Self-adaptive anti-risk chain scission risk simulation method based on industrial brain

Abstract

The invention discloses a self-adaptive anti-risk chain scission risk simulation method based on an industrial brain. The method comprises the following steps: acquiring a bidding database and a company information database; constructing a supply chain knowledge graph by using the bid invitation database and the company information database; performing attack simulation by using the supply chain knowledge graph to obtain an attack simulation result; according to the attack simulation result, carrying out enterprise operation state updating, enterprise anti-risk capability updating, overall network stability evaluation and case tracking to obtain a processing result; and performing situation awareness of the future link breakage risk according to the processing result. By implementing the method provided by the invention, the anti-risk capability of the enterprise after the supply chain is attacked can be effectively simulated, and particularly, the enterprise can realize self-adaptive quick response in chain breakage risk diffusion by contacting the operation state and the current capital scale of the enterprise.

Description

Technical Field

[0001] The present invention relates to a chain break risk simulation method, and more specifically to an adaptive and risk-resistant chain break risk simulation method based on an industrial brain. Background Art

[0002] In the context of increasingly complex global supply chains, supply chain disruption risk has become a focus of attention for enterprises and academia. Supply chain disruption risk refers to the risk that a problem occurs in a certain link of the supply chain, causing the entire system to fail to operate normally. This may be caused by a variety of factors such as natural disasters, market fluctuations, political conflicts or logistics disruptions. In order to effectively predict, evaluate and respond to this risk, there are several simulation methods: The first is a method based on system dynamics, which analyzes the dynamic changes of supply chain disruptions and their long-term impact by building feedback structures for each link. This method usually uses differential equations to describe the interactions between supply chain elements and is suitable for long-term chain disruption risk prediction and strategy analysis. However, the model construction is relatively complex, and the accuracy depends on a deep understanding of the system structure, and the simulation of short-term and local risks may not be accurate enough.

[0003] The second is an agent-based modeling method, which assigns specific behavioral rules to each participant in the supply chain, such as suppliers, manufacturers, logistics providers, or customers, to simulate the operation of the supply chain and the impact of disruptions. This method can dynamically display the behavior and interaction of each agent in the case of a chain break, and is suitable for complex, multi-level supply chain disruption scenarios. However, this method has a high computational complexity, and the accuracy of the model depends on the rationality of the agent's behavioral rules and the reliability of the data.

[0004] The third is the network analysis and graph theory method, which regards the supply chain as a network system and evaluates the impact of a node interruption on the entire network by analyzing the topological structure of nodes (enterprises, warehouses, transportation nodes, etc.) and edges (material flows, information flows, etc.). This method can intuitively analyze the structural vulnerability of the supply chain, identify key nodes and paths, and is suitable for evaluating overall resilience and the propagation effect after interruption. However, there are currently few methods that consider the adaptive changes in the risk resistance of enterprises under the risk of chain disruption.

[0005] Therefore, it is necessary to design a new solution to effectively simulate the risk resistance of enterprises after the supply chain is attacked, especially by linking the operating status and current capital scale of the enterprise, so that the enterprise can achieve adaptive and rapid response in the spread of supply chain disruption risk. Summary of the invention

[0006] The purpose of the present invention is to overcome the defects of the prior art and provide an adaptive and risk-resistant chain break risk simulation method based on the industrial brain.

[0007] To achieve the above purpose, the present invention adopts the following technical solution: a chain break risk simulation method based on adaptive risk resistance, comprising: Access to bidding database and company information database; Constructing a supply chain knowledge graph using the bidding database and the company information database; Performing attack simulation using the supply chain knowledge graph to obtain attack simulation results; According to the attack simulation results, the enterprise's business status is updated, the enterprise's risk resistance capability is updated, the overall network stability is evaluated, and the case is tracked to obtain the processing results; Based on the processing results, situation awareness of future chain break risks is performed.

[0008] The further technical solution is: the use of the bidding database and the company information database to construct a supply chain knowledge graph includes: Setting an initial node, searching the upstream and downstream structures of a set depth in the company information database and the bidding database, and using the ID to search for relevant information for each node; In the bidding database, the upstream and downstream relationships between nodes are queried based on the edge ID to determine the transaction relationship; A supply chain knowledge graph is constructed based on the node-related information and transaction relationships.

[0009] A further technical solution is: using the supply chain knowledge graph to perform attack simulation to obtain attack simulation results, including: Using a degree-based attack strategy to perform a degree attack according to the supply chain knowledge graph to obtain a first attack result; Adopting a closeness centrality-based strategy to attack the supply chain knowledge graph based on closeness centrality to obtain a second attack result; Using a registered capital-based attack strategy to attack the supply chain knowledge graph with registered capital to obtain a third attack result; The first attack result, the second attack result and the third attack result are combined to obtain an attack simulation result.

[0010] A further technical solution is: the degree-based attack strategy is used to perform a degree attack according to the supply chain knowledge graph to obtain a first attack result, including: Calculate the degree centrality of each enterprise according to the supply chain knowledge graph; The degree centrality of each enterprise is sorted, and the nodes whose ranking meets the requirements are selected as attack targets for attack to obtain the first attack result.

[0011] A further technical solution is: the strategy based on proximity centrality is used to attack the supply chain knowledge graph based on proximity centrality to obtain a second attack result, including: Calculate the proximity centrality of each enterprise based on the supply chain knowledge graph; The closeness centrality of each enterprise is sorted, and the nodes whose rankings meet the requirements are selected as attack targets for attack to obtain the second attack result.

[0012] The further technical solution is: the registered capital-based attack strategy is used to attack the supply chain knowledge graph with registered capital to obtain a third attack result, including: Obtain the registered capital of the enterprise; The registered capital of each enterprise is sorted, and the nodes whose rankings meet the requirements are selected as attack targets for attack to obtain the third attack result.

[0013] A further technical solution is: updating the business status of the enterprise, updating the enterprise's risk resistance capability, evaluating the overall network stability and tracking the cases according to the attack simulation results to obtain the processing results, including: use Update the business status of the enterprise, where j is the neighbor node of node enterprise i, is the time interval, represents the influence coefficient of all neighborhood fixed nodes, is the weight of each neighbor node, defined as , Neighbor node The number of transactions with the central enterprise, Indicates the current moment, It is the last moment; Used to quantify the current risk resistance of enterprises; use Calculate the risk resistance of the enterprise and adopt Calculate the risk resistance of neighboring enterprises, where: represents the neighbor weights between different enterprises; ; Expressed as the coefficient of change of capital outflow; is the risk factor, , Defined as neighbor nodes The number of transactions with the central enterprise, Indicates the current moment, It is the last moment; is the weight of each neighbor node, ; use Evaluate overall network stability, where is the proportion of affected nodes; N is the total number of nodes included in the supply chain network, The value is 0 or 1. The threshold for the stability of the business status of the enterprise is set at the time; Starting from the set initial node in the bidding database, nodes are extracted to build a supply chain network, and tracking experiments are carried out on supply chains with significant changes.

[0014] A further technical solution is: the situation awareness of future chain break risks based on the processing results includes: The supply chain network is dynamically monitored, risk predicted and responded to in an emergency according to the processing results.

[0015] The present invention also provides a chain-break risk simulation device based on adaptive risk resistance, comprising: A database acquisition unit, used to acquire a bidding database and a company information database; A knowledge graph construction unit, used to construct a supply chain knowledge graph using the bidding database and the company information database; An initial attack simulation unit, used to perform attack simulation using the supply chain knowledge graph to obtain an attack simulation result; A processing unit, used to update the business status of the enterprise, update the risk resistance of the enterprise, evaluate the overall network stability, and track cases according to the attack simulation results to obtain processing results; A situation awareness unit is used to perform situation awareness of future chain break risks based on the processing results.

[0016] The present invention further provides a computer device, which includes a memory and a processor. The memory stores a computer program, and the processor implements the above method when executing the computer program.

[0017] Compared with the prior art, the present invention has the following beneficial effects: the present invention obtains the bidding database and the company information database to construct a supply chain knowledge graph; uses the knowledge graph to simulate attacks and obtain relevant simulation results; updates the business status, risk resistance and overall network stability of the enterprise according to the simulation results, and conducts case tracking; finally, based on the processing results, realizes situational awareness of future chain break risks. It effectively simulates the risk resistance of enterprises after the supply chain is attacked, especially by linking the business status and current capital scale of the enterprise, so that the enterprise can achieve adaptive and rapid response in the spread of chain break risks.

[0018] The present invention is further described below in conjunction with the accompanying drawings and specific embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0020] Figure 1 A schematic diagram of an application scenario of a chain-break risk simulation method based on adaptive risk resistance provided by an embodiment of the present invention; Figure 2 A schematic diagram of a flow chart of a method for simulating chain-break risk based on adaptive risk resistance provided by an embodiment of the present invention; Figure 3 A schematic diagram of a sub-process of a method for simulating chain-break risk based on adaptive risk resistance provided by an embodiment of the present invention; Figure 4 A schematic diagram of a sub-process of a method for simulating chain-break risk based on adaptive risk resistance provided by an embodiment of the present invention; Figure 5 A schematic diagram of a sub-process of a method for simulating chain-break risk based on adaptive risk resistance provided by an embodiment of the present invention; Figure 6 A schematic diagram of a sub-process of a method for simulating chain-break risk based on adaptive risk resistance provided by an embodiment of the present invention; Figure 7 A schematic diagram of a sub-process of a method for simulating chain-break risk based on adaptive risk resistance provided by an embodiment of the present invention; Figure 8 A graph showing the overall affected node ratio change provided by an embodiment of the present invention; Fig. 9 A graph showing the risk resistance capability changes of A Co., Ltd. provided in an embodiment of the present invention; Fig.10 A graph showing the risk resistance capability changes of A Co., Ltd. provided in an embodiment of the present invention; Fig.11 A schematic block diagram of a chain break risk simulation device based on adaptive risk resistance provided by an embodiment of the present invention; Fig.12 A schematic block diagram of a knowledge graph construction unit of a chain-break risk simulation device based on adaptive risk resistance provided by an embodiment of the present invention; Fig.13 A schematic block diagram of an initial attack simulation unit of a link-breaking risk simulation device based on adaptive risk resistance provided by an embodiment of the present invention; Fig.14 A schematic block diagram of a first attack simulation subunit of a link-break risk simulation device based on adaptive risk resistance provided by an embodiment of the present invention; Fig.15 A schematic block diagram of a second attack simulation subunit of a link-break risk simulation device based on adaptive risk resistance provided by an embodiment of the present invention; Fig.16 A schematic block diagram of a third attack simulation subunit of the link-breaking risk simulation device based on adaptive risk resistance provided by an embodiment of the present invention; Fig.17 A schematic block diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0023] It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0024] It should be further understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0025] See also Figure 1 and Figure 2 , Figure 1 A schematic diagram of an application scenario of a method for simulating chain break risk based on adaptive risk resistance provided in an embodiment of the present invention. Figure 2A schematic flow chart of a chain-break risk simulation method based on adaptive risk resistance provided in an embodiment of the present invention. The chain-break risk simulation method based on adaptive risk resistance is applied in a server. The server interacts with the terminal for data, and by constructing a knowledge graph of the enterprise supply chain, simulates the impact of emergencies in the market on core enterprises, and analyzes their gradual impact on upstream and downstream enterprises. Specifically, by analyzing the degree of correlation between enterprises and the distribution of registered capital, the structure and dynamics of the supply chain network are deeply explored, and the importance of enterprises in the network is evaluated using centrality indicators, thereby simulating the adaptive recovery capabilities of enterprises when facing chain-break risks, and constructing a chain-break risk simulation model. This model reveals the changes in corporate behavior and its subsequent impact under different business attack strategies.

[0026] Through these analyses, the method of this embodiment not only reveals the complexity of the supply chain, but also deepens the understanding of the dynamics of corporate behavior, providing valuable insights for companies and market participants in the industry, helping them to more accurately grasp industry trends, capture market opportunities, and maintain their advantages in a highly competitive environment.

[0027] Figure 2 FIG. 1 is a flow chart of a method for simulating chain-break risk based on adaptive risk resistance provided by an embodiment of the present invention. Figure 2 As shown, the method includes the following steps S110 to S150.

[0028] S110, obtaining a bidding database and a company information database.

[0029] In this embodiment, the bidding database contains information related to the bidding of various projects, including project announcements, bidding units, bidding results, contract amounts, implementing units and other data.

[0030] The company information database contains basic information about the enterprise, such as registered capital, business scope, legal representative, shareholder information, financial status, etc.

[0031] By effectively acquiring and integrating the bidding database and the company information database, the present invention can provide data-based decision support for supply chain management. This process not only ensures the comprehensiveness of information, but also lays a solid foundation for subsequent risk prediction and dynamic monitoring.

[0032] S120. Construct a supply chain knowledge graph using the bidding database and the company information database.

[0033] In this embodiment, the supply chain knowledge graph is a comprehensive information structure that aims to present relevant information of each link of the supply chain in a graphical way. It visualizes different entities (such as companies, products, projects, contracts, etc.) and their relationships in the form of nodes and edges to help analyze and understand the complexity of the supply chain. Its main components are as follows: node: Enterprises: Various companies involved in the supply chain, such as suppliers, manufacturers, distributors, etc.

[0034] Product: The good or service that moves through the supply chain.

[0035] Project: The specific project in the bidding information.

[0036] Contract: An agreement signed by the parties that contains the terms and conditions of the transaction.

[0037] side: Relationship: The connection between different nodes, representing the business relationship between them, for example: The bidding relationship between enterprises and projects.

[0038] Partnerships between businesses.

[0039] The execution relationship between the project and the contract.

[0040] In this embodiment, a knowledge graph is used to integrate information scattered in different databases to form a comprehensive supply chain view; the supply chain knowledge graph makes complex supply chain relationships more intuitive through visualization, helping companies make wise decisions in a rapidly changing market environment.

[0041] In one embodiment, see Figure 3 , the above-mentioned step S120 may include steps S121~S123.

[0042] S121, setting an initial node, searching the upstream and downstream structures of a set depth in the company information database and the bidding database, and using the ID to search for relevant information for each node.

[0043] In this embodiment, the set depth is the maximum depth, and its value is 20. Of course, in other embodiments, other values ​​can be selected according to actual conditions.

[0044] Relevant information includes the corresponding company name, telephone number, province, city, legal representative, registered capital, certification time, enterprise type, and industry type.

[0045] S122. In the bidding database, query the upstream and downstream relationships between nodes according to the edge ID to determine the transaction relationship.

[0046] The transaction relationship includes the bidder and the successful bidder, and the corresponding number of bids or successful bids is also recorded.

[0047] S123. Construct a supply chain knowledge graph based on the node-related information and transaction relationships.

[0048] Specifically, the formation of the knowledge graph is actually a systematic, iterative update process, with the "entity-relationship-entity" triple as the core structure. First, the original data, that is, the data in the bidding database and the company information database, needs to be processed. The data source can include structured, semi-structured or unstructured data. Knowledge elements are extracted through a series of automated or semi-automated technical means. The process of constructing a knowledge graph can be roughly divided into four stages: knowledge storage, information extraction, knowledge integration and knowledge calculation.

[0049] Knowledge storage: This stage mainly designs the underlying storage method to effectively store various types of knowledge, including basic attribute knowledge, associated knowledge, and event knowledge. The original data types of knowledge graphs are usually divided into three categories: structured data (such as relational databases), unstructured data (such as pictures, audio, and video), and semi-structured data (such as XML and JSON).

[0050] Information extraction: The core task of this stage is to extract entities, attributes and relationships between entities from unstructured data. Specifically, it includes entity extraction (named entity recognition), relationship extraction (identifying the relationship between entities) and attribute extraction (collecting various attribute information of entities).

[0051] Knowledge integration: In this phase, new knowledge is integrated into the existing knowledge graph to ensure the consistency of the knowledge base by eliminating contradictions and ambiguities. This process includes entity linking from unstructured or semi-structured data (resolving ambiguity of entities with the same name) and knowledge merging of structured data to ensure effective integration of multi-source data.

[0052] Knowledge computing: In this phase, knowledge graphs are further improved through knowledge reasoning, quality assessment, and knowledge updating to form a structured and networked knowledge system. The reasoning process is used to fill in missing relationships or discover new knowledge, while quality assessment ensures the high quality of the knowledge base by quantifying the credibility of knowledge. Knowledge updating includes the introduction of new concepts and the updating of entities, relationships, and attribute values, and the reliability and consistency of the data source must be carefully considered.

[0053] Through the above steps, the initial construction of the knowledge graph is completed, forming a dynamic knowledge system that can be continuously updated and expanded.

[0054] S130. Perform attack simulation using the supply chain knowledge graph to obtain attack simulation results.

[0055] In this embodiment, the attack simulation result refers to the result obtained by performing different types of attack simulations on the supply chain knowledge graph.

[0056] In the actual environment, companies may be attacked or affected by specific events (such as policy changes, natural disasters, etc.). In this case, different attack strategies for the supply chain network can help analyze and understand the vulnerability of the network. This embodiment can simulate the interruption process of supply chain relationships under different circumstances by implementing these three attack strategies. This simulation helps enterprises identify the vulnerability of key nodes, assess potential risks, and provide a basis for formulating more effective defense strategies. By deeply understanding the impact of different attack strategies, enterprises can be better prepared to deal with various emergencies and improve their overall risk resistance.

[0057] In one embodiment, see Figure 4 , the above-mentioned step S130 may include steps S131~S134.

[0058] S131. Use a degree-based attack strategy to perform a degree attack according to the supply chain knowledge graph to obtain a first attack result.

[0059] In this embodiment, the first attack result refers to the result obtained by performing a degree attack on the supply chain knowledge graph.

[0060] Degree refers to the number of edges directly connected to a node in the network. Degree-based attack strategies will prioritize attacking nodes with high connectivity, which usually play a key role in the network.

[0061] By attacking these critical nodes, the connectivity of the entire network can be rapidly reduced, leading to wider supply chain disruptions.

[0062] In one embodiment, see Figure 5 , the above-mentioned step S131 may include steps S1311~S1312.

[0063] S1311. Calculate the degree centrality of each enterprise according to the supply chain knowledge graph; S1312. Sort the degree centrality of each enterprise, and select the nodes whose rankings meet the requirements as attack targets to attack, so as to obtain a first attack result.

[0064] In this embodiment, the attack targets the nodes with the most connections in the supply chain network to quickly destroy the most densely connected areas. Degree centrality is used to measure the number of direct connections between a node and other nodes. By calculating the degree centrality of each node, key hub nodes with a large number of direct connections in the supply chain network can be identified.

[0065] In the specific implementation process, the degree centrality of all nodes will be sorted first, and then the nodes with the top p percent degree centrality values ​​will be selected for attack. After the attack, these enterprises will be considered bankrupt and the nodes will be marked as "attacked". All edges connected to the node will be deleted to simulate the interruption of the transaction relationship between the enterprise and its suppliers and customers. This will have a chain reaction on the entire network.

[0066] By attacking the nodes with the most connections first, the overall structure of the network can be quickly disintegrated, achieving the purpose of rapid interference. The calculation of degree centrality allows attackers to clearly identify key nodes and avoid wasting ineffective attack resources. The collapse of key nodes after attacking them will trigger a chain reaction of other nodes, further expanding the scope of influence and leading to greater supply chain disruptions. After understanding this attack strategy, enterprises can better identify their own key nodes, thereby formulating targeted defense measures and enhancing overall risk resistance.

[0067] S132. Use a closeness centrality-based strategy to attack the supply chain knowledge graph based on closeness centrality to obtain a second attack result.

[0068] In this embodiment, the second attack result refers to the result obtained by performing a proximity centrality attack on the supply chain knowledge graph.

[0069] Closeness centrality measures the distance between a node and other nodes. The higher the centrality, the greater the influence of the node in the network. This strategy prioritizes attacking nodes that are close to the center. Attacking these nodes can effectively disrupt the flow of information and cause widespread network impact, making it difficult for other nodes to quickly obtain resources or information.

[0070] In one embodiment, see Figure 6 , the above-mentioned step S132 may include steps S1321~S1322.

[0071] S1321. Calculate the proximity centrality of each enterprise based on the supply chain knowledge graph.

[0072] S1322. Sort the closeness centrality of each enterprise, and select the nodes whose rankings meet the requirements as attack targets to attack, so as to obtain a second attack result.

[0073] In this embodiment, the node with the shortest connection distance to other nodes is attacked, which may disrupt the entire network structure. Closeness centrality is used to measure the average shortest path length between a node and all other nodes in the network.

[0074] The specific calculation steps are as follows: For each node v in the network, calculate the shortest path length from it to all other nodes. This step can be implemented using the Dijkstra algorithm. The basic idea of ​​the Dijkstra algorithm is to start from the starting node, gradually expand to other nodes, and continuously update the shortest distance to each node until all nodes are processed.

[0075] After using Dijkstra's algorithm to calculate the shortest path length from each node to all other nodes, these lengths are added together to get the total distance sum(d(v,t)). This total distance reflects the overall distance between the node and all other nodes in the network.

[0076] Calculate the closeness centrality C(v) of node v using the formula: C(v) = (n-1) / sum(d(v,t)). Where n is the total number of nodes in the network, and d(v,t) is the shortest path length from node v to node t.

[0077] Repeat the above steps for all nodes in the network to get the closeness centrality score of each node. This process requires a Dijkstra algorithm calculation for each node, and then applying the closeness centrality formula. Finally, all nodes are sorted from high to low according to the closeness centrality score.

[0078] Nodes with high proximity centrality are usually able to quickly establish connections with other nodes, so in the supply chain, these nodes are often important companies with rapid response capabilities.

[0079] In the specific attack implementation process, the closeness centrality of each node is first calculated, and then the nodes with the top p percent closeness centrality values ​​are selected for attack. After the attack, these companies will be considered bankrupt, which will have a significant impact on the entire supply chain network.

[0080] By attacking the node with the shortest connection distance to other nodes, a large number of network connections can be destroyed in a short period of time, causing widespread chaos. Attacking nodes with high proximity centrality can effectively utilize resources and ensure the accuracy and efficiency of the attack. These nodes are usually key response nodes, and the consequences of attacking them will quickly spread to other parts of the network, exacerbating the instability of the network. After understanding this attack strategy, enterprises can identify their key roles in the network and take measures in advance to enhance the resilience and risk resistance of the network.

[0081] S133. Use a registered capital-based attack strategy to attack the supply chain knowledge graph with registered capital to obtain a third attack result.

[0082] In this embodiment, the third attack result refers to the result obtained by using a registered capital-based attack strategy to attack the supply chain knowledge graph.

[0083] Registered capital reflects the size and financial strength of a company. This strategy selects companies with larger registered capital to attack, which usually occupy an important position in the supply chain. Attacking these large companies may cause damage to their financial situation, thus affecting the stability and reliability of the entire supply chain.

[0084] In one embodiment, see Figure 7 , the above-mentioned step S133 may include steps S1331~S1332.

[0085] S1331. Obtaining the registered capital of the enterprise; S1332. Sort the registered capital of each enterprise, and select nodes whose rankings meet the requirements as attack targets to attack, so as to obtain a third attack result.

[0086] In this embodiment, the method aims to minimize the influence of these key nodes by selecting enterprises with larger registered capital as target nodes. Enterprises with larger registered capital usually occupy an important position in the supply chain and undertake key supply or production functions.

[0087] When carrying out the attack, the registered capital of all enterprises is first sorted, and the enterprises with the top p percent of registered capital are selected for attack. Once these enterprises are attacked, they will be regarded as closed down, which will have a significant impact on the entire supply chain.

[0088] Attacking companies with the largest registered capital can effectively weaken their core role in the supply chain and cause greater damage. Since these companies are usually closely connected to many other companies, their collapse will trigger a chain reaction and affect the stability of the entire network. Focusing attacks on companies with high registered capital can ensure efficient use of resources and achieve faster attack results. This strategy can help companies recognize their own vulnerabilities in the network and prompt them to take measures to enhance their risk resistance and resilience.

[0089] S134. Combine the first attack result, the second attack result, and the third attack result to obtain an attack simulation result.

[0090] S140, updating the enterprise's business status, updating the enterprise's risk resistance capability, evaluating the overall network stability, and tracking cases according to the attack simulation results to obtain processing results.

[0091] In this embodiment, the processing result refers to the result obtained after updating the business operation status of the enterprise, updating the enterprise's risk resistance capability, evaluating the overall network stability, and tracking the cases.

[0092] In one embodiment, the above step S140 may include the following steps: use Update the business status of the enterprise, where j is the neighbor node of node enterprise i, i.e., the upstream and downstream enterprises, is the time interval, which controls the speed of state change. represents the influence coefficient of all neighborhood fixed nodes, is the weight of each neighbor node, defined as , which describes the intensity of mutual influence between enterprises, Neighbor node The number of transactions with the central enterprise, Indicates the current moment, It is the last moment; Used to quantify the current risk resistance of enterprises; use Calculate the risk resistance of the enterprise and adopt Calculate the risk resistance of neighboring enterprises, where: represents the neighbor weights between different enterprises; ; Expressed as the coefficient of change of capital outflow; is the risk factor, , Defined as neighbor nodes The number of transactions with the central enterprise, Indicates the current moment, It is the last moment; is the weight of each neighbor node, ; use Assess overall network stability, where: is the proportion of affected nodes; N is the total number of nodes included in the supply chain network, The value is 0 or 1. The threshold for the stability of the business status of the enterprise is set at the time; Starting from the set initial node in the bidding database, nodes are extracted to build a supply chain network, and tracking experiments are carried out on supply chains with significant changes.

[0093] Specifically, for the update of business status of enterprises, the business stability of enterprises can be measured by a state indicator ranging from 0 to 1. At the initial moment, some enterprise nodes will be attacked, and their state values ​​are set to 1, while the state of unattacked enterprises is 0. Over time, the attacked enterprises may spread instability to other enterprises through their connections with neighboring enterprises, causing their states to gradually become unstable. At the same time, the state update of the enterprise itself will also be affected by the combined effects of time and upstream and downstream enterprises. Through the state indicator, the business stability of the enterprise can be monitored in real time and potential risks can be identified in time. The model can reveal the mutual influence between enterprises and help understand how instability spreads from affected enterprises to other enterprises. Through the state update formula, enterprises can formulate more effective response strategies based on the status of themselves and neighboring enterprises to enhance their risk resistance. Enterprises can use this model for long-term planning to reduce the negative impact of external shocks and thus enhance their overall competitiveness.

[0094] For the update of the enterprise's anti-risk ability, in order to effectively evaluate the enterprise's anti-risk ability, in this embodiment, a dynamic model that changes with the registered capital is introduced. The risk tolerance of an enterprise in actual operation is often closely related to its capital status. Especially in the face of emergencies, the capital loss of an enterprise is directly related to the decline in its anti-risk ability. Therefore, this embodiment simulates the update process of the enterprise's anti-risk ability through the change of the enterprise's registered capital.

[0095] Risk resistance is specifically defined as: ,in, It is used to indicate the capital situation of an enterprise. The initial value is its registered capital, i.e. the capital strength of the enterprise when it is not affected by external shocks. The size of the registered capital represents the risk tolerance of the enterprise under normal operating conditions. It is a coefficient of variation, which is used to control the reasonable fluctuation of risk resistance, to avoid the rapid collapse of the enterprise due to a single event or to completely transfer risks to affiliated enterprises.

[0096] As the business activities of an enterprise proceed, especially when encountering risk events, the capital of the enterprise will change. When the risk level of the enterprise reaches or exceeds a certain preset threshold When the enterprise's risk resistance is updated, the formula is as follows: ; This formula shows that the risk resistance of an enterprise will gradually decline with the loss of capital, simulating the attenuation of the risk resistance of an enterprise due to the accumulation of risks during its operations.

[0097] Enterprises are often connected to each other through industrial chains or other cooperative relationships. When the risk resistance of an enterprise decreases, its impact on neighboring enterprises also needs to be considered. In order to simulate this impact, the present invention introduces neighbor weights between different enterprises. , and iteratively calculate neighboring enterprises through the following formula Changes in risk resistance: ; The definition is as follows: ;in Expressed as a coefficient of change in capital outflow, multiplying this coefficient ensures that the increased risk of the enterprise has limited impact on itself and its neighbors rather than leading to its own rapid collapse or being entirely passed on to affiliated enterprises.

[0098] The risk factor is defined as: ;in, Defined as neighbor nodes The number of transactions with the central enterprise, Indicates the current moment, The increase in the number of transactions often means that the risk exposure of the enterprise is expanding, so the risk coefficient increases with the increase in the number of transactions. In this way, the transaction activities of the enterprise are directly linked to the risks it faces, reflecting the risk level faced by the enterprise under different operating conditions.

[0099] is the weight of each neighbor node. Its introduction fully considers the impact of transaction frequency on risk transmission. It is specifically defined as: .

[0100] Through the above methods, this embodiment quantifies the risk transmission path between enterprises, simulates how risks are transmitted between different enterprises through direct or indirect business connections in a complex supply chain network, and reflects the risk diffusion process in the enterprise network.

[0101] For the overall network stability assessment, hour, The value is 1, otherwise it is 0. By calculating the proportion of affected nodes, the impact of emergencies on the supply chain network can be quantified, which is convenient for enterprises to conduct risk assessment. It can quickly identify which nodes (enterprises) are below the threshold, so as to determine the enterprises that need the most attention and support and improve the response speed. The node status changes can be updated and monitored at any time to detect potential problems in time and improve the overall transparency and flexibility of the supply chain. By understanding the overall stability, targeted preventive measures can be taken to enhance the resilience of the supply chain and reduce the adverse effects of future emergencies.

[0102] For case tracking, in order to focus on the impact of attacks on supply chain changes, this embodiment starts from the set initial node in the bidding database, extracts nodes to build a supply chain network, and conducts tracking experiments on supply chains with significant changes. The details are as follows: First, the basic situation of the network is shown in Table 1.

[0103] Table 1. Supply chain network statistics

[0104] Initially, 11,012 nodes were obtained, and they were screened based on registered capital. Nodes with null values ​​or registered capital less than 30,000 were removed, and 4,416 nodes and 1,738 edges were retained.

[0105] The specific experimental parameter settings in the tracking experiment are shown in Table 2.

[0106] Table 2. Summary of experimental parameters

[0107] In the tracking experiment, 0.5 was selected as the coefficient of change in risk resistance The value of is mainly based on the impact of various risk factors faced by the enterprise in its business operations. This setting is based on empirical observations and can provide a reasonable intervention point in enterprise risk management. It is based on the empirical estimation of the speed of capital loss of enterprises. This value can ensure that in the simulation, capital loss gradually increases as the business conditions of the enterprise deteriorate, avoiding sudden and uncontrollable losses. At the same time, it maintains a moderate risk diffusion speed to prevent the instability of the entire network caused by excessive capital loss.

[0108] The setting of the two thresholds reflects the critical points between normal operation and affected status of enterprises. It means that when the enterprise's status value is greater than 0.5, the capital loss will be evaluated. This setting is based on realistic considerations. The capital loss of an enterprise does not happen all at once when it goes bankrupt, but gradually occurs as its operating conditions deteriorate. This setting ensures that the model can accurately simulate the gradual capital loss of an enterprise in a deteriorating state. This indicates that all enterprises in the supply chain network with a status value greater than 0.5 at this moment are considered as affected nodes. This is because in empirical observations, when the enterprise status value exceeds 0.5, it can be considered that the enterprise has begun to show signs of poor management. Conducting a supply chain stability assessment at this time will help identify risks and take intervention measures at an earlier stage.

[0109] The initial attack ratio is set to 20%. Through empirical analysis, selecting the top 20% of nodes as attack targets can effectively simulate the most serious impact of chain-breaking attacks and help formulate more targeted risk management strategies.

[0110] The experimental results obtained after case tracking are as follows: The experimental results show that the overall supply chain network has a certain degree of elasticity. Figure 8As shown, although the failure of key nodes will have a rapid and widespread impact on the network, causing a greater impact in the initial stage, the network tends to stabilize after a period of time, and the proportion of affected nodes increases from 20% to 27% and then changes little, and the network can maintain overall operation after the failure of some nodes.

[0111] For the case tracking of a specific node, for example, if the supply chain of a limited company changes significantly, the present invention selects the supply chain starting from the enterprise for tracking, focusing on the upstream and downstream changes in the area of ​​significant changes to analyze the impact of the broken chain.

[0112] Specific as Fig. 9 As shown in the figure, the supply chain of company A has changed significantly. The present invention selects the supply chain starting from this company for tracking and focuses on Fig. 9 The upstream and downstream changes of the area shown in the middle color block are used to analyze the impact of the chain break; the numbers on the arrows represent the initial transaction times, and the dotted lines represent the nodes that collapsed in the initial attack and the corresponding disappeared transaction relationships. Table 3 shows the basic information of the initial supply chain.

[0113] Table 3. Initial status details table

[0114] Since company C has a higher registered capital, it is attacked first under the attack strategy based on the size of registered capital. At time 1, the state changes to 1, and the company goes bankrupt. At time 2, the state value of company A rises by 0.2437, and the capital of its neighbors drops sharply to 4,629,932 yuan, and its risk resistance drops to 0.2885. At this time, the states of the nodes and neighbors are shown in Table 4.

[0115] Table 4. The situation of a sharp decline in risk resistance at time 2

[0116] Since then, the status values ​​of nodes and neighbors that are operating normally have continued to increase. Since the number of transactions has not changed, the risk coefficient is always 0, and there is no further loss of capital in Company A. At time 7, the node's own state reaches the capital update threshold of 0.5, which means that the business situation may be unstable. However, according to Table 5, before time 7, the state of the surviving neighbor nodes is less than 0.5, and the normal transaction with Company A can be maintained. The number of transactions has not changed, and the capital is not updated at time 7. Start updating capital, because company B's status has reached 0.5 and the total number of transactions has dropped from 4 to 2.

[0117] Table 5. Changes in enterprise status from time 7 to time 8

[0118] As shown in Table 6, the capital decrease at time 9 is because the status of company D also exceeds 0.5, and since then the number of transactions of company A has been 0.

[0119] Table 6. Enterprise status at time 9

[0120] After that, the status of the node and its neighbors has been greater than 0.5 but less than 1. Therefore, the risk resistance of capital and nodes has not changed. Since then, the risk resistance of company A has stabilized at around 0.2823, and the change process is shown in Fig.10 .

[0121] The initial transaction times, nodes that crashed in the initial attack, and corresponding disappeared transaction relationships are displayed on the supply chain network. The initial basic information of the supply chain is also presented.

[0122] According to the content displayed by the supply chain network and the initial basic information of the supply chain, the bankruptcy of each enterprise after the attack is determined, and finally a risk resistance change chart is presented, such as Fig.10 shown.

[0123] S150: Perform situation awareness of future chain break risks based on the processing results.

[0124] In this embodiment, the supply chain network is dynamically monitored, risk predicted, and emergency responded to according to the processing results. Dynamic monitoring and risk prediction of the supply chain network are achieved, thereby providing decision support and ensuring the stability and resilience of the supply chain. By combining big data analysis, machine learning, and intelligent decision support systems, various emergencies and sustainable operation risks in the supply chain can be efficiently responded to.

[0125] Specifically, the steps for dynamic monitoring and data updating include: Real-time data collection: Using crawler technology, real-time collection of information such as the operating status, transaction data, and capital flow of each node in the supply chain. Data sources include company databases, bidding information, financial statements, and official announcements.

[0126] By building a comprehensive supply chain knowledge graph, a reliable data foundation is provided for subsequent risk prediction and decision support.

[0127] Data update mechanism: Establish an automated data update mechanism to ensure that information is always up to date. When new data enters the system, node and edge information is automatically updated, and relevant indicators (such as degree centrality, closeness centrality, and registered capital, etc.) are recalculated. This mechanism improves the efficiency and accuracy of data updates and provides solid support for risk prediction and emergency response.

[0128] The specific steps for using the risk prediction model are as follows: By deeply analyzing historical data, the model can identify potential risk signals, such as abnormal fluctuations in operating conditions and capital outflows. In the current scenario, the model can identify high-risk nodes and predict the vulnerability of the supply chain under different attack strategies.

[0129] The steps of risk warning and emergency response include: A real-time risk warning system is established. When the operating status or capital change of a certain node exceeds the preset threshold, the system will automatically issue a warning. The warning information includes potential risk nodes, upstream and downstream companies that may be affected, and recommended emergency measures. Timely risk warnings enable companies to take quick measures to reduce the possibility of risk spread and ensure the stable operation of the supply chain.

[0130] Based on the early warning information, formulate corresponding emergency response strategies, including adjusting the supply chain structure, finding alternative suppliers and strengthening communication with key nodes; the implementation of these emergency response strategies can effectively respond to emergencies, reduce the impact of risks on the supply chain, and maintain its continuity and stability.

[0131] The specific steps of trend analysis and decision support include: Regularly generate analytical reports on the overall stability of the supply chain, risk status of key nodes, and potential risks of supply chain disruptions; these reports help management fully understand the operation of the supply chain, make scientific decisions, and prepare for potential risks in the future.

[0132] Based on the supply chain knowledge graph and risk prediction model, an intelligent decision support system is built; the system can simulate supply chain changes under different strategies, evaluate the effectiveness of each strategy, and help enterprises choose the best risk management solution. This intelligent decision support can improve the flexibility and adaptability of enterprises in complex market environments.

[0133] The specific steps of case tracking and model optimization include: Establish a supply chain disruption risk case library to record the cause, impact scope and response measures of each disruption incident; the case library not only includes simulated cases, but also covers actual supply chain disruption incidents, which helps to accumulate rich risk management experience.

[0134] Through case analysis, risk prediction models and emergency response strategies are continuously optimized; each analysis result will be used to adjust model parameters to improve prediction accuracy and response effects; continuous experience accumulation and model optimization enhance the company's risk management capabilities and improve the resilience of the supply chain.

[0135] The situational awareness of this embodiment can enable real-time data collection and risk warning systems to enable enterprises to respond quickly to emergencies and reduce losses; comprehensive data analysis and trend reports help management make more scientific decisions; by timely identifying and responding to risks, enterprises can reduce potential economic losses and operational interruption costs; effective emergency response strategies and continuous model optimization make the supply chain more risk-resistant and able to adapt to market changes; the construction of a case library promotes the accumulation of enterprise experience in risk management and provides a reference for future decision-making.

[0136] Through the above method, the future situation awareness system of this embodiment can realize comprehensive monitoring and management of the supply chain, provide strong risk management support for enterprises, ensure the stability and resilience of the supply chain, and promote the sustainable development of enterprises.

[0137] The above-mentioned chain-break risk simulation method based on adaptive risk resistance constructs a supply chain knowledge graph by acquiring the bidding database and the company information database; uses the knowledge graph to simulate attacks and obtain relevant simulation results; updates the business status, risk resistance and overall network stability of the enterprise according to the simulation results, and conducts case tracking; finally, based on the processing results, realizes situational awareness of future chain-break risks. It effectively simulates the risk resistance of enterprises after the supply chain is attacked, especially by linking the business status and current capital scale of the enterprise, so that the enterprise can achieve adaptive and rapid response in the spread of chain-break risks.

[0138] Fig.11 is a schematic block diagram of a chain break risk simulation device based on adaptive risk resistance provided by an embodiment of the present invention. Fig.11 As shown, corresponding to the above-mentioned chain-breaking risk simulation method based on adaptive risk resistance, the present invention also provides a chain-breaking risk simulation device 300 based on adaptive risk resistance. The chain-breaking risk simulation device 300 based on adaptive risk resistance includes a unit for executing the above-mentioned chain-breaking risk simulation method based on adaptive risk resistance, and the device can be configured in a server. Specifically, please refer to Fig.11 The adaptive anti-risk based chain-breaking risk simulation device 300 includes a database acquisition unit 301, a knowledge graph construction unit 302, an initial attack simulation unit 303, a processing unit 304 and a situation awareness unit 305.

[0139] A database acquisition unit 301 is used to acquire a bidding database and a company information database; a knowledge graph construction unit 302 is used to construct a supply chain knowledge graph using the bidding database and the company information database; an initial attack simulation unit 303 is used to perform attack simulation using the supply chain knowledge graph to obtain attack simulation results; a processing unit 304 is used to update the business operating status, update the enterprise risk resistance capability, evaluate the overall network stability, and track cases based on the attack simulation results to obtain processing results; a situation awareness unit 305 is used to perform situation awareness of future chain break risks based on the processing results.

[0140] In one embodiment, if Fig.12 As shown, the knowledge graph construction unit 302 includes an initial node setting subunit 3021, a transaction relationship determination subunit 3022 and a graph construction subunit 3023.

[0141] The initial node setting subunit 3021 is used to set the initial node, query the upstream and downstream structure of the set depth in the company information database and the bidding database, and use the ID to query the relevant information for each node; the transaction relationship determination subunit 3022 is used to query the upstream and downstream relationships between nodes in the bidding database according to the edge ID to determine the transaction relationship; the graph construction subunit 3023 is used to construct a supply chain knowledge graph based on the node related information and transaction relationships.

[0142] In one embodiment, if Fig.13 As shown, the initial attack simulation unit 303 includes a first attack simulation subunit 3031 , a second attack simulation subunit 3032 , a third attack simulation subunit 3033 and a combination subunit 3034 .

[0143] The first attack simulation subunit 3031 is used to adopt a degree-based attack strategy to perform a degree attack on the supply chain knowledge graph to obtain a first attack result; the second attack simulation subunit 3032 is used to adopt a proximity-centrality-based strategy to perform a proximity-centrality attack on the supply chain knowledge graph to obtain a second attack result; the third attack simulation subunit 3033 is used to adopt a registered capital-based attack strategy to perform a registered capital attack on the supply chain knowledge graph to obtain a third attack result; the combination subunit 3034 is used to combine the first attack result, the second attack result and the third attack result to obtain an attack simulation result.

[0144] In one embodiment, if Fig.14 As shown, the first attack simulation subunit 3031 includes a degree centrality calculation module 30311 and a degree attack module 30312.

[0145] The degree centrality calculation module 30311 is used to calculate the degree centrality of each enterprise based on the supply chain knowledge graph; the degree attack module 30312 is used to sort the degree centrality of each enterprise and select the nodes whose rankings meet the requirements as attack targets for attack to obtain the first attack result.

[0146] In one embodiment, if Fig.15 As shown, the second attack simulation subunit 3032 includes a proximity centrality calculation module 30321 and a proximity centrality attack module 30322 .

[0147] The proximity centrality calculation module 30321 is used to calculate the proximity centrality of each enterprise based on the supply chain knowledge graph; the proximity centrality attack module 30322 is used to sort the proximity centrality of each enterprise and select the nodes whose rankings meet the requirements as attack targets for attack to obtain a second attack result.

[0148] In one embodiment, if Fig.16 As shown, the third attack simulation subunit 3033 includes a capital acquisition module 30331 and a capital attack module 30332 .

[0149] The capital acquisition module 30331 is used to obtain the registered capital of the enterprise; the capital attack module 30332 is used to sort the registered capital of each enterprise and select the nodes whose ranking meets the requirements as attack targets for attack to obtain the third attack result.

[0150] In one embodiment, the processing unit 304 is used to adopt Update the business status of the enterprise, where j is the neighbor node of node enterprise i, is the time interval, represents the influence coefficient of all neighborhood fixed nodes, is the weight of each neighbor node, defined as , Neighbor node The number of transactions with the central enterprise, Indicates the current moment, It is the last moment; Used to quantify the current risk resistance of enterprises; Calculate the risk resistance of the enterprise and adopt Calculate the risk resistance of neighboring enterprises, where: represents the neighbor weights between different enterprises; ; Expressed as the coefficient of change of capital outflow; is the risk factor, , Defined as neighbor nodes The number of transactions with the central enterprise, Indicates the current moment, It is the last moment; is the weight of each neighbor node, ;use Assess overall network stability, where: is the proportion of affected nodes; N is the total number of nodes included in the supply chain network, The value is 0 or 1. The threshold for the stability of the enterprise's operating status is set at the time; starting from the set initial node in the bidding database, nodes are extracted to build a supply chain network, and tracking experiments are carried out on supply chains with significant changes.

[0151] In one embodiment, the situation awareness unit 305 is used to dynamically monitor, predict risks, and respond to emergencies on the supply chain network based on the processing results.

[0152] It should be noted that technical personnel in the relevant field can clearly understand that the specific implementation process of the above-mentioned chain break risk simulation device 300 based on adaptive risk resistance and each unit can refer to the corresponding description in the aforementioned method embodiment, and for the convenience and conciseness of the description, it will not be repeated here.

[0153] The above-mentioned chain-break risk simulation device 300 based on adaptive risk resistance can be implemented in the form of a computer program. The computer program can be used in Fig.17 Runs on the computer device shown.

[0154] See also Fig.17 , Fig.17 5 is a schematic block diagram of a computer device provided in an embodiment of the present application. The computer device 500 may be a server, wherein the server may be an independent server or a server cluster composed of multiple servers.

[0155] See also Fig.17 The computer device 500 includes a processor 502 , a memory and a network interface 505 connected via a system bus 501 , wherein the memory may include a non-volatile storage medium 503 and an internal memory 504 .

[0156] The non-volatile storage medium 503 can store an operating system 5031 and a computer program 5032. The computer program 5032 includes program instructions, and when the program instructions are executed, the processor 502 can execute a chain-break risk simulation method based on adaptive risk resistance.

[0157] The processor 502 is used to provide computing and control capabilities to support the operation of the entire computer device 500 .

[0158] The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute a chain break risk simulation method based on adaptive risk resistance.

[0159] The network interface 505 is used to communicate with other devices over the network. Fig.17 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the computer device 500 to which the solution of the present application is applied. The specific computer device 500 may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0160] The processor 502 is used to run the computer program 5032 stored in the memory to implement the following steps: Obtain a bidding database and a company information database; use the bidding database and the company information database to construct a supply chain knowledge graph; use the supply chain knowledge graph to perform attack simulation to obtain attack simulation results; based on the attack simulation results, update the business operating status, update the enterprise risk resistance, evaluate the overall network stability, and track cases to obtain processing results; based on the processing results, perform situational awareness of future chain break risks.

[0161] In one embodiment, when implementing the step of building a supply chain knowledge graph using the bidding database and the company information database, the processor 502 specifically implements the following steps: Set an initial node, query the upstream and downstream structure of a set depth in the company information database and the bidding database, and use the ID to query relevant information for each node; in the bidding database, query the upstream and downstream relationship between nodes according to the edge ID to determine the transaction relationship; construct a supply chain knowledge graph based on the node related information and transaction relationship.

[0162] In one embodiment, when the processor 502 implements the step of using the supply chain knowledge graph to perform attack simulation to obtain an attack simulation result, the processor 502 specifically implements the following steps: A degree-based attack strategy is used to perform a degree attack on the supply chain knowledge graph to obtain a first attack result; a proximity-centrality-based attack strategy is used to perform a proximity-centrality attack on the supply chain knowledge graph to obtain a second attack result; a registered capital-based attack strategy is used to perform a registered capital attack on the supply chain knowledge graph to obtain a third attack result; the first attack result, the second attack result and the third attack result are combined to obtain an attack simulation result.

[0163] In one embodiment, when the processor 502 implements the step of using the degree-based attack strategy to perform a degree attack according to the supply chain knowledge graph to obtain a first attack result, the processor 502 specifically implements the following steps: The degree centrality of each enterprise is calculated according to the supply chain knowledge graph; the degree centrality of each enterprise is sorted, and the nodes whose rankings meet the requirements are selected as attack targets for attack to obtain a first attack result.

[0164] In one embodiment, when the processor 502 implements the step of using a strategy based on proximity centrality to attack the supply chain knowledge graph based on proximity centrality to obtain a second attack result, the processor 502 specifically implements the following steps: The proximity centrality of each enterprise is calculated according to the supply chain knowledge graph; the proximity centrality of each enterprise is sorted, and the nodes whose rankings meet the requirements are selected as attack targets to attack and obtain a second attack result.

[0165] In one embodiment, when the processor 502 implements the step of using the registered capital-based attack strategy to attack the supply chain knowledge graph with registered capital to obtain the third attack result, the processor 502 specifically implements the following steps: Obtain the registered capital of the enterprise; sort the registered capital of each enterprise, and select the nodes whose rankings meet the requirements as attack targets to attack, so as to obtain a third attack result.

[0166] In one embodiment, when the processor 502 implements the step of updating the enterprise operation status, updating the enterprise risk resistance capability, evaluating the overall network stability, and tracking the case according to the attack simulation result to obtain the processing result, the processor 502 specifically implements the following steps: use Update the business status of the enterprise, where j is the neighbor node of node enterprise i, is the time interval, represents the influence coefficient of all neighborhood fixed nodes, is the weight of each neighbor node, defined as , Neighbor node The number of transactions with the central enterprise, Indicates the current moment, It is the last moment; Used to quantify the current risk resistance of enterprises; Calculate the risk resistance of the enterprise and adopt Calculate the risk resistance of neighboring enterprises, where: represents the neighbor weights between different enterprises; ; Expressed as the coefficient of change of capital outflow; is the risk factor, , Defined as neighbor nodes The number of transactions with the central enterprise, Indicates the current moment, It is the last moment; is the weight of each neighbor node, ;use Evaluate overall network stability, where is the proportion of affected nodes; N is the total number of nodes included in the supply chain network, The value is 0 or 1. The threshold for the stability of the enterprise's operating status is set at the time; starting from the set initial node in the bidding database, nodes are extracted to build a supply chain network, and tracking experiments are carried out on supply chains with significant changes.

[0167] In one embodiment, when the processor 502 implements the step of performing situation awareness of future link break risk according to the processing result, the processor 502 specifically implements the following steps: The supply chain network is dynamically monitored, risk predicted and responded to in an emergency according to the processing results.

[0168] It should be understood that in the embodiment of the present application, the processor 502 may be a central processing unit 304 (CPU), and the processor 502 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0169] It can be understood by those skilled in the art that all or part of the processes in the method for implementing the above embodiment can be completed by instructing the relevant hardware through a computer program. The computer program includes program instructions, and the computer program can be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the process steps of the embodiment of the above method.

[0170] Therefore, the present invention also provides a storage medium. The storage medium may be a computer-readable storage medium. The storage medium stores a computer program, wherein when the computer program is executed by a processor, the processor executes the following steps: Obtain a bidding database and a company information database; use the bidding database and the company information database to construct a supply chain knowledge graph; use the supply chain knowledge graph to perform attack simulation to obtain attack simulation results; based on the attack simulation results, update the business operating status, update the enterprise risk resistance, evaluate the overall network stability, and track cases to obtain processing results; based on the processing results, perform situational awareness of future chain break risks.

[0171] In one embodiment, when the processor executes the computer program to implement the step of building a supply chain knowledge graph using the bidding database and the company information database, the processor specifically implements the following steps: Set an initial node, query the upstream and downstream structure of a set depth in the company information database and the bidding database, and use the ID to query relevant information for each node; in the bidding database, query the upstream and downstream relationship between nodes according to the edge ID to determine the transaction relationship; construct a supply chain knowledge graph based on the node related information and transaction relationship.

[0172] In one embodiment, when the processor executes the computer program to implement the step of using the supply chain knowledge graph to perform attack simulation to obtain an attack simulation result, the processor specifically implements the following steps: A degree-based attack strategy is used to perform a degree attack on the supply chain knowledge graph to obtain a first attack result; a proximity-centrality-based attack strategy is used to perform a proximity-centrality attack on the supply chain knowledge graph to obtain a second attack result; a registered capital-based attack strategy is used to perform a registered capital attack on the supply chain knowledge graph to obtain a third attack result; the first attack result, the second attack result and the third attack result are combined to obtain an attack simulation result.

[0173] In one embodiment, when the processor executes the computer program to implement the step of using a degree-based attack strategy to perform a degree attack according to the supply chain knowledge graph to obtain a first attack result, the processor specifically implements the following steps: The degree centrality of each enterprise is calculated according to the supply chain knowledge graph; the degree centrality of each enterprise is sorted, and the nodes whose rankings meet the requirements are selected as attack targets for attack to obtain a first attack result.

[0174] In one embodiment, when the processor executes the computer program to implement the step of using a proximity centrality-based strategy to attack the supply chain knowledge graph based on proximity centrality to obtain a second attack result, the processor specifically implements the following steps: The proximity centrality of each enterprise is calculated according to the supply chain knowledge graph; the proximity centrality of each enterprise is sorted, and the nodes whose rankings meet the requirements are selected as attack targets to attack and obtain a second attack result.

[0175] In one embodiment, when the processor executes the computer program to implement the step of using the registered capital-based attack strategy to attack the supply chain knowledge graph with registered capital to obtain the third attack result, the processor specifically implements the following steps: Obtain the registered capital of the enterprise; sort the registered capital of each enterprise, and select the nodes whose rankings meet the requirements as attack targets to attack, so as to obtain a third attack result.

[0176] In one embodiment, when the processor executes the computer program to implement the step of updating the business status of the enterprise, updating the risk resistance of the enterprise, evaluating the overall network stability, and tracking the cases according to the attack simulation results to obtain the processing results, the processor specifically implements the following steps: use Update the business status of the enterprise, where j is the neighbor node of node enterprise i, is the time interval, represents the influence coefficient of all neighborhood fixed nodes, is the weight of each neighbor node, defined as , Neighbor node The number of transactions with the central enterprise, Indicates the current moment, It is the last moment; Used to quantify the current risk resistance of enterprises; Calculate the risk resistance of the enterprise and adopt Calculate the risk resistance of neighboring enterprises, where: represents the neighbor weights between different enterprises; ; Expressed as the coefficient of change of capital outflow; is the risk factor, , Defined as neighbor nodes The number of transactions with the central enterprise, Indicates the current moment, It is the last moment; is the weight of each neighbor node, ;use Evaluate overall network stability, where is the proportion of affected nodes; N is the total number of nodes included in the supply chain network, The value is 0 or 1. The threshold for the stability of the enterprise's operating status is set at the time; starting from the set initial node in the bidding database, nodes are extracted to build a supply chain network, and tracking experiments are carried out on supply chains with significant changes.

[0177] In one embodiment, when the processor executes the computer program to implement the step of performing situation awareness of future chain break risks according to the processing result, the processor specifically implements the following steps: The supply chain network is dynamically monitored, risk predicted and responded to in an emergency according to the processing results.

[0178] The storage medium may be a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk, etc., which are computer-readable storage media that can store program codes.

[0179] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0180] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of each unit is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0181] The steps in the method of the embodiment of the present invention can be adjusted in order, combined and deleted according to actual needs. The units in the device of the embodiment of the present invention can be combined, divided and deleted according to actual needs. In addition, the functional units in various embodiments of the present invention can be integrated into a processing unit 304, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0182] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, terminal, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention.

[0183] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A chain-break risk simulation method based on adaptive risk resistance is characterized by: include: Access to bidding database and company information database; Constructing a supply chain knowledge graph using the bidding database and the company information database; Performing attack simulation using the supply chain knowledge graph to obtain attack simulation results; According to the attack simulation results, the enterprise's business status is updated, the enterprise's risk resistance capability is updated, the overall network stability is evaluated, and the case is tracked to obtain the processing results; Based on the processing results, situation awareness of future chain break risks is performed.

2. The method for simulating chain-break risk based on adaptive risk resistance according to claim 1 is characterized in that: The use of the bidding database and the company information database to construct a supply chain knowledge graph includes: Setting an initial node, searching the upstream and downstream structures of a set depth in the company information database and the bidding database, and using the ID to search for relevant information for each node; In the bidding database, the upstream and downstream relationships between nodes are queried based on the edge ID to determine the transaction relationship; A supply chain knowledge graph is constructed based on the node-related information and transaction relationships.

3. The method for simulating chain-break risk based on adaptive risk resistance according to claim 1 is characterized in that: The using the supply chain knowledge graph to perform attack simulation to obtain attack simulation results includes: Using a degree-based attack strategy to perform a degree attack according to the supply chain knowledge graph to obtain a first attack result; Adopting a closeness centrality-based strategy to attack the supply chain knowledge graph based on closeness centrality to obtain a second attack result; Using a registered capital-based attack strategy to attack the supply chain knowledge graph with registered capital to obtain a third attack result; The first attack result, the second attack result and the third attack result are combined to obtain an attack simulation result.

4. The method for simulating chain-break risk based on adaptive risk resistance according to claim 3 is characterized in that: The adopting of the degree-based attack strategy to perform a degree attack according to the supply chain knowledge graph to obtain a first attack result includes: Calculate the degree centrality of each enterprise according to the supply chain knowledge graph; The degree centrality of each enterprise is sorted, and the nodes whose ranking meets the requirements are selected as attack targets for attack to obtain the first attack result.

5. The method for simulating chain-break risk based on adaptive risk resistance according to claim 3 is characterized in that: The method of using a proximity-centrality-based strategy to attack the supply chain knowledge graph based on proximity-centrality to obtain a second attack result includes: Calculate the proximity centrality of each enterprise based on the supply chain knowledge graph; The closeness centrality of each enterprise is sorted, and the nodes whose rankings meet the requirements are selected as attack targets for attack to obtain the second attack result.

6. The method for simulating chain-break risk based on adaptive risk resistance according to claim 3 is characterized in that: The registered capital-based attack strategy is used to attack the supply chain knowledge graph with registered capital to obtain a third attack result, including: Obtain the registered capital of the enterprise; The registered capital of each enterprise is sorted, and the nodes whose rankings meet the requirements are selected as attack targets for attack to obtain the third attack result.

7. The method for simulating chain-break risk based on adaptive risk resistance according to claim 1 is characterized in that: The enterprise operation status update, enterprise risk resistance update, overall network stability assessment and case tracking are performed according to the attack simulation results to obtain processing results, including: use Update the business status of the enterprise, where j is the neighbor node of node enterprise i, is the time interval, represents the influence coefficient of all neighborhood fixed nodes, is the weight of each neighbor node, defined as , Neighbor node The number of transactions with the central enterprise, Indicates the current moment, It is the last moment; Used to quantify the current risk resistance of enterprises; use Calculate the risk resistance of the enterprise and adopt Calculate the risk resistance of neighboring enterprises, where: represents the neighbor weights between different enterprises; ; Expressed as the coefficient of change of capital outflow; is the risk factor, , Defined as neighbor nodes The number of transactions with the central enterprise, Indicates the current moment, It is the last moment; is the weight of each neighbor node, ; use Evaluate overall network stability, where is the proportion of affected nodes; N is the total number of nodes included in the supply chain network, The value is 0 or 1. The threshold for the stability of the business status of the enterprise is set at the time; Starting from the set initial node in the bidding database, nodes are extracted to build a supply chain network, and tracking experiments are carried out on supply chains with significant changes.

8. The method for simulating chain-break risk based on adaptive risk resistance according to claim 1, characterized in that: The situation awareness of future chain break risks according to the processing results includes: The supply chain network is dynamically monitored, risk predicted and responded to in an emergency according to the processing results.

9. A chain-break risk simulation device based on adaptive risk resistance is characterized in that: include: A database acquisition unit, used to acquire a bidding database and a company information database; A knowledge graph construction unit, used to construct a supply chain knowledge graph using the bidding database and the company information database; An initial attack simulation unit, used to perform attack simulation using the supply chain knowledge graph to obtain an attack simulation result; A processing unit, used to update the business status of the enterprise, update the risk resistance of the enterprise, evaluate the overall network stability, and track cases according to the attack simulation results to obtain processing results; A situation awareness unit is used to perform situation awareness of future chain break risks based on the processing results.

10. A computer device, characterized in that: The computer device comprises a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the method according to any one of claims 1 to 8 when executing the computer program.

Images