined whether there are related parties among the enterprises in the closed loop, whether there is a real flow of goods between the enterprises, and whether the transaction prices between the enterprises deviate from the market price; if there are related parties among the enterprises in the closed loop, no real flow of goods between the enterprises, and the transaction prices between the enterprises deviate from the market price, then it is determined that there is financing trade risk in the supply chain.

[0048] In one specific embodiment, the relationship could be that the companies share a common controlling shareholder, provide mutual guarantees, or have similar registered addresses. Whether genuine goods are transferred between the companies is determined based on IoT (Internet of Things) logistics trajectories and the existence of weighing records.

[0049] In another optional embodiment, the financial supply chain risk identification method provided in this application further includes: Risk warnings are issued when it is determined that there are financing trade risks in the supply chain.

[0050] In another optional embodiment, considering the possibility that several companies may engage in repeated pledging to obtain financing funds, risk identification of the financial supply chain is performed based on a risk knowledge graph, including: identifying whether there is a risk of repeated pledging in the financial supply chain based on the risk knowledge graph.

[0051] In one specific embodiment, if it is determined in the risk knowledge graph that two or more outstanding financing applications are simultaneously attached to the same pledged asset node or the same invoice node, then it is determined that there is a risk of double pledging in the financial supply chain.

[0052] In another optional embodiment, considering that commodity prices fluctuate wildly in reality, leading to highly unstable collateral value, traditional static credit lines cannot reflect the risk of the pledge ratio in a timely manner, and this risk can spread along the upstream and downstream of the supply chain, triggering a chain reaction of risks. Therefore, the financial supply chain risk identification method provided in this application embodiment further includes: obtaining the real-time market price of the pledged assets, the quantity of the pledged assets, the discount coefficient, and the financing balance; determining the pledge ratio based on the real-time market price of the pledged assets, the quantity of the pledged assets, the discount coefficient, and the financing balance; and determining that there is pledge ratio risk in the financial supply chain if the pledge ratio exceeds a preset pledge ratio threshold.

[0053] In one specific embodiment, the collateral ratio is determined based on the real-time market price of the collateral, the quantity of the collateral, the discount factor, and the outstanding loan balance, including: Based on the real-time market price of the pledged assets, the quantity of pledged assets, the discount factor, and the outstanding loan balance, the pledge ratio is calculated using the following formula: ; ; in, This represents the pledge ratio at time t, where L represents the outstanding loan balance. Q represents the value of the pledged collateral at time t, and Q represents the quantity of the pledged collateral. This represents the real-time market price of the pledged asset at time t, and h represents the discount factor.

[0054] In a more specific embodiment, historical price sequences of the collateral are collected, and annualized volatility is calculated; the maximum possible loss of the collateral is determined as a benchmark; and a discount factor is determined based on the benchmark and the annualized volatility. Additionally, the discount factor can be adjusted by considering factors such as collateral price trends, collateral liquidity, and the length of the financing term.

[0055] It should be noted that the preset pledge ratio threshold is set according to actual needs, and this application does not impose any restrictions on it.

[0056] In another alternative embodiment, when it is determined that there is a risk of collateralization in the financial supply chain, measures such as increasing margin or supplementing collateral are taken.

[0057] In another alternative embodiment, the financial supply chain risk identification method further includes: Obtain the price fluctuation amount of the commodity; if the price fluctuation amount of the commodity exceeds the preset price fluctuation threshold, identify all companies holding the commodity in the risk knowledge graph; determine the direct exposure loss of each company among all companies holding the commodity based on the quantity of the commodity held by the company and the price fluctuation amount of the commodity; determine the inter-company transmission weight based on the proportion of inter-company transaction volume; determine the company's transmitted exposure loss based on the inter-company transmission weight; and determine the company's total exposure loss by summing the direct exposure loss and the transmitted exposure loss. The total exposure loss is used to quantify the impact of market price fluctuations on the company.

[0058] In one specific embodiment, the direct exposure loss of each firm holding the goods is determined by multiplying the quantity of goods held by the firm by the price fluctuation of the goods. For example, if a firm holds 5,000 tons of hot-rolled coils and the price drops by 200 yuan per ton, its direct exposure loss is 1 million yuan.

[0059] In another specific embodiment, for example, Company A is the buyer, Company B is a Tier 1 supplier, and Company C is a Tier 2 supplier. Assuming Company B's total annual sales revenue is 100 million yuan, and its sales to Company A are 60 million yuan, then the transmission weight of Company A to Company B is 0.6. Similarly, if Company C's total annual sales revenue is 50 million yuan, and its sales to Company B are 25 million yuan, then the transmission weight of Company B to Company C is 0.5. If Company A goes bankrupt due to poor management and owes Company B 20 million yuan, then Company B's transmission exposure loss is 20 million yuan. 0.6 = 12 million; Company B loses 12 million. Assuming Company B owes Company C 10 million, then Company C's pass-through loss is 10 million. 0.5=5 million yuan.

[0060] In another optional embodiment, the financial supply chain risk identification method provided in this application further includes: determining the network centrality and bridging centrality of an enterprise based on a risk knowledge graph; determining the network importance score of an enterprise based on the network centrality and bridging centrality; determining the risk amplification effect value by multiplying the network importance score by the total exposure loss; and determining the target risk enterprise based on the risk amplification effect value.

[0061] It's important to note that network centrality measures how closely a company is directly or indirectly connected to other companies in a network. Higher centrality indicates greater overlap in business operations between the company and other companies. Bridging centrality measures a company's ability to act as a "bridge" connecting two previously unconnected companies. Higher bridging centrality indicates a stronger "bridge" function for the company.

[0062] In one specific embodiment, a network importance score for an enterprise is obtained by weighted summation of network centrality and bridging centrality.

[0063] In another specific embodiment, all enterprises are ranked in descending order according to the risk amplification effect value calculated above. Nodes with the highest ranking (e.g., exceeding the mean by 2 standard deviations or ranking in the top 20%) are marked as "critical nodes that may trigger a chain of defaults under price shocks." It should be noted that these enterprises typically meet the following criteria simultaneously: holding a large position in the commodity, being located at the hub of a trade network, and having high upstream and downstream dependence.

[0064] In another optional embodiment, the financial supply chain risk identification method provided in this application further includes: The risk identification results, real-time collateral ratio, and total exposure loss obtained from the risk identification of the financial supply chain are input into a pre-set large language model to generate a risk assessment report. The risk assessment report includes the conclusion and basis of the business authenticity, the risk identification results, the total exposure loss and collateral ratio recommendations, and the recommended risk control measures.

[0065] In one specific embodiment, the generated risk assessment report might be: The authenticity of the trade background for this application is questionable: Contract HT-2026-00821 has complete invoices, but lacks corresponding warehouse entry and exit records. Furthermore, the applicant company shares the same ultimate controlling shareholder with the upstream seller. This trade, along with two other contracts, forms a closed loop, suggesting a potential financing transaction. Coupled with the recent 8% drop in hot-rolled coil prices over the past 30 days, the current pledge ratio has risen to 82% (warning line 80%). Overall recommendation: Temporarily suspend loan disbursement, require supplementary genuine entry and exit documents, and additional margin.

[0066] In this embodiment, by constructing a risk knowledge graph, the limitations of single-document review are overcome, enabling the discovery of commodity-specific frauds such as circular trading and double pledging, which require a global perspective of the trade network for identification. LLM is used to automatically transform scattered and heterogeneous contracts, documents, and public opinion into standardized risk control elements within the graph, solving the problem of multi-source data fusion and significantly reducing manual due diligence costs. Real-time commodity price fluctuations are coupled with the valuation of purchase rights and risk transmission, addressing the problem of lag in price risk response in static credit models. Transmission simulation is performed on a fine-grained graph containing document-level entities, more accurately locating key nodes of chain risks than traditional graphs containing only enterprise nodes. The generated judgment conclusions are fed back to the original evidence, meeting financial regulatory compliance requirements and reducing manual due diligence, which previously required several days, to the hour level.

[0067] This application also provides an application scenario in which the above-mentioned financial supply chain risk identification method is applied. Specifically, the financial supply chain risk identification method provided in this embodiment can be applied in the home appliance supply and sales scenario, where the financial supply chain is the financial supply chain corresponding to the home appliances. The method involves acquiring multi-source heterogeneous data corresponding to the home appliance financial supply chain; determining risk characteristics based on the multi-source heterogeneous data; aligning the risk characteristics to obtain standardized entities and standardized relationships; constructing a risk knowledge graph based on the standardized entities and standardized relationships; and identifying risks in the financial supply chain based on the risk knowledge graph.

[0068] Based on the same inventive concept, this application also provides a financial supply chain risk identification device for implementing the financial supply chain risk identification method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more embodiments of the financial supply chain risk identification device provided below can be found in the limitations of the financial supply chain risk identification method described above, and will not be repeated here.

[0069] In one exemplary embodiment, such as Figure 3 As shown, a financial supply chain risk identification device is provided, comprising: Module 301 is used to acquire multi-source heterogeneous data corresponding to the financial supply chain. Module 302 is used to determine risk characteristics based on multi-source heterogeneous data; Alignment module 303 is used to align risk features to obtain standardized entities and standardized relationships; Module 304 is used to construct a risk knowledge graph based on standardized entities and standardized relationships. The risk knowledge graph includes at least the following nodes: enterprise entity nodes, contract flow nodes, goods flow nodes, bill flow nodes, and capital flow nodes. Risk identification module 305 is used to identify risks in the financial supply chain based on risk knowledge graph.

[0070] In one optional embodiment, the risk identification module is used for: Based on risk knowledge graphs, identify whether the financial supply chain exhibits at least one of the following anomalies: There are mismatches in risk characteristics, missing risk characteristics, and temporal contradictions among risk characteristics.

[0071] In one optional embodiment, the risk identification module is used for: Directed loop detection is performed on the financial supply chain based on risk knowledge graph to obtain a closed loop; Determine whether there are related parties among the enterprises in the closed loop, whether there is a real flow of goods between the enterprises, and whether the transaction prices between the enterprises deviate from the market price. If there are related parties among the enterprises in the closed loop, no real goods are transferred between the enterprises, and the transaction prices between the enterprises deviate from the market price, then the supply chain is identified as having financing trade risks.

[0072] In one optional embodiment, the risk identification module is used for: Identify the risk of double pledging in the financial supply chain based on risk knowledge graphs.

[0073] In an optional embodiment, the financial supply chain risk identification device further includes a module for performing the following operations: Obtain real-time market prices, quantities, discount rates, and financing balances of the pledged assets; The pledge ratio is determined based on the real-time market price of the pledged assets, the quantity of the pledged assets, the discount factor, and the outstanding financing balance. If the pledge ratio exceeds the preset pledge ratio threshold, it is determined that there is a pledge ratio risk in the financial supply chain.

[0074] In an optional embodiment, the financial supply chain risk identification device further includes a module for performing the following operations: To obtain the price fluctuation amount of a commodity; If the price fluctuation of a commodity exceeds a preset price fluctuation threshold, all companies holding the commodity will be identified in the risk knowledge graph. The direct exposure loss of each firm holding the goods is determined based on the quantity of goods held by the firm and the price fluctuation of the goods. The weight of inter-enterprise transmission is determined based on the proportion of inter-enterprise transaction volume. Determine the transmission exposure loss of each firm based on the inter-firm transmission weight. The sum of direct exposure loss and transmitted exposure loss is determined as the firm's total exposure loss, which is used to quantify the impact of market price fluctuations on the firm.

[0075] In an optional embodiment, the financial supply chain risk identification device further includes a module for performing the following operations: Determine the network centrality and bridging centrality of enterprises based on risk knowledge graphs; Determine an enterprise's network importance score based on network centrality and bridging centrality; The product of the network importance score and the total exposure loss is determined as the risk amplification effect value; Target risk companies are identified based on the risk amplification effect value.

[0076] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 4As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores financial supply chain risk identification data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a financial supply chain risk identification method.

[0077] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0078] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0079] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0080] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0081] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0082] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0083] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0084] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0085] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for identifying financial supply chain risks, characterized in that, The financial supply chain risk identification method includes: Acquire multi-source heterogeneous data corresponding to the financial supply chain; Risk characteristics are determined based on the aforementioned multi-source heterogeneous data; Aligning the aforementioned risk characteristics yields standardized entities and standardized relationships; A risk knowledge graph is constructed based on the standardized entities and standardized relationships. The risk knowledge graph includes at least the following nodes: enterprise entity nodes, contract flow nodes, goods flow nodes, bill flow nodes, and capital flow nodes. Risk identification is performed on the financial supply chain based on the aforementioned risk knowledge graph.

2. The financial supply chain risk identification method according to claim 1, characterized in that, The risk identification of the financial supply chain based on the risk knowledge graph includes: Based on the risk knowledge graph, identify whether the financial supply chain exhibits at least one of the following anomalies: There are mismatches in risk characteristics, missing risk characteristics, and temporal contradictions among risk characteristics.

3. The financial supply chain risk identification method according to claim 1, characterized in that, The risk identification of the financial supply chain based on the risk knowledge graph includes: Based on the risk knowledge graph, directed loop detection is performed on the financial supply chain to obtain a closed loop; Determine whether there are related relationships between the enterprises in the closed loop, whether there is a real flow of goods between the enterprises, and whether the transaction prices between the enterprises deviate from the market price. If there are related parties among the enterprises in the closed loop, no real goods flow between the enterprises, and the transaction prices between the enterprises deviate from the market price, then the supply chain is determined to have financing trade risks.

4. The financial supply chain risk identification method according to claim 1, characterized in that, The risk identification of the financial supply chain based on the risk knowledge graph includes: Based on the risk knowledge graph, it is possible to identify whether there is a risk of double pledging in the financial supply chain.

5. The financial supply chain risk identification method according to claim 1, characterized in that, The financial supply chain risk identification method also includes: Obtain real-time market prices, quantities, discount rates, and financing balances of the pledged assets; The pledge ratio is determined based on the real-time market price of the pledged assets, the quantity of the pledged assets, the discount factor, and the outstanding financing balance. If the pledge ratio exceeds a preset pledge ratio threshold, then the financial supply chain is determined to have pledge ratio risk.

6. The financial supply chain risk identification method according to claim 1, characterized in that, The financial supply chain risk identification method also includes: To obtain the price fluctuation amount of a commodity; If the price fluctuation of the commodity exceeds a preset price fluctuation threshold, all companies holding the commodity are identified in the risk knowledge graph. The direct exposure loss of each of the companies holding the commodity is determined based on the quantity of the commodity held by the company and the price fluctuation of the commodity. The weight of inter-enterprise transmission is determined based on the proportion of inter-enterprise transaction volume. The transmission exposure loss of the enterprise is determined based on the inter-enterprise transmission weight. The sum of the direct exposure loss and the transmitted exposure loss is determined as the company's total exposure loss, which is used to quantify the impact of market price fluctuations on the company.

7. The financial supply chain risk identification method according to claim 6, characterized in that, The financial supply chain risk identification method also includes: The network centrality and bridging centrality of enterprises are determined based on the aforementioned risk knowledge graph; The network importance score of the enterprise is determined based on the network centrality and bridging centrality. The product of the network importance score and the total exposure loss is determined as the risk amplification effect value; Target risk companies are identified based on the risk amplification effect value.

8. A financial supply chain risk identification device, characterized in that, The financial supply chain risk identification method includes: The acquisition module is used to acquire multi-source heterogeneous data corresponding to the financial supply chain; The determination module is used to determine risk characteristics based on the multi-source heterogeneous data; An alignment module is used to align the risk features to obtain standardized entities and standardized relationships; The construction module is used to construct a risk knowledge graph based on the standardized entities and standardized relationships. The risk knowledge graph includes at least the following nodes: enterprise entity nodes, contract flow nodes, goods flow nodes, bill flow nodes, and capital flow nodes. The risk identification module is used to identify risks in the financial supply chain based on the risk knowledge graph.

9. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the steps of the financial supply chain risk identification method according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the steps of the financial supply chain risk identification method according to any one of claims 1-7.

Images