Supply chain risk management method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses a supply chain risk management method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring risk assessment information of each supplier in a supply chain; constructing a supply relation graph of the supply chain; according to the risk assessment information of each supplier, determining the supplier having the risk event; according to the supply relation graph, determining an influence result of the supplier having the risk event; the influence result comprises other suppliers influenced by the supplier having the risk event and the influence degree; and determining a coping strategy according to the influence result. By acquiring the risk assessment information of each supplier in the supply chain, more comprehensive and more prospective risk perception is realized based on the multi-source risk assessment information, the chain reaction and the real influence range of the risk can be dynamically analyzed according to the supply relation graph, and the coping strategy is directly generated, so that the dependence on human experience is reduced, the coping measure is more accurate and efficient, and the user experience is improved. And the coping and developing capabilities of an enterprise in a complex and changeable environment are greatly improved.

Description

Technical Field

[0001] This invention relates to the field of supply chain risk technology, and in particular to a supply chain risk management method, a supply chain risk management device, an electronic device, and a computer-readable storage medium. Background Technology

[0002] Today, supply chain management has become a key factor in corporate competitiveness, and the stability of the supply chain directly affects a company's production efficiency, cost control, and customer satisfaction. However, supply chains face a variety of internal and external risks, which may arise from market changes, political instability, natural disasters, supplier issues, and many other factors.

[0003] Current risk assessment methods typically rely on structured data from a single dimension, making it difficult to comprehensively cover diverse risks. The limited data sources result in incomplete risk assessments and an inability to effectively analyze risk propagation paths. Summary of the Invention

[0004] In view of the above problems, embodiments of the present invention are proposed to provide a supply chain risk management method, a supply chain risk management device, an electronic device, and a computer-readable storage medium that overcome or at least partially solve the above problems.

[0005] To address the above problems, a first aspect of the present invention provides a supply chain risk management method, the method comprising: Obtain risk assessment information from each supplier in the supply chain; Construct a supply relationship diagram of the aforementioned supply chain; Based on the risk assessment information of each supplier, the supplier in which the risk event occurred is identified; Based on the supply relationship diagram, determine the impact of the risk event on the supplier; the impact includes other suppliers affected by the supplier whose risk event occurred and the degree of impact. Based on the described impact, determine the corresponding response strategy.

[0006] Optionally, constructing the supply relationship diagram of the supply chain includes: Construct a supply relationship graph for each supplier in the supply chain; the nodes of the supply relationship graph are the suppliers, customers, and logistics providers; the edges of the supply relationship graph are the business relationships between each pair of suppliers, customers, and logistics providers; the edge weights of the supply relationship graph are the degree of dependence of the business relationships; the business relationships include at least one of procurement relationships, logistics relationships, and information sharing relationships; the degree of dependence includes at least one of procurement ratio, transportation frequency, and information sharing intensity.

[0007] Optionally, the risk assessment information of each supplier in the supply chain includes the supplier's operational data and market information; the operational data includes at least one of purchase orders, supplier performance, on-time delivery rate, quality pass rate, geographical location, supplier factory operating rate, logistics hub index, and equipment status; the market information includes at least one of supplier news, social media sentiment, geopolitical reports, and market dynamics.

[0008] Optionally, determining the supplier where the risk event occurred based on the risk assessment information of each supplier includes: Sentiment analysis is performed on the market information in the risk assessment information of each supplier, and a sentiment score corresponding to the market information is generated; Based on the operational data and the sentiment score, the risk score of each supplier is determined; Based on the risk scores of each supplier, the supplier in question is identified as having experienced a risk event.

[0009] Optionally, the step of performing sentiment analysis on the market information in the risk assessment information of each supplier and generating a sentiment score corresponding to the market information includes: The text data of the market information is preprocessed, and specific words in the preprocessed text data are identified; Obtain the number of specific words, their corresponding weights, and their corresponding sentiment polarity values ​​in the preprocessed text data; The sentiment score corresponding to the market information is determined based on the number of the specific words, the weight of the specific words, and the sentiment polarity value of the specific words.

[0010] Optionally, determining the impact of the risk event based on the supply relationship diagram includes: The supply relationship graph is input into a pre-trained risk assessment model, and the embedding vector of each node in the supply relationship graph is extracted through the risk assessment model; the embedding vector represents the position and influence of the node in the supply relationship graph. Based on the identified suppliers of the risk event and the embedded vector, the risk assessment model determines the risk diffusion path of the suppliers of the risk event in the supply chain. Based on the risk diffusion path, the affected suppliers are identified, and the degree of impact on the affected suppliers is assessed.

[0011] Optionally, determining the response strategy based on the impact results includes: Based on the described impact, multiple initial response strategies are generated; The various initial response strategies were evaluated; Based on the evaluation results of the initial response strategy assessment, the target response strategy is determined.

[0012] Optionally, determining the target response strategy based on the evaluation results of the initial response strategy evaluation includes: Based on the evaluation results of the initial response strategy assessment, candidate response strategies are determined from the multiple initial response strategies; Obtain user preference information and / or business scenarios, and determine the target response strategy from the candidate response strategies based on the user preference information and / or business scenarios.

[0013] According to a second aspect of the present invention, a supply chain risk management apparatus is provided, the apparatus comprising: The assessment information acquisition module is used to acquire risk assessment information from each supplier in the supply chain; A supply relationship diagram construction module is used to construct the supply relationship diagram of the supply chain; The risk supplier identification module is used to identify the supplier in which a risk event has occurred based on the risk assessment information of each supplier. The impact result determination module is used to determine the impact result of the supplier experiencing the risk event based on the supply relationship diagram; the impact result includes other suppliers affected by the supplier experiencing the risk event and the degree of impact; The response strategy determination module is used to determine the response strategy based on the impact results.

[0014] Optionally, the supply relationship graph construction module includes: The relationship graph construction submodule is used to construct the supply relationship graph of each supplier in the supply chain; the nodes of the supply relationship graph are the suppliers, customers, and logistics providers; the edges of the supply relationship graph are the business relationships between each pair of suppliers, customers, and logistics providers; the edge weights of the supply relationship graph are the degree of dependence of the business relationships; the business relationships include at least one of procurement relationships, logistics relationships, and information sharing relationships; the degree of dependence includes at least one of procurement ratio, transportation frequency, and information sharing intensity.

[0015] Optionally, the risk assessment information of each supplier in the supply chain includes the supplier's operational data and market information; the operational data includes at least one of purchase orders, supplier performance, on-time delivery rate, quality pass rate, geographical location, supplier factory operating rate, logistics hub index, and equipment status; the market information includes at least one of supplier news, social media sentiment, geopolitical reports, and market dynamics.

[0016] Optionally, the risk supplier determination module includes: The sentiment score generation submodule is used to perform sentiment analysis on the market information in the risk assessment information of each supplier and generate a sentiment score corresponding to the market information. The risk scoring determination submodule is used to determine the risk score of each supplier based on the operational data and the sentiment score; The supplier determination submodule is used to determine the supplier in which a risk event has occurred based on the risk scores of each supplier.

[0017] Optionally, the emotion rating generation submodule includes: A word recognition unit is used to preprocess the text data of the market information and identify specific words in the preprocessed text data; The word information acquisition unit is used to acquire the number of specific words, their corresponding weights, and their corresponding sentiment polarity values ​​in the preprocessed text data. The scoring unit is used to determine the sentiment score corresponding to the market information based on the number of the specific words, the weight of the specific words, and the sentiment polarity value of the specific words.

[0018] Optionally, the influence result determination module includes: The vector extraction submodule is used to input the supply relationship graph into a pre-trained risk assessment model, and extract the embedding vector of each node in the supply relationship graph through the risk assessment model; the embedding vector represents the position and influence of the node in the supply relationship graph; The risk assessment submodule is used to determine the risk diffusion path of the supplier experiencing the risk event in the supply chain through the risk assessment model based on the identified supplier and the embedding vector, identify the affected suppliers based on the risk diffusion path, and assess the degree of impact on the affected suppliers.

[0019] Optionally, the response strategy determination module includes: The initial strategy generation submodule is used to generate multiple initial response strategies based on the impact results. The strategy evaluation submodule is used to evaluate the various initial response strategies. The target strategy determination submodule is used to determine the target response strategy based on the evaluation results of the initial response strategy evaluation.

[0020] Optionally, the target strategy determination submodule includes: The candidate strategy determination unit is used to determine candidate response strategies from the multiple initial response strategies based on the evaluation results of the initial response strategy evaluation. The target response strategy determination unit is used to acquire user preference information and / or business scenarios, and determine the target response strategy from the candidate response strategies based on the user preference information and / or business scenarios.

[0021] According to a third aspect of the present invention, an electronic device is provided, comprising: a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements the steps of the supply chain risk management method as described in any of the preceding embodiments.

[0022] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the steps of the supply chain risk management method as described in any of the preceding embodiments.

[0023] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects: This invention discloses a supply chain risk management method, apparatus, electronic device, and storage medium. The method includes: acquiring risk assessment information of each supplier in the supply chain; constructing a supply relationship diagram of the supply chain; identifying the supplier experiencing a risk event based on the risk assessment information of each supplier; determining the impact of the risk event based on the supply relationship diagram; the impact result includes other suppliers affected by the risk event and the degree of impact; and determining a response strategy based on the impact result. By acquiring risk assessment information of each supplier in the supply chain, a more comprehensive and forward-looking risk perception is achieved based on multi-source risk assessment information. The supply relationship diagram enables dynamic analysis of the chain reactions and true scope of impact of risks, and directly generates response strategies, reducing reliance on human experience and making response measures more accurate and efficient, greatly enhancing the enterprise's ability to cope with and develop in complex and ever-changing environments. Attached Figure Description

[0024] Figure 1 This is a flowchart illustrating the steps of a supply chain risk management method provided in an embodiment of the present invention; Figure 2 This is a flowchart of another supply chain risk management method provided by an embodiment of the present invention; Figure 3 This is a logical block diagram of a supply chain risk management method provided in an embodiment of the present invention; Figure 4 This is a structural block diagram of a supply chain risk management device provided in an embodiment of the present invention. Detailed Implementation

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

[0026] Current risk assessment methods typically rely on structured data from a single dimension, making it difficult to comprehensively cover diverse risks. The limited data sources result in incomplete risk assessments and an inability to effectively analyze risk propagation paths.

[0027] One of the core concepts of this invention is that by acquiring risk assessment information from each supplier in the supply chain, a more comprehensive and forward-looking risk perception can be achieved based on multi-source risk assessment information. According to the supply relationship diagram, the chain reaction and true scope of impact of risks can be dynamically analyzed, and response strategies can be directly generated, reducing reliance on human experience and making response measures more accurate and efficient.

[0028] Reference Figure 1 The diagram illustrates a flowchart of a supply chain risk management method provided by an embodiment of the present invention. The method specifically includes the following steps: Step 101: Obtain risk assessment information for each supplier in the supply chain; A supplier is a business or individual that provides products, services or raw materials to another business.

[0029] A supply chain is a network of interconnected organizations, people, activities, information, and resources, with the core objective of realizing the entire process of a product or service from raw materials to the final consumer. It includes suppliers, manufacturers, distributors and retailers, logistics service providers, and consumers / customers.

[0030] Supplier risk assessment information refers to a collection of various data used to analyze and quantify the negative impact that suppliers may have on their downstream businesses, such as logistics providers and distributors.

[0031] In this embodiment of the invention, relevant data of each supplier in the supply chain are obtained from multiple data sources, including structured data (such as purchase orders, supplier performance, on-time delivery rate, quality pass rate, geographical location, etc.) and unstructured data (such as supplier news, social media sentiment, geopolitical reports, market dynamics, etc.).

[0032] First, multi-source data fusion technology is used to comprehensively obtain risk assessment information from each supplier in the supply chain. Internally, operational data from each supplier is acquired, such as structured indicators like historical purchase orders, on-time delivery rates, and quality pass rates. Externally, market information related to suppliers is captured and monitored in real time, including unstructured information such as news sentiment, social media activity, geopolitical reports, and market fluctuations.

[0033] By incorporating IoT sensor data and satellite remote sensing imagery, information such as supplier factory operating status and logistics hub activity is acquired through remote sensing technology, and image recognition technology is used to assess their operational status. Sensor networks collect data on the operating status of key equipment and environmental parameters as auxiliary indicators of supply chain operational health. This data is then analyzed and transformed into key quantitative indicators reflecting the real-time operational status of suppliers, such as factory operating rates, logistics hub activity indices, and equipment operating status.

[0034] Step 102: Construct the supply relationship diagram of the supply chain; A supply chain diagram is a visual representation of the complex dependencies between supplier entities in a supply chain. It primarily consists of two elements: nodes and edges. Nodes are entities or functional units within the supply chain. Edges represent the connections, relationships, or interactions between nodes. The weights of the edges are key to quantifying these relationships, indicating their strength or degree of dependence.

[0035] In this embodiment of the invention, a supply chain network diagram is established with suppliers as nodes and relationships such as procurement, logistics, and collaboration as edges.

[0036] By constructing a supply chain relationship diagram, the complex supply chain structure is transformed into a computable model. The process involves identifying supply chain entities and relationships: all entities in the supply chain are treated as nodes, including core enterprises, suppliers at all levels, logistics service providers, and key customers; business dependencies between entities are used as edges, encompassing not only direct procurement and logistics relationships but also potential indirect relationships through data correlation analysis, such as multiple Tier 1 suppliers sharing the same Tier 2 supplier or sharing the same key logistics hub. Next, the edges in the diagram are quantified and weighted, for example, by defining relationship strength based on the proportion of procurement amount and logistics dependence, thus obtaining the supply relationship diagram for each supplier in the supply chain.

[0037] Step 103: Based on the risk assessment information of each supplier, determine the supplier in which the risk event occurred; In this embodiment of the invention, the risk assessment information of each supplier generated by the fusion of multi-source data is analyzed to determine the comprehensive risk score of each supplier. When the comprehensive risk score of any supplier rises sharply within a preset period, or when a key risk dimension (such as the negative sentiment index of public opinion or the failure rate of IoT devices) exceeds a preset threshold, it will be marked as a candidate for a risk event. The analysis focuses not only on the static score but also on the dynamic trend of the risk indicators. Cross-validation and root cause analysis are performed on the supplier's related data to eliminate data noise interference and ultimately confirm whether it is a source of a risk event.

[0038] The system will acquire relevant data from multiple data sources for each supplier in the supply chain, including operational data such as structured indicators like historical purchase orders, on-time delivery rates, and quality pass rates, as well as market information related to suppliers, including unstructured information such as news sentiment, social media activity, geopolitical reports, and market fluctuations. Natural language processing technology will be used to process the text data of market information related to suppliers, and the operational data will be integrated with the processed market information to obtain a comprehensive risk score for each supplier.

[0039] The comprehensive risk score obtained from each supplier is an important basis for determining whether a supplier is in a high-risk state. Risk level thresholds can be set based on the scores, but this embodiment of the invention does not limit this.

[0040] Step 104: Based on the supply relationship diagram, determine the impact of the risk event on the supplier; the impact includes other suppliers affected by the supplier whose risk event occurred and the degree of impact. The impact of a risk event on a supplier includes the other suppliers affected by the risk event and the extent of the impact on the supplier.

[0041] In this embodiment of the invention, based on identifying the supplier where the risk event occurred, the propagation effect of the risk is dynamically simulated and quantified using a pre-constructed supply relationship graph. The supplier node where the risk event occurred is injected into the graph neural network model as the initial risk signal, and a multi-round iterative risk propagation simulation is initiated based on the message passing mechanism of the graph neural network. During this process, the risk signal spreads along the edges in the supply relationship graph, according to the relationship strength represented by its weight, to upstream and downstream nodes and related nodes. In each iteration, neighboring nodes aggregate risk information from their related nodes and update their own risk state embedding vector accordingly.

[0042] Risk propagation simulation can identify the risk propagation network centered on the source of the risk event. Its output impact results include a list of other affected suppliers and the degree of impact. This degree can be reflected not only in the specific increase in risk score, but also quantified as an estimate of key business indicators such as delivery delay days and potential cost increases.

[0043] Step 105: Determine the response strategy based on the impact results.

[0044] In this embodiment of the invention, based on determining the impact of a supplier experiencing a risk event, the impact results, including a list of other affected suppliers and their specific degrees of impact, are used as input. A series of initial response plans are then automatically generated based on a strategy database. These plans cover multiple levels, including operations, strategy, and collaboration, such as activating backup suppliers, utilizing safety stock, adjusting production schedules, or providing financial support.

[0045] The generated strategy set is then subjected to in-depth evaluation, based on a multi-dimensional assessment that includes cost, execution time, expected risk reduction rate, and feasibility. Finally, based on the user's preset decision-making preferences or through a digital twin simulation platform to pre-test and verify the top-level strategies, the optimal response strategy with the highest scenario adaptability is recommended.

[0046] Reference Figure 2 This document illustrates a flowchart of another supply chain risk management method provided by an embodiment of the present invention. The risk assessment information for each supplier in the supply chain includes operational data and market information for each supplier. The operational data includes at least one of purchase orders, supplier performance, on-time delivery rate, quality pass rate, geographical location, supplier factory operating rate, logistics hub index, and equipment status. The market information includes at least one of supplier news, social media sentiment, geopolitical reports, and market dynamics. The method includes: Step 201: Obtain risk assessment information for each supplier in the supply chain; Supplier risk assessment information refers to a collection of data used to analyze and quantify the potential negative impact of suppliers on their downstream businesses, such as logistics providers and distributors. This includes each supplier's operational data and market information; operational data includes at least one of the following: purchase orders, supplier performance, on-time delivery rate, quality pass rate, geographical location, supplier factory utilization rate, logistics hub index, and equipment status; market information includes at least one of the following: supplier news, social media sentiment, geopolitical reports, and market dynamics. In this embodiment of the invention, relevant data of each supplier in the supply chain are obtained from multiple data sources, including structured data (such as purchase orders, supplier performance, on-time delivery rate, quality pass rate, geographical location, etc.) and unstructured data (such as supplier news, social media sentiment, geopolitical reports, market dynamics, etc.).

[0047] First, multi-source data fusion technology is used to comprehensively obtain risk assessment information from each supplier in the supply chain. Internally, operational data from each supplier is acquired, such as structured indicators like historical purchase orders, on-time delivery rates, and quality pass rates. Externally, market information related to suppliers is captured and monitored in real time, including unstructured information such as news sentiment, social media activity, geopolitical reports, and market fluctuations.

[0048] By incorporating IoT sensor data and satellite remote sensing imagery, information such as supplier factory operating status and logistics hub activity is acquired through remote sensing technology, and image recognition technology is used to assess their operational status. Sensor networks collect data on the operating status of key equipment and environmental parameters as auxiliary indicators of supply chain operational health. This data is then analyzed and transformed into key quantitative indicators reflecting the real-time operational status of suppliers, such as factory operating rates, logistics hub activity indices, and equipment operating status.

[0049] After obtaining risk assessment information from each supplier in the supply chain, proceed to step 202.

[0050] Step 202: Construct the supply relationship diagram of the supply chain; In this embodiment of the invention, a supply chain network diagram is established with suppliers as nodes and relationships such as procurement, logistics, and collaboration as edges.

[0051] By constructing a supply chain relationship diagram, the complex supply chain structure is transformed into a computable model. The process involves identifying supply chain entities and relationships: all entities in the supply chain are treated as nodes, including core enterprises, suppliers at all levels, logistics service providers, and key customers; business dependencies between entities are used as edges, encompassing not only direct procurement and logistics relationships but also potential indirect relationships through data correlation analysis, such as multiple Tier 1 suppliers sharing the same Tier 2 supplier or sharing the same key logistics hub. Next, the edges in the diagram are quantified and weighted, for example, by defining relationship strength based on the proportion of procurement amount and logistics dependence, thus obtaining the supply relationship diagram for each supplier in the supply chain.

[0052] In some embodiments, step 202 may include the following sub-steps: Sub-step S11: Construct a supply relationship diagram for each supplier in the supply chain; the nodes of the supply relationship diagram are the suppliers, customers, and logistics providers; the edges of the supply relationship diagram are the business relationships between each pair of suppliers, customers, and logistics providers; the edge weights of the supply relationship diagram are the degree of dependence of the business relationships; the business relationships include at least one of procurement relationships, logistics relationships, and information sharing relationships; the degree of dependence includes at least one of procurement ratio, transportation frequency, and information sharing intensity.

[0053] The constructed supply chain diagram shows the supply relationships between various suppliers: Nodes: Represent entities such as suppliers, customers, logistics providers, and raw material suppliers. Edges: Represent business relationships such as procurement, logistics, collaboration, and information sharing. Edge weights: Represent the degree of dependence, such as procurement ratio, transportation frequency, and information sharing intensity.

[0054] Introducing indirect relationships includes not only direct transaction relationships (such as A purchasing from B), but also: shared logistics providers (both A and B use D's logistics services), shared raw materials (both A and B use E's raw materials), and shared information systems (A and B use F's enterprise resource planning system). These indirect relationships have a significant impact on risk propagation and need to be included in the supply relationship diagram structure.

[0055] In this embodiment of the invention, a dynamic and quantitative network model for supply chain risk analysis is provided by constructing a supply relationship graph. First, key entities in the network are identified and defined as nodes, including not only suppliers at all levels but also core customers and logistics service providers, ensuring the integrity of the network structure. The business relationships between nodes are represented as edges, which explicitly characterize various business flows such as procurement, logistics, and information sharing. Each edge is assigned a quantitative weight, for example, quantifying procurement dependence by the proportion of procurement amount, logistics dependence by transportation frequency, and information sharing intensity by the level of data interaction, thereby transforming qualitative business relationships into calculable and comparable numerical indicators.

[0056] This supply chain diagram transforms the previously vague and subjective supply chain dependencies into a clear and computable structured model. This diagram accurately identifies the relationships between suppliers and provides a foundation for subsequent risk propagation simulations, significantly improving the accuracy of risk propagation path identification.

[0057] After constructing the supply relationship diagram of the supply chain, proceed to step 203.

[0058] Step 203: Based on the risk assessment information of each supplier, determine the supplier in which the risk event occurred; In this embodiment of the invention, the risk assessment information of each supplier generated by the fusion of multi-source data is analyzed to determine the comprehensive risk score of each supplier. When the comprehensive risk score of any supplier rises sharply within a preset period, or when a key risk dimension (such as the negative sentiment index of public opinion or the failure rate of IoT devices) exceeds a preset threshold, it will be marked as a candidate for a risk event. The analysis focuses not only on the static score but also on the dynamic trend of the risk indicators. Cross-validation and root cause analysis are performed on the supplier's related data to eliminate data noise interference and ultimately confirm whether it is a source of a risk event.

[0059] The system will acquire relevant data from multiple data sources across the supply chain, including operational data such as structured metrics like historical purchase orders, on-time delivery rates, and quality pass rates, as well as unstructured market information such as news, social media activity, geopolitical reports, and market fluctuations. Natural language processing (NLP) technology will be used to process the textual data related to the supplier's market information. The operational data will then be integrated with the processed market information to obtain a comprehensive risk score for each supplier. Based on this comprehensive risk score, the suppliers at risk of experiencing incidents will be identified.

[0060] In some embodiments, step 203 may include the following sub-steps: Sub-step S21: Perform sentiment analysis on the market information in the risk assessment information of each supplier, and generate a sentiment score corresponding to the market information; Sentiment score is a quantified numerical indicator calculated using natural language processing technology. It is used to objectively measure the subjective emotions, attitudes, and biases contained in a piece of textual information (such as news, reports, and social media posts). Sentiment scores are within a continuous numerical range, such as [-1, +1]. -1.0 indicates extreme negativity, such as a news headline like "Supplier A declares bankruptcy, factory seized by creditors." 0.0 indicates neutrality, such as a factual report like "Supplier B holds its annual shareholders' meeting today." +1.0 indicates extreme positiveness, such as a report like "Supplier C breaks through technological bottlenecks, secures huge orders, stock price soars."

[0061] In this embodiment of the invention, natural language processing technology is used to segment, identify entities, and perform sentiment analysis on unstructured market information text data, extracting key semantic features and converting them into numerical risk indicators. For example, a sentiment score of -0.7 is assigned to negative news about a supplier, indicating that the supplier currently poses a high risk.

[0062] In-depth sentiment intelligence analysis is conducted on unstructured market information from various supplier risk assessments. This process utilizes natural language processing technology to preprocess collected market information, such as supplier news, social media sentiment, geopolitical reports, and market dynamics, including word segmentation, noise reduction, and entity recognition. Subsequently, the overall sentiment polarity of the text is determined, categorized as positive, negative, or neutral, enabling more precise identification of targeted sentiment tendencies strongly related to specific suppliers or their industries and products. This qualitative semantic understanding is then transformed into a standardized numerical output—a sentiment score—thus converting vague market opinions into quantifiable and comparable risk warning indicators.

[0063] In some embodiments, step S21 may include the following sub-steps: Sub-step S211: Preprocess the text data of the market information and identify specific words in the preprocessed text data; Unstructured market information such as news, social media, geopolitical reports, etc. does not have a fixed format or fields, has diverse content forms and complex semantics, and cannot be directly used for model input. It must be transformed into structured and numerical information through natural language processing techniques.

[0064] In the embodiment of the present invention, automated preprocessing is performed on the obtained market information text data to lay a foundation for subsequent in-depth semantic analysis. This process includes word segmentation, that is, splitting a continuous text sequence into independent lexical units; removing stop words to filter out high-frequency but low-information words such as "of" and "in"; and text normalization, such as converting to lowercase and performing stemming to eliminate noise caused by morphological variations.

[0065] Perform specific word recognition on the preprocessed clean text data. These specific words are predefined domain keywords highly relevant to supply chain risks, and their categories mainly include risk entities (such as supplier names, raw material names), risk events (such as strikes, fires, sanctions), and sentiment modifiers (such as shortages, delays, innovations, stability). By identifying specific words in the text data, the core risk elements in the text can be accurately captured.

[0066] Sub-step S212: Obtain the quantity, corresponding weight, and corresponding sentiment polarity value of the specific words in the preprocessed text data; The sentiment polarity value is a predefined numerical label assigned to a single word or phrase, used to precisely represent the inherent positive or negative attitude and emotional color of the word in a specific context.

[0067] In the embodiment of the present invention, on the basis of completing text preprocessing and specific word recognition, further quantitative feature extraction is performed on these keyword words. Count the occurrence frequencies of different categories of specific words. For example, count the number of risk event words such as "strike" and "fire" to measure the density and concentration of risk signals in the text. Subsequently, the system assigns a weight value to each word, and this weight is determined based on its importance in the field of supply chain risks. Obtain the sentiment polarity value of each specific word (such as +1 for positive and -1 for negative). The sentiment polarity value of a word can be determined based on static mapping of a sentiment dictionary, model prediction based on deep learning, and dynamic evaluation in combination with the context.

[0068] Sub-step S213: Determine the sentiment score corresponding to the market information according to the quantity of the specific words, the weight corresponding to the specific words, and the sentiment polarity value corresponding to the specific words.

[0069] The sentiment score corresponding to the market information can be determined by the following formula:

[0070] Where S represents the sentiment score; n represents the number of specific words in the text; w i This represents the weight of the i-th specific word; e i This represents the sentiment polarity value of the i-th specific word (e.g., +1 for positive, -1 for negative). i The weights of each word are not fixed values, but dynamically adjustable variables. Initially, a base weight is set, and the weights are automatically adjusted based on actual usage feedback (such as whether risk events are correctly identified after they occur), thus achieving closed-loop optimization.

[0071] In this embodiment of the invention, the quantitative features of specific words in the text are fused into a single sentiment score. Based on the number, weight, and sentiment polarity values ​​of the acquired specific words, a weighted average is used to quantify the semantic sentiment tendency of the text. This sentiment score is the weighted sum of the sentiment polarity values ​​of all specific words in the text and their corresponding weights, calculated using the sentiment score calculation formula. By comprehensively considering the importance and emotional intensity of different words in risk assessment, a comprehensive indicator that accurately reflects the overall sentiment tendency of market information is derived.

[0072] This step represents the final result of the text-based risk analysis. The sentiment score not only reflects the overall direction of market opinion (positive or negative), but also amplifies the influence of key risk event terms through the introduction of weights, ensuring a high correlation between the score and the actual severity of supply chain risks. This provides intuitive and comparable quantitative input for subsequent comprehensive risk assessments and risk communication simulations.

[0073] Sub-step S22: Determine the risk score of each supplier based on the operational data and the sentiment score; The risk score for each supplier is determined by weighted fusion of structured operational data and sentiment scores corresponding to market information. For example, the on-time delivery rate, quality pass rate, and sentiment score of a supplier are weighted together to obtain a comprehensive risk score. The weights of each component in the comprehensive risk score calculation are dynamically adjustable variables. Initially, basic weights are set, and the weights are automatically adjusted based on actual usage feedback (such as whether risk events are correctly identified after they occur) to achieve closed-loop optimization. This embodiment of the invention does not limit the scope of this approach.

[0074] In this embodiment of the invention, operational data on the internal status of suppliers are combined with sentiment scores reflecting the dynamics of the external environment to determine the comprehensive risk score of each supplier. Quantitative operational indicators such as on-time delivery rate and quality pass rate are weighted and integrated with a quantitative indicator—sentiment scores from market opinion—and appropriate dynamic weights are assigned to each indicator based on its historical performance and contribution to the prediction of actual risk events. The comprehensive risk score for each supplier is then calculated.

[0075] Sub-step S23: Based on the risk scores of each supplier, determine the supplier in which the risk event occurred.

[0076] Risk scoring is a crucial basis for determining whether a supplier is in a high-risk state, and risk level thresholds can be set based on the score. The comprehensive risk score can be used as part of supplier performance evaluation to assess the supplier's overall performance, develop supplier classification and management strategies, and decide whether to introduce new suppliers or eliminate existing ones. In risk assessment models, the risk score can serve as the "starting point" for initial risk events, used to initiate risk diffusion simulations.

[0077] In this embodiment of the invention, based on the risk scores of each supplier, they are compared in real time with preset industry and historical thresholds, with a focus on monitoring short-term trends in their scores. When the absolute value of any supplier's comprehensive risk score exceeds a set warning threshold, or when its score shows a sharp increase (e.g., an increase exceeding 50%) within a specific time window, it is initially marked as a candidate for a risk event. Cross-validation is performed on the multi-dimensional data associated with that supplier to ultimately confirm whether it is a source of a risk event. By analyzing the risk scores of each supplier, potential risks can be sensitively identified, thereby achieving early warning of risks and providing a clear target for subsequent accurate and efficient simulation of impacts and formulation of response strategies.

[0078] After identifying the supplier where the risk event occurred, proceed to step 204.

[0079] Step 204: Input the supply relationship graph into a pre-trained risk assessment model, and extract the embedding vector of each node in the supply relationship graph through the risk assessment model; the embedding vector represents the position and influence of the node in the supply relationship graph; The supply relationship graph is input into a pre-trained risk assessment model, and the embedding vector of each node is extracted. This embedding vector represents its position and influence in the supply chain network.

[0080] The embedding vector of each node can be determined using the following formula:

[0081] Among them, h j (l)N represents the embedding vector of node j at layer l; (i) d represents the set of neighboring nodes of node i; i W represents the degree of node i; (l) σ is a learnable weight matrix; σ is the activation function. This represents the embedding vector of node i at layer l+1. degree d i d represents the total number of edges connecting node i to other nodes in the supply graph; that is, d i = The number of all neighboring nodes of node i. Degree d i This is typically used for normalization to prevent nodes with high degrees from having an excessive influence on their neighbors. The weight matrix is ​​automatically learned during model training and continuously optimized and determined through the backpropagation algorithm during training.

[0082] In this embodiment of the invention, the constructed supply relationship graph is input into a pre-trained risk assessment model, which is typically based on a graph neural network architecture, and this embodiment of the invention does not limit this.

[0083] Through the message passing and aggregation mechanism within the risk assessment model, each node (supplier, customer, etc.) receives and integrates information from its neighboring nodes. After multiple iterations, the model generates an embedding vector for each node in the graph. This vector is automatically learned by the model from the graph's structural data and represents the node's global position and influence strength within the entire supply relationship network.

[0084] After extracting the embedding vector of each node in the supply relationship graph through the risk assessment model, step 205 is executed.

[0085] Step 205: Based on the identified supplier of the risk event and the embedding vector, determine the risk diffusion path of the supplier of the risk event in the supply chain through the risk assessment model, identify the affected suppliers based on the risk diffusion path, and assess the degree of impact of the affected suppliers.

[0086] When a risk event occurs at a certain node, the risk assessment model simulates the diffusion path of the risk in the supply chain network through its propagation mechanism, identifies potentially affected upstream and downstream suppliers, and assesses their risk levels. For example, if a tier-one supplier experiences a delivery delay, the risk assessment model can predict its potential impact on tier-two suppliers and issue an early warning.

[0087] In this embodiment of the invention, a pre-trained risk assessment model is fed with a identified risk event supplier and its embedding vector as input. The risk assessment model utilizes its message passing mechanism to simulate the multi-round iterative diffusion of risk signals along the edges of the supply relationship graph. Based on the relationship strength represented by the edge weights, the state of its neighboring nodes and even more distant nodes is dynamically updated. Through simulation, the model can obtain a clear risk diffusion path and output a list of all nodes whose states have changed significantly as affected suppliers. Finally, the system quantifies the impact of each affected supplier by comparing the state changes of nodes before and after risk diffusion (such as the offset of the embedding vector or the derived risk value). This step dynamically and correlates the simulation of the chain reaction of risk, enabling a clear understanding of the risk propagation path and its scope, and allowing for the early quantification of potential business losses.

[0088] After determining the impact of the risk event on the supplier, proceed to step 206.

[0089] Step 206: Determine the response strategy based on the impact results.

[0090] Based on the impact, multiple response strategies are automatically generated, including but not limited to: changing suppliers, increasing safety stock, finding alternative materials, and adjusting production plans.

[0091] In this embodiment of the invention, based on determining the impact of a supplier experiencing a risk event, the impact results, including a list of other affected suppliers and their specific degrees of impact, are used as input. A series of initial response plans are then automatically generated based on a strategy database. These plans cover multiple levels, including operations, strategy, and collaboration, such as activating backup suppliers, utilizing safety stock, adjusting production schedules, or providing financial support.

[0092] The generated strategy set is then subjected to in-depth evaluation, based on a multi-dimensional assessment that includes cost, execution time, expected risk reduction rate, and feasibility. Finally, based on the user's preset decision-making preferences or through a digital twin simulation platform to pre-test and verify the top-level strategies, the optimal response strategy with the highest scenario adaptability is recommended.

[0093] In some embodiments, step 206 may include the following sub-steps: Sub-step S31: Based on the impact results, generate multiple initial response strategies; Sub-step S32: Evaluate the various initial response strategies; Sub-step S33: Determine the target response strategy based on the evaluation results of the initial response strategy evaluation.

[0094] In this embodiment of the invention, based on the obtained risk impact results, multiple initial response strategies are generated, covering various aspects from activating backup suppliers and utilizing safety stock to adjusting production plans. A multi-objective optimization algorithm is used to evaluate the generated strategy set, based on a multi-dimensional function that includes cost, execution time, expected risk reduction rate, and feasibility.

[0095] A multi-objective optimization algorithm (such as NSGA-II) is used to evaluate each strategy from multiple dimensions, including cost, feasibility, and expected results, to generate a Pareto front solution set. The Pareto front solution set refers to the set of coping strategies.

[0096] The multi-objective optimization process based on multi-objective optimization algorithms first encodes multiple initial strategies into individuals and initializes the population. Then, iteratively executes the following steps: calculating the function value of each strategy on multiple objectives such as cost, time, risk, and feasibility; hierarchically sorting the population according to non-dominance relationships, and calculating the crowding degree within the same level to maintain the distribution of solutions; generating new populations based on sorting and crowding degree using genetic operators such as selection, crossover, and mutation, and merging parent and child individuals, repeating the above process until convergence, and finally outputting the Pareto front solution set representing the optimal trade-off.

[0097] The recommendation strategy is validated and optimized through a simulation platform, and a multi-dimensional objective function system including cost, time, risk and feasibility is constructed. The function value is determined by business rules, model prediction and user preferences. Then, based on the congestion calculation, the distribution diversity of the solution set on the Pareto front is guaranteed to avoid local optima. Finally, a set of strategies that achieve the optimal balance among multiple conflicting objectives is output.

[0098] Based on the generated response strategies and the evaluation results, target response strategies are determined. The systematic generation and evaluation process ensures the comprehensiveness and scientific rigor of the strategies. Multi-dimensional evaluation avoids the limitations of single-dimensional assessments. Finally, simulation rehearsals or preference selection ensure the feasibility of the recommended strategies.

[0099] In some embodiments, step S33 may include the following sub-steps: Sub-step S331: Based on the evaluation results of the initial response strategy evaluation, determine candidate response strategies from the multiple initial response strategies; Sub-step S332: Obtain user preference information and / or business scenario, and determine the target response strategy from the candidate response strategies based on the user preference information and / or business scenario.

[0100] In this embodiment of the invention, after obtaining the multi-objective evaluation results of the initial strategy, candidate response strategies are first selected from multiple strategies based on the evaluation results of the initial response strategy evaluation. Then, by acquiring user preference information (such as cost priority or time priority) and specific business scenarios (such as ensuring supply during peak season or reducing costs during off-season), the target response strategy that best fits the current management objectives and actual business needs is accurately selected from the candidate strategies. By introducing the dimensions of user preferences and business scenarios, it is ensured that the finally selected strategy not only conforms to the current management priorities of the enterprise, but also adapts to the specific operational situation, avoiding the dilemma of optimal but inapplicable decision-making.

[0101] Reference Figure 3 This diagram illustrates a logical block diagram of a supply chain risk management method provided by an embodiment of the present invention, based on... Figure 3 This diagram illustrates the logic of an embodiment of the present invention. It describes how risk assessment information from each supplier in the supply chain is acquired, and then a supply relationship diagram is constructed. Based on the acquired risk assessment information, a risk score is determined for each supplier. Using a risk assessment model, the risk propagation path and affected suppliers are determined according to the supply relationship diagram and the risk scores of each supplier. Multiple initial response strategies are generated, evaluated, and finally, a target response strategy is determined.

[0102] This invention discloses a supply chain risk management method, apparatus, electronic device, and storage medium. The method includes: acquiring risk assessment information of each supplier in the supply chain; constructing a supply relationship diagram of the supply chain; identifying the supplier experiencing a risk event based on the risk assessment information of each supplier; determining the impact of the risk event based on the supply relationship diagram; the impact result includes other suppliers affected by the risk event and the degree of impact; and determining a response strategy based on the impact result. By acquiring risk assessment information of each supplier in the supply chain, a more comprehensive and forward-looking risk perception is achieved based on multi-source risk assessment information. The supply relationship diagram enables dynamic analysis of the chain reactions and true scope of impact of risks, and directly generates response strategies, reducing reliance on human experience and making response measures more accurate and efficient, greatly enhancing the enterprise's ability to cope with and develop in complex and ever-changing environments.

[0103] It should be noted that, for the sake of simplicity, the method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0104] Reference Figure 4The diagram illustrates a structural block diagram of a supply chain risk management device according to an embodiment of the present invention. The device includes: The assessment information acquisition module 301 is used to acquire risk assessment information of each supplier in the supply chain; Supply relationship diagram construction module 302 is used to construct the supply relationship diagram of the supply chain; The risk supplier determination module 303 is used to determine the supplier in which a risk event has occurred based on the risk assessment information of each supplier. The impact result determination module 304 is used to determine the impact result of the supplier that has experienced a risk event based on the supply relationship diagram; the impact result includes other suppliers affected by the supplier that has experienced a risk event and the degree of impact; The response strategy determination module 305 is used to determine the response strategy based on the impact results.

[0105] In some embodiments, the supply relationship diagram construction module 302 includes: The relationship graph construction submodule is used to construct the supply relationship graph of each supplier in the supply chain; the nodes of the supply relationship graph are the suppliers, customers, and logistics providers; the edges of the supply relationship graph are the business relationships between each pair of suppliers, customers, and logistics providers; the edge weights of the supply relationship graph are the degree of dependence of the business relationships; the business relationships include at least one of procurement relationships, logistics relationships, and information sharing relationships; the degree of dependence includes at least one of procurement ratio, transportation frequency, and information sharing intensity.

[0106] In some embodiments, the risk assessment information of each supplier in the supply chain includes each supplier's operational data and market information; the operational data includes at least one of purchase orders, supplier performance, on-time delivery rate, quality pass rate, geographical location, supplier factory utilization rate, logistics hub index, and equipment status; the market information includes at least one of supplier news, social media sentiment, geopolitical reports, and market dynamics.

[0107] In some embodiments, the risk supplier determination module 303 includes: The sentiment score generation submodule is used to perform sentiment analysis on the market information in the risk assessment information of each supplier and generate a sentiment score corresponding to the market information. The risk scoring determination submodule is used to determine the risk score of each supplier based on the operational data and the sentiment score; The supplier determination submodule is used to determine the supplier in which a risk event has occurred based on the risk scores of each supplier.

[0108] In some embodiments, the emotion rating generation submodule includes: A word recognition unit is used to preprocess the text data of the market information and identify specific words in the preprocessed text data; The word information acquisition unit is used to acquire the number of specific words, their corresponding weights, and their corresponding sentiment polarity values ​​in the preprocessed text data. The scoring unit is used to determine the sentiment score corresponding to the market information based on the number of the specific words, the weight of the specific words, and the sentiment polarity value of the specific words.

[0109] In some embodiments, the influence result determination module 304 includes: The vector extraction submodule is used to input the supply relationship graph into a pre-trained risk assessment model, and extract the embedding vector of each node in the supply relationship graph through the risk assessment model; the embedding vector represents the position and influence of the node in the supply relationship graph; The risk assessment submodule is used to determine the risk diffusion path of the supplier experiencing the risk event in the supply chain through the risk assessment model based on the identified supplier and the embedding vector, identify the affected suppliers based on the risk diffusion path, and assess the degree of impact on the affected suppliers.

[0110] In some embodiments, the response strategy determination module 305 includes: The initial strategy generation submodule is used to generate multiple initial response strategies based on the impact results. The strategy evaluation submodule is used to evaluate the various initial response strategies. The target strategy determination submodule is used to determine the target response strategy based on the evaluation results of the initial response strategy evaluation.

[0111] In some embodiments, the target strategy determination submodule includes: The candidate strategy determination unit is used to determine candidate response strategies from the multiple initial response strategies based on the evaluation results of the initial response strategy evaluation. The target response strategy determination unit is used to acquire user preference information and / or business scenarios, and determine the target response strategy from the candidate response strategies based on the user preference information and / or business scenarios.

[0112] As the apparatus embodiment is basically similar to the method embodiment, it is described in a relatively simple manner. For relevant details, please refer to the description of the method embodiment.

[0113] This invention also provides an electronic device, including: a processor, a memory, and a computer program stored in the memory and capable of running on the processor. When the computer program is executed by the processor, it implements the various processes of the above-described supply chain risk management method embodiments and achieves the same technical effects. To avoid repetition, it will not be described again here.

[0114] This invention also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the various processes of the above-described supply chain risk management method embodiments and achieves the same technical effects. To avoid repetition, it will not be described again here.

[0115] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0116] Furthermore, it should be noted that the scope of the methods and apparatus in the embodiments of the present invention is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. In addition, features described with reference to certain examples may be combined in other examples.

[0117] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0118] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of the present invention.

Claims

1. A supply chain risk management method, characterized in that, The method includes: Obtain risk assessment information from each supplier in the supply chain; Construct a supply relationship diagram for the aforementioned supply chain; Based on the risk assessment information of each supplier, the supplier in which the risk event occurred is identified; Based on the supply relationship diagram, determine the impact of the risk event on the supplier; the impact includes other suppliers affected by the supplier whose risk event occurred and the degree of impact. Based on the described impact, determine the corresponding response strategy.

2. The supply chain risk management method according to claim 1, characterized in that, The construction of the supply chain relationship diagram includes: Construct a supply relationship graph for each supplier in the supply chain; the nodes of the supply relationship graph are the suppliers, customers, and logistics providers; the edges of the supply relationship graph are the business relationships between each pair of suppliers, customers, and logistics providers; the edge weights of the supply relationship graph are the degree of dependence of the business relationships; the business relationships include at least one of procurement relationships, logistics relationships, and information sharing relationships; the degree of dependence includes at least one of procurement ratio, transportation frequency, and information sharing intensity.

3. The supply chain risk management method according to claim 1, characterized in that, The risk assessment information for each supplier in the supply chain includes each supplier's operational data and market information; the operational data includes at least one of purchase orders, supplier performance, on-time delivery rate, quality pass rate, geographical location, supplier factory operating rate, logistics hub index, and equipment status; the market information includes at least one of supplier news, social media sentiment, geopolitical reports, and market dynamics.

4. The supply chain risk management method according to claim 3, characterized in that, The step of determining the supplier in question based on the risk assessment information of each supplier includes: Sentiment analysis is performed on the market information in the risk assessment information of each supplier, and a sentiment score corresponding to the market information is generated; Based on the operational data and the sentiment score, the risk score of each supplier is determined; Based on the risk scores of each supplier, the supplier in question is identified as having experienced a risk event.

5. The supply chain risk management method according to claim 4, characterized in that, The process of performing sentiment analysis on the market information in the risk assessment information of each supplier and generating a sentiment score corresponding to the market information includes: The text data of the market information is preprocessed, and specific words in the preprocessed text data are identified; Obtain the number of specific words, their corresponding weights, and their corresponding sentiment polarity values ​​in the preprocessed text data; The sentiment score corresponding to the market information is determined based on the number of specific words, the weight of the specific words, and the sentiment polarity value of the specific words.

6. The supply chain risk management method according to claim 1, characterized in that, Determining the impact of the risk event based on the supply relationship diagram includes: The supply relationship graph is input into a pre-trained risk assessment model, and the embedding vector of each node in the supply relationship graph is extracted through the risk assessment model; the embedding vector represents the position and influence of the node in the supply relationship graph. Based on the identified suppliers of the risk event and the embedded vector, the risk assessment model determines the risk diffusion path of the suppliers of the risk event in the supply chain. Based on the risk diffusion path, the affected suppliers are identified, and the degree of impact on the affected suppliers is assessed.

7. The supply chain risk management method according to claim 1, characterized in that, The step of determining a response strategy based on the impact includes: Based on the described impact, multiple initial response strategies are generated; The various initial response strategies were evaluated; Based on the evaluation results of the initial response strategy assessment, the target response strategy is determined.

8. The supply chain risk management method according to claim 7, characterized in that, The step of determining the target response strategy based on the evaluation results of the initial response strategy evaluation includes: Based on the evaluation results of the initial response strategy assessment, candidate response strategies are determined from the multiple initial response strategies; Obtain user preference information and / or business scenarios, and determine the target response strategy from the candidate response strategies based on the user preference information and / or business scenarios.

9. A supply chain risk management device, characterized in that, The device includes: The assessment information acquisition module is used to acquire risk assessment information from each supplier in the supply chain; A supply relationship diagram construction module is used to construct the supply relationship diagram of the supply chain; The risk supplier identification module is used to identify the supplier in which a risk event has occurred based on the risk assessment information of each supplier. The impact result determination module is used to determine the impact result of the supplier experiencing the risk event based on the supply relationship diagram; the impact result includes other suppliers affected by the supplier experiencing the risk event and the degree of impact; The response strategy determination module is used to determine the response strategy based on the impact results.

10. An electronic device, characterized in that, include: A processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the supply chain risk management method as described in any one of claims 1-8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program that, when executed by a processor, implements the steps of the supply chain risk management method as described in any one of claims 1-8.

Images