Intelligent risk control system based on big data

Abstract

The invention provides an intelligent risk control system based on big data, and relates to the technical field of risk analysis, the system integrates and cleans various supply chain data through a data acquisition module to ensure the accuracy of analysis, and a coefficient generation module generates a logistics congestion risk coefficient and a production stability coefficient by using a big data analysis technology. Therefore, the on-time delivery capability and the delivery completion degree of the supply chain are dynamically evaluated, and the real-time performance and the accuracy of evaluation are improved. The index generation module generates a failure learning index by analyzing problem response data, comprehensively evaluates the ability to deal with sudden problems, and identifies an improved space; the threshold judgment module establishes a comprehensive risk index by comprehensively analyzing the generated coefficients, automatically predicts a risk early warning level according to a set risk threshold, and timely triggers countermeasures; the system enhances the flexibility and anti-risk capability of the supply chain, and enables enterprises to realize more efficient operation management in dynamic markets.

Description

Technical Field

[0001] The present invention relates to the technical field of risk analysis, and in particular to an intelligent risk control system based on big data. Background Art

[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, and the number of partners, logistics path selection, and production capacity involved are increasing, which has brought unprecedented challenges to the stability and risk management of the supply chain. In this context, many companies and scientific research institutions have invested a lot of resources in developing supply chain risk control systems based on big data. These systems evaluate and predict various potential risks in the supply chain by integrating multi-source data and using advanced data analysis techniques. However, traditional supply chain risk management systems often rely on static historical data analysis and lack the ability to respond to real-time dynamic changes in a timely manner, which makes it difficult to play an effective role in a rapidly changing market environment. In particular, in terms of logistics congestion, production stability, and problem response speed, existing technologies have failed to fully utilize the real-time analysis capabilities of big data, and thus cannot provide accurate risk warnings and response measures.

[0003] In the prior art, the publication number is CN115860485A, and the name is a supply chain risk control system and method based on big data and artificial intelligence, including: supply chain data calling module, supply chain exception analysis module, backup supply node intelligent processing module, risk warning module; the output end of the supply chain data calling module is connected to the input end of the supply chain exception analysis module; the output end of the supply chain exception analysis module is connected to the input end of the backup supply node intelligent processing module; the output end of the backup supply node intelligent processing module is connected to the input end of the risk warning module. It can analyze the rationality of the backup supply nodes set under the supply chain exception in advance, can effectively improve the monitoring and setting of the backup supply nodes, improve the supply chain's tolerance in the face of risks, and reduce losses.

[0004] Although the existing supply chain risk control technology has made significant progress, there are still some significant shortcomings. First, the traditional system's analysis of logistics routes and delivery on-time rates mostly stays at the simple regression analysis of historical data, lacking in-depth analysis of real-time logistics information, resulting in insufficient accuracy and real-time performance of the logistics congestion risk coefficient; second, the correlation between production capacity fluctuations and historical cooperation frequency has not been fully explored, and the existing technology ignores the changes in dynamic data when generating production stability coefficients, which limits the accuracy of production stability assessment. In addition, the existing risk management system often analyzes problem response data too one-sidedly, and fails to fully consider the complex relationship between problem level, response time and quantity, resulting in the generated failure learning index being difficult to truly reflect the resilience and problem-solving efficiency of the supply chain.

[0005] The above information disclosed in the above Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not form the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] The purpose of the present invention is to provide an intelligent risk control system based on big data to solve the problems raised in the above background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions: An intelligent risk control system based on big data, the specific steps include: Data acquisition module: used to acquire the supply chain data set of each supply chain in the past M supply-demand collaborations, including but not limited to logistics path data, delivery on-time rate, capacity index, historical collaboration frequency and problem response data, and clean and standardize these data to generate a quantifiable analysis data set; Coefficient generation module: used to analyze the generated analysis data set based on big data analysis technology to generate logistics congestion risk coefficients and production stability coefficients related to supply chain risks, where: The logistics congestion risk coefficient is composed of logistics route data and delivery on-time rate, and the logistics congestion risk coefficient is used to evaluate the probability trend of each supply chain delivering the required supply on time under the current logistics route data; The production stability coefficient is composed of production capacity indicators and historical cooperation frequency, and is used to evaluate the delivery completion of each supply chain in the current cooperation; Index generation module: used to obtain the problem response data of each supply chain in each supply-demand cooperation, which includes problem level index, problem response time and number of problems; The problem response data are analyzed and processed to generate a failure learning index, which is used to evaluate the frequency and level of problems in each supply chain in the current cooperation, as well as its efficiency in solving problems; 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 the risk threshold of the comprehensive risk index for each supply chain, compare and analyze the comprehensive risk index with the corresponding risk threshold, and predict the risk warning level of the corresponding supply chain based on the analysis results; Based on the predicted risk warning level, corresponding response measures are automatically triggered.

[0008] Compared with the prior art, the present invention has the following beneficial effects: through the collaborative work of multiple modules, more accurate and real-time management of supply chain risks is achieved; first, the data acquisition module can effectively integrate and clean various supply chain data, including logistics routes, on-time delivery rates, production capacity indicators, etc., to generate quantifiable analysis data sets; this process ensures the accuracy and consistency of the data, providing a solid foundation for subsequent analysis; Secondly, the coefficient generation module uses big data analysis technology to dynamically generate logistics congestion risk coefficients and production stability coefficients. The logistics congestion risk coefficient evaluates the on-time delivery capability of the supply chain in real time by accurately analyzing logistics path data and delivery on-time rate; the production stability coefficient accurately evaluates the delivery completion of the supply chain by considering production 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 and accuracy of risk assessment. In addition, the index generation module generates a failure learning index through comprehensive analysis of problem response data, which can comprehensively evaluate the response efficiency and solution effect of the supply chain when problems occur. This function not only reflects the supply chain's ability to deal with sudden problems, but also helps identify potential room for improvement. Finally, the threshold judgment module established a comprehensive risk index system by comprehensively analyzing the logistics congestion risk coefficient, failure learning index and production stability coefficient; the system can automatically predict the risk warning level of the supply chain according to the set risk threshold and trigger corresponding response measures in a timely manner; this automated risk management capability significantly enhances the flexibility and risk resistance of the supply chain, enabling enterprises to achieve more efficient operation management in a rapidly changing market environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 It is a schematic diagram of the overall system module flow of the present invention. DETAILED DESCRIPTION

[0010] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0011] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly. Embodiment 1:

[0012] See also Figure 1 , the present invention provides a technical solution: An intelligent risk control system based on big data, the specific steps include: Data acquisition module: used to acquire the supply chain data set of each supply chain in the past M supply-demand cooperation based on the enterprise resource planning system (ERP) and the supply chain management system (SCM), the supply chain data set includes but is not limited to logistics path data, delivery on-time rate, capacity index, historical cooperation frequency and problem response data, and clean and standardize these data to generate a quantifiable analysis data set; Coefficient generation module: used to analyze the generated analysis data set based on big data analysis technology to generate logistics congestion risk coefficients and production stability coefficients related to supply chain risks, where: The logistics congestion risk coefficient is composed of logistics route data and delivery on-time rate, and the logistics congestion risk coefficient is used to evaluate the probability trend of each supply chain delivering the required supply on time under the current logistics route data; The production stability coefficient is composed of production capacity indicators and historical cooperation frequency, and is used to evaluate the delivery completion of each supply chain in the current cooperation; Index generation module: used to obtain the problem response data of each supply chain in each supply-demand cooperation, which includes problem level index, problem response time and number of problems; The problem response data are analyzed and processed to generate a failure learning index, which is used to evaluate the frequency and level of problems in each supply chain in the current cooperation, as well as its efficiency in solving problems; 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 the risk threshold of the comprehensive risk index for each supply chain, compare and analyze the comprehensive risk index with the corresponding risk threshold, and predict the risk warning level of the corresponding supply chain based on the analysis results; Based on the predicted risk warning level, corresponding response measures are automatically triggered.

[0013] Further explanation: the generation of the analysis data set includes: 1.1) Integrate data sources: Configure API interfaces of ERP and SCM systems to seamlessly access all data related to each supply chain; this includes logistics routing data, on-time delivery rates, capacity indicators, historical cooperation frequency, and problem response data; 1.2) Real-time data collection: Set up an automated data collection module to extract the latest data from ERP and SCM systems at regular intervals of 24 hours; 1.3) Data cleaning: Outlier detection and processing: Using an anomaly detection algorithm based on machine learning, this embodiment uses isolation forest or DBSCAN to identify and remove outliers in the data set, such as extreme delivery delays or abnormal production capacity fluctuations; based on the company's pre-cooperation requirements, this embodiment sets standard values ​​for all data related to each supply chain, and preliminarily sets the outlier value to be 35% of all data related to each supply chain that exceeds the corresponding standard value; Missing value filling: Multiple Imputation is used to fill in missing data caused by technical failures to maintain the integrity of the data set; 1.4) Data Standardization: Unified dimension conversion: convert data in different units into unified units; Normalization: Normalize different indicators (Min-Max Scaling) and scale the data uniformly to the range of 0 to 1 to eliminate the impact of dimensional differences on the analysis results; 1.5) Data labeling: 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 times: Each supply-demand cooperation is assigned a unique identifier j to form a sequence set {1, 2, ..., j, ..., M}, where M is the total number of cooperation times; 1.6) Data storage and access optimization: The processed supply chain data set is stored in the database system to generate a quantifiable analysis data set, and the analysis data set is used as historical data. In this embodiment, a NoSQL database is used, and indexes are configured to accelerate data retrieval and analysis. Data visualization preparation: Generate preliminary charts and reports through data visualization tools to provide data overview and preliminary analysis results.

[0014] Further explanation: the acquisition of logistics congestion risk coefficient and production stability coefficient includes: Define the logistics congestion risk coefficient of the i-th supply chain in the j-th cooperation as , the calculation formula is as follows:

[0015] in, is the logistics path data of the i-th supply chain in the j-th cooperation, defined as:

[0016] is the actual transportation time of the ith supply chain in the jth collaboration; it is based on real-time traffic data collection; is the estimated transportation time of the ith supply chain in the jth collaboration; is an influencing factor used to adjust the impact of road conditions on path evaluation; , The specific value is determined by the expert group through experimental data and will not be elaborated on here; is the on-time delivery rate, with a value range of [0,1]; is the weight coefficient of the corresponding parameter; it needs to be adjusted through historical data; e is the natural index; Used to limit The valid value range of is (0,1); This embodiment sets The initial values ​​of are 0.2 and 0.8 respectively; this indicates that the priority of on-time delivery rate is the highest. Even if the impact of road conditions on path evaluation increases, as long as the delivery can be completed within the specified delivery time, it is sufficient. 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 lead to a lower probability of on-time delivery of the required supply; like The closer the value is to 1, the lower the logistics congestion, which will gradually improve the on-time delivery rate, and thus lead to a higher probability of on-time delivery of the required supply; The production stability coefficient of the i-th supply chain in the j-th cooperation is defined as , the calculation formula is as follows:

[0017] in, is the capacity indicator of the i-th supply chain in the j-th collaboration, defined as:

[0018] is the potential capacity of the i-th supply chain in the time period T corresponding to the j-th cooperation; is the capacity utilization rate, ranging from [0,1]; T is the given time period; is the expected output of the ith supply chain in the jth collaboration; is the adjustment factor, Used to limit The valid value range is (0,1); The specific value is determined by the expert group through experimental data and will not be elaborated on here; is the correction factor, defined The calculation formula is:

[0019] in is the historical cooperation frequency of the i-th supply chain in the past M supply-demand cooperations, and As a correction coefficient, j1 is the actual number of cooperations of the i-th supply chain in the past M supply-demand cooperations, and j1≤M; When the i-th supply chain has cooperated more times in the past M supply-demand cooperation, it will lead to The larger the value, the higher the dependence of the supply chain, and the lower the corresponding production stability coefficient value; like The closer the value is to 0, the higher the production stability is, which in turn leads to a higher degree of delivery completion in the current cooperation; like The closer the value is to 1, the lower the production stability is, which in turn leads to lower delivery completion in the current cooperation.

[0020] Further explanation: the generation of the failure learning index specifically includes: Define the failure learning index of the i-th supply chain in the j-th cooperation as , the calculation formula is as follows:

[0021] Among them, the problem level indicators include quality level and severity index; K is the total number of problem categories; is the quality level of the i-th supply chain under the j-th cooperation on the k-th problem, defined as:

[0022] is the empirical impact factor of the k-th type of problem, and its value range is [1,10]. The quantification rules of the empirical impact factor are as follows: Based on the expert group system, the basic effort level or basic resource corresponding value for solving the k-th problem is determined; 1: The difficulty of solving this type of problem increases by less than 1%.

[0023] 2: The difficulty of solving such problems increases by 1%-2%.

[0024] 3: The difficulty of solving this type of problem increases by between 2% and 3%.

[0025] 4: The difficulty of solving this type of problem increases by between 3% and 5%.

[0026] 5: The difficulty of solving this type of problem increases by between 5% and 7%.

[0027] 6: The difficulty of solving this type of problem increases by between 7% and 10%.

[0028] 7: The difficulty of solving this type of problem increases by between 10% and 15%.

[0029] 8: The difficulty of solving this type of problem increases by between 15% and 20%.

[0030] 9: The difficulty of solving this type of problem increases by between 20% and 30%.

[0031] 10: The difficulty of solving this type of problem increases by more than 30%.

[0032] The increased difficulty of solving such problems refers to the increase in the degree of effort or resources required to solve such problems over the corresponding base value; It is an adjustment parameter used for standardization; is the severity index of the k-th problem of the i-th supply chain under the j-th cooperation, defined as:

[0033] is the risk impact level of the i-th supply chain on the k-th problem in the j-th cooperation, and its value range is [1,10]. The quantification rules are as follows: exist When the value is any one of 1, 2, and 3, it is set to a low risk level: the impact on business objectives is low and no additional measures are required; in this embodiment, there are defective quality problems in the range of 2% to 6%, which do not affect the delivery of the final product; When the value is 1, there are quality defects within the range of (2%, 3%), which will not affect the delivery of the final product; When the value is 2, there are quality defects within the range of (3%, 4%), which will not affect the delivery of the final product; When the value is 3, there are quality defects within the range of (4%, 6%), which will not affect the delivery of the final product; exist When the value is any one of 4, 5, and 6, it is set as a medium risk level: it has a moderate impact on the business objectives and needs to take measures to control it; in this embodiment, it is a small defect that will cause the progress of the supply and demand project to be delayed by more than 10%; When the value is 4, there are small defects that will cause delays in the supply and demand project schedule (between 10% and 13%); When the value is 5, there are small defects that will cause delays in the supply and demand project schedule (13%, 16%]; When the value is 6, there are small defects that will cause delays in the supply and demand project schedules (16%, 19%]; exist When the value is any one of 7, 8, 9 and 10, it is set as a high risk level: there is a significant impact on the business objectives, and measures must be taken immediately to control it; in this embodiment, the failure of more than 3% of key components leads to production stagnation; When the value is 7, the failure of key components between (3%, 5%) leads to production stagnation, or there are quality problems with defects within the range of (6%, 10%), or there are small defects that cause delays in the progress of supply and demand projects between (19%, 25%); When the value is 8, the failure of key components between (5%, 10%) leads to production stagnation, or there are quality problems with defects within the range of (10%, 18%), or there are small defects between (25%, 35%) that cause delays in the progress of supply and demand projects; When the value is 9, the failure of key components between (10%, 13%) leads to production stagnation, or there are quality problems with defects within the range of (18%, 26%), or there are small defects that cause delays in the progress of supply and demand projects between (35%, 41%); When the value is 10, more than 13% of the key components fail, resulting in production stagnation, or more than 26% of the defects are quality problems, or there are small defects that cause more than 41% delay in the supply and demand project schedule; is the cost impact level of the i-th supply chain on the k-th problem under the j-th cooperation, and its value range is [1,10]. The specific quantitative rules of the cost impact level are as follows: 1: Cost increase is less than 1%; 2: The cost increase is between 1% and 2%.

[0034] 3: The cost increase is between 2% and 3%.

[0035] 4: The cost increase is between 3% and 5%.

[0036] 5: The cost increase is between 5% and 7%.

[0037] 6: The cost increase is between 7% and 10%.

[0038] 7: The cost increase is between 10%-15%.

[0039] 8: The cost increase is between 15%-20%.

[0040] 9: Cost increase is between 20%-30%.

[0041] 10: Costs increased by more than 30%.

[0042] The higher the level, the larger the corresponding value; is the response time of the i-th supply chain to the k-th type of problem under the j-th cooperation; is a weight function, which represents the weight of the k-th type of problem, which is set according to the priority of the problem and ranges from (0,1]; is the total number of problems of the ith supply chain under the jth collaboration; is the normalization constant, and The combination of The valid value range of is (0,1); when The closer it is to 0, the more frequent the problem is, the higher the level of the problem is, and the lower the response efficiency is; when The closer it is to 1, the fewer problems there are and the lower the problem level is, and the higher the response efficiency is.

[0043] Further explanation: the comprehensive risk index is compared and analyzed with the corresponding risk threshold, and the risk warning level of the corresponding supply chain is predicted based on the analysis results; specifically, it includes: Define the comprehensive risk index of the i-th supply chain under the j-th cooperation as , the calculation formula is as follows:

[0044] in, The weights of logistics congestion risk, production stability and failure learning index reflect the relative importance of each factor in the comprehensive risk calculation; these weights are determined based on historical data and business priorities and meet ; The value range is (0,1); is the logistics congestion risk coefficient of the i-th supply chain in the j-th cooperation; is the production stability coefficient of the i-th supply chain in the j-th collaboration; is the failure learning index of the ith supply chain in the jth collaboration; based on ,limited The valid value range of is (0,1); and based on historical data and business requirements, the risk threshold of the i-th supply chain is set to ; ; The value represents the maximum risk level range that the supply chain can accept; and The closer the value of is to 0, the worse the corresponding technical effect is. The closer it is to 1, the worse the corresponding technical effect; The following numerical percentage settings are adjusted based on experimental data or expert group evaluation; when and At least one of the values ​​is reduced, or Increase, and With an increasing trend, if it leads to When , the corresponding supply chain risk is high level; like When the comprehensive risk index exceeds the set risk threshold within this high-level range , indicating that the supply chain faces a higher risk; specifically, when The value exceeds 10% of When a high-risk situation occurs, the system needs to immediately initiate a high-risk warning; specifically, it needs to send an alert to relevant decision makers and operators through dashboards, emails, text messages, etc., so that they can respond quickly; in this case, the potential disruption of logistics and production must be carefully evaluated, and the risk factor of logistics congestion at this time Less than 0.2, production stability coefficient Greater than 0.8, ensuring that the response measures taken are targeted; In the high-risk high-level range, it is recommended to take immediate action plans; set the threshold value to ,if If the supply chain is above this critical value, urgent supply chain restructuring needs to be initiated, including finding alternative suppliers and optimizing inventory management; in addition, reassessing and weights to improve the accuracy of decision making; The interaction between the parameters in this range needs to be closely monitored; when the risk factor of logistics congestion For every 10% decrease, the comprehensive risk index increases by 5%, and When it remains above 90%, the stability of the supply chain needs to be adjusted; when and At least one value in is increased, or Reduce, and With a decreasing trend, if it leads to When , the corresponding supply chain risk is low level; like In this interval, the comprehensive risk index is lower than the set risk threshold , indicating that the supply chain is in a safe state; when The value is lower than 20% of When the supply chain is considered to be very stable, the logistics congestion risk coefficient is The production stability coefficient needs to be maintained above 0.8 It needs to be lower than 0.3 to ensure maximum cost-effectiveness of the supply chain; In the low-risk and low-level range, the existing supply chain strategy needs to be maintained, but regular risk reviews are required; a monitoring point is set as ,like If it is lower than this value, then A1% of the risk monitoring resources will be temporarily suspended and used to optimize other business processes; in this embodiment, A1 is 30; like When , the corresponding supply chain risk is medium level; like In this interval, the comprehensive risk index is equal to the set risk threshold , indicating that the supply chain is at a balance between risk and security; when Exactly equal to When the risk of logistics congestion increases, we must remain vigilant to avoid sudden increases in risk. Fluctuates within the range of 0.5±0.1, while the production stability coefficient Fluctuates within the range of 0.5±0.1 to ensure rapid adaptation to any changes; In the medium-risk range, a dynamic monitoring system needs to be established to adjust strategies in real time; the warning line value is set at ,like Beyond this, the controllability and resilience of the supply chain needs to be assessed immediately; ensuring and Within the control range to avoid supply chain instability caused by unexpected situations.

[0045] The controllability of a supply chain refers to the ability of an enterprise to effectively manage and regulate all aspects and processes of the supply chain. It involves comprehensive control over information flow, material flow, and capital flow to ensure that the supply chain can operate as planned. Controllability emphasizes the monitoring and management of daily operations to ensure that the supply chain can quickly respond to changes in market demand, handle abnormal situations, and achieve efficient resource allocation. A highly controllable supply chain can reduce volatility and uncertainty through accurate data, timely communication, and effective coordination.

[0046] Supply chain resilience refers to the ability of a supply chain to recover and adapt quickly in the face of external and internal shocks or changes. A resilient supply chain is able to continue to operate in the face 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, which are achieved through a diverse supplier network, flexible inventory strategies, alternative transportation methods, and agile operational processes. This resilience enables companies to remain competitive in an uncertain environment and reduce the impact of risks.

[0047] The controllability of this embodiment includes: Order fulfillment accuracy: Calculates the percentage of customer orders that are completed on time and accurately; Inventory turnover rate: measures the efficiency of inventory management, showing the number of times inventory is used or replaced in a certain period; Supply Chain Cycle Time: The total time from raw material procurement to product delivery. Shorter cycle times reflect higher controllability.

[0048] Supply chain resilience, including: Recovery time: The time required to return to normal operating levels after a supply chain disruption.

[0049] Backup supply capacity: The proportion of backup supply available in the event of a supply chain disruption.

[0050] Risk response speed: the time from the occurrence of an external or internal event to the implementation of effective response measures. Embodiment 2:

[0051] Based on Example 1, in order to verify the effectiveness of the supply chain comprehensive risk index model, a simulation experiment is constructed to evaluate the risk performance of six sample supply chains under different cooperation conditions. The goal of the experiment is 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.

[0052] 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 logistics, production and management levels. The experiment lasted for five months, with a monthly cooperation evaluation, for a total of five cooperations.

[0053] Set a logistics congestion risk factor for each supply chain , production stability coefficient and failure learning index .

[0054] Each coefficient is determined using historical data and industry standards and to ensure the accuracy of each parameter value.

[0055] Determine the weights of logistics congestion risk, production stability and failure learning index, and set them respectively It is 0.4, 0.3, 0.3.

[0056] The weight allocation is based on the analysis of previous data to ensure the main impact of logistics on the overall risk, and consider the auxiliary role of production stability and failure learning.

[0057] Calculate the comprehensive risk index for each cooperation period .

[0058] Set risk thresholds for each supply chain , which are 0.7, 0.65, 0.6, 0.68, 0.63 and 0.66 respectively, to reflect the risk tolerance of different supply chains.

[0059] After each collaboration, logistics, production and learning data are collected and analyzed, and parameter values ​​are adjusted based on actual results.

[0060] Each supply chain is assessed for risk level, automatically triggering appropriate response measures such as adjusting inventory levels, optimizing transportation routes and evaluating new suppliers.

[0061] 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.

[0062] Through comparative analysis, the accuracy and practicality of the supply chain risk index model are verified, and the supply chain management strategy is optimized. For details, please refer to the following Tables 1, 2, 3, 4, 5 and 6: Table 1 Risk performance of supply chain A:

[0063] Table 2 Risk performance of supply chain B:

[0064] Table 3 Risk performance of supply chain C:

[0065] Table 4 Risk performance of supply chain D:

[0066] Table 5 Risk performance of supply chain E:

[0067] Table 6 Risk performance of supply chain F:

[0068] The experimental results demonstrate the model's risk assessment capabilities at different stages and potential optimization directions for supply chain management. These data provide a substantial basis for the formulation of supply chain optimization strategies.

[0069] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0070] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0071] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0072] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. An intelligent risk control system based on big data, characterized in that: The specific steps include: Data acquisition module: used to acquire the supply chain data set of each supply chain in the past M supply-demand collaborations, including but not limited to logistics path data, delivery on-time rate, capacity index, historical collaboration frequency and problem response data, and clean and standardize these data to generate a quantifiable analysis data set; Coefficient generation module: used to analyze the generated analysis data set based on big data analysis technology to generate logistics congestion risk coefficients and production stability coefficients related to supply chain risks, where: The logistics congestion risk coefficient is composed of logistics route data and delivery on-time rate, and the logistics congestion risk coefficient is used to evaluate the probability trend of each supply chain delivering the required supply on time under the current logistics route data; The production stability coefficient is composed of production capacity indicators and historical cooperation frequency, and is used to evaluate the delivery completion of each supply chain in the current cooperation; Index generation module: used to obtain the problem response data of each supply chain in each supply-demand cooperation, which includes problem level index, problem response time and number of problems; The problem response data are analyzed and processed to generate a failure learning index, which is used to evaluate the frequency and level of problems in each supply chain in the current cooperation, as well as its efficiency in solving problems; 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 the risk threshold of the comprehensive risk index for each supply chain, compare and analyze the comprehensive risk index with the corresponding risk threshold, and predict the risk warning level of the corresponding supply chain based on the analysis results; Based on the predicted risk warning level, corresponding response measures are automatically triggered.

2. The intelligent risk control system based on big data according to claim 1 is characterized in that: Generation of analytical data sets, including: 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 times: Each supply-demand cooperation is assigned a unique identifier j to form a sequence set {1, 2, ..., j, ..., M}, where M is the total number of cooperation times; The processed supply chain data set is stored in a database system to generate a quantifiable analytical data set, and the analytical data set is used as historical data.

3. The intelligent risk control system based on big data according to claim 2 is characterized in that: The acquisition of logistics congestion risk coefficient and production stability coefficient includes: Define the logistics congestion risk coefficient of the i-th supply chain in the j-th cooperation as , the calculation formula is as follows: in, is the logistics path data of the i-th supply chain in the j-th cooperation, defined as: , is the actual transportation time of the i-th supply chain in the j-th collaboration; is the estimated transportation time of the ith supply chain in the jth collaboration; is an influencing factor used to adjust the impact of road conditions on path evaluation; ; is the on-time delivery rate, with a value range of [0,1]; is the weight coefficient of the corresponding parameter; e is the natural exponent; Used to limit The valid value range of 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 lead to a lower probability of on-time delivery of the required supply; like The closer the value is to 1, the lower the logistics congestion, which will gradually improve the on-time delivery rate, and thus lead to a higher probability of on-time delivery of the required supply; The production stability coefficient of the i-th supply chain in the j-th cooperation is defined as , the calculation formula is as follows: in, is the capacity indicator of the i-th supply chain in the j-th collaboration, defined as: , is the potential capacity of the i-th supply chain in the time period T corresponding to the j-th cooperation; is the capacity utilization rate, ranging from [0,1]; T is the given time period; is the expected output of the ith supply chain in the jth collaboration; is the adjustment factor, Used to limit The valid value range is (0,1); is the correction factor, defined The calculation formula is: in is the historical cooperation frequency of the i-th supply chain in the past M supply-demand cooperations, and As a correction coefficient, j1 is the actual number of cooperations of the i-th supply chain in the past M supply-demand cooperations, and j1≤M; When the i-th supply chain has cooperated more times in the past M supply-demand cooperation, it will lead to The larger the value, the higher the dependence of the supply chain, and the lower the corresponding production stability coefficient value; like The closer the value is to 0, the higher the production stability is, which in turn leads to a higher degree of delivery completion in the current cooperation; like The closer the value is to 1, the lower the production stability is, which in turn leads to lower delivery completion in the current cooperation.

4. The intelligent risk control system based on big data according to claim 3 is characterized in that: The generation of the failure learning index includes: Define the failure learning index of the i-th supply chain in the j-th cooperation as , the calculation formula is as follows: Among them, the problem level indicators include quality level and severity index; K is the total number of problem categories; is the quality level of the i-th supply chain under the j-th cooperation on the k-th problem, defined as: , is the empirical impact factor of the k-th type of problem, ranging from [1,10]; the larger the level, the larger the corresponding value; It is an adjustment parameter used for standardization; is the severity index of the k-th problem of the i-th supply chain under the j-th cooperation, defined as: , is the risk impact level of the i-th supply chain on the k-th problem under the j-th cooperation, and its value range is [1,10]. The larger the level, the larger the corresponding value. is the cost impact level of the i-th supply chain on the k-th problem under the j-th cooperation, and its value range is [1,10]. The larger the level, the larger the corresponding value. is the response time of the i-th supply chain to the k-th type of problem under the j-th cooperation; is the weight function, representing the weight of the k-th type of problem, ranging from (0,1]; is the total number of problems of the ith supply chain under the jth collaboration; is the normalization constant, and The combination of The valid value range of is (0,1); when The closer it is to 0, the more frequent the problem is, the higher the level of the problem is, and the lower the response efficiency is; when The closer it is to 1, the fewer problems there are and the lower the problem level is, and the higher the response efficiency is.

5. The intelligent risk control system based on big data according to claim 4 is characterized in that: Compare and analyze the comprehensive risk index with the corresponding risk threshold, and predict the risk warning level of the corresponding supply chain based on the analysis results; Specifically include: Define the comprehensive risk index of the i-th supply chain under the j-th cooperation as , the calculation formula is as follows: in, are the weights of logistics congestion risk, production stability and failure learning index respectively; is the logistics congestion risk coefficient of the i-th supply chain in the j-th cooperation; is the production stability coefficient of the i-th supply chain in the j-th collaboration; is the failure learning index of the ith supply chain in the jth collaboration; based on ,limited The valid value range of is (0,1); and based on historical data and business requirements, the risk threshold of the i-th supply chain is set to ; ; and The closer the value of is to 0, the worse the corresponding technical effect is. The closer it is to 1, the worse the corresponding technical effect.

6. The intelligent risk control system based on big data according to claim 5 is characterized in that: when and At least one of the values ​​is reduced, or Increase, and With an increasing trend, if it leads to When , the corresponding supply chain risk is high level; when The value exceeds 10% of When the system needs to immediately initiate a high-risk warning; Set the threshold to ,if Above this critical value, urgent supply chain restructuring needs to be initiated, including finding alternative suppliers and optimizing inventory management; when and At least one value in is increased, or Reduce, and With a decreasing trend, if it leads to When , the corresponding supply chain risk is low level; when The value is lower than 20% of When the supply chain is considered stable; In the low-risk and low-level range, the existing supply chain strategy needs to be maintained, but regular risk reviews are required; a monitoring point is set as ,like If it is lower than this value, the risk monitoring resources of A1% will be suspended; like When , the corresponding supply chain risk is medium level; In the medium-risk range, the warning line is set at ,like Beyond this, the controllability and resilience of the supply chain needs to be assessed immediately.

Images