Risk early warning method and system based on automobile service supply chain

Abstract

The present invention relates to a risk warning method and system based on an automobile service supply chain, comprising the following steps: performing topological network modeling on the automobile service supply chain based on the supply chain data to obtain a topological network structure of the automobile service supply chain; identifying whether there are supply chain risk points in the topological network structure through a preset recognition algorithm, and if so, performing a risk impact analysis on the supply chain data through the supply chain risk points in the topological network structure to obtain a risk impact analysis result; performing risk scenario classification on the risk impact analysis result to obtain a risk scenario type; performing a risk warning assessment based on the risk scenario type to obtain a risk warning assessment result, and formulating a risk mitigation plan based on the risk scenario type and the risk warning assessment result, thereby solving the problem of poor communication between various links in the supply chain due to information asymmetry, making it difficult to effectively respond to emergencies.

Description

Technical Field

[0001] The present invention relates to the field of automobile service technology, and in particular to a risk early warning method and system based on an automobile service supply chain. Background Art

[0002] With the acceleration of global economic integration and the rapid development of information technology, the automotive service supply chain is facing unprecedented challenges. On the one hand, increasing market uncertainty, such as fluctuating raw material prices and frequent policy adjustments, can directly or indirectly impact supply chain stability. On the other hand, with increasingly diverse and personalized consumer demands, automakers and service providers need to respond more flexibly and efficiently to market changes, requiring greater transparency and agility within the supply chain. However, in practice, information asymmetry and inadequate coordination mechanisms lead to poor communication between supply chain links, inefficient decision-making, and difficulties in effectively responding to emergencies.

[0003] Furthermore, the automotive service supply chain involves multiple complex links, from parts production and vehicle manufacturing to sales and after-sales service. Each link presents potential risk points. For example, suppliers may be unable to deliver on time due to natural disasters or equipment failures, while logistics may also encounter unexpected situations such as traffic disruptions and cargo damage. These issues not only increase operating costs for companies but can also lead to decreased customer satisfaction and even damage brand reputation. Therefore, accurately identifying and promptly addressing supply chain risks has become a pressing issue for companies.

[0004] To address these challenges, this study proposes a risk early warning method for the automotive service supply chain. This method comprehensively collects and analyzes data from all links in the supply chain, utilizes advanced graph theory algorithms to construct a supply chain topology network model, and incorporates specialized identification algorithms to identify potential risk points. Subsequently, through in-depth impact analysis and scenario classification of these risk points, the method provides decision-makers with scientific risk early warning assessments, enabling them to implement effective mitigation measures in advance and reduce the impact of supply chain risks on normal business operations. This approach not only enhances the supply chain's resilience to risk but also promotes the healthy development of the entire industry. Summary of the Invention

[0005] The main purpose of the present invention is to provide a risk warning method and system based on the automotive service supply chain, which solves the problem of poor communication between various links in the supply chain due to information asymmetry and makes it difficult to effectively respond to emergencies.

[0006] To achieve the above objectives, the present invention provides a risk early warning method based on an automotive service supply chain, comprising the following steps:

[0007] Collect data from each link in the automotive service supply chain to obtain supply chain data;

[0008] Using a preset graph theory algorithm, a topological network model is performed on the automotive service supply chain based on the supply chain data to obtain a topological network structure of the automotive service supply chain;

[0009] Identify whether there are supply chain risk points in the topological network structure using a preset identification algorithm; if so, perform a risk impact analysis on the supply chain data using the supply chain risk points in the topological network structure to obtain a risk impact analysis result;

[0010] Performing risk scenario classification on the risk impact analysis results to obtain risk scenario types;

[0011] A risk warning assessment is performed based on the risk scenario type to obtain a risk warning assessment result, and a risk mitigation plan is formulated based on the risk scenario type and the risk warning assessment result.

[0012] Furthermore, the various links include suppliers, manufacturers, distributors, and retailers. The data of each link in the automotive service supply chain is collected to obtain supply chain data, including:

[0013] Through the distributed crawler system, we collect multi-source heterogeneous data from suppliers, manufacturers, distributors, and retailers in the automotive service supply chain to obtain original supply chain data;

[0014] Preprocessing the raw supply chain data to obtain clean supply chain data;

[0015] By using data fusion technology, the clean supply chain data from different sources is fused to obtain fused data in a unified format;

[0016] Performing data parsing on the unstructured text data in the fused data to extract key information from the fused data;

[0017] The key information is trend-forecasted using a preset long-short memory network to obtain supply chain activity trend data, which is used as supply chain data.

[0018] Furthermore, the topological network modeling of the automotive service supply chain is performed based on the supply chain data using a preset graph theory algorithm to obtain a topological network structure of the automotive service supply chain, including:

[0019] Utilizing a preset graph theory algorithm, extracting entities and relationships between entities in the supply chain data; wherein the entities include suppliers, manufacturers, distributors, and retailers;

[0020] Constructing a supply chain entity relationship table based on the entities and the relationships between the entities; wherein the supply chain entity relationship table includes nodes and edges, with the entities as nodes and the relationships between the entities as edges;

[0021] Utilizing the node degree centrality layer in the graph theory algorithm to calculate the importance of each node in the supply chain entity relationship table to obtain a node importance score; wherein the node importance score includes the in-degree and out-degree of each node;

[0022] Calculate the frequency of the in-degree and out-degree of each node to obtain the in-degree frequency and out-degree frequency of each node;

[0023] Using a preset community detection algorithm, identifying corresponding entities and upstream and downstream entities of the corresponding entities in the supply chain entity relationship table based on the node importance score, so as to obtain a supply chain community structure diagram;

[0024] Labeling entities corresponding to the node importance scores to obtain labeled corresponding entities, and attaching the labeled corresponding entities to the supply chain community structure diagram to obtain a labeled supply chain community structure diagram;

[0025] Calculating the transmission path of the edge between each of the nodes based on the in-degree frequency and the out-degree frequency between each of the nodes; wherein the transmission path represents the importance between the nodes, a shorter transmission path represents a closer connection between the nodes, and a longer transmission path represents a looser connection between the nodes;

[0026] A topological network model is performed on the automobile service supply chain based on the labeled supply chain community structure diagram and the transmission path to obtain a topological network structure of the automobile service supply chain.

[0027] Furthermore, the risk impact analysis is performed on the supply chain data through the supply chain risk points in the topological network structure to obtain risk impact analysis results; wherein the risk impact analysis results include potential risk points and the impact range of supply chain risk points, including:

[0028] Performing correlation analysis on the supply chain data through the supply chain risk points in the topological network structure to obtain a risk propagation path diagram;

[0029] Based on the risk propagation path diagram, the propagation probability of the supply chain risk point to the transmission path is calculated to obtain a risk propagation probability matrix; wherein the rows of the risk propagation probability matrix represent the starting nodes of the transmission path, the columns of the risk propagation probability matrix represent the ending nodes of the transmission path, and the elements of the risk propagation probability matrix represent the propagation probability values ​​from the starting node to the ending node;

[0030] Extracting time series features from the risk propagation probability matrix to obtain a risk propagation time series feature vector;

[0031] Based on the risk propagation time series feature vector, risk prediction is performed on the supply chain data to obtain a risk impact degree prediction result, and the risk impact degree prediction result is used as a risk impact analysis result;

[0032] Performing a vulnerability assessment on the supply chain data based on the risk impact prediction result to obtain a network vulnerability index;

[0033] When the network vulnerability index is less than a preset vulnerability index, determining the potential risk point based on the network vulnerability index;

[0034] A spatial analysis is performed on the network vulnerability index to obtain the impact range of supply chain risk points.

[0035] Furthermore, the risk impact analysis results are classified into risk scenarios to obtain risk scenario types, including:

[0036] The potential risk points of the risk impact analysis results are used as rows and the impact ranges are used as columns to construct a risk feature matrix; wherein the elements of the risk feature matrix represent the risk degree;

[0037] Inputting the risk feature matrix into a preset multi-level decision tree algorithm for analysis to obtain a risk feature hierarchy tree;

[0038] Using a support vector machine classification algorithm, the risk feature hierarchical tree is preliminarily classified to obtain a preliminary risk scenario type;

[0039] Performing risk scenario probability inference on the preliminary risk scenario type to obtain a probabilistic risk scenario type;

[0040] Performing correlation analysis on the probabilistic risk scenario types to obtain correlated risk scenario types;

[0041] Risk scenario types are classified based on the preliminary risk scenario types, the probabilistic risk scenario types, and the associated risk scenario types to obtain risk scenario types.

[0042] Furthermore, performing a risk warning assessment based on the risk scenario type to obtain a risk warning assessment result, and formulating a risk mitigation plan based on the risk scenario type and the risk warning assessment result, includes:

[0043] Performing vector conversion on the risk scenario type to obtain a type conversion vector;

[0044] Performing high-dimensional mapping on the type conversion vector to obtain an enhanced risk scenario feature vector;

[0045] Adaptively assigning weights to the enhanced risk scenario feature vector to obtain a weighted risk feature vector;

[0046] Performing time series analysis on the weighted risk feature vector through a preset long short-term memory network to obtain a risk warning assessment result;

[0047] Performing risk path simulation on the supply chain data based on the risk warning assessment results to obtain a risk development path;

[0048] Based on the risk development path and risk scenario type, a risk mitigation plan is obtained.

[0049] Furthermore, the risk mitigation plan includes a diversified supplier strategy, a multi-channel logistics strategy and a resource reserve strategy.

[0050] The present invention also provides a risk early warning system based on the automotive service supply chain, comprising:

[0051] The collection module is used to collect data from various links in the automotive service supply chain to obtain supply chain data;

[0052] a modeling module, configured to use a preset graph theory algorithm to perform topological network modeling on the automotive service supply chain based on the supply chain data, thereby obtaining a topological network structure of the automotive service supply chain;

[0053] an analysis module, configured to identify whether there are supply chain risk points in the topological network structure using a preset identification algorithm; if so, perform a risk impact analysis on the supply chain data using the supply chain risk points in the topological network structure to obtain a risk impact analysis result;

[0054] A classification module is used to classify the risk impact analysis results into risk scenarios to obtain risk scenario types;

[0055] The assessment module is used to perform risk warning assessment based on the risk scenario type, obtain risk warning assessment results, and formulate risk mitigation plans based on the risk scenario type and the risk warning assessment results.

[0056] The present invention also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.

[0057] The present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of any of the above methods are implemented.

[0058] The present invention provides a risk warning method for an automotive service supply chain, comprising the following steps: collecting data from various links in the automotive service supply chain to obtain supply chain data; using a preset graph theory algorithm to perform topological network modeling on the automotive service supply chain based on the supply chain data to obtain a topological network structure of the automotive service supply chain; identifying whether there are supply chain risk points within the topological network structure using a preset recognition algorithm; if so, performing a risk impact analysis on the supply chain data using the supply chain risk points in the topological network structure to obtain a risk impact analysis result; classifying the risk impact analysis result by risk scenario to obtain a risk scenario type; performing a risk warning assessment based on the risk scenario type to obtain a risk warning assessment result; and formulating a risk mitigation plan based on the risk scenario type and the risk warning assessment result. This technical solution solves the problem of poor communication between various links in the supply chain due to information asymmetry, making it difficult to effectively respond to emergencies. By classifying the risk impact analysis result by risk scenario, different types of risks can be classified and managed, facilitating enterprises to formulate targeted risk mitigation strategies based on different risk scenarios. This refined management approach helps improve enterprises' adaptability and decision-making capabilities in the face of complex and changing market environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 This is a schematic diagram of the steps of a risk early warning method based on an automobile service supply chain in one embodiment of the present invention;

[0060] Figure 2 This is a structural block diagram of a risk early warning system based on an automobile service supply chain in one embodiment of the present invention;

[0061] Figure 3 It is a schematic block diagram of the structure of a computer device according to an embodiment of the present invention.

[0062] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0064] like Figure 1 As shown, Figure 1 This is a schematic diagram of the steps of a risk early warning method based on an automobile service supply chain in one embodiment of the present invention;

[0065] In one embodiment of the present invention, a risk early warning method based on an automotive service supply chain is provided, comprising the following steps:

[0066] Step S1: Collect data from each link in the automotive service supply chain to obtain supply chain data.

[0067] Specifically, collecting data from every link in the automotive service supply chain to generate supply chain data is the foundation of the entire risk early warning method. To implement this step, the scope and targets of data collection must be determined, encompassing all key supply chain links, from raw material procurement, parts production, vehicle assembly, logistics and transportation, to final sales and after-sales service. For example, in the automotive manufacturing process, important data to collect includes raw material quality reports from suppliers, time records for each process on the production line, inventory changes in the warehouse management system, and customer feedback from point-of-sale services. IoT devices such as sensors and RFID tags can automatically collect this data in real time, ensuring its freshness and reliability. Furthermore, leveraging big data platforms and technologies, data from various channels and formats can be integrated and cleansed to ensure consistency and integrity. This not only provides high-quality data support for subsequent graph theory modeling and risk point identification, but also helps companies gain a comprehensive understanding of the supply chain's operational status, promptly identifying potential issues and laying a solid foundation for accurate risk early warning. For example, in an actual application of supply chain risk warning, by continuously monitoring the quality data of parts provided by a certain automobile brand supplier, the system successfully predicted the risk of a large-scale recall that might be caused by unstable production of the supplier, thereby saving the company a lot of costs and avoiding reputation loss.

[0068] Step S2: Using a preset graph theory algorithm, a topological network model is performed on the automobile service supply chain based on the supply chain data to obtain a topological network structure of the automobile service supply chain.

[0069] Specifically, a pre-defined graph theory algorithm is used to construct a topological network model of the automotive service supply chain based on the supply chain data, thereby obtaining the topological network structure of the automotive service supply chain. This is a key step in implementing the risk early warning method. This process first requires selecting appropriate graph theory algorithms, such as shortest path algorithms and community detection algorithms. These algorithms can help us understand and analyze the relationships and complexity between nodes in the supply chain. Next, based on the previously collected supply chain data, each link in the supply chain is considered a node in the graph, and the interactions between nodes, such as logistics, information flow, and capital flow, are represented as edges. In this way, a topological network structure that reflects the actual operation of the automotive service supply chain can be constructed. For example, in the automotive manufacturing industry, the vehicle manufacturer can be considered the central node in the network, surrounded by numerous other nodes such as suppliers, distributors, and retailers. When these nodes are connected through various forms of interaction, a complex network is formed. In this network, not only can the position and function of each node be clearly identified, but also the stability of the supply chain and potential risk points can be assessed by analyzing indicators such as the strength of connections between nodes and path length. For example, if a key supplier has close ties with multiple downstream companies, a problem with that supplier could quickly ripple through other nodes, impacting the entire supply chain. This modeling allows companies to more intuitively understand the overall layout of their supply chain, providing strong support for subsequent risk identification and early warning.

[0070] Step S3: Identify whether there are supply chain risk points in the topological network structure through a preset identification algorithm. If so, perform risk impact analysis on the supply chain data through the supply chain risk points in the topological network structure to obtain risk impact analysis results.

[0071] Specifically, a preset identification algorithm is used to identify whether supply chain risk points exist within the topological network structure. If so, a risk impact analysis is performed on the supply chain data using the supply chain risk points within the topological network structure to obtain risk impact analysis results. This process is the core component of the risk early warning method. After completing the supply chain topological network modeling, a specially designed identification algorithm is then applied to identify potential risk points within the network. These identification algorithms are typically based on machine learning or statistical principles and can automatically analyze network structural characteristics, such as node degree centrality and betweenness centrality, to determine which nodes or relationships between nodes may be sources of risk. For example, in the automotive service supply chain, if a supplier node has a very high degree centrality, indicating close connections with multiple other nodes, then any problems with that supplier, such as supply disruptions or quality issues, could have widespread impacts across the entire supply chain. After identifying these risk points, the next step is to conduct an in-depth risk impact analysis. This involves leveraging existing supply chain data to assess the potential impact of these risk points on other parts of the supply chain, including but not limited to production delays, increased costs, and decreased customer satisfaction. For example, if a supplier with a high centrality experience serious quality issues, analyzing transaction records and historical performance data between upstream and downstream nodes can predict the potential impact of this incident, including production delays, additional quality control costs, and the number of customer complaints. This analysis not only helps companies understand the potential harm of specific risk points but also provides a valuable basis for developing effective risk mitigation strategies.

[0072] Step S4: classify the risk impact analysis results into risk scenarios to obtain risk scenario types.

[0073] Specifically, the risk impact analysis results are classified into risk scenario types. This step aims to further refine the results of the risk impact analysis to facilitate subsequent risk warning assessments and the development of mitigation plans. After identifying supply chain risk points and analyzing their impact, we have gained a preliminary understanding of the potential impacts of each risk point. However, these impacts can be multifaceted, affecting different aspects of the supply chain, such as production delays, increased costs, and decreased customer satisfaction. Therefore, to more effectively manage and address these risks, it is necessary to classify them according to specific criteria to form different risk scenario types. For example, in the automotive service supply chain, risk scenarios can be divided into several major categories, such as supply chain disruptions, quality incidents, and market demand changes. Each major category can be further subdivided into further subcategories based on specific circumstances. For example, supply chain disruptions can be further divided into interruptions in the supply of critical raw materials and important components; quality incidents can be divided into supplier product quality issues and quality issues in the manufacturing process. Through this classification, companies can more clearly understand the specific impacts of different types of risks on their business, providing a basis for developing more targeted risk mitigation measures. For example, in the risk scenario of a disruption in the supply of critical raw materials, companies can mitigate the risk by establishing a diversified supplier system and increasing safety stocks. In the risk scenario of supplier product quality issues, measures such as strengthening supplier quality management and introducing third-party quality certification can be taken to prevent and reduce such risks. Such categorization and refinement not only helps companies enhance their understanding of risks but also promotes the optimization and improvement of their risk management strategies, thereby enhancing the resilience of the entire supply chain.

[0074] Step S5: Perform a risk warning assessment based on the risk scenario type to obtain a risk warning assessment result, and formulate a risk mitigation plan based on the risk scenario type and the risk warning assessment result.

[0075] Specifically, a risk early warning assessment is conducted based on the risk scenario type, resulting in a risk early warning assessment result. A risk mitigation plan is then developed based on the risk scenario type and the risk early warning assessment result. This process is the final and crucial step in the entire risk early warning method. After completing the risk scenario classification, companies need to conduct a detailed early warning assessment for each risk scenario to determine its likelihood of occurrence and potential impact. This assessment process can utilize a combination of quantitative and qualitative analysis. Quantitative analysis primarily relies on historical data and statistical models to predict the probability of risk occurrence and the potential economic losses it will cause; qualitative analysis focuses on expert judgment and industry experience to assess the impact of the risk on non-financial aspects such as brand image and customer satisfaction. For example, in the automotive service supply chain, if the risk scenario involves a disruption in the supply of critical components, companies can analyze the frequency, duration, and impact of similar past events on production plans to estimate the likelihood of such a risk occurring in the future and the potential resulting production delays and additional costs. Furthermore, factors such as the supplier's credibility and the availability of alternative suppliers should be considered to comprehensively assess the overall impact of the risk. After obtaining the risk early warning assessment results, companies can develop specific risk mitigation plans based on these findings. These plans should address the specific characteristics of different risk scenarios and propose practical preventative measures and emergency response plans. Taking the disruption of critical component supply as an example, mitigation measures that companies can implement include, but are not limited to: establishing a more robust supply chain management system and partnering with multiple suppliers to ensure supply chain diversity; increasing safety stocks, especially for critical components, to prepare for emergencies; conducting regular supply chain health checks to promptly identify and resolve potential issues; and strengthening communication and collaboration with suppliers to jointly improve supply chain flexibility and responsiveness. This approach not only allows companies to be fully prepared before risks occur, but also allows them to take swift action when risks do arise, minimizing losses and ensuring normal business operations.

[0076] In a specific embodiment, the various links include suppliers, manufacturers, distributors, and retailers. The data of each link in the automotive service supply chain is collected to obtain supply chain data, including:

[0077] Through the distributed crawler system, we collect multi-source heterogeneous data from suppliers, manufacturers, distributors, and retailers in the automotive service supply chain to obtain original supply chain data;

[0078] Preprocessing the raw supply chain data to obtain clean supply chain data;

[0079] By using data fusion technology, the clean supply chain data from different sources is fused to obtain fused data in a unified format;

[0080] Performing data parsing on the unstructured text data in the fused data to extract key information from the fused data;

[0081] The key information is trend-forecasted using a preset long-short memory network to obtain supply chain activity trend data, which is used as supply chain data.

[0082] Specifically, the various links mentioned include suppliers, manufacturers, distributors, and retailers. Collecting data from each link in the automotive service supply chain to generate supply chain data is a complex and sophisticated process designed to ensure comprehensiveness, accuracy, and availability. First, a distributed crawler system collects heterogeneous data from suppliers, manufacturers, distributors, and retailers in the automotive service supply chain to generate raw supply chain data. This involves using automated tools to crawl data from multiple platforms and systems on the internet. This data may come from sources such as suppliers' official websites, manufacturers' ERP systems, distributors' sales records, and retailers' customer feedback. For example, in the automotive manufacturing industry, material specifications and supply plans can be obtained from suppliers, production schedules and quality inspection reports from manufacturers, inventory levels and order status from distributors, and sales performance and customer reviews from retailers. All of this data forms the basis of raw supply chain data. Next, this raw supply chain data is preprocessed to generate clean supply chain data. This preprocessing process primarily includes steps such as data cleaning, deduplication, and format conversion. The goal is to eliminate errors, redundancies, and inconsistencies in the data and ensure that the data meets a certain quality and standard. For example, duplicate supplier records are removed, incorrectly formatted date fields are corrected, and missing values ​​are filled in. This process ensures the accuracy and reliability of subsequent analysis. Then, using data fusion technology, the clean supply chain data from different sources is fused to generate unified, fused data. Data fusion refers to the integration of data from different sources and formats into a unified dataset for comprehensive analysis. In the automotive service supply chain, this may involve matching and merging supplier bills of materials with manufacturer production schedules, distributor inventory records with retailer sales data, and so on. Data fusion technology can help companies overcome the challenges of multi-source data and achieve integrated data management. Next, data parsing is performed on the unstructured text data within the fused data to extract key information. Unstructured text data refers to information without a fixed format or structure, such as emails, social media comments, and customer service records. Natural language processing (NLP) technology can be used to extract valuable information from this data, such as customer satisfaction ratings for a particular car model and supplier credit ratings. This key information is crucial for understanding dynamic changes in the supply chain. Finally, a pre-set long short-term memory (LSTM) network is used to predict the trends of this key information, generating supply chain activity trend data, which is then used as supply chain data. LSTM is a special type of recurrent neural network (RNN) that is particularly well-suited for processing time series data and can capture patterns in data over time.In the automotive service supply chain, LSTM models can be used to analyze historical data on key indicators such as supplier delivery times, manufacturer production cycles, distributor inventory turnover rates, and retailer sales growth rates to predict future trends. For example, if the model predicts a significant increase in demand for a particular car model in the next quarter, a company can increase inventory in advance to avoid sales losses due to supply shortages. This approach enables companies to better anticipate and respond to market changes, improving supply chain flexibility and competitiveness.

[0083] In a specific embodiment, the topological network modeling of the automotive service supply chain is performed based on the supply chain data using a preset graph theory algorithm to obtain a topological network structure of the automotive service supply chain, including:

[0084] Utilizing a preset graph theory algorithm, extracting entities and relationships between entities in the supply chain data; wherein the entities include suppliers, manufacturers, distributors, and retailers;

[0085] Constructing a supply chain entity relationship table based on the entities and the relationships between the entities; wherein the supply chain entity relationship table includes nodes and edges, with the entities as nodes and the relationships between the entities as edges;

[0086] Utilizing the node degree centrality layer in the graph theory algorithm to calculate the importance of each node in the supply chain entity relationship table to obtain a node importance score; wherein the node importance score includes the in-degree and out-degree of each node;

[0087] Calculate the frequency of the in-degree and out-degree of each node to obtain the in-degree frequency and out-degree frequency of each node;

[0088] Using a preset community detection algorithm, identifying corresponding entities and upstream and downstream entities of the corresponding entities in the supply chain entity relationship table based on the node importance score, so as to obtain a supply chain community structure diagram;

[0089] Labeling entities corresponding to the node importance scores to obtain labeled corresponding entities, and attaching the labeled corresponding entities to the supply chain community structure diagram to obtain a labeled supply chain community structure diagram;

[0090] Calculating the transmission path of the edge between each of the nodes based on the in-degree frequency and the out-degree frequency between each of the nodes; wherein the transmission path represents the importance between the nodes, a shorter transmission path represents a closer connection between the nodes, and a longer transmission path represents a looser connection between the nodes;

[0091] A topological network model is performed on the automobile service supply chain based on the labeled supply chain community structure diagram and the transmission path to obtain a topological network structure of the automobile service supply chain.

[0092] Specifically, a preset graph theory algorithm is used to perform topological network modeling of the automotive service supply chain based on the supply chain data, thereby obtaining the topological network structure of the automotive service supply chain. This is a multi-level, multi-step process designed to reveal the complex relationships and structural characteristics within the supply chain through mathematical models and algorithms. First, a preset graph theory algorithm is used to extract entities and the relationships between them from the supply chain data. Entities here include suppliers, manufacturers, distributors, and retailers in the supply chain, while relationships between entities encompass the interactions between these entities in terms of materials, information, and capital. For example, in the automotive service supply chain, suppliers provide raw materials to manufacturers, who process these raw materials into auto parts and assemble them into finished vehicles. Distributors are responsible for distributing the finished vehicles to retailers, who then sell directly to consumers. These relationships form the basic framework of the supply chain. Next, a supply chain entity relationship table is constructed based on the entities and their relationships. In this process, each entity in the supply chain is treated as a node in the graph, and the relationships between entities are represented as edges between nodes. This approach simplifies complex supply chain relationships into an intuitive network model. For example, the supply relationship between supplier A and manufacturer B can be represented as a directed edge from node A to node B. The supply chain entity relationship table not only contains basic node and edge information but may also include edge weights, such as transaction volume and frequency. This information facilitates subsequent analysis. The node degree centrality layer in the graph theory algorithm is then used to calculate the importance of each node in the supply chain entity relationship table, yielding a node importance score. Node degree centrality is a key metric for measuring a node's importance within a network, reflecting the number of connections it has with other nodes. In a directed graph, a node's degree centrality can be further divided into in-degree and out-degree, representing the number of edges pointing to and emanating from the node, respectively. By calculating the in-degree and out-degree of each node, an importance score can be obtained. A higher score indicates a more important node in the network. For example, in the automotive service supply chain, a supplier with a high out-degree indicates that it supplies raw materials to multiple manufacturers and is a key node in the supply chain. Furthermore, the in-degree and out-degree frequencies of each node are calculated to obtain the in-degree and out-degree frequencies of each node. Frequency here refers to the number of occurrences per unit time, for example, the number of times a supplier supplies goods to multiple manufacturers per month. By calculating these frequencies, we can more accurately assess the activity and influence of nodes in the supply chain. For example, a supplier with a high out-degree but a low supply frequency may not be as important as it appears. Using a preset community detection algorithm, we identify the corresponding entities and their upstream and downstream entities in the supply chain entity relationship table based on the node importance scores to generate a supply chain community structure diagram.Community detection algorithms can identify closely connected groups of nodes in a network. These groups often represent different subsystems or subnetworks within a supply chain. For example, community detection algorithms can reveal that some suppliers and manufacturers form a close collaborative network, while other distributors and retailers form independent subnetworks. Identifying these community structures allows for a deeper analysis of each community's internal operating mechanisms and external interaction patterns. Entities corresponding to the node importance scores are labeled to obtain labeled entities, which are then attached to the supply chain community structure diagram to obtain a labeled supply chain community structure diagram. This process not only increases the information content of the network model but also makes the model more intuitive and understandable. For example, in the supply chain community structure diagram, nodes of different importance can be distinguished by color or size, making it easy to identify key nodes in the supply chain at a glance. The transmission paths of the edges between each node are calculated based on the in-degree and out-degree frequencies between the nodes. The transmission paths here represent the strength of the connection between the nodes. A shorter transmission path indicates a closer connection between the two nodes; a shorter transmission path indicates a looser connection. For example, in the automotive service supply chain, if the supply frequency between a supplier and multiple manufacturers is high and the supply time interval is short, it means that these manufacturers are highly dependent on the supplier and this path in the supply chain is relatively important. Finally, based on the labeled supply chain community structure diagram and the transmission path, a topological network model is performed on the automotive service supply chain to obtain the topological network structure of the automotive service supply chain. Through this series of steps, not only can the overall architecture of the supply chain be intuitively displayed, but the complex relationships and importance between each node in the supply chain can also be revealed, providing a solid foundation for subsequent risk identification, impact analysis, and early warning assessment. For example, through the topological network structure, enterprises can clearly see which suppliers are key nodes and which paths are weak links in the supply chain, so that targeted measures can be taken to improve the stability and risk resistance of the supply chain.

[0093] In a specific embodiment, the risk impact analysis is performed on the supply chain data through the supply chain risk points in the topological network structure to obtain a risk impact analysis result; wherein the risk impact analysis result includes the potential risk points and the impact range of the supply chain risk points, including:

[0094] Performing correlation analysis on the supply chain data through the supply chain risk points in the topological network structure to obtain a risk propagation path diagram;

[0095] Based on the risk propagation path diagram, the propagation probability of the supply chain risk point to the transmission path is calculated to obtain a risk propagation probability matrix; wherein the rows of the risk propagation probability matrix represent the starting nodes of the transmission path, the columns of the risk propagation probability matrix represent the ending nodes of the transmission path, and the elements of the risk propagation probability matrix represent the propagation probability values ​​from the starting node to the ending node;

[0096] Extracting time series features from the risk propagation probability matrix to obtain a risk propagation time series feature vector;

[0097] Based on the risk propagation time series feature vector, risk prediction is performed on the supply chain data to obtain a risk impact degree prediction result, and the risk impact degree prediction result is used as a risk impact analysis result;

[0098] Performing a vulnerability assessment on the supply chain data based on the risk impact prediction result to obtain a network vulnerability index;

[0099] When the network vulnerability index is less than a preset vulnerability index, determining the potential risk point based on the network vulnerability index;

[0100] A spatial analysis is performed on the network vulnerability index to obtain the impact range of supply chain risk points.

[0101] Specifically, performing risk impact analysis on the supply chain data using the supply chain risk points in the topological network structure to obtain risk impact analysis results is a systematic and meticulous process designed to comprehensively assess the scope and extent of the impact of potential risk points in the supply chain. First, correlation analysis is performed on the supply chain data using the supply chain risk points in the topological network structure to generate a risk propagation path diagram. This involves utilizing the constructed topological network structure and the identified supply chain risk points to analyze how these risk points propagate to other components through the nodes and edges in the network. For example, in the automotive service supply chain, if a key supplier experiences a supply issue, a risk propagation path diagram can be used to analyze how this issue affects the manufacturers, distributors, and retailers that rely on that supplier. The path diagram not only illustrates the path of risk propagation but also the speed and scope of the spread. Next, based on the risk propagation path diagram, the propagation probability of the supply chain risk point along the transmission path is calculated to generate a risk propagation probability matrix. The rows of the risk propagation probability matrix represent the starting nodes of the transmission path, the columns represent the ending nodes of the transmission path, and the matrix elements represent the propagation probability values ​​from the starting node to the ending node. This process quantifies the probability of risk propagation within the supply chain network through mathematical models and statistical methods. For example, if a supply issue with supplier A could affect manufacturers B and C, the calculated probability of transmission from A to B is 0.8, and the probability of transmission from A to C is 0.6. These probability values ​​form part of a risk transmission probability matrix. This allows for a more accurate assessment of the path and likelihood of risk transmission. Next, time series feature extraction is performed on the risk transmission probability matrix to obtain a risk transmission time series feature vector. Time series feature extraction involves analyzing the probability of risk transmission over time to extract key parameters that reflect the dynamic characteristics of risk transmission. For example, the temporal trend of the probability of risk transmission can be calculated, or the fluctuations of risk transmission over different time periods can be analyzed. These time series feature vectors help us better understand the dynamic process of risk transmission and provide a basis for subsequent risk prediction. Based on the risk transmission time series feature vectors, risk prediction is performed on the supply chain data to obtain a risk impact prediction result, which is used as the risk impact analysis result. This process uses machine learning or statistical models, combined with the time series feature vectors and historical data, to predict the impact of the risk over a period of time. For example, by analyzing the impact and duration of similar risk events in historical data, we can predict the specific impact of the current risk event on various links in the supply chain, such as the number of days of production delays and additional costs. These predictions not only help companies prepare in advance but also provide a scientific basis for formulating risk mitigation measures. Based on the risk impact prediction results, the supply chain data is assessed for vulnerability, resulting in a network vulnerability index.The network vulnerability index (NVI) measures the vulnerability of a supply chain network to risks. It is typically calculated by comprehensively considering multiple factors, including network structural characteristics, node importance, and risk propagation probability. For example, if a node has both high in-degree and out-degree, and a high risk propagation probability, this indicates that the node plays a crucial role in the network. A problem with this node could significantly impact the entire supply chain. By calculating the NVI, weak links in the supply chain can be identified. When the NVI is lower than a preset value, potential risk points are identified based on the NVI. The preset vulnerability index serves as a threshold for determining whether a supply chain network is at high risk. If the calculated NVI is lower than this threshold, the supply chain network presents a high risk and requires focused attention and management. For example, if a supplier's NVI is significantly lower than the preset value, this indicates that the supplier is a potential risk point in the supply chain. Enterprises need to strengthen their collaborative management with the supplier to reduce the likelihood of risk. Spatial analysis of the NVI reveals the impact of supply chain risk points. Spatial analysis involves analyzing the impact of risk points on various links in the supply chain from a geographic perspective. For example, map visualization tools can visually demonstrate the impact of a particular risk point on suppliers, manufacturers, distributors, and retailers in different regions. This spatial analysis not only helps companies understand the global impact of risks but also supports the development of regional risk response strategies. For example, if a key supplier is located in an area prone to natural disasters, the company can diversify the risk and improve supply chain resilience by increasing the number of suppliers in other regions. Through this series of steps, companies can not only comprehensively assess the scope and extent of potential risk points in the supply chain, but also provide strong support for the development of scientific risk mitigation measures, thereby improving the stability and risk resistance of the supply chain.

[0102] In a specific embodiment, the risk impact analysis result is subjected to risk scenario classification to obtain a risk scenario type, including:

[0103] The potential risk points of the risk impact analysis results are used as rows and the impact ranges are used as columns to construct a risk feature matrix; wherein the elements of the risk feature matrix represent the risk degree;

[0104] Inputting the risk feature matrix into a preset multi-level decision tree algorithm for analysis to obtain a risk feature hierarchy tree;

[0105] Using a support vector machine classification algorithm, the risk feature hierarchical tree is preliminarily classified to obtain a preliminary risk scenario type;

[0106] Performing risk scenario probability inference on the preliminary risk scenario type to obtain a probabilistic risk scenario type;

[0107] Performing correlation analysis on the probabilistic risk scenario types to obtain correlated risk scenario types;

[0108] Risk scenario types are classified based on the preliminary risk scenario types, the probabilistic risk scenario types, and the associated risk scenario types to obtain risk scenario types.

[0109] Specifically, classifying the risk impact analysis results into risk scenario types is a multi-stage, multi-level analysis process designed to transform complex risk impact analysis results into easily understandable and manageable risk scenario types. First, a risk signature matrix is ​​constructed, with the potential risk points from the risk impact analysis results as rows and the impact areas as columns. The risk signature matrix is ​​a two-dimensional table, where each row represents a potential risk point, each column represents the supply chain link or region that the risk point may affect, and the matrix elements represent the degree of risk. For example, in the automotive service supply chain, if a supply issue with supplier A is identified as a potential risk point, and this issue may affect manufacturers B, C, and D, then the risk signature matrix would include supplier A as a row and manufacturers B, C, and D as columns. The matrix elements represent the degree of impact of supplier A's supply issue on these three manufacturers, which can be a value between 0 and 1, with 1 indicating the greatest impact and 0 indicating no impact. Next, the risk signature matrix is ​​input into a pre-defined multi-level decision tree algorithm for analysis, resulting in a risk signature hierarchy tree. The multi-level decision tree algorithm is a commonly used machine learning method that can perform multi-level segmentation and classification based on the characteristics of input data. During this process, the algorithm gradually divides the risk feature hierarchy into different risk feature hierarchies based on the data in the risk feature matrix. For example, the first level might be divided based on the type of risk point (such as supplier issues or logistics issues), while the second level is further divided based on the scope of impact of the risk point (such as local impact or global impact). This hierarchical division can more clearly demonstrate the characteristics of the risk point and its impact path. Then, the support vector machine classification algorithm is used to perform a preliminary classification of the risk feature hierarchy tree to obtain preliminary risk scenario types. Support vector machines (SVMs) are powerful classification algorithms that can process high-dimensional data and find optimal classification boundaries. At this stage, by inputting the data in the risk feature hierarchy tree into the SVM algorithm, the risk points can be preliminarily classified into different risk scenario types. For example, the SVM algorithm might preliminarily classify supplier A's supply issues as risk scenarios such as "supply chain disruption" or "quality incident." The preliminary classification results provide a foundation for subsequent detailed analysis. Furthermore, the preliminary risk scenario types are subjected to risk scenario probabilistic inference to obtain probabilistic risk scenario types. This process uses statistical methods or probabilistic models to assess the probability of each preliminary risk scenario. For example, the probability that Supplier A's supply issue falls under the "supply chain disruption" scenario can be calculated to be 0.7, and the probability that it falls under the "quality incident" scenario can be calculated to be 0.3. Through probabilistic inference, the credibility of each risk scenario can be more accurately assessed, providing a basis for subsequent decision-making. Next, correlation analysis is performed on these probabilistic risk scenario types to determine associated risk scenario types. Correlation analysis involves discovering connections between different risk scenario types by mining correlations between data.For example, if a supply problem from supplier A could lead to both a "supply chain disruption" and a "quality incident," there may be a correlation between these two risk scenario types. Through correlation analysis, complex risk scenarios can be identified, meaning that a single risk point could simultaneously trigger multiple risk scenarios. This analysis helps companies more fully understand the complexity of risk and develop more comprehensive risk management strategies. Finally, risk scenarios are classified based on the preliminary risk scenario types, probabilistic risk scenario types, and associated risk scenario types to produce risk scenario types. This final classification comprehensively considers the results of multiple levels of analysis, including not only the preliminary classification types but also the results of probabilistic inference and correlation analysis. For example, the final risk scenario types might include "single supply chain disruption," "single quality incident," or "combined supply chain disruption and quality incident." This classification allows companies to more accurately identify and manage different types of risks, providing a scientific basis for developing specific response measures. Through this series of steps, companies can not only transform complex risk impact analysis results into easily understandable and manageable risk scenario types, but also more comprehensively assess and address various potential risks in the supply chain, thereby improving supply chain stability and risk resilience. For example, in the automotive service supply chain, through the above method, companies can identify which suppliers are key risk points, which specific risk scenarios these risk points may trigger, and the scope and probability of the impact of these risk scenarios, so as to formulate targeted risk management strategies and improve the overall resilience of the supply chain.

[0110] In a specific embodiment, performing a risk warning assessment based on the risk scenario type to obtain a risk warning assessment result, and formulating a risk mitigation plan based on the risk scenario type and the risk warning assessment result, includes:

[0111] Performing vector conversion on the risk scenario type to obtain a type conversion vector;

[0112] Performing high-dimensional mapping on the type conversion vector to obtain an enhanced risk scenario feature vector;

[0113] Adaptively assigning weights to the enhanced risk scenario feature vector to obtain a weighted risk feature vector;

[0114] Performing time series analysis on the weighted risk feature vector through a preset long short-term memory network to obtain a risk warning assessment result;

[0115] Performing risk path simulation on the supply chain data based on the risk warning assessment results to obtain a risk development path;

[0116] Based on the risk development path and risk scenario type, a risk mitigation plan is obtained.

[0117] Specifically, performing a risk warning assessment based on the risk scenario types, obtaining a risk warning assessment result, and formulating a risk mitigation plan based on the risk scenario types and the risk warning assessment results is a multi-level, multi-step process designed to comprehensively assess and manage risks in the supply chain through advanced data analysis and machine learning techniques. First, the risk scenario types are vectorized to produce a type-conversion vector. This process converts qualitative risk scenario types into quantitative vector form, facilitating subsequent mathematical operations and model processing. For example, in the automotive service supply chain, if the risk scenario types include "supply chain disruption," "quality incident," and "market demand change," these types can be encoded as [1, 0, 0], [0, 1, 0], and [0, 0, 1], respectively, to form a type-conversion vector. This method converts complex text descriptions into a digital form that can be processed by computers. Next, the type-conversion vector undergoes high-dimensional mapping to produce an enhanced risk scenario feature vector. High-dimensional mapping is a technique for converting low-dimensional data into high-dimensional data, which can increase the data's expressiveness and discriminability. For example, by using a kernel function (such as a radial basis function) for high-dimensional mapping, the aforementioned type conversion vector [1, 0, 0] can be mapped to a higher-dimensional vector, such as [1, 0, 0, 0.5, 0.3, 0.2]. This high-dimensionally mapped vector not only preserves the original information but also adds new features, helping to improve the accuracy and robustness of subsequent analysis. Then, adaptive weighting is performed on the enhanced risk scenario feature vector to obtain a weighted risk feature vector. Adaptive weighting dynamically adjusts the weight of each feature based on its importance to highlight key features and suppress noise. For example, by using an adaptive weighting algorithm (such as gradient boosting or random forest), each feature in the enhanced risk scenario feature vector can be assigned a weight. These weights reflect the importance of each feature in risk assessment and help improve the model's predictive performance. For example, if the "supply chain disruption" feature has a greater risk impact in certain situations, its weight may be assigned a higher value. Furthermore, a time series analysis of the weighted risk feature vector is performed using a pre-defined long short-term memory (LSTM) network to obtain a risk warning assessment result. LSTM is a specialized recurrent neural network particularly well-suited for processing time series data, capturing patterns in data over time. In this process, the LSTM model uses historical data and the current weighted risk feature vector to predict the probability and impact of risks occurring over a period of time. For example, by analyzing the frequency and scope of supply chain disruptions and quality incidents over the past few months, the LSTM model can predict the likelihood of these risk events occurring within the next month and their impact on the supply chain. This type of time series analysis not only provides short-term risk warnings but also helps companies develop long-term risk management strategies.Based on the risk warning assessment results, a risk path simulation is performed on the supply chain data to determine the risk development path. Risk path simulation uses simulation technology to simulate the risk's propagation process and development trends within the supply chain. For example, if the LSTM model predicts that a key supplier may experience supply issues within the next month, risk path simulation can be used to analyze how this issue affects manufacturers, distributors, and retailers that rely on that supplier, and how these impacts evolve over time. Risk path simulation allows companies to more intuitively understand the risk's propagation path and scope, providing a basis for formulating response measures. Finally, based on the risk development path and risk scenario type, a risk mitigation plan is derived. This process combines the risk warning assessment results with the risk path simulation results to develop specific mitigation measures for each risk scenario type. For example, for the "supply chain disruption" risk scenario, companies can implement measures such as establishing a diversified supplier system and increasing safety stock; for the "quality incident" risk scenario, they can strengthen supplier quality management and introduce third-party quality certification. In this way, companies can not only be fully prepared before risks occur, but also take swift action when risks do arise, minimizing losses and ensuring the normal operation of the supply chain. Through this series of steps, companies can not only comprehensively assess and manage potential risks within their supply chains, but also develop scientific and effective risk mitigation plans, enhancing the stability and resilience of their supply chains. For example, in the automotive service supply chain, using this approach, companies can identify key suppliers as key risk points, the specific risk scenarios these risk points may trigger, and the scope and probability of these risk scenarios. This allows them to develop targeted risk management strategies and improve the overall resilience of their supply chains.

[0118] In a specific embodiment, the risk mitigation plan includes a diversified supplier strategy, a multi-channel logistics strategy, and a resource reserve strategy.

[0119] The above describes the risk warning method based on the automobile service supply chain in the embodiment of the present invention. The following describes the risk warning system based on the automobile service supply chain in the embodiment of the present invention. Figure 2 In one embodiment of the present invention, a risk early warning system based on an automobile service supply chain includes:

[0120] The collection module 21 is used to collect data from various links in the automotive service supply chain to obtain supply chain data;

[0121] A modeling module 22 is configured to use a preset graph theory algorithm to perform topological network modeling on the automotive service supply chain based on the supply chain data to obtain a topological network structure of the automotive service supply chain;

[0122] An analysis module 23 is configured to identify whether there are supply chain risk points in the topological network structure using a preset identification algorithm, and if so, perform a risk impact analysis on the supply chain data using the supply chain risk points in the topological network structure to obtain a risk impact analysis result;

[0123] A classification module 24 is configured to classify the risk impact analysis results into risk scenarios to obtain risk scenario types;

[0124] The evaluation module 25 is configured to perform a risk warning evaluation based on the risk scenario type, obtain a risk warning evaluation result, and formulate a risk mitigation plan based on the risk scenario type and the risk warning evaluation result.

[0125] In this embodiment, for the specific implementation of each unit in the above system embodiment, please refer to the above method embodiment, which will not be repeated here.

[0126] Reference Figure 3 In an embodiment of the present invention, a computer device is also provided, wherein the internal structure of the computer device can be as follows: Figure 3 As shown. The computer device includes a processor, memory, display screen, input device, network interface and database connected via a system bus. The processor of the computer design is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the above method is implemented.

[0127] Those skilled in the art will understand that Figure 3 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention and does not constitute a limitation on the computer device to which the solution of the present invention is applied.

[0128] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which implements the above-described method when executed by a processor. It is understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0129] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware using a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the above-described method embodiments. Any reference to memory, storage, database, or other media provided herein and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM.

[0130] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, apparatus, article, or method comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, apparatus, article, or method. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, apparatus, article, or method comprising the element.

[0131] The above description is only a preferred embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A risk early warning method based on the automotive service supply chain, characterized in that: The following steps are involved: Collect data from each link in the automotive service supply chain to obtain supply chain data; Using a preset graph theory algorithm, a topological network model is performed on the automotive service supply chain based on the supply chain data to obtain a topological network structure of the automotive service supply chain; Identify whether there are supply chain risk points in the topological network structure using a preset identification algorithm; if so, perform a risk impact analysis on the supply chain data using the supply chain risk points in the topological network structure to obtain a risk impact analysis result; Performing risk scenario classification on the risk impact analysis results to obtain risk scenario types; Performing a risk warning assessment based on the risk scenario type to obtain a risk warning assessment result, and formulating a risk mitigation plan based on the risk scenario type and the risk warning assessment result; The risk impact analysis is performed on the supply chain data through the supply chain risk points in the topological network structure to obtain risk impact analysis results; wherein the risk impact analysis results include potential risk points and the impact range of the supply chain risk points, including: Performing correlation analysis on the supply chain data through the supply chain risk points in the topological network structure to obtain a risk propagation path diagram; Based on the risk propagation path diagram, the propagation probability of the supply chain risk point to the transmission path is calculated to obtain a risk propagation probability matrix; wherein the rows of the risk propagation probability matrix represent the starting nodes of the transmission path, the columns of the risk propagation probability matrix represent the ending nodes of the transmission path, and the elements of the risk propagation probability matrix represent the propagation probability values ​​from the starting node to the ending node; Extracting time series features from the risk propagation probability matrix to obtain a risk propagation time series feature vector; Based on the risk propagation time series feature vector, risk prediction is performed on the supply chain data to obtain a risk impact degree prediction result, and the risk impact degree prediction result is used as a risk impact analysis result; Performing a vulnerability assessment on the supply chain data based on the risk impact prediction result to obtain a network vulnerability index; When the network vulnerability index is less than a preset vulnerability index, determining the potential risk point based on the network vulnerability index; Performing spatial analysis on the network vulnerability index to obtain the impact range of supply chain risk points; The risk impact analysis results are classified into risk scenario categories to obtain risk scenario types, including: The potential risk points of the risk impact analysis results are used as rows and the impact ranges are used as columns to construct a risk feature matrix; wherein the elements of the risk feature matrix represent the risk degree; Inputting the risk feature matrix into a preset multi-level decision tree algorithm for analysis to obtain a risk feature hierarchy tree; Using a support vector machine classification algorithm, the risk feature hierarchical tree is preliminarily classified to obtain a preliminary risk scenario type; Performing risk scenario probability inference on the preliminary risk scenario type to obtain a probabilistic risk scenario type; Performing correlation analysis on the probabilistic risk scenario types to obtain correlated risk scenario types; Risk scenario types are classified based on the preliminary risk scenario types, the probabilistic risk scenario types, and the associated risk scenario types to obtain risk scenario types.

2. The risk early warning method based on the automotive service supply chain according to claim 1 is characterized in that: The various links include suppliers, manufacturers, distributors, and retailers. The data of each link in the automotive service supply chain is collected to obtain supply chain data, including: Through the distributed crawler system, we collect multi-source heterogeneous data from suppliers, manufacturers, distributors, and retailers in the automotive service supply chain to obtain original supply chain data; Preprocessing the raw supply chain data to obtain clean supply chain data; By using data fusion technology, the clean supply chain data from different sources is fused to obtain fused data in a unified format; Performing data parsing on the unstructured text data in the fused data to extract key information from the fused data; The key information is trend-forecasted using a preset long-short memory network to obtain supply chain activity trend data, which is used as supply chain data.

3. The risk early warning method based on the automotive service supply chain according to claim 2 is characterized in that: The method of using a preset graph theory algorithm to perform topological network modeling on the automotive service supply chain based on the supply chain data to obtain a topological network structure of the automotive service supply chain includes: Utilizing a preset graph theory algorithm, extracting entities and relationships between entities in the supply chain data; wherein the entities include suppliers, manufacturers, distributors, and retailers; Constructing a supply chain entity relationship table based on the entities and the relationships between the entities; wherein the supply chain entity relationship table includes nodes and edges, with the entities as nodes and the relationships between the entities as edges; Utilizing the node degree centrality layer in the graph theory algorithm to calculate the importance of each node in the supply chain entity relationship table to obtain a node importance score; wherein the node importance score includes the in-degree and out-degree of each node; Calculate the frequency of the in-degree and out-degree of each node to obtain the in-degree frequency and out-degree frequency of each node; Using a preset community detection algorithm, identifying corresponding entities and upstream and downstream entities of the corresponding entities in the supply chain entity relationship table based on the node importance score, so as to obtain a supply chain community structure diagram; Labeling entities corresponding to the node importance scores to obtain labeled corresponding entities, and attaching the labeled corresponding entities to the supply chain community structure diagram to obtain a labeled supply chain community structure diagram; Calculating the transmission path of the edge between each of the nodes based on the in-degree frequency and the out-degree frequency between each of the nodes; wherein the transmission path represents the importance between the nodes, a shorter transmission path represents a closer connection between the nodes, and a longer transmission path represents a looser connection between the nodes; A topological network model is performed on the automobile service supply chain based on the labeled supply chain community structure diagram and the transmission path to obtain a topological network structure of the automobile service supply chain.

4. The risk early warning method based on the automotive service supply chain according to claim 1 is characterized in that: The risk warning assessment is performed based on the risk scenario type to obtain a risk warning assessment result, and a risk mitigation plan is formulated based on the risk scenario type and the risk warning assessment result, including: Performing vector conversion on the risk scenario type to obtain a type conversion vector; Performing high-dimensional mapping on the type conversion vector to obtain an enhanced risk scenario feature vector; Adaptively assigning weights to the enhanced risk scenario feature vector to obtain a weighted risk feature vector; Performing time series analysis on the weighted risk feature vector through a preset long short-term memory network to obtain a risk warning assessment result; Performing risk path simulation on the supply chain data based on the risk warning assessment results to obtain a risk development path; Based on the risk development path and risk scenario type, a risk mitigation plan is obtained.

5. The risk early warning method based on the automotive service supply chain according to claim 1 is characterized in that: The risk mitigation plans include diversified supplier strategy, multi-channel logistics strategy and resource reserve strategy.

6. A risk early warning system based on the automotive service supply chain, characterized by: The method for executing a risk early warning method based on an automotive service supply chain according to any one of claims 1 to 5 comprises: The collection module is used to collect data from various links in the automotive service supply chain to obtain supply chain data; a modeling module, configured to use a preset graph theory algorithm to perform topological network modeling on the automotive service supply chain based on the supply chain data, thereby obtaining a topological network structure of the automotive service supply chain; an analysis module, configured to identify whether there are supply chain risk points in the topological network structure using a preset identification algorithm; if so, perform a risk impact analysis on the supply chain data using the supply chain risk points in the topological network structure to obtain a risk impact analysis result; A classification module is used to classify the risk impact analysis results into risk scenarios to obtain risk scenario types; An assessment module is configured to perform a risk warning assessment based on the risk scenario type, obtain a risk warning assessment result, and formulate a risk mitigation plan based on the risk scenario type and the risk warning assessment result; The risk impact analysis is performed on the supply chain data through the supply chain risk points in the topological network structure to obtain risk impact analysis results; wherein the risk impact analysis results include potential risk points and the impact range of the supply chain risk points, including: Performing correlation analysis on the supply chain data through the supply chain risk points in the topological network structure to obtain a risk propagation path diagram; Based on the risk propagation path diagram, the propagation probability of the supply chain risk point to the transmission path is calculated to obtain a risk propagation probability matrix; wherein the rows of the risk propagation probability matrix represent the starting nodes of the transmission path, the columns of the risk propagation probability matrix represent the ending nodes of the transmission path, and the elements of the risk propagation probability matrix represent the propagation probability values ​​from the starting node to the ending node; Extracting time series features from the risk propagation probability matrix to obtain a risk propagation time series feature vector; Based on the risk propagation time series feature vector, risk prediction is performed on the supply chain data to obtain a risk impact degree prediction result, and the risk impact degree prediction result is used as a risk impact analysis result; Performing a vulnerability assessment on the supply chain data based on the risk impact prediction result to obtain a network vulnerability index; When the network vulnerability index is less than a preset vulnerability index, determining the potential risk point based on the network vulnerability index; Performing spatial analysis on the network vulnerability index to obtain the impact range of supply chain risk points; The risk impact analysis results are classified into risk scenario categories to obtain risk scenario types, including: The potential risk points of the risk impact analysis results are used as rows and the impact ranges are used as columns to construct a risk feature matrix; wherein the elements of the risk feature matrix represent the risk degree; Inputting the risk feature matrix into a preset multi-level decision tree algorithm for analysis to obtain a risk feature hierarchy tree; Using a support vector machine classification algorithm, the risk feature hierarchical tree is preliminarily classified to obtain a preliminary risk scenario type; Performing risk scenario probability inference on the preliminary risk scenario type to obtain a probabilistic risk scenario type; Performing correlation analysis on the probabilistic risk scenario types to obtain correlated risk scenario types; Risk scenario types are classified based on the preliminary risk scenario types, the probabilistic risk scenario types, and the associated risk scenario types to obtain risk scenario types.

7. A computer device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images