Supply chain risk early warning system based on big data analysis

Abstract

The invention relates to the field of supply chain risk early warning, and discloses a supply chain risk early warning system based on big data analysis, and the system collects supplier information, production progress data and transportation track data through a data collection module, and carries out the cleaning, conversion and integration through a data preprocessing module. The risk assessment model module outputs a supply chain risk index, and the risk early warning module performs early warning according to the supply chain risk index; meanwhile, the system is provided with a risk coping strategy generation module and a visualization module; the risk assessment model adopts a specific formula to calculate risk indexes and comprehensively considers a plurality of key risk factors; according to the risk assessment model, supply chain risk indexes can be accurately quantified by deeply analyzing supplier information, production progress data and transportation track data, combining a specific calculation formula and comprehensively considering a plurality of key risk factors and complex relationships thereof, an accurate risk assessment result is provided for an enterprise, and the risk assessment efficiency is improved. And enterprises are helped to deeply understand the risk condition of the supply chain.

Description

Technical Field

[0001] The present invention relates to the field of supply chain risk early warning, and in particular to a supply chain risk early warning system based on big data analysis. Background Art

[0002] With increasingly fierce market competition and rapidly changing consumer demands, the risks facing supply chains are proliferating and becoming increasingly complex. Traditionally, supply chain risks have primarily focused on supply disruptions and demand fluctuations. However, in addition to these common risks, supply chains are now facing a variety of new risks, such as natural disasters, exchange rate fluctuations, and information security. For example, the frequent occurrence of natural disasters in recent years, such as floods and earthquakes, often causes severe damage to key nodes in the supply chain, paralyzing the entire supply chain.

[0003] To address these complex and diverse supply chain risks, companies have been seeking effective risk early warning methods. Traditional risk early warning methods rely primarily on manual experience and simple statistical analysis. For example, companies use simple statistics on historical order data to predict future demand. However, this approach has many limitations. First, manual experience is often significantly influenced by subjective factors, and different personnel may have different risk assessments, resulting in inaccurate early warning results. Second, simple statistical analysis methods cannot process massive and complex data, making it difficult to capture hidden risk factors in the supply chain.

[0004] The rapid development of big data technology has demonstrated tremendous potential in the field of supply chain risk early warning. Big data is characterized by large volumes of data, diverse data types, rapid data processing speeds, and low data value density. By collecting, organizing, and analyzing the massive amounts of data generated within the supply chain, companies can gain a more comprehensive and in-depth understanding of supply chain operations, enabling them to identify potential risk factors in a timely manner.

[0005] However, the existing supply chain risk warning still has some defects. For example, the existing supply chain warning only considers transportation and product supply, resulting in a lack of overall analysis of the entire supply chain nodes, making it impossible to guarantee the accuracy of the warning. Summary of the Invention

[0006] The purpose of the present invention is to provide a supply chain risk early warning system based on big data analysis to solve the technical problem that the existing supply chain early warning only considers transportation and product supply, resulting in a lack of overall analysis of the entire supply chain nodes and the inability to guarantee the accuracy of the early warning.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] A supply chain risk early warning system based on big data analysis, including:

[0009] A data collection module is used to collect various data related to supply chain operations from various nodes in the supply chain, including supplier information, production progress data, and transportation trajectory data;

[0010] Data preprocessing module, used to clean, convert and integrate the collected data;

[0011] The risk assessment model module receives the data preprocessed by the data preprocessing module and outputs the supply chain risk indicators through the risk assessment model;

[0012] The risk warning module, based on the output results of the risk assessment model, issues warning information in a timely manner when the supply chain risk indicators exceed the preset threshold.

[0013] As a further technical solution, the risk assessment model is expressed as:

[0014] Among them, A is the supplier risk coefficient obtained based on supplier information processing, B is the production schedule risk coefficient obtained based on production schedule data processing, and C is the transportation risk coefficient obtained based on transportation trajectory data processing. x 、B x 、C x These are the reference values of supplier risk coefficient, production schedule risk coefficient and transportation risk coefficient obtained based on historical data analysis.

[0015] As a further technical solution, the calculation formula of the supplier risk coefficient A is:

[0016] Where n is the total number of suppliers, ρ1 and ρ2 are influencing factors, which are comprehensively formulated based on experimental data and historical data. ρ1+ρ2=1, Di is the on-time delivery rate of the i-th supplier, Pi is the importance weight of the i-th supplier's supply of raw materials or parts to the overall production, Ei represents the product quality pass rate of the i-th supplier, and Si is the weight of the i-th supplier's irreplaceable degree in the supply market.

[0017] As a further technical solution, the calculation formula of the production schedule risk coefficient B is:

[0018] Where m is the total number of production batches, Lj represents the number of production delay days of the jth production batch, and θ1 is the weight of the production delay time risk factor, with a value range of [0, 1];

[0019] p is the total number of production cycles, Fk represents the ratio of equipment failures in the kth production cycle to the total number of production operations, θ2 is the weight of the equipment failure risk factor, and its value range is [0, 1], and θ1+θ2=1.

[0020] As a further technical solution, the calculation formula of the transportation risk coefficient C is:

[0021]

[0022] Where N is the total number of transport times, Oq represents the on-time arrival rate of the qth transport, Vq represents the ratio of the value of the goods in the qth transport to the total value of the goods transported, τ1 is the weight of the transport punctuality risk factor, and its value range is [0, 1]. Yq represents the cargo damage rate during the qth transport, τ2 is the weight of the cargo damage risk factor, and its value range is [0, 1], and τ1+τ2=1.

[0023] As a further technical solution, the system also includes a risk response strategy generation module. When the risk warning module issues a warning message, it can automatically generate a corresponding risk response strategy based on the risk type and level. The risk response strategy includes adjusting production plans, finding alternative suppliers, and optimizing logistics distribution routes.

[0024] As a further technical solution, the process of determining risk type and level is as follows:

[0025] Compare the supplier risk factor, production schedule risk factor, and transportation risk factor with the corresponding risk thresholds;

[0026] When the supplier risk coefficient exceeds the corresponding risk threshold, it is judged that there is a supply interruption risk; when the production schedule risk coefficient exceeds the corresponding risk threshold, it is judged that there is a production schedule delay risk; when the transportation risk coefficient exceeds the corresponding risk threshold, it is judged that there is a transportation risk;

[0027] Each risk factor is compared with the preset threshold range. If it falls within the threshold range, the risk level is moderate; if it exceeds the threshold range, the risk level is severe; if it is below the threshold range, the risk level is mild.

[0028] As a further technical solution, the system also includes a visualization module for displaying the supply chain operation data, the output results of the risk assessment model and the early warning information to the user in the form of intuitive charts, including bar charts, line charts or maps.

[0029] Beneficial effects of the present invention:

[0030] (1) The risk assessment model of the present invention can accurately quantify supply chain risk indicators through in-depth analysis of supplier information, production progress data, and transportation trajectory data, combined with specific calculation formulas, and comprehensive consideration of multiple key risk factors and their complex relationships. It can provide enterprises with accurate risk assessment results and help them gain a deeper understanding of the risk status of their supply chains;

[0031] (2) The risk warning module can issue warning information in a timely manner based on the output results of the risk assessment model when the supply chain risk indicators exceed the preset threshold, and notify relevant personnel through various means, so that enterprises can respond quickly and take measures to deal with risks in advance, avoid the expansion and spread of risks, and effectively reduce the losses caused by risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The present invention will be further described below with reference to the accompanying drawings.

[0033] Figure 1 This is a system structure diagram of the present invention. DETAILED DESCRIPTION

[0034] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0035] See also Figure 1 As shown, the present invention is a supply chain risk early warning system based on big data analysis, comprising:

[0036] A data collection module is used to collect various data related to supply chain operations from various nodes in the supply chain, including supplier information, production progress data, and transportation trajectory data;

[0037] A data preprocessing module is used to clean, convert, and integrate the collected data; the cleaning process includes removing duplicate data, correcting erroneous data, and filling missing data; the conversion process includes converting data in different formats into a unified format; and the integration process includes integrating data from different data sources;

[0038] The risk assessment model module receives the data preprocessed by the data preprocessing module and outputs the supply chain risk index through the risk assessment model. The model can comprehensively consider multiple risk factors in the supply chain and determine the weight of each risk factor by learning from historical data.

[0039] The risk warning module, based on the output of the risk assessment model, issues timely warnings when supply chain risk indicators exceed preset thresholds. This warning information includes, but is not limited to, the risk type, risk level, and potentially affected supply chain nodes. Warnings are sent to relevant personnel via various means, such as SMS, email, or system pop-up windows.

[0040] The risk assessment model is expressed as:

[0041] A is the supplier risk coefficient obtained based on supplier information processing, B is the production schedule risk coefficient obtained based on production schedule data processing, and C is the transportation risk coefficient obtained based on transportation trajectory data processing. x 、B x 、C x are reference values for the supplier risk factor, production schedule risk factor, and transportation risk factor, respectively, derived from historical data analysis. α, β, and γ are weighting coefficients. The above formula comprehensively considers multiple key risk factors across supplier, production, and transportation data, and weights each factor to reflect its complex interrelationships and varying levels of importance. Ultimately, the supply chain risk indicator, R, is calculated. A larger R value indicates a higher supply chain risk.

[0042] The calculation formula of the supplier risk coefficient A is:

[0043] n is the total number of suppliers, ρ1 and ρ2 are influencing factors, which are formulated based on experimental data and historical data. ρ1+ρ2=1. Di is the on-time delivery rate of the i-th supplier. The on-time delivery rate is calculated by the ratio of the number of orders actually delivered on time to the total number of orders, reflecting the supplier's performance in terms of timeliness of delivery. Pi is the importance weight of the raw materials or parts supplied by the i-th supplier to the overall production. It can be determined based on factors such as the proportion of the items supplied by the supplier in the product cost and the criticality to the production process. The value range is [0, 1]. It reflects the risk impact of all suppliers on the supply chain due to untimely delivery. Among them, (1-Di) represents the proportion of suppliers who fail to deliver on time. After multiplying it by the importance weight Pi and accumulating it, the sum is divided by the total number of suppliers n to obtain the average risk contribution of each supplier due to untimely delivery. Ei represents the product quality qualification rate of the i-th supplier, which is calculated by the ratio of the number of qualified products to the total number of delivered products, reflecting the quality status of the supplier's products. Si is the weight of the degree of irreplaceability of the i-th supplier in the supply market. If the items provided by the supplier are unique or there are few alternative suppliers in the market, the Si value is higher, otherwise it is lower. The value range is [0, 1]. The risk impact of product quality issues of all suppliers on the supply chain is measured. (1-Ei) represents the proportion of unqualified products, which is multiplied by the irreplaceability weight Si and then accumulated. The sum is then divided by the total number of suppliers n to obtain the average risk contribution of each supplier due to product quality issues.

[0044] The calculation formula of the production schedule risk coefficient B is:

[0045] m is the total number of production batches, Lj represents the number of days of production delay for the jth production batch, and is calculated by the difference between the actual production completion time and the planned production completion time to reflect the delay in production progress. The average number of delay days for each production batch is obtained by adding up the delay days of all production batches and dividing it by the total number of production batches m. θ1 is the weight of the production delay time risk factor, and its value range is [0, 1].

[0046] p is the total number of production cycles, and Fk represents the ratio of equipment failures to the total number of production operations in the kth production cycle. It is obtained by dividing the number of equipment failures by the total number of production operations, reflecting the impact of equipment operation stability on production progress. Accumulate the proportion of equipment failures in all production cycles and divide it by the total number of production cycles p to obtain the average proportion of the impact of equipment failures on production progress in each production cycle; θ2 is the weight of the equipment failure risk factor, with a value range of [0, 1], and θ1+θ2=1.

[0047] The calculation formula of the transportation risk coefficient C is:

[0048] N is the total number of transport times, Oq represents the on-time arrival rate of the qth transport, which is calculated by the ratio of the on-time arrival times to the total number of transport times, reflecting the punctuality of the transport process. Vq is the ratio of the value of the goods transported in the qth transport to the value of the total transported goods, which is used to measure the importance of this transport in the entire transport business. It reflects the risk impact of all transport operations on the supply chain due to late arrival. (1-Oq) represents the proportion of late arrivals. The sum is multiplied by the proportion of transported goods value Vq and then divided by the total number of transports N to obtain the average risk contribution of each transport due to late arrival. It is the weight of the transport punctuality risk factor and has a value range of [0, 1].

[0049] Yq represents the cargo damage rate during the qth transportation process, which is calculated by the ratio of the number of damaged goods to the total number of transported goods, reflecting the safety status of the goods during transportation. The cargo damage rate during all transportation processes is accumulated and divided by the total number of transportation times N to obtain the average cargo damage rate per transportation; τ2 is the weight of the cargo damage risk factor, with a value range of [0, 1], and τ1+τ2=1.

[0050] The system also includes a risk response strategy generation module. When the risk warning module issues a warning message, it can automatically generate a corresponding risk response strategy based on the risk type and level. The risk response strategy includes adjusting production plans, finding alternative suppliers, and optimizing logistics distribution routes.

[0051] The process of determining risk type and level is:

[0052] Compare the supplier risk factor, production schedule risk factor, and transportation risk factor with the corresponding risk thresholds;

[0053] When the supplier risk coefficient exceeds the corresponding risk threshold, it is judged that there is a supply interruption risk; when the production schedule risk coefficient exceeds the corresponding risk threshold, it is judged that there is a production schedule delay risk; when the transportation risk coefficient exceeds the corresponding risk threshold, it is judged that there is a transportation risk;

[0054] Each risk factor is compared with the preset threshold range. If it falls within the threshold range, the risk level is moderate; if it exceeds the threshold range, the risk level is severe; if it is below the threshold range, the risk level is mild.

[0055] For example, when the risk of supply disruption is mild, supplier supervision is strengthened; when the risk of supply disruption is moderate, small-scale purchases are made from potential local suppliers; and when the risk of supply disruption is severe, alternative suppliers are sought.

[0056] When the production progress risk coefficient is mild, production progress supervision is strengthened; when the production progress risk coefficient is moderate, production scheduling is optimized to allocate resources to other production lines; when the production progress risk coefficient is severe, production plans are adjusted to concentrate resources to complete urgent orders;

[0057] When the transportation risk coefficient is mild, the logistics distribution route will be optimized; when the transportation risk coefficient is moderate, in addition to optimizing the logistics distribution route, the transportation insurance amount will be increased, and at the same time, important goods will be given additional protective packaging based on the value and importance of the goods; if the transportation risk coefficient is severe, the logistics supplier will be changed and the transportation method will be changed.

[0058] In this example, the risk response strategy generation module can automatically generate response strategies based on the risk type and level after the risk warning module issues information. For example, in a supply disruption risk scenario, if the risk is mild, supervision will be strengthened; if the risk is moderate, procurement will be sought from local potential suppliers; if the risk is severe, alternative suppliers will be sought. This hierarchical and precise response ensures that companies can quickly take effective measures at different risk levels to prevent further deterioration of the risk, greatly improving the timeliness and pertinence of risk response. Compared with traditional manual decision-making, automatically generated strategies save decision-making time, enabling companies to respond to risks more quickly and reduce losses.

[0059] Adopting different response strategies based on risk levels can help companies allocate resources rationally, achieve cost control and optimize benefits. In the case of supply disruption risks, the cost of strengthening supervision under mild risks is relatively low, while finding alternative suppliers under severe risks, although costly, can avoid production losses caused by long-term supply disruptions, thereby reducing the company's overall operating costs. In terms of transportation risks, adjusting insurance amounts, protective measures, suppliers and transportation methods according to the degree of risk can not only ensure the safety and timely delivery of goods, but also avoid excessive investment, thus achieving a balance between cost and benefit.

[0060] The system also includes a visualization module for presenting supply chain operational data, the output results of the risk assessment model, and early warning information to users in the form of intuitive charts, including bar charts, line charts, or maps, to facilitate real-time monitoring and analysis of supply chain risk status by users.

[0061] In this embodiment, the visualization module presents complex supply chain operational data, risk assessment results, and early warning information in the form of intuitive bar charts, line graphs, or maps. Compared to traditional text or tabular data, users can capture key information more quickly. For example, by comparing the risk factors of different suppliers using a bar chart, it is clear at a glance which suppliers are more risky. By using a line chart to show the changing trend of production schedule risk factors over time, potential risk fluctuations in the production process can be quickly identified. This improves the efficiency of information acquisition, allowing enterprise decision-makers and relevant personnel to quickly grasp the overall risk status of the supply chain, providing strong support for timely decision-making.

[0062] It should be noted that the calculation formulas and various parameters involved in the calculations in the present invention have been dimensionally processed in advance, and the process of dimensionless processing is well known in the industry and will not be described here.

[0063] The above is a detailed description of an embodiment of the present invention. However, the content described is only a preferred embodiment of the present invention and should not be considered to limit the scope of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A supply chain risk early warning system based on big data analysis, characterized by: include: A data collection module is used to collect various data related to supply chain operations from various nodes in the supply chain, including supplier information, production progress data, and transportation trajectory data; Data preprocessing module, used to clean, convert and integrate the collected data; The risk assessment model module receives the data preprocessed by the data preprocessing module and outputs the supply chain risk indicators through the risk assessment model; The risk warning module, based on the output results of the risk assessment model, issues warning information in a timely manner when the supply chain risk indicators exceed the preset threshold.

2. The supply chain risk early warning system based on big data analysis according to claim 1 is characterized in that: The risk assessment model is expressed as: Among them, A is the supplier risk coefficient obtained based on supplier information processing, B is the production schedule risk coefficient obtained based on production schedule data processing, and C is the transportation risk coefficient obtained based on transportation trajectory data processing. x 、B x 、C x These are the reference values of supplier risk coefficient, production schedule risk coefficient and transportation risk coefficient obtained based on historical data analysis.

3. The supply chain risk early warning system based on big data analysis according to claim 2 is characterized in that: The calculation formula of the supplier risk coefficient A is: Where n is the total number of suppliers, ρ1 and ρ2 are influencing factors, which are comprehensively formulated based on experimental data and historical data. ρ1+ρ2=1, Di is the on-time delivery rate of the i-th supplier, Pi is the importance weight of the i-th supplier's supply of raw materials or parts to the overall production, Ei represents the product quality pass rate of the i-th supplier, and Si is the weight of the i-th supplier's irreplaceable degree in the supply market.

4. The supply chain risk early warning system based on big data analysis according to claim 3 is characterized in that: The calculation formula of the production schedule risk coefficient B is: Where m is the total number of production batches, Lj represents the number of production delay days of the jth production batch, and θ1 is the weight of the production delay time risk factor, with a value range of [0, 1]; p is the total number of production cycles, Fk represents the ratio of equipment failures in the kth production cycle to the total number of production operations, θ2 is the weight of the equipment failure risk factor, and its value range is [0, 1], and θ1+θ2=1.

5. The supply chain risk early warning system based on big data analysis according to claim 4 is characterized in that: The calculation formula of the transportation risk coefficient C is: Where N is the total number of transport times, Oq represents the on-time arrival rate of the qth transport, Vq represents the ratio of the value of the goods in the qth transport to the total value of the goods transported, τ1 is the weight of the transport punctuality risk factor, and its value range is [0, 1]. Yq represents the cargo damage rate during the qth transport, τ2 is the weight of the cargo damage risk factor, and its value range is [0, 1], and τ1+τ2=1.

6. The supply chain risk early warning system based on big data analysis according to claim 2 is characterized in that: The system also includes a risk response strategy generation module. When the risk warning module issues a warning message, it can automatically generate a corresponding risk response strategy based on the risk type and level. The risk response strategy includes adjusting production plans, finding alternative suppliers, and optimizing logistics distribution routes.

7. The supply chain risk early warning system based on big data analysis according to claim 6 is characterized in that: The process of determining risk type and level is: Compare the supplier risk factor, production schedule risk factor, and transportation risk factor with the corresponding risk thresholds; When the supplier risk coefficient exceeds the corresponding risk threshold, it is judged that there is a supply interruption risk; when the production schedule risk coefficient exceeds the corresponding risk threshold, it is judged that there is a production schedule delay risk; when the transportation risk coefficient exceeds the corresponding risk threshold, it is judged that there is a transportation risk; Compare each risk factor with the preset threshold range. If it falls within the threshold range, the risk level is moderate; If it exceeds the threshold range, the risk level is severe; if it is below the threshold range, the risk level is mild.

8. The supply chain risk early warning system based on big data analysis according to claim 1 is characterized in that: The system also includes a visualization module for displaying supply chain operation data, output results of the risk assessment model and early warning information to users in the form of intuitive charts, including bar charts, line charts or maps.

Images