A Big Data-Based Intelligent Risk Control System

Abstract

This invention provides an intelligent risk control system based on big data, relating to the field of risk analysis technology. The system integrates and cleans various supply chain data through a data acquisition module to ensure the accuracy of the analysis. A coefficient generation module utilizes big data analytics to generate logistics congestion risk coefficients and production stability coefficients, thereby dynamically assessing the supply chain's on-time delivery capability and delivery completion rate, improving the real-time nature and accuracy of the assessment. An index generation module analyzes problem response data to generate a failure learning index, comprehensively assessing the ability to respond to unexpected problems and identifying areas for improvement. A threshold judgment module establishes a comprehensive risk index through comprehensive analysis of the generated coefficients and automatically predicts the risk warning level based on set risk thresholds, triggering timely countermeasures. This system enhances the flexibility and resilience of the supply chain, enabling enterprises to achieve more efficient operation and management in a dynamic market.

Description

Technical Field

[0001] This invention relates to the field of risk analysis technology, specifically to an intelligent risk control system based on big data. Background Technology

[0002] In modern supply chain management, the rise and widespread application of big data technology has greatly promoted the development of intelligent supply chain management systems. With the acceleration of globalization, supply chain networks are becoming increasingly complex, involving a growing number of partners, logistics route selection, and production capacity, posing unprecedented challenges to supply chain stability and risk management. Against this backdrop, many enterprises and research institutions have invested heavily in developing big data-based supply chain risk control systems. These systems integrate multi-source data and utilize advanced data analytics to assess and predict various potential risks in the supply chain. However, traditional supply chain risk management systems often rely on static historical data analysis, lacking the ability to respond promptly to real-time dynamic changes, making them ineffective in rapidly changing market environments. Particularly in areas such as logistics congestion, production stability, and problem response speed, existing technologies have failed to fully utilize the real-time analytical capabilities of big data, thus failing to provide accurate risk warnings and countermeasures.

[0003] In the prior art, publication number CN115860485A, entitled "A Supply Chain Risk Control System and Method Based on Big Data and Artificial Intelligence," the system includes: a supply chain data retrieval module, a supply chain exception analysis module, a backup supply node intelligent processing module, and a risk early warning module. The output of the supply chain data retrieval module is connected to the input of the supply chain exception analysis module; the output of the supply chain exception analysis module is connected to the input of the backup supply node intelligent processing module; and the output of the backup supply node intelligent processing module is connected to the input of the risk early warning module. This system can analyze the rationality of backup supply nodes set up under supply chain exceptions in advance, effectively improve the monitoring and setting of backup supply nodes, enhance the supply chain's resilience in the face of risks, and reduce losses.

[0004] Despite significant advancements in existing supply chain risk control technologies, several notable shortcomings remain. First, traditional systems often rely on simple regression analysis of historical data to analyze logistics routes and on-time delivery rates, lacking in-depth analysis of real-time logistics information. This results in insufficient accuracy and real-time performance of logistics congestion risk coefficients. Second, the correlation between production capacity fluctuations and historical cooperation frequency is not fully explored. Existing technologies neglect dynamic data changes when generating production stability coefficients, limiting the accuracy of production stability assessments. Furthermore, existing risk management systems often provide overly simplistic analysis of problem response data, failing to adequately consider the complex relationships between problem level, response time, and quantity. Consequently, the generated failure learning index fails to accurately reflect the supply chain's resilience and problem-solving efficiency.

[0005] The information disclosed in the background section above is only intended to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0006] The purpose of this invention is to provide an intelligent risk control system based on big data to solve the problems mentioned in the background art.

[0007] To achieve the above objectives, the present invention provides the following technical solution:

[0008] A big data-based intelligent risk control system includes the following steps:

[0009] Data acquisition module: used to acquire supply chain datasets from the past M supply and demand collaborations of each supply chain. The supply chain datasets include, but are not limited to, logistics route data, on-time delivery rate, capacity indicators, historical collaboration frequency and problem response data. The data is then cleaned and standardized to generate quantifiable analysis datasets.

[0010] Coefficient generation module: Used to analyze the generated dataset based on big data analytics to generate logistics congestion risk coefficients and production stability coefficients related to supply chain risks, including:

[0011] The logistics congestion risk coefficient consists of logistics route data and on-time delivery rate, and is used to assess the probability trend of each supply chain delivering the required supply on time under the current logistics route data.

[0012] The production stability coefficient consists of capacity indicators and historical cooperation frequency, and is used to assess the delivery completion rate of each supply chain in the current cooperation.

[0013] Index generation module: used to obtain problem response data of each supply chain in each supply and demand cooperation. The problem response data includes problem level indicators, problem response time and number of problems;

[0014] The system analyzes and processes the data related to these issues to generate a failure learning index. This index is used to assess the frequency and severity of problems in current collaborations across different supply chains, as well as their efficiency in resolving these problems.

[0015] Threshold judgment module: used to obtain and analyze the logistics congestion risk coefficient, failure learning index and production stability coefficient to establish a comprehensive risk index for each supply chain;

[0016] Set risk thresholds for each supply chain in relation to the comprehensive risk index, compare and analyze the comprehensive risk index with the corresponding risk thresholds, and predict the risk warning level of the corresponding supply chain based on the analysis results;

[0017] Based on the predicted risk warning level, corresponding response measures will be automatically triggered.

[0018] Compared with existing technologies, the beneficial effects of this invention are: through the collaborative work of multiple modules, more accurate and real-time management of supply chain risks is achieved; firstly, the data acquisition module can effectively integrate and clean various types of supply chain data, including logistics routes, on-time delivery rates, and capacity indicators, to generate quantifiable analytical datasets; this process ensures the accuracy and consistency of the data, providing a solid foundation for subsequent analysis.

[0019] Secondly, the coefficient generation module utilizes big data analytics to dynamically generate logistics congestion risk coefficients and production stability coefficients. The logistics congestion risk coefficient assesses the on-time delivery capability of the supply chain in real time by accurately analyzing logistics route data and delivery timeliness rates. The production stability coefficient accurately assesses the delivery completion rate of the supply chain by considering capacity indicators and historical cooperation frequency. Compared with traditional static analysis methods, our invention can adapt to changes in the supply chain environment more flexibly, improving the real-time nature and accuracy of risk assessment.

[0020] In addition, the index generation module generates a failure learning index through comprehensive analysis of problem response data, which can comprehensively evaluate the supply chain's response efficiency and problem-solving effectiveness when problems occur. This function not only reflects the supply chain's ability to cope with unexpected problems, but also helps to identify potential areas for improvement.

[0021] Finally, the threshold judgment module establishes a comprehensive risk index system by comprehensively analyzing the logistics congestion risk coefficient, failure learning index, and production stability coefficient. This system can automatically predict the risk warning level of the supply chain based on the set risk threshold and trigger corresponding countermeasures in a timely manner. This automated risk management capability significantly enhances the flexibility and resilience of the supply chain, enabling enterprises to achieve more efficient operation and management in a rapidly changing market environment. Attached Figure Description

[0022] Figure 1 This is a schematic diagram of the overall system module flow of the present invention. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments.

[0024] It should be noted that, unless otherwise defined, the technical or scientific terms used in this invention should have the ordinary meaning understood by one of ordinary skill in the art to which this invention pertains. The terms "first," "second," and similar terms used in this invention do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly. Example 1:

[0025] Please see Figure 1 The present invention provides a technical solution:

[0026] A big data-based intelligent risk control system includes the following steps:

[0027] Data acquisition module: Based on the Enterprise Resource Planning (ERP) system and Supply Chain Management (SCM) system, it acquires the supply chain dataset of each supply chain in the past M supply and demand cooperation. The supply chain dataset includes, but is not limited to, logistics route data, on-time delivery rate, capacity indicators, historical cooperation frequency and problem response data. The module cleans and standardizes the data to generate a quantifiable analysis dataset.

[0028] Coefficient generation module: Used to analyze the generated dataset based on big data analytics to generate logistics congestion risk coefficients and production stability coefficients related to supply chain risks, including:

[0029] The logistics congestion risk coefficient consists of logistics route data and on-time delivery rate, and is used to assess the probability trend of each supply chain delivering the required supply on time under the current logistics route data.

[0030] The production stability coefficient consists of capacity indicators and historical cooperation frequency, and is used to assess the delivery completion rate of each supply chain in the current cooperation.

[0031] Index generation module: used to obtain problem response data of each supply chain in each supply and demand cooperation. The problem response data includes problem level indicators, problem response time and number of problems;

[0032] The system analyzes and processes the data related to these issues to generate a failure learning index. This index is used to assess the frequency and severity of problems in current collaborations across different supply chains, as well as their efficiency in resolving these problems.

[0033] Threshold judgment module: used to obtain and analyze the logistics congestion risk coefficient, failure learning index and production stability coefficient to establish a comprehensive risk index for each supply chain;

[0034] Set risk thresholds for each supply chain in relation to the comprehensive risk index, compare and analyze the comprehensive risk index with the corresponding risk thresholds, and predict the risk warning level of the corresponding supply chain based on the analysis results;

[0035] Based on the predicted risk warning level, corresponding response measures will be automatically triggered.

[0036] To further explain, the generation of the analysis dataset specifically includes:

[0037] 1.1) Integrate data sources: Configure API interfaces for ERP and SCM systems to seamlessly access all data related to each supply chain; this includes logistics route data, on-time delivery rate, capacity indicators, historical cooperation frequency, and problem response data;

[0038] 1.2) Real-time data collection: Set up an automated data collection module to extract the latest data from the ERP and SCM systems at fixed time intervals of 24 hours;

[0039] 1.3) Data cleaning:

[0040] Outlier Detection and Handling: Using machine learning-based anomaly detection algorithms, this embodiment employs Isolation Forest or DBSCAN to identify and remove outliers in the dataset, such as extreme delivery delays or abnormal capacity fluctuations. Based on the enterprise's pre-defined cooperation requirements, this embodiment sets standard values ​​for all data related to each supply chain, and initially sets outliers as all data related to each supply chain exceeding the corresponding standard values ​​by 35%.

[0041] Missing value imputation: Multiple imputation is used to fill in missing data caused by technical failures in order to maintain the integrity of the dataset;

[0042] 1.4) Data Standardization:

[0043] Unified unit conversion: Converting data with different units into a unified unit;

[0044] Normalization: Normalize different indicators (Min-MaxScaling) to scale the data uniformly to the range of 0 to 1 in order to eliminate the influence of differences in units on the analysis results;

[0045] 1.5) Data tagging:

[0046] Supply chain serialization: Assign a unique identifier i to each supply chain to form a sequence set {1,2,…,i,…,N}, where N is the total number of supply chains;

[0047] Serialization of cooperation counts: Each supply and demand cooperation is assigned a unique identifier j, forming a sequence set {1,2,…,j,…,M}, where M is the total number of cooperations;

[0048] 1.6) Data storage and access optimization: The processed supply chain dataset is stored in a database system to generate a quantifiable analytical dataset, which is also used as historical data. This embodiment uses a NoSQL database and is configured with indexes to accelerate data retrieval and analysis.

[0049] Data visualization preparation: Generate preliminary charts and reports using data visualization tools to provide a data overview and preliminary analysis results.

[0050] To further explain, the acquisition of the logistics congestion risk coefficient and the production stability coefficient specifically includes:

[0051] Define the logistics congestion risk coefficient of the i-th supply chain in the j-th collaboration as: The calculation formula is as follows:

[0052]

[0053] in, It is the logistics path data of the i-th supply chain in the j-th cooperation, defined as:

[0054]

[0055] It represents the actual transportation time of the i-th supply chain in the j-th cooperation; based on real-time traffic data collection.

[0056] It is the estimated transportation time for the i-th supply chain in the j-th collaboration;

[0057] It is an influencing factor used to adjust the impact of road conditions on route assessment; , The specific values ​​were determined by the expert panel based on experimental data and will not be elaborated upon further.

[0058] It is the on-time delivery rate, with a value range of [0,1]. These are the weighting coefficients for the corresponding parameters; they need to be adjusted using historical data; e is the natural index. Used to limit The valid range of values ​​for is (0,1);

[0059] This embodiment is set The initial values ​​are 0.2 and 0.8 respectively; this indicates that the on-time delivery rate has the highest priority, and even if the impact of road conditions on the route assessment increases, as long as the delivery can be completed within the specified delivery time, it is acceptable.

[0060] like The closer the value is to 0, the higher the degree of logistics congestion, which will gradually reduce the on-time delivery rate and thus the lower the probability of delivering the required supply on time.

[0061] like The closer the value is to 1, the lower the degree of logistics congestion, which will gradually improve the on-time delivery rate, and thus lead to a higher probability of delivering the required supplies on time.

[0062] Define the production stability coefficient of the i-th supply chain in the j-th cooperation as: The calculation formula is as follows:

[0063]

[0064] in, It is the capacity indicator of the i-th supply chain in the j-th cooperation, defined as:

[0065]

[0066] It represents the potential capacity of the i-th supply chain under the time period T corresponding to the j-th cooperation. It represents the capacity utilization rate, ranging from [0,1]; T is the given time period.

[0067] It is the projected output of the i-th supply chain in the j-th collaboration; It is an adjustment factor. Used to limit The valid value range is (0,1); The specific values ​​were determined by the expert panel based on experimental data and will not be elaborated upon further.

[0068] As the correction factor, define The calculation formula is:

[0069]

[0070] in Let be the historical cooperation frequency of the i-th supply chain in the past M supply and demand collaborations, and As a correction coefficient, j1 is the actual number of collaborations of the i-th supply chain in the past M supply and demand collaborations, and j1≤M;

[0071] The more times the i-th supply chain has cooperated in the past M supply and demand collaborations, the more likely it is to lead to... The larger the value, the higher the dependence of the supply chain, and the lower the corresponding production stability coefficient.

[0072] like The closer the value is to 0, the higher the production stability, which in turn leads to a higher degree of delivery completion in the current collaboration;

[0073] like The closer the value is to 1, the lower the production stability, which in turn leads to a lower delivery completion rate in the current collaboration.

[0074] To further explain, the generation of the failure learning index specifically includes:

[0075] Define the failure learning index of the i-th supply chain in the j-th collaboration as: The calculation formula is as follows:

[0076]

[0077] The problem level indicators include quality level and severity index; K is the total number of problem categories;

[0078] The quality level of the i-th supply chain regarding the k-th type of problem under the j-th cooperation is defined as:

[0079]

[0080] This is the empirical influence factor for the k-th type of problem, with a value range of [1, 10]. The quantification rules for the empirical influence factor are as follows:

[0081] Based on the expert group system, the basic effort level or corresponding value of basic resources for solving the k-th type of problem is determined;

[0082] 1: The difficulty of solving this type of problem increases by less than 1%.

[0083] 2: The difficulty of solving this type of problem increases by 1%-2%.

[0084] 3: The difficulty of solving this type of problem increases by 2%-3%.

[0085] 4: The difficulty of solving this type of problem increases by 3%-5%.

[0086] 5: The difficulty of solving this type of problem increases by 5%-7%.

[0087] 6: The difficulty of solving this type of problem increases by 7%-10%.

[0088] 7: The difficulty of solving this type of problem increases by 10%-15%.

[0089] 8: The difficulty of solving this type of problem increases by 15%-20%.

[0090] 9: The difficulty of solving this type of problem increases by 20%-30%.

[0091] 10: The difficulty of solving this type of problem increases by more than 30%.

[0092] The increased difficulty in solving this type of problem refers to the increase in the amount of effort or resources required to solve it based on the corresponding baseline value.

[0093] It involves adjusting parameters for standardization processing;

[0094] It is the severity index of the i-th supply chain regarding the k-th type of problem under the j-th cooperation, defined as:

[0095]

[0096] It represents the risk impact level of the i-th supply chain regarding the k-th type of problem under the j-th cooperation, with a value range of [1, 10]. The quantification rules are as follows:

[0097] exist When the value is any one of 1, 2, or 3, it is set as a low-risk level: the impact on business objectives is low and no additional measures are required; in this embodiment, there are 2% to 6% of defective quality issues, which do not affect the final product delivery.

[0098] When the value is 1, there are defective quality issues within the range of (2%, 3%), which do not affect the final product delivery;

[0099] When the value is 2, there are quality defects in the range of (3%, 4%), which do not affect the final product delivery.

[0100] When the value is 3, there are defective quality issues within the range of (4%, 6%), which do not affect the final product delivery;

[0101] exist When the value is any one of 4, 5, or 6, it is set as a medium risk level: it has a moderate impact on business objectives and requires control measures; in this embodiment, it is a minor defect that will cause a delay of more than 10% in the supply and demand project schedule.

[0102] When the value is 4, there is a minor defect that may cause a delay in the supply and demand project schedule between 10% and 13%.

[0103] When the value is 5, there is a minor defect that may cause delays in the supply and demand project schedules between 13% and 16%.

[0104] When the value is 6, there is a minor defect that may cause delays in the supply and demand project schedules between 16% and 19%.

[0105] exist When the value is any one of 7, 8, 9, or 10, it is set as a high-risk level: it has a significant impact on business objectives and measures must be taken immediately to control it; in this embodiment, the failure of more than 3% of the key components leads to production stoppage.

[0106] When the value is 7, the failure of key components between (3%, 5%) causes production to stop, or there are defective quality problems within the range of (6%, 10%), or there are minor defects that cause delays in the supply and demand project schedule between (19%, 25%).

[0107] When the value is 8, the failure of key components between (5%, 10%) causes production to stop, or there are defective quality problems within the range of (10%, 18%), or there are minor defects that cause delays in the supply and demand project schedule between (25%, 35%).

[0108] When the value is 9, the failure of key components between (10%, 13%) causes production to stop, or there are defective quality problems within the range of (18%, 26%), or there are minor defects that cause delays in the supply and demand project schedule between (35%, 41%).

[0109] When the value is 10, more than 13% of the failures of key components cause production to stop, or there are more than 26% of defective quality problems, or there are minor defects that cause the supply and demand project schedule to be delayed by more than 41%.

[0110] This represents the cost impact level of the i-th supply chain regarding the k-th type of problem under the j-th cooperation, with a value range of [1, 10]. The specific quantification rules for the cost impact level are as follows:

[0111] 1: Cost increase is less than 1%;

[0112] 2: Costs will increase by 1%-2%.

[0113] 3: Costs will increase by 2%-3%.

[0114] 4. Costs will increase by 3%-5%.

[0115] 5: Costs will increase by 5%-7%.

[0116] 6: Costs will increase by 7%-10%.

[0117] 7: Costs will increase by 10%-15%.

[0118] 8: Costs will increase by 15%-20%.

[0119] 9. Costs will increase by 20%-30%.

[0120] 10: Costs increased by more than 30%.

[0121] The higher the level, the larger the corresponding value;

[0122] It is the response time of the i-th supply chain regarding the k-th type of problem in the j-th cooperation;

[0123] It is a weight function, representing the weight of the k-th type of problem. The specific weight is set according to the priority of the problem, and the range is (0,1].

[0124] It represents the total number of problems in the i-th supply chain under the j-th cooperation.

[0125] It is the normalization constant. and The combination of these is used to limit The effective range of values ​​is (0,1);

[0126] when The closer it is to 0, the more frequent and higher the severity of the problem, and the lower the response efficiency.

[0127] when The closer it is to 1, the fewer the problems and the lower the problem level, and the higher the response efficiency.

[0128] To further explain, the comprehensive risk index will be compared and analyzed with the corresponding risk thresholds, and the risk warning level of the corresponding supply chain will be predicted based on the analysis results; specifically including:

[0129] Define the comprehensive risk index of the i-th supply chain under the j-th cooperation as: The calculation formula is as follows:

[0130]

[0131] in, The weights for logistics congestion risk, production stability, and failure learning index are respectively assigned to reflect the relative importance of each factor in the overall risk calculation; these weights are determined based on historical data and business priorities, and satisfy the following conditions: ; The values ​​are all within the range of (0,1);

[0132] It is the logistics congestion risk coefficient of the i-th supply chain in the j-th cooperation;

[0133] It is the production stability coefficient of the i-th supply chain in the j-th cooperation;

[0134] It is the failure learning index of the i-th supply chain in the j-th cooperation;

[0135] based on ,limited The effective range is (0,1); and based on historical data and business requirements, the risk threshold for the i-th supply chain is set as follows: ; ; The value is determined by representing the maximum acceptable risk level range for the supply chain.

[0136] and The closer the value is to 0, the worse the corresponding technical effect. The closer it is to 1, the worse the corresponding technical effect;

[0137] The following percentage values ​​are adjusted based on experimental data or expert panel evaluations;

[0138] when and At least one of the values ​​decreased, or Increase, and When there is an increasing trend, if it leads to At this time, the corresponding supply chain risk level is high;

[0139] like At this point, within this high-level range, the comprehensive risk index exceeds the set risk threshold. This indicates that the supply chain faces high risks; specifically, when The value exceeds 10%, that is, reaching In such cases, the system needs to immediately activate a high-risk warning; specifically, alerts should be sent to relevant decision-makers and operators via dashboards, emails, and SMS messages to ensure a rapid response; in this situation, a thorough assessment of potential disruptions to logistics and production is essential, including the risk factor for logistics congestion. Less than 0.2, production stability coefficient A value greater than 0.8 ensures that the response measures taken are targeted.

[0140] In high-risk, high-level zones, it is recommended to implement immediate action plans; a threshold value should be set. ,if If the value exceeds this threshold, an emergency supply chain restructuring is required, including finding alternative suppliers and optimizing inventory management; in addition, a reassessment is necessary. and The weighting of these factors is used to improve the accuracy of decision-making.

[0141] The interaction between parameters within this range needs to be closely monitored; when the logistics congestion risk coefficient... For every 10% decrease, the overall risk index increases by 5%, and Maintaining a level above 90% necessitates adjustments to the stability of the supply chain.

[0142] when and At least one of the values ​​increased, or Reduce, and When there is a decreasing trend, if it leads to At this time, the corresponding supply chain risk level is low;

[0143] like During this period, the overall risk index is below the set risk threshold. This indicates that the supply chain is in a secure state; when The value is lower than 20%, that is, reaching At that time, the supply chain was considered to be operating very stably; at this time, the risk of logistics congestion was considered to be high. The production stability coefficient needs to be maintained above 0.8. It needs to be below 0.3 to ensure maximum cost-effectiveness of the supply chain;

[0144] In the low-risk, low-level range, the existing supply chain strategy should be maintained, but regular risk reviews are necessary; a monitoring point should be established. ,like If the value is lower than this, the risk monitoring resources for A1% will be temporarily suspended and used to optimize other business processes; in this example, A1 is 30.

[0145] like At this time, the corresponding supply chain risk level is medium.

[0146] like During this period, the comprehensive risk index equals the set risk threshold. This indicates that the supply chain is at a balance between risk and security; when Exactly equal to At this time, vigilance must be maintained to avoid a sudden increase in risk; at this time, the risk factor for logistics congestion is high. It fluctuates within the range of 0.5 ± 0.1, while the production stability coefficient It fluctuates within a range of 0.5±0.1 to ensure rapid adaptation to any changes;

[0147] In the medium-risk, intermediate-level range, a dynamic monitoring system needs to be established to adjust strategies in real time; a warning threshold value needs to be set. ,like Beyond this range, the controllability and resilience of the supply chain need to be assessed immediately; ensure and Within controllable limits to avoid supply chain instability caused by unforeseen circumstances.

[0148] Supply chain controllability refers to a company's ability to effectively manage and regulate all links and processes within the supply chain. It involves comprehensive control over the flow of information, materials, and capital to ensure the supply chain operates according to plan. Controllability emphasizes the monitoring and management of daily operations, ensuring the supply chain can quickly respond to changes in market demand, handle anomalies, and achieve efficient resource allocation. A highly controllable supply chain can reduce volatility and uncertainty through accurate data, timely communication, and effective coordination.

[0149] Supply chain resilience refers to the ability of a supply chain to quickly recover and adapt to external and internal shocks or changes. A resilient supply chain can maintain continuous operation in the event of natural disasters, market fluctuations, supply disruptions, and even quickly return to normal after these events. Supply chain resilience is reflected in its flexibility, responsiveness, and recovery capabilities, achieved through a diversified supplier network, flexible inventory strategies, alternative transportation methods, and agile operational processes. This resilience enables companies to remain competitive and mitigate the impact of risks in uncertain environments.

[0150] The controllability of this embodiment includes:

[0151] Order fulfillment accuracy rate: Calculates the percentage of customer orders that are fulfilled on time and accurately;

[0152] Inventory turnover rate: measures the efficiency of inventory management, showing the number of times inventory is used or replaced within a certain period;

[0153] Supply chain cycle time: The total time from raw material procurement to product delivery. A shorter cycle time reflects a higher degree of controllability.

[0154] Supply chain resilience includes:

[0155] Recovery time: The time required to return to normal operating levels after a disruption to the supply chain.

[0156] Backup supply capacity: The proportion of backup supply available in the event of a supply chain disruption.

[0157] Risk response speed: The time from the occurrence of an external or internal event to the implementation of effective countermeasures. Example 2:

[0158] Building upon Example 1, to further verify the effectiveness of the comprehensive supply chain risk index model, a simulation experiment was constructed to evaluate the risk performance of six sample supply chains under different collaborations. The objective of the experiment was to test the comprehensive risk index of the supply chain under different conditions and observe its changes in logistics congestion risk, production stability, and failure learning index.

[0159] Six sample supply chains were prepared, named "Supply Chain A," "Supply Chain B," "Supply Chain C," "Supply Chain D," "Supply Chain E," and "Supply Chain F." Each supply chain undertook different product transportation tasks in the experiment, involving different levels of logistics, production, and management. The experiment lasted for five months, with a cooperation evaluation conducted monthly, for a total of five collaborations.

[0160] Set a logistics congestion risk factor for each supply chain Production stability coefficient and failure learning index .

[0161] Each coefficient was determined using historical data and industry standards. and The initial values ​​are used to ensure the accuracy of each parameter value.

[0162] The weights of logistics congestion risk, production stability, and failure learning index are determined, and corresponding settings are established. The values ​​are 0.4, 0.3, and 0.3.

[0163] The weighting is based on historical data analysis to ensure that logistics has the main impact on overall risk, while also taking into account the auxiliary role of production stability and failure learning.

[0164] Calculate the comprehensive risk index for each cooperation period. .

[0165] Set risk thresholds for each supply chain The values ​​are 0.7, 0.65, 0.6, 0.68, 0.63, and 0.66, respectively, to reflect the risk tolerance of different supply chains.

[0166] After each collaboration, logistics, production, and learning data are collected and analyzed, and the parameter values ​​are adjusted based on the actual results.

[0167] Each supply chain undergoes a risk level assessment, automatically triggering corresponding response measures, such as adjusting inventory levels, optimizing transportation routes, and evaluating new suppliers.

[0168] Record the parameter values ​​and calculation results of each collaboration in Excel to analyze the risk performance of each supply chain and the effectiveness of the response strategies.

[0169] Comparative analysis was conducted to verify the accuracy and practicality of the supply chain risk index model and to optimize supply chain management strategies. See Tables 1, 2, 3, 4, 5, and 6 below for details.

[0170] Table 1. Risk profile of Supply Chain A:

[0171]

[0172] Table 2 Risk profile of Supply Chain B:

[0173]

[0174] Table 3 Risk profile of Supply Chain C:

[0175]

[0176] Table 4 Risk profile of Supply Chain D:

[0177]

[0178] Table 5. Risk Performance of Supply Chain E:

[0179]

[0180] Table 6 Risk Performance of Supply Chain F:

[0181]

[0182] The experimental results demonstrate the model's risk assessment capabilities at different stages, as well as its potential optimization directions for supply chain management. This data provides substantial evidence for the formulation of supply chain optimization strategies.

[0183] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0184] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented in software, the above embodiments can be implemented, in whole or in part, as a computer program product. Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution.

[0185] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0186] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A big data-based intelligent risk control system, characterized in that, The specific steps include: Data acquisition module: used to acquire supply chain datasets from the past M supply and demand collaborations of each supply chain. The supply chain datasets include, but are not limited to, logistics route data, on-time delivery rate, capacity indicators, historical collaboration frequency and problem response data. The data is then cleaned and standardized to generate quantifiable analysis datasets. Coefficient generation module: Used to analyze the generated dataset based on big data analytics to generate logistics congestion risk coefficients and production stability coefficients related to supply chain risks, including: The logistics congestion risk coefficient consists of logistics route data and on-time delivery rate, and is used to assess the probability trend of each supply chain delivering the required supply on time under the current logistics route data. The production stability coefficient consists of capacity indicators and historical cooperation frequency, and is used to assess the delivery completion rate of each supply chain in the current cooperation. Define the logistics congestion risk coefficient of the i-th supply chain in the j-th collaboration as: ; Define the production stability coefficient of the i-th supply chain in the j-th cooperation as: ; The calculation formula is as follows: ； in, It is the logistics path data of the i-th supply chain in the j-th cooperation, defined as: ； It is the actual transportation time of the i-th supply chain in the j-th cooperation; It is the estimated transportation time for the i-th supply chain in the j-th collaboration; It is an influencing factor used to adjust the impact of road conditions on route assessment; ; It is the on-time delivery rate, with a value range of [0,1]. These are the weighting coefficients for the corresponding parameters; e is the natural exponent. Used to limit The valid range of values ​​for is (0,1), and ; like The closer the value is to 0, the higher the degree of logistics congestion, which will gradually reduce the on-time delivery rate and thus the lower the probability of delivering the required supply on time. like The closer the value is to 1, the lower the degree of logistics congestion, which will gradually improve the on-time delivery rate, and thus lead to a higher probability of delivering the required supplies on time. The calculation formula is as follows: ； in, It is the capacity indicator of the i-th supply chain in the j-th cooperation, defined as: ； It represents the potential capacity of the i-th supply chain under the time period T corresponding to the j-th cooperation. It represents the capacity utilization rate, ranging from [0,1]; T is the given time period. It is the projected output of the i-th supply chain in the j-th collaboration; It is an adjustment factor. Used to limit The valid value range is (0,1); As the correction factor, define The calculation formula is: ； in Let be the historical cooperation frequency of the i-th supply chain in the past M supply and demand collaborations, and As a correction coefficient, j1 is the actual number of collaborations of the i-th supply chain in the past M supply and demand collaborations, and j1≤M; The more times the i-th supply chain has cooperated in the past M supply and demand collaborations, the more likely it is to lead to... The larger the value, the higher the dependence of the supply chain, and the lower the corresponding production stability coefficient. like The closer the value is to 0, the higher the production stability, which in turn leads to a higher degree of delivery completion in the current collaboration; like The closer the value is to 1, the lower the production stability, which in turn leads to a lower delivery completion rate in the current collaboration. Index generation module: used to obtain problem response data of each supply chain in each supply and demand cooperation. The problem response data includes problem level indicators, problem response time and number of problems; The system analyzes and processes the data related to these issues to generate a failure learning index. This index is used to assess the frequency and severity of problems in current collaborations across different supply chains, as well as their efficiency in resolving these problems. Define the failure learning index of the i-th supply chain in the j-th collaboration as: ; The generation of the failure learning index specifically includes: The calculation formula is as follows: ； The problem level indicators include quality level and severity index; K is the total number of problem categories; The quality level of the i-th supply chain regarding the k-th type of problem under the j-th cooperation is defined as: ； It is the empirical influence factor for the k-th type of problem, with a value range of [1, 10]; the higher the level, the larger the corresponding value. It involves adjusting parameters for standardization processing; It is the severity index of the i-th supply chain regarding the k-th type of problem under the j-th cooperation, defined as: ； It represents the risk impact level of the i-th supply chain regarding the k-th type of problem under the j-th cooperation, with a value range of [1, 10]; the higher the level, the larger the corresponding value. It represents the cost impact level of the i-th supply chain regarding the k-th type of problem under the j-th cooperation, with a value range of [1, 10]; the higher the level, the larger the corresponding value. It is the response time of the i-th supply chain regarding the k-th type of problem in the j-th cooperation; It is a weight function, representing the weight of the k-th type of problem, with a range of (0,1]. It represents the total number of problems in the i-th supply chain under the j-th cooperation. It is the normalization constant. and The combination of these is used to limit The effective range of values ​​is (0,1); when The closer it is to 0, the more frequent and higher the severity of the problem, and the lower the response efficiency. when The closer it is to 1, the fewer the problems and the lower the problem level, and the higher the response efficiency. Threshold judgment module: used to obtain and analyze the logistics congestion risk coefficient, failure learning index and production stability coefficient to establish a comprehensive risk index for each supply chain; Set risk thresholds for each supply chain in relation to the comprehensive risk index, compare and analyze the comprehensive risk index with the corresponding risk thresholds, and predict the risk warning level of the corresponding supply chain based on the analysis results; Define the comprehensive risk index of the i-th supply chain under the j-th cooperation as: The calculation formula is as follows: ； in, The weights are respectively for logistics congestion risk, production stability, and failure learning index; It is the logistics congestion risk coefficient of the i-th supply chain in the j-th cooperation; It is the production stability coefficient of the i-th supply chain in the j-th cooperation; It is the failure learning index of the i-th supply chain in the j-th cooperation; based on ,limited The effective range is (0,1); and based on historical data and business requirements, the risk threshold for the i-th supply chain is set as follows: ; ; and The closer the value is to 0, the worse the corresponding technical effect. The closer it is to 1, the worse the corresponding technical effect; Based on the predicted risk warning level, corresponding response measures will be automatically triggered. when and At least one of the values ​​decreased, or Increase, and When there is an increasing trend, if it leads to At this time, the corresponding supply chain risk level is high; when The value exceeds 10%, that is, reaching In such cases, the system needs to immediately activate a high-risk warning; Set the threshold value as ,if If the value exceeds this threshold, an emergency supply chain restructuring needs to be initiated, including finding alternative suppliers and optimizing inventory management. when and At least one of the values ​​increased, or Reduce, and When there is a decreasing trend, if it leads to At this time, the corresponding supply chain risk level is low; when The value is lower than 20%, that is, reaching At that time, it was believed that the supply chain was operating stably; In the low-risk, low-level range, the existing supply chain strategy should be maintained, but regular risk reviews are necessary; a monitoring point should be established. ,like If the value is lower than this, risk monitoring resources for A1% will be temporarily suspended; like At this time, the corresponding supply chain risk level is medium. In the medium-risk, intermediate-level range, a warning line is set as follows: ,like If this range is exceeded, the controllability and resilience of the supply chain need to be assessed immediately.

2. The intelligent risk control system based on big data according to claim 1, characterized in that: The generation of the analysis dataset specifically includes: Supply chain serialization: Assign a unique identifier i to each supply chain to form a sequence set {1,2,…,i,…,N}, where N is the total number of supply chains; Serialization of cooperation counts: Each supply and demand cooperation is assigned a unique identifier j, forming a sequence set {1,2,…,j,…,M}, where M is the total number of cooperations; The processed supply chain dataset is stored in a database system to generate quantifiable analytical datasets, which are then used as historical data.

Images