Industrial chain breakpoint treatment-oriented monitoring method and system

Abstract

The invention relates to the technical field of industrial chain monitoring and treatment, in particular to a monitoring method and system for industrial chain breakpoint treatment. The method comprises the steps that production, logistics, finance, policy and environment dynamic information is acquired through multi-source data, industrial chain comprehensive characteristics are generated through standardization, fractal dimension embedding expression and cross-dimension fusion, and historical trend dependency is introduced to enhance prospective prediction; a dynamic coupling network is constructed, and risk propagation intensity between nodes is quantified by using a dynamic edge weight, so that cross-level breakpoint propagation analysis is realized; risk indexes are calculated by fusing node features and a network structure, breakpoint candidate nodes are screened in combination with an adaptive threshold value, and a multi-step evolution trend is predicted by adopting a nonlinear propagation function and mapped into a multi-level early warning level. And generating a governance strategy according to the risk level, and evaluating the effect in real time and dynamically adjusting parameters through a closed-loop optimization mechanism. According to the invention, closed-loop management of risk identification, prediction and adaptive treatment is realized.

Description

Technical Field

[0001] This invention relates to the field of supply chain monitoring and governance technology, specifically to a monitoring method and system for addressing supply chain disruptions. Background Technology

[0002] Against the backdrop of the increasing complexity of the global industrial chain and the diversification of sudden disturbance factors, the prevention and control of breakpoint risks faces common technical challenges such as dynamic fusion of multi-source heterogeneous data, cross-level dependency quantification, and forward-looking early warning.

[0003] Chinese invention patent application CN117094558A discloses a method and system for identifying supply chain risks based on time-series graphs. The method includes: acquiring supply chain data and constructing a risk factor graph with time-series information to obtain a risk factor time-series graph; acquiring supply chain risk data; acquiring supply chain state sequences and supply chain state transition graphs, and extracting risk factor time-series graph data based on the supply chain state sequences and supply chain state transition graphs to obtain risk factor time-series sequence data; performing static embedding and dynamic embedding on the supply chain risk data and risk factor time-series sequence data respectively to obtain static embedding vectors and dynamic embedding vectors respectively; performing joint information embedding on the dynamic embedding vectors and risk factor time-series graphs to obtain a set of result vectors for joint information embedding; performing information fusion based on an attention mechanism on the set of result vectors for static embedding and joint information embedding to obtain a fusion result; and finally identifying and predicting supply chain risks.

[0004] Existing solutions need to take into account the collaborative analysis capabilities of micro-level enterprise behavior, meso-level linkages, and macro-level regional impacts, while also addressing the real-time response needs of complex risk factors such as financial fluctuations, geopolitical policy adjustments, and natural disasters. This will drive the development of supply chain governance towards a systematic approach characterized by real-time perception, adaptive modeling, and intelligent decision-making loops. Summary of the Invention

[0005] The purpose of this invention is to address the problems existing in the background technology by proposing a monitoring method and system for managing supply chain disruptions.

[0006] The technical solution of this invention: a monitoring method for addressing supply chain disruptions, comprising the following specific implementation steps: S1. Collect dynamic information on production, logistics, finance, policy and environment related to the industrial chain through multi-source data collection; standardize the multi-source data and fill in missing values, and construct a fractal embedding representation for each type of data; fuse the embedding vectors across dimensions to generate a comprehensive embedding representation of the industrial chain; introduce historical trend dependence to perform dynamic feature enhancement to obtain the enhanced comprehensive features; S2. Based on the enhanced comprehensive features and the personalized attributes of each node in the industry chain, a node feature vector for each node is generated by fusion; the instantaneous dependency sensitivity between nodes is calculated based on the node feature vector, and a dynamic adjacency matrix is ​​constructed by combining the historical dependency strength index; based on the dynamic adjacency matrix and the node set, a three-layer dynamic coupling network is constructed, and the coupling weight between cross-level nodes is quantified by the cross-layer scaling factor. S3. Based on a dynamic coupling network, the system integrates the node's own state, upstream dependency sensitivity, and downstream transmission potential to calculate the breakpoint risk index for each node; it dynamically calculates an adaptive threshold based on the distribution of risk indices across the entire network to screen candidate breakpoint nodes; it performs multi-step risk evolution prediction on the candidate breakpoint nodes using a nonlinear risk propagation function to obtain the predicted risk value; and it maps the predicted risk value to a multi-level early warning system. S4. Based on the early warning level and risk evolution trend, generate multi-objective governance strategies, and use a closed-loop optimization mechanism to evaluate the effectiveness of strategy implementation and dynamically adjust parameters in real time.

[0007] Preferably, the fractal embedding representation maps the observed data of each class of data to a low-dimensional feature space through an embedding mapping function to obtain an embedding vector; The embedding mapping function is a learnable parameter function that includes a weight matrix and a bias term.

[0008] The preferred cross-dimensional fusion process is as follows: Align embedding vectors from different dimensions according to time synchronization; Construct an attention weight matrix to assess the importance of each dimension to the overall industry chain status; The weighted vectors of each dimension are combined, and a unified integrated embedding representation is generated through nonlinear transformation and feature mapping.

[0009] Preferably, historical trend dependence is introduced for dynamic feature enhancement, specifically as follows: Extract historical time windows from the integrated embedded sequence; Embedded vectors within the window are sequentially modeled using a recurrent neural network to capture temporal dependencies and dynamic evolutionary features; By adjusting the weights of different time steps, a context vector containing historical trend information is generated.

[0010] Preferably, the three-layer dynamically coupled network includes: The nodes in the process layer are supply, production, logistics, and sales. The nodes in the enterprise layer are specific enterprise entities; The nodes in the regional layer can be at least one of geographical regions or industrial clusters; Each layer of nodes is connected by cross-layer edges, and the edge weight is calculated by multiplying the coupling factor by the cross-layer scaling factor.

[0011] Preferably, the breakpoint risk index for each node is calculated as follows: Taking into account the node's own status, upstream dependency sensitivity, and downstream transmission potential; The risk value transmitted by upstream nodes and the transmission potential of downstream nodes are weighted and aggregated using a node risk comprehensive function; Risk is dynamically adjusted by combining the coupling strength between nodes and historical dependency information.

[0012] Preferably, the adaptive threshold is calculated dynamically, specifically as follows: The adaptive threshold is dynamically calculated based on the mean and standard deviation of the risk values ​​of all nodes in the network. The sensitivity of the screening is controlled by adjusting the threshold coefficient, that is: ; Where, θ t The risk threshold for the breakpoint at time t; This represents the average risk value of all nodes at time t. This represents the standard deviation of the risk values ​​of all nodes at time t; This represents the threshold adjustment coefficient, which controls the screening sensitivity.

[0013] Preferably, the nonlinear risk propagation function is based on a dynamically coupled network, integrates node feature vectors with the risk values ​​of upstream and downstream nodes, and predicts the node risk at the next time step through a nonlinear mapping mechanism.

[0014] Preferably, the predicted risk value is mapped to a multi-level early warning system, specifically as follows: The continuous risk value is transformed into a discrete four-level early warning level: low, medium, high, and extremely high, through a risk level mapping function. The risk level mapping function dynamically adjusts the threshold range based on the trend, peak size, and fluctuation characteristics of the predicted risk value within the time window, combined with the overall risk distribution of the network.

[0015] The technical solution of this invention: A monitoring system for managing supply chain disruptions, used to execute the aforementioned monitoring method for managing supply chain disruptions, comprising: The multi-source data acquisition and preprocessing module is used to acquire multi-source dynamic data of the industrial chain in real time, and to preprocess, standardize and fuse the data to generate a comprehensive feature vector of the node. The industrial chain dynamic coupling network construction module is used to dynamically generate multi-layer coupling networks and establish the coupling strength between nodes based on the comprehensive characteristics and dependencies of nodes; The breakpoint risk identification and dynamic evolution prediction module is used to quantify risks, screen candidate nodes, and predict multi-step risk evolution by utilizing network structure and node characteristics, and to generate multi-level early warning levels. The adaptive governance strategy generation and closed-loop optimization module is used to intelligently generate multi-objective governance strategies based on early warning information, and dynamically adjust the strategy parameters through a closed-loop optimization algorithm to perform adaptive iteration of the governance strategy.

[0016] Compared with the prior art, the above-mentioned technical solution of the present invention has the following beneficial technical effects: This invention designs a monitoring method and system for managing supply chain disruptions. By fusing multi-source heterogeneous data and using multi-layer dynamic network modeling, it significantly improves the accuracy and timeliness of supply chain disruption monitoring. Specifically, it employs embedded mapping and cross-dimensional fusion functions to achieve unified representation of multi-source data from production, logistics, and finance, solving the feature fragmentation problem caused by data heterogeneity in traditional methods and enhancing the robustness and information integrity of the monitoring system. Furthermore, it constructs a three-layer dynamic coupling network (link layer / enterprise layer / regional layer) combined with cross-layer scaling factors to accurately quantify the inter-node dependency sensitivity and cross-level risk propagation paths, breaking through the limitations of single-layer supply chain models. This invention overcomes the limitations of traditional methods in representing complex industrial chain topologies. It achieves multi-step evolution prediction based on a nonlinear risk propagation function, and identifies high-risk nodes in advance through dynamic threshold screening and risk level mapping, significantly improving the foresight and positioning accuracy of breakpoint early warning. It dynamically generates multi-objective governance strategies such as resource adjustment and path switching based on a closed-loop optimization mechanism, and provides real-time feedback on execution effect optimization parameters, effectively overcoming the lag in traditional manual decision-making and improving the resilience of the industrial chain while reducing intervention costs. This invention realizes an intelligent closed-loop process of "monitoring-prediction-governance," providing a quantifiable, adaptive, and highly responsive systematic solution for industrial chain security management. Attached Figure Description

[0017] Figure 1 This is a flowchart of a monitoring method for addressing supply chain disruptions proposed in this invention. Figure 2 This is a system architecture diagram of a monitoring system for addressing supply chain disruptions proposed in this invention. Detailed Implementation

[0018] Example 1, as Figure 1 As shown, the monitoring method for addressing supply chain disruptions proposed in this invention includes the following specific implementation steps: S1. Through multi-source data collection, time-series embedding, dynamic fusion, and feature enhancement, a comprehensive representation of the industrial chain operation is formed, laying the foundation for the identification and management of breakpoint risks. The specific implementation process is as follows: S11. Dynamically collect multi-source data related to the operation of the industrial chain. Data sources include, but are not limited to: production data (output, raw material inventory, equipment operating efficiency), logistics data (transportation delay, channel congestion index, warehouse turnover rate), financial data (credit level, capital liquidity, financing constraints), policy data (regulatory adjustments, trade barriers), and environmental data (natural disaster indicators, energy supply fluctuations). To ensure the comparability of data from different sources, standardization and missing value imputation methods were used to obtain the collected multi-source data D(t): ; Among them, D i (t) represents the observation data collected from data source i; N represents the total number of data sources; S12, For each type of data D i (t), construct the fractal-dimensional embedding representation: ; Among them, E i (t) represents the embedding vector of the observation data from data source i at time t; W i This represents the set of parameters for the embedding function, including the weight matrix and bias terms. This represents the embedding mapping function, used to map observed data to a low-dimensional feature space; It should be noted that the embedded mapping function This is a method for converting multidimensional heterogeneous data into low-dimensional feature representations. It can preserve the structural characteristics and temporal patterns of the data itself, while mapping different types of data to the same feature space for unified processing and analysis. In supply chain monitoring, embedding mapping functions can transform multi-source data such as production, logistics, finance, policy, and environment into vector representations that are computable and comparable. This allows the system to capture the unique information of each type of data and achieve cross-dimensional fusion analysis, thus providing an accurate and reliable input basis for breakpoint risk identification and dynamic evolution prediction. Through the above fractal embedding operation, a set of embedding vectors is obtained at time t. : ; S13. After obtaining the embedding vectors of each dimension, they are further fused to generate the overall temporal representation X of the industry chain. t : ; Among them, X t The comprehensive embedding representation of time t; Represents a cross-dimensional fusion function; Represents the set of parameters for the fusion layer; It should be noted that the cross-dimensional fusion function First, the embedding vectors from different dimensions are aligned in time synchronization to ensure the integrity of information in each dimension at each time point. Then, by constructing an attention weight matrix, the importance of each dimension to the overall industry chain status at the current time point is evaluated, thereby adaptively allocating weights to reflect their relative influence. Next, the weighted vectors of each dimension are combined, and a unified comprehensive representation is generated through nonlinear transformation and feature mapping. In this process, the fusion function can dynamically capture the interrelationships and temporal changes of different dimensions, so that the final comprehensive representation not only retains the independent features of each dimension, but also reflects the overall trend and key driving factors across dimensions, providing high-fidelity, multi-level input features for subsequent breakpoint risk identification. S14. Introduce a dynamic feature enhancement mechanism, adding historical trend dependence on the comprehensive embedding to improve the foresight of breakpoint prediction: ; in, This represents the enhanced overall features; This indicates that parameters are extracted from the context. This represents the comprehensive embedding over the past k time steps; Represents the history window context function; It should be noted that the history window context function First, a certain length of historical time window is extracted from the collected comprehensive embedding sequence. These time windows can cover the recent changes in the operating status of the industrial chain and potential fluctuation patterns. Then, the embedding vectors within the window are sequentially modeled. Recurrent neural networks (RNNs) are used to capture time dependencies and dynamic evolution features. During the modeling process, the weights of different time steps are adjusted so that the model can focus on historical moment information that has a greater impact on the risk of future breakpoints. At the same time, comprehensive representations are extracted through hidden states or feature aggregation methods. The final generated context vector contains both historical trend information and can dynamically reflect the current state and future change potential.

[0019] S2. The enhanced comprehensive features output in step S1. The process transforms the industry chain into a structured, analyzable network. This network structure reveals the dependencies between enterprises or links and the propagation paths of potential breakpoints, providing a foundation for subsequent breakpoint identification and governance strategy generation. The specific implementation process is as follows: S21. Integrate global information with local attributes to form computable node features, enabling each node to dynamically adjust its feature representation according to the state of the industry chain. Specifically: Define the set of nodes in the industry chain as V = {v1, v2, ..., v} i ,…,v n}; Among them, v iLet be the i-th node, and each node corresponds to an enterprise, production process, or key industry segment; n is the total number of nodes. The enhanced comprehensive features output in step S1 Personalized attributes of each node (Including but not limited to enterprise size, process type, geographical location, and historical breakpoint frequency) are fused to obtain the node feature vector H. i (t): ; in, The feature fusion function is represented in this embodiment, which uses weighted concatenation to fuse enhanced comprehensive features and node individual attributes into a computable feature vector; S22. By using dynamic edge weights, the intensity of potential risk propagation between nodes is quantified, upstream and downstream sensitivity is captured, and a quantitative basis for predicting breakpoint risks is provided. Specifically: Based on node features H i (t) Calculate the coupling strength and dependency sensitivity between nodes, and construct the dynamic adjacency matrix A. t : ; in, W represents the immediate dependency sensitivity of node i on node j, with a value range of [0,1]. c This represents the coupling parameter matrix between nodes, characterizing the influence weights between the node eigenvectors; A represents the weighting coefficients that balance immediate features and historical dependencies; t S represents the dynamic adjacency matrix, i.e., the dependence or coupling strength of node i to node j at time t; ij Indicators representing the strength of historical dependency between node i and node j, such as long-term transaction frequency, supply and demand dependency, or historical cooperation data; S23. Utilizing multi-layered networks, simultaneously capturing micro-level firm behavior, process dependence, and macro-level regional impact, to achieve cross-level breakpoint risk propagation analysis, namely: dividing the industry chain into a three-layered network: process layer, firm layer, and regional layer. Link layer: The nodes are the supply, production, logistics and sales links, reflecting the status of the entire chain process; Enterprise layer: Nodes are specific enterprise entities, reflecting their micro-level operational status; Regional layer: Nodes represent geographical regions or industrial clusters, reflecting the impact of the macro environment; Nodes in each layer are connected by cross-layer edges, and the edge weights are multiplied by the cross-layer scaling factor using the coupling factor in small step S22. : ; in, This represents the coupling weight between nodes i and j across layers; This represents the cross-layer scaling factor, which reflects the propagation ratio between different layers. In this embodiment, it is set and optimized based on actual experience or historical data of the industry chain. S24. The constructed industrial chain network is dynamically updated according to the operational status of the industrial chain, and can also make local responses to emergencies, ensuring that the breakpoint risk prediction model can reflect the actual situation of the industrial chain in real time. Specifically: At each time step t, based on node features H i (t) and coupling factor Update network structure: G t =(V,A t ); When an abnormal event or sudden disturbance is detected, the local edge weights are adjusted in real time: ; Among them, G t The dynamic network of the industrial chain at time t is represented, including the set of nodes and the dynamic edge weight matrix; This represents the local disturbance adjustment value, used for dynamic correction of edge weights when a sudden event occurs. It is calculated based on the event intensity, node sensitivity, and historical anomaly data.

[0020] S3. The dynamic coupling network G of the industrial chain constructed based on step S2 t =(V,A t This involves identifying potential breakpoints and links, predicting the evolution of breakpoint risks along the industrial chain, and providing decision support for governance strategies. The specific implementation process is as follows: S31. By combining node characteristics with network structure, risk indicators are calculated, considering not only the node's own state but also quantifying upstream transmission risks and downstream potential impacts, to conduct a multi-dimensional comprehensive risk assessment, specifically: For each network node v i Calculate the breakpoint risk index R i (t), taking into account the node's own state, upstream dependency sensitivity, and downstream transmission potential: ; Among them, R i (t) represents node v i The breakpoint risk index at time t reflects the probability of a breakpoint occurring at that node and its potential impact on the entire industry chain; U(i) represents the set of upstream neighbors of node i, that is, all nodes that have a supply relationship or dependency relationship with node i; D(i) represents the set of downstream neighbors of node i, that is, all nodes that depend on node i. This represents the coupling weight of node j∈U(i) to node i, i.e., the upstream risk transmission capability; R represents the coupling weight of node i to node k∈D(i), i.e., the potential for the risk of a node to propagate downstream;j (t-1) represents the risk value of upstream node j in the previous time step, which is used to dynamically recursively estimate the node risk and is obtained by quantifying the node risk in the previous time step. Represents the node risk synthesis function; It should be noted that the node risk comprehensive function First, starting from the feature vectors of each node, these feature vectors integrate the node's own attribute information and the enhanced comprehensive features from step S1. Through nonlinear mapping, multidimensional attributes are unified into the same representation space, while preserving the individual differences of nodes and the state information of the entire chain. Then, the historical risk value of the node and the risk transmission of its upstream nodes are taken into consideration. Through weighted aggregation or association calculation based on attention mechanism, the function can simultaneously reflect the node's own vulnerability, upstream risk pressure, and downstream potential impact. Then, the risk is dynamically adjusted by combining the coupling strength between nodes and historical dependency information. The final generated function can quantify the breakpoint risk of each node in a multi-dimensional and multi-level industrial chain network and provide reliable input for subsequent candidate node screening and dynamic evolution prediction. S32. By using a dynamic threshold screening method, which adapts to different industrial chain states, the risk concentration areas are highlighted, specifically: Based on the node risk indicator R i (t) Set adaptive threshold θ t (threshold θ) t Based on dynamic adjustment of the risk distribution across the entire network, potential breakpoint nodes are screened: ; ; Among them, B t θ represents the set of candidate nodes for breakpoints at time t, i.e., nodes whose risk value is higher than a threshold. t The risk threshold for the breakpoint at time t is used to filter candidate nodes; This represents the average risk value of all nodes at time t. This represents the standard deviation of the risk values ​​of all nodes at time t; This represents the threshold adjustment coefficient, which controls the screening sensitivity. S33. Simulate the dynamic process of breakpoint risk propagating from nodes to upstream and downstream and across layers, and predict the evolution trend of supply chain breakpoints, that is: using the dynamic multi-layer coupled network G from step S2. t Establish a breakpoint risk propagation model: ; in, This represents the predicted risk value of node i at the next time step; This represents a nonlinear risk propagation function used to predict the risk at the next time step. It should be noted that the nonlinear risk propagation function Based on the dynamic coupling network of the industrial chain constructed in step S2, the feature vector of each node is combined with the risk values ​​of its upstream and downstream nodes. An initial risk response representation is formed through multi-dimensional feature fusion. This representation reflects the node's own state, historical risk transmission, and upstream and downstream coupling strength. A nonlinear mapping mechanism is introduced, which can be a graph neural network or attention mechanism. Different influence weights and coupling relationships between nodes are nonlinearly weighted through learnable parameters, so that risk transmission in the network can reflect the sensitivity and propagation strength of different nodes. Then, through training or iterative optimization, the function can capture the non-uniformity, suddenness, and cross-level impact of risk propagation. This ensures that the function output reasonably reflects the risk evolution trend under the conditions of local node disturbance or full-chain anomaly. Finally, a nonlinear risk propagation function that can be used for multi-step breakpoint prediction and dynamic early warning is formed, realizing the complete mapping of industrial chain risk from micro nodes to macro chains. S34. By using multi-step prediction and grading, the potential location and severity of breakpoints can be predicted in advance, providing a quantitative basis for governance strategies. Specifically: For candidate breakpoint node B t Multi-step risk evolution prediction is performed on the upstream and downstream neighbors to generate short-term and medium-term risk evolution curves; Map the prediction results to a multi-level early warning system L i (t)∈{low, medium, high, extremely high}: ; Among them, L i (t) represents the warning level (low, medium, high, extremely high) of node i, used to characterize the severity of the breakpoint risk, based on the predicted risk. Obtained through transformation using a mapping function; τ represents the risk level mapping function; τ represents the prediction time window length, i.e., the time span of multi-step evolution prediction. It should be noted that the risk level mapping function It is a nonlinear function that transforms continuous risk values ​​into discrete level labels. Its core idea is to comprehensively judge the risk status of a node based on the trend, peak size, and fluctuation characteristics of the predicted risk values ​​within a time window, and map them to low, medium, high, or extremely high levels. This function is usually implemented by setting dynamic threshold intervals, with different intervals corresponding to different risk levels. These intervals are not fixed, but are dynamically adjusted in combination with statistical characteristics such as the overall risk distribution of the network, historical mean, and standard deviation, so as to ensure that the mapping results can truly reflect the changes in the system's operating environment. S35. The predicted breakpoint risks and evolution trends are presented through multi-dimensional visualization, including node risk heatmaps, link risk propagation diagrams, and cross-layer network evolution dynamic diagrams.

[0021] S4. Based on the breakpoint risk prediction and multi-level early warning information generated in step S3, formulate targeted governance strategies for potential breakpoints in the industrial chain, and achieve dynamic adjustment and adaptive iteration of the strategies through closed-loop optimization. Through the cycle of risk-strategy-feedback-optimization, the breakpoint governance process of complex industrial chains is systematized and made intelligent, specifically as follows: Based on the risk level and evolution trend of candidate breakpoint nodes, multi-objective governance strategies are automatically generated, including but not limited to node resource adjustment, inventory optimization, alternative path switching in the supply chain, and collaborative intervention by key enterprises. The strategy generation process fully considers the node risk priority, governance cost, intervention timeliness, and the chain reaction of the strategy on the entire network to avoid new risk spillovers that may be caused by single-point governance. Through a closed-loop optimization mechanism, the effectiveness of governance strategies is evaluated in real time: continuously monitor changes in node risks and execution feedback, and dynamically adjust strategy parameters, such as intervention intensity, execution order, and resource allocation ratio, to maximize risk mitigation and supply chain stability. The optimization process uses adaptive algorithms, which can combine predicted risk evolution curves and network coupling characteristics to achieve multi-objective trade-offs, while avoiding reliance on traditional fixed rules and human experience.

[0022] Example 2, as Figure 2 As shown, the present invention proposes a monitoring system for supply chain disruption governance, which is used to execute a monitoring method for supply chain disruption governance proposed in Embodiment 1, including: a multi-source data acquisition and preprocessing module, a supply chain dynamic coupling network construction module, a disruption risk identification and dynamic evolution prediction module, and an adaptive governance strategy generation and closed-loop optimization module.

[0023] The multi-source data acquisition and preprocessing module is responsible for acquiring multi-source dynamic data from all links of the industry chain in real time, and performing preprocessing, noise reduction, missing value filling and standardization on the acquired data. It also generates a comprehensive feature vector for each node through feature extraction, cross-source fusion and dynamic embedding technology, ensuring that the node characteristics and the overall industry chain status are represented efficiently and accurately, providing high-quality input for subsequent network construction. The industrial chain dynamic coupling network construction module, based on the comprehensive characteristics of nodes and the upstream and downstream dependencies of the supply chain, dynamically generates a multi-layer coupling network, establishes the edge weights and coupling strength between nodes, and considers cross-level influence and time changes to form a structured network that can reflect the operating status of the industrial chain and the interaction of nodes, providing a network foundation for identifying breakpoint risks. The breakpoint risk identification and dynamic evolution prediction module uses network structure and node characteristics to quantify the risk of each node and screen candidate breakpoints. It also predicts the multi-step evolution trend of risk through nonlinear propagation modeling and generates multi-level early warning levels. The module also considers upstream transmission risk, downstream impact and historical risk dynamics to achieve closed-loop analysis from node risk quantification to full-chain evolution prediction. The adaptive governance strategy generation and closed-loop optimization module intelligently generates multi-objective governance strategies based on predicted breakpoint risks and early warning information, including resource allocation, inventory optimization, supply chain switching, and collaborative intervention by key enterprises. Through a closed-loop optimization algorithm, the module dynamically adjusts strategy parameters to achieve adaptive iteration of governance strategies, continuously optimizes the breakpoint mitigation effect and supply chain stability, and provides feedback on strategy execution results for the next round of strategy adjustment and optimization decisions.

[0024] The embodiments of the present invention have been described in detail above with reference to the accompanying drawings. However, the present invention is not limited thereto. Various changes can be made within the scope of knowledge possessed by those skilled in the art without departing from the spirit of the present invention.

Claims

1. A monitoring method for addressing supply chain disruptions, characterized in that, The specific implementation steps include the following: S1. Collect dynamic information on production, logistics, finance, policy and environment related to the industrial chain through multi-source data collection; standardize the multi-source data and fill in missing values, and construct a fractal embedding representation for each type of data; fuse the embedding vectors across dimensions to generate a comprehensive embedding representation of the industrial chain; introduce historical trend dependence to perform dynamic feature enhancement to obtain the enhanced comprehensive features; S2. Based on the enhanced comprehensive features and the personalized attributes of each node in the industry chain, a node feature vector for each node is generated by fusing them; based on The node feature vector is used to calculate the instantaneous dependency sensitivity between nodes, and a dynamic adjacency matrix is ​​constructed by combining the historical dependency strength index. Based on the dynamic adjacency matrix and the node set, a three-layer dynamic coupling network is constructed, and the coupling weight between nodes across layers is quantified by the cross-layer scaling factor. S3. Based on the dynamic coupling network, the node's own state, upstream dependency sensitivity and downstream transmission potential are integrated to calculate the breakpoint risk index of each node. Based on the distribution of risk indicators of all network nodes, an adaptive threshold is dynamically calculated to screen candidate nodes for breakpoints; a multi-step risk evolution prediction is performed on the candidate nodes for breakpoints using a nonlinear risk propagation function to obtain the predicted risk value. Map the predicted risk values ​​to multiple warning levels; S4. Based on the early warning level and risk evolution trend, generate multi-objective governance strategies, and use a closed-loop optimization mechanism to evaluate the effectiveness of strategy implementation and dynamically adjust parameters in real time.

2. The monitoring method for addressing supply chain disruptions according to claim 1, characterized in that, Fractal-dimensional embedding means that the observed data of each class of data is mapped to a low-dimensional feature space through an embedding mapping function to obtain an embedding vector. The embedding mapping function is a learnable parameter function that includes a weight matrix and a bias term.

3. The monitoring method for addressing supply chain disruptions according to claim 2, characterized in that, The cross-dimensional fusion process is as follows: Align embedding vectors from different dimensions according to time synchronization; Construct an attention weight matrix to assess the importance of each dimension to the overall industry chain status; The weighted vectors of each dimension are combined, and a unified integrated embedding representation is generated through nonlinear transformation and feature mapping.

4. The monitoring method for addressing supply chain disruptions according to claim 3, characterized in that, Introducing historical trend dependence for dynamic feature enhancement, specifically: Extract historical time windows from the integrated embedded sequence; Embedded vectors within the window are sequentially modeled using a recurrent neural network to capture temporal dependencies and dynamic evolutionary features; By adjusting the weights of different time steps, a context vector containing historical trend information is generated.

5. The monitoring method for addressing supply chain disruptions according to claim 1, characterized in that, Three-layer dynamically coupled networks include: The nodes in the process layer are supply, production, logistics, and sales. The nodes in the enterprise layer are specific enterprise entities; The nodes in the regional layer can be at least one of geographical regions or industrial clusters; Each layer of nodes is connected by cross-layer edges, and the edge weight is calculated by multiplying the coupling factor by the cross-layer scaling factor.

6. The monitoring method for addressing supply chain disruptions according to claim 5, characterized in that, Calculate the breakpoint risk index for each node, specifically as follows: Taking into account the node's own status, upstream dependency sensitivity, and downstream transmission potential; The risk value transmitted by upstream nodes and the transmission potential of downstream nodes are weighted and aggregated using a node risk comprehensive function; Risk is dynamically adjusted by combining the coupling strength between nodes and historical dependency information.

7. The monitoring method for addressing supply chain disruptions according to claim 6, characterized in that, The adaptive threshold is calculated dynamically, specifically as follows: The adaptive threshold is dynamically calculated based on the mean and standard deviation of the risk values ​​of all nodes in the network. The sensitivity of the screening is controlled by adjusting the threshold coefficient, that is: ； Where, θ t The risk threshold for the breakpoint at time t; This represents the average risk value of all nodes at time t. This represents the standard deviation of the risk values ​​of all nodes at time t; This represents the threshold adjustment coefficient, which controls the screening sensitivity.

8. The monitoring method for addressing supply chain disruptions according to claim 7, characterized in that, The nonlinear risk propagation function is based on a dynamically coupled network. It integrates the node feature vectors with the risk values ​​of upstream and downstream nodes and predicts the node risk at the next time step through a nonlinear mapping mechanism.

9. A monitoring method for addressing supply chain disruptions according to claim 8, characterized in that, The predicted risk values ​​are mapped to multiple warning levels, specifically as follows: The continuous risk value is transformed into a discrete four-level early warning level: low, medium, high, and extremely high, through a risk level mapping function. The risk level mapping function dynamically adjusts the threshold range based on the trend, peak size, and fluctuation characteristics of the predicted risk value within the time window, combined with the overall risk distribution of the network.

10. A monitoring system for managing supply chain disruptions, used to execute the monitoring method for managing supply chain disruptions as described in any one of claims 1 to 9, characterized in that, include: The multi-source data acquisition and preprocessing module is used to acquire multi-source dynamic data of the industrial chain in real time, and to preprocess, standardize and fuse the data to generate a comprehensive feature vector of the node. The industrial chain dynamic coupling network construction module is used to dynamically generate multi-layer coupling networks and establish the coupling strength between nodes based on the comprehensive characteristics and dependencies of nodes; The breakpoint risk identification and dynamic evolution prediction module is used to quantify risks, screen candidate nodes, and predict multi-step risk evolution by utilizing network structure and node characteristics, and to generate multi-level early warning levels. The adaptive governance strategy generation and closed-loop optimization module is used to intelligently generate multi-objective governance strategies based on early warning information, and dynamically adjust the strategy parameters through a closed-loop optimization algorithm to perform adaptive iteration of the governance strategy.

Images