Supply chain risk assessment method and device based on big data, equipment and medium

Abstract

The invention relates to the technical field of supply chain management, and discloses a supply chain risk assessment method and device based on big data, equipment and a medium, and the method comprises the steps: obtaining enterprise operation data of a supplier, and carrying out the preprocessing of the enterprise operation data; a risk assessment system is established based on a preset risk database and an expert archive library, the risk assessment system comprises a plurality of risk indexes, and each risk index corresponds to one or more risk factors; performing risk scoring on the supplier according to the preprocessed enterprise operation data and a risk assessment system; sorting the risk scores, and screening out suppliers of corresponding risk levels according to a sorting result; and generating a corresponding risk early warning report based on each high-risk supplier, and performing risk control on the high-risk suppliers. The supply chain risk management assessment accuracy can be improved.

Description

Technical Field

[0001] The present application relates to the field of supply chain management technology, and specifically, to a supply chain risk assessment method, device, equipment and medium based on big data. Background Art

[0002] In the era of big data, enterprises have a vast amount of data resources, which can be used to analyze and assess supplier risks. However, due to the complexity and uncertainty of supplier information, enterprises often face problems such as unstable supplier operations, delivery delays, quality issues, and financial risks. These risks will not only affect the product quality and production schedule of the enterprise, but may also cause damage to the enterprise's reputation and economic losses.

[0003] Therefore, the existing problems of low accuracy in supply chain risk assessment and inability to conduct effective management are issues that need to be addressed urgently. Summary of the invention

[0004] The main purpose of this application is to provide a supply chain risk assessment method based on big data, aiming to solve the technical problems of low accuracy and inability to effectively manage existing supply chain risk assessments.

[0005] Based on this, the first aspect of this application proposes a supply chain risk assessment method based on big data, including:

[0006] Acquire the enterprise operation data of the supplier and pre-process the enterprise operation data;

[0007] Establishing a risk assessment system based on a preset risk database and expert archive, wherein the risk assessment system includes a plurality of risk indicators, each of which corresponds to one or more risk factors;

[0008] According to the pre-processed enterprise operation data and risk assessment system, the supplier is given a risk score, wherein the risk score is calculated based on the risk factor corresponding to each risk indicator and the enterprise operation data of the supplier;

[0009] Sorting the risk scores, and selecting suppliers with corresponding risk levels according to the sorting results;

[0010] Generate corresponding risk warning reports for each high-risk supplier and perform risk control on high-risk suppliers.

[0011] Furthermore, the step of obtaining the supplier's enterprise operation data and preprocessing the enterprise operation data includes:

[0012] Collect supplier’s business operation data;

[0013] Cleaning and processing the enterprise operation data to obtain first data;

[0014] Performing format conversion and standardization processing on the first data to obtain pre-processed enterprise operation data;

[0015] Based on the goal of supply chain risk assessment, key features and indicators are extracted from the pre-processed enterprise operation data to obtain feature data;

[0016] The characteristic data and the pre-processed enterprise operation data are stored.

[0017] Furthermore, the risk assessment system established based on the preset risk database and expert archive includes:

[0018] Collecting historical data on the supply chain, and cleaning and formatting the historical data to obtain first risk data;

[0019] Storing the first risk data to form a risk database and updating it regularly;

[0020] Collect risk assessment data from people with preset domain expert labels in the expert archive;

[0021] Data collation and weight assessment are performed based on the risk assessment data to form the risk assessment system.

[0022] Furthermore, the step of performing risk scoring on the supplier based on the pre-processed enterprise operation data and the risk assessment system, wherein the risk score is calculated based on the risk factor corresponding to each risk indicator and the enterprise operation data of the supplier, comprises:

[0023] Constructing a risk scoring model based on the risk indicators and risk factors in the risk assessment system;

[0024] Inputting the pre-processed enterprise operation data into the risk scoring model to obtain a preliminary risk score of the supplier;

[0025] Based on the preliminary risk score, combined with the preset requirements of the supply chain risk assessment, weight adjustment or score optimization is performed to obtain the final risk score result.

[0026] Furthermore, the step of sorting the risk scores and screening out high-risk suppliers and low-risk suppliers according to the sorting results includes:

[0027] sorting the risk scores from high to low;

[0028] According to the preset risk threshold, the sorted risk scores are divided into three levels: high risk, medium risk and low risk;

[0029] Suppliers belonging to a high-risk level will be judged as high-risk suppliers, suppliers belonging to a medium-risk level will be judged as medium-risk suppliers, and suppliers belonging to a low-risk level will be judged as low-risk suppliers.

[0030] Furthermore, the step of generating a corresponding risk warning report based on each high-risk supplier and performing risk control on the high-risk supplier includes:

[0031] For each high-risk supplier, generate a detailed risk warning report based on the risk score and risk factors in the risk assessment system;

[0032] Send the risk warning report to relevant personnel or systems for risk response and processing;

[0033] Formulate risk control measures based on the content of the risk warning report and focus on and monitor high-risk suppliers;

[0034] Regular evaluation and adjustment are conducted on the risk control effects of high-risk suppliers to ensure the effectiveness of risk control.

[0035] The second aspect of the present application proposes a supply chain risk assessment device based on big data, comprising:

[0036] A preprocessing module, used to obtain the enterprise operation data of the supplier and preprocess the enterprise operation data;

[0037] A risk assessment system establishment module, used to establish a risk assessment system based on a preset risk database and expert archive, wherein the risk assessment system includes a plurality of risk indicators, each of which corresponds to one or more risk factors;

[0038] A risk scoring module, used to perform risk scoring on the supplier based on the pre-processed enterprise operation data and the risk assessment system, wherein the risk score is calculated based on the risk factor corresponding to each risk indicator and the enterprise operation data of the supplier;

[0039] A sorting and screening module, used to sort the risk scores and screen out suppliers with corresponding risk levels according to the sorting results;

[0040] The risk control module is used to generate corresponding risk warning reports based on each high-risk supplier and perform risk control on high-risk suppliers.

[0041] Furthermore, the risk assessment system establishment module includes:

[0042] A historical data cleaning unit, used for collecting historical data on the supply chain, and cleaning and formatting the historical data to obtain first risk data;

[0043] A storage and updating unit, used for storing the first risk data, forming a risk database and updating it regularly;

[0044] The expert data collection module is used to collect risk assessment data of people with preset domain expert labels from the expert archive;

[0045] The weight assessment module is used to perform data sorting and weight assessment based on the risk assessment data to form the risk assessment system.

[0046] The third aspect of the present application proposes a supply chain risk assessment device based on big data, comprising:

[0047] processor;

[0048] Memory for storing computer programs;

[0049] Wherein, when the processor executes the computer program, it implements any of the above-mentioned supply chain risk assessment methods based on big data.

[0050] The fourth aspect of the present application proposes a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the supply chain risk assessment method based on big data described in any one of the above items is implemented.

[0051] Beneficial effects:

[0052] This application can establish a multi-dimensional risk assessment system by collecting and pre-processing the supplier's business operation data, combining the expert archive and risk database, and accurately assessing supplier risks based on objective data. Through the risk assessment system and pre-processed data, suppliers can be accurately scored for risk and high-risk suppliers can be screened out. Furthermore, risk warning reports can be generated for high-risk suppliers, and risk control can be carried out in advance to reduce losses caused by supply chain risks. This method can help companies accurately assess and manage supply chain risks, improve the transparency and stability of the supply chain, and at the same time improve the company's market competitiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 This is a schematic diagram of the steps of a supply chain risk assessment method based on big data according to an embodiment of the present application;

[0054] Figure 2 It is a schematic block diagram of the structure of a supply chain risk assessment device based on big data according to an embodiment of the present application;

[0055] Figure 3 is a schematic block diagram of the structure of a computer device according to an embodiment of the present application;

[0056] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0058] It will be appreciated by those skilled in the art that, unless expressly stated, the singular forms "one", "above", and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present application refers to the presence of features, integers, steps, operations, elements, modules, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, modules, components, and / or groups thereof. It should be understood that when an element is said to be "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may also be an intermediate element. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein includes all or any module and all combinations of one or more associated listed items.

[0059] It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as those generally understood by those skilled in the art to which this application belongs. It should also be understood that terms such as those defined in general dictionaries should be understood to have meanings consistent with those in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless specifically defined as here.

[0060] Reference Figure 1 The present application embodiment provides a supply chain risk assessment method based on big data, comprising the following steps S1-S5:

[0061] S1: Obtain the enterprise operation data of the supplier and pre-process the enterprise operation data;

[0062] In step S1, the enterprise operation data of the supplier is obtained and preprocessed, which is the first step of the supply chain risk assessment method based on big data. This step is mainly aimed at collecting and processing the enterprise data of the supplier to provide an accurate data basis for subsequent risk assessment. First, the enterprise operation data of the supplier is collected. These data may include financial data (such as operating income, profit, balance sheet, etc.), sales data (such as sales, sales channels, customer analysis, etc.), procurement data (such as raw material procurement amount, supplier stability, supply cycle, etc.), production data (such as capacity utilization, production efficiency, product quality, etc.). The data can be obtained through reports, databases or batch data imports provided by suppliers. The acquired data may have problems such as missing values, duplicate values, and outliers, and needs to be preprocessed to clean and process these data. The preprocessing process includes steps such as data cleaning, data conversion, and data standardization. Data cleaning can remove incomplete or erroneous data, data conversion can unify the data format, and data standardization can adjust the data to a comparable standard form. In the preprocessing process, key features and indicators can be extracted from the preprocessed data based on the goal of supply chain risk assessment. This can be achieved through statistical methods (such as mean, standard deviation, correlation coefficient, etc.) or machine learning algorithms (such as feature selection algorithm, principal component analysis, etc.) or data mining, statistical analysis, variable selection, etc. The extracted features can reflect information on the supplier's financial status, supply chain stability, production capacity, etc. These features and indicators will become an important data basis for subsequent risk assessment. Through this embodiment, it can be ensured that the acquired enterprise operation data is accurate and complete, and through efficient, accurate and comprehensive processing of enterprise data, reliable data support is provided for subsequent risk assessment, thereby improving the accuracy and operability of the assessment.

[0063] S2: Establishing a risk assessment system based on a preset risk database and expert archive, wherein the risk assessment system includes a plurality of risk indicators, each of which corresponds to one or more risk factors;

[0064] In step S2, a multi-dimensional risk assessment system is mainly established, which includes multiple risk indicators, each of which corresponds to one or more risk factors. First, a risk database is established based on the historical data of the supply chain. These data may include information on supplier delivery delays, product quality issues, supplier operating conditions, etc. By analyzing and sorting the historical data, a risk database is established for subsequent risk assessment. In addition, it is necessary to establish an expert archive to collect evaluation data of various risks by experts in the field. The evaluation of these experts may include information such as weights, scoring criteria, and risk levels for different risk indicators and factors. The establishment of an expert archive can obtain expert opinions and organize them for archiving through expert interviews, questionnaires, etc. On this basis, specific risk indicators and corresponding risk factors are formulated. For example, supplier delivery delay can be used as a risk indicator, and factors such as supplier production capacity and logistics transportation that affect delivery delay can be used as their corresponding risk factors.

[0065] Assume that a company purchases raw materials from multiple suppliers, one of which is an important supplier A. In order to assess the risk of supplier A, the company operates according to the method of embodiment S2: First, the company organizes historical data, including information such as delayed delivery, product quality problems, and financial status of supplier A. These data are stored in the risk database for subsequent risk assessment. Then collect opinions and scores based on the risk assessment of supplier A by supply chain management experts, procurement experts, and experts in the industry, wherein the evaluations of these experts are organized and archived in the expert archive. Based on historical data and expert opinions, the company sets a series of risk indicators, such as the on-time delivery rate, product quality qualification rate, and stability of business conditions of supplier A. Each indicator corresponds to a series of risk factors, such as the reasons for delayed delivery, factors affecting product quality, and external factors affecting business conditions. Through these steps, the company can establish a multi-dimensional risk assessment system that can comprehensively assess the risk of supplier A. Using historical data and expert opinions, the company can have a more comprehensive understanding of the potential risks of supplier A and take corresponding risk management measures to ensure the stability and reliability of the supply chain.

[0066] S3: sorting the risk scores, and screening out suppliers with corresponding risk levels according to the sorting results;

[0067] In step S3, first, the enterprise operation data of the supplier is collected. These data may include the basic information, business conditions, delivery records, product quality data, etc. of the supplier; according to the risk assessment system, a corresponding weight is set for each risk indicator. The weight is determined according to the specific situation of the supply chain and the expert opinions. For example, the weight of the on-time delivery rate of the batch of products may be higher than the stability of the product quality. According to the enterprise operation data of the supplier, according to the preset risk factors, the corresponding factor score is calculated for each supplier. For example, if a supplier has a higher on-time delivery rate, its corresponding factor score is higher. The score of each risk factor is weighted according to its weight to obtain the score of each risk indicator. Finally, the score of each risk indicator is combined to obtain the overall risk score of the supplier. In this embodiment, by analyzing the enterprise operation data of the supplier, a quantitative risk score is obtained according to the risk assessment system, so that the risk assessment is more objective and quantifiable, which is convenient for comparison between suppliers. By scoring the risk of suppliers, high-risk suppliers in the supply chain can be accurately identified, which helps enterprises to discover potential risks in advance and take corresponding measures. Based on real enterprise operation data, using big data analysis technology, quantitative assessment is more accurate and reliable than traditional manual assessment methods. Data-driven risk scoring avoids the subjectivity of manual assessment, improves the fairness of assessment, and avoids unfair assessments caused by preferences among suppliers. By scoring suppliers' risks and using data analysis and risk assessment systems, accurate quantitative assessment of supplier risks is achieved, providing strong support for supply chain management decisions and improving the stability and reliability of the supply chain. Compared with existing methods, this embodiment has stronger objectivity, accuracy and risk warning capabilities.

[0068] S4: sorting the risk scores, and screening out suppliers with corresponding risk levels according to the sorting results;

[0069] In step S4, after completing the risk scoring of the supplier, the enterprise can sort the suppliers according to the scoring results. Generally, the sorting can be performed from high to low according to the specific risk score value, or the suppliers can be divided into different risk levels, all suppliers are sorted according to their risk score results, and they are assigned to the corresponding levels according to the above risk level standards. The risk level classification can include classifying suppliers into three risk levels, for example: High risk: The risk score is high and may require priority attention and management. Medium risk: The risk level is medium and requires regular monitoring. Low risk: The risk score is low and can be regarded as a relatively reliable supplier. Screening high-risk suppliers: Focus on the high-risk supplier group. The enterprise can conduct further in-depth analysis on these suppliers in order to find the reasons for the high risk and formulate corresponding risk management strategies. In addition, the risk score and risk level of the supplier can be updated regularly and dynamically adjusted according to the changes in the supplier's operating conditions. When the risk level of the supplier changes, its management strategy is adjusted accordingly. For example, if a high-risk supplier is effectively controlled through risk management measures, it can be downgraded to medium risk. By sorting and screening supplier risk scores, companies can allocate resources in a targeted manner, focus on managing high-risk suppliers, prevent supply chain risks, and ensure the security and stability of the supply chain. At the same time, it also provides positive feedback to low-risk suppliers to promote their continuous improvement. This approach helps companies better manage suppliers and improve the overall efficiency of the supply chain.

[0070] S5: Generate corresponding risk warning reports for each high-risk supplier and perform risk control on high-risk suppliers.

[0071] In step S5, first, according to the risk scoring result in embodiment S3, each high-risk supplier is determined and identified. A high-risk supplier is a supplier whose risk score is above the set threshold. For each high-risk supplier, a corresponding risk warning report is generated. The report content should include but is not limited to the basic information of the supplier, risk scoring details, risk factor analysis, existing problems and potential risks, recommended risk control measures, etc. Among them, based on the analysis of the problems and potential risks of high-risk suppliers in the risk warning report, corresponding risk control measures are formulated. These measures may include but are not limited to: strengthening regular supervision and inspection of high-risk suppliers to ensure that they fulfill their contractual obligations and quality requirements; in-depth analysis of the potential risk causes of high-risk suppliers, finding the root causes of the problems and solving them in a targeted manner; considering establishing backup suppliers or diversified supply chains to reduce dependence on high-risk suppliers; renegotiating and refining contract terms with high-risk suppliers, clarifying responsibilities and obligations, and reducing cooperation risks. After implementing risk control measures, the risk status of high-risk suppliers is regularly evaluated and monitored. According to the actual effect, the risk control strategy is adjusted and optimized in a timely manner to ensure that the control effect meets expectations. Through this embodiment, enterprises can timely identify high-risk suppliers and take effective risk control measures to reduce supply chain risks and ensure the normal operation and stability of the supply chain. At the same time, through continuous risk assessment and control, enterprises can better manage supplier relationships and improve the efficiency and competitiveness of the overall supply chain.

[0072] Through steps S1 to S5, the risk assessment system established in this application is the basis for ensuring the accuracy of risk identification and assessment. The system covers various risk factors that suppliers may face, and provides clear guidance for subsequent scoring and ranking. Through in-depth analysis and collection of supplier operation data, enterprises can have a more comprehensive understanding of the supplier's operating conditions and risk levels, and then score and rank suppliers according to the risk assessment system, which helps enterprises to formulate different management strategies according to risk levels, so that enterprises can focus on high-risk suppliers, so as to formulate risk control measures in a targeted manner. This helps enterprises to prioritize the risks that are most likely to cause losses when resources are limited, generate risk warning reports and implement risk control measures, so that enterprises can respond to supply chain risks in a timely manner and ensure the stability and reliability of the supply chain. At the same time, through regular evaluation and monitoring, enterprises can continuously optimize risk management strategies and improve the overall efficiency of the supply chain. This application helps enterprises identify and control supply chain risks, and can also improve the stability and reliability of the supply chain, providing strong guarantees for the long-term development of enterprises.

[0073] In one embodiment, the step of obtaining the enterprise operation data of the supplier and preprocessing the enterprise operation data includes:

[0074] S10. Collect supplier’s business operation data;

[0075] S11, cleaning and processing the enterprise operation data to obtain first data;

[0076] S12, performing format conversion and standardization processing on the first data to obtain pre-processed enterprise operation data;

[0077] S13. Based on the goal of supply chain risk assessment, key features and indicators are extracted from the pre-processed enterprise operation data to obtain feature data;

[0078] S14: storing the characteristic data and the pre-processed enterprise operation data.

[0079] In this embodiment, comprehensive enterprise operation data including financial statements, operating performance, delivery records, quality control records, customer feedback, etc. are collected from suppliers. These data can be directly provided by suppliers, extracted from internal enterprise systems, or obtained from third-party data sources. Data cleaning is performed on the collected enterprise operation data, including deleting duplicate information, correcting erroneous data, filling missing values, etc. For example, if the financial statement data of a supplier is incomplete, it can be completed or estimated. The units and formats in the first data are unified, and the data is converted into a comparable and compatible format. For example, the financial data of different suppliers are sorted into ledgers and reports according to the same standard to facilitate subsequent comparative analysis. According to the objectives of supply chain risk assessment, key features and indicators related to suppliers are extracted from the pre-processed enterprise operation data. These features and indicators may include: Financial health: financial indicators such as supplier's cash flow, debt ratio, profit margin, etc. Operational efficiency: operational indicators such as delivery on time rate, delivery speed, product qualification rate, etc. Customer satisfaction: feedback scores from customers, complaint rates, etc. Supply stability: number of raw material suppliers, inventory levels, logistics efficiency, etc. The characteristic data and pre-processed enterprise operation data are then stored in a secure and accessible database for subsequent risk analysis and assessment. At the same time, it is also convenient to update and maintain the latest operation data of suppliers at any time. Through the above steps, enterprises can obtain clear, standardized and comparable supplier enterprise operation data, as well as key characteristics and indicators for subsequent risk analysis and assessment, laying a data foundation for supply chain risk assessment.

[0080] In one embodiment, establishing a risk assessment system based on a preset risk database and expert archive includes:

[0081] S20, collecting historical data on the supply chain, and cleaning and formatting the historical data to obtain first risk data;

[0082] S21, storing the first risk data to form a risk database and updating it regularly;

[0083] S22, collecting risk assessment data of people with preset domain expert labels from the expert archive;

[0084] S23. Perform data sorting and weight assessment based on the risk assessment data to form the risk assessment system.

[0085] In this embodiment, historical data of each link in the supply chain is collected, including delivery delay records, quality problem reports, customer complaint information, supplier performance evaluation, etc. These historical data are cleaned and formatted to ensure data consistency and accuracy, and the first risk data is obtained. Establish and update the risk database to store the first risk data in a special risk database and update it regularly. The database should be convenient for data query, filtering and analysis. The database is regularly maintained and updated to ensure that it contains the latest and relevant risk information. At the same time, the evaluation data of supply chain risks from domain experts in the expert archive is collected. These experts should have rich experience and professional knowledge, and their opinions and evaluations have high credibility. The expert archive should contain the basic information, professional field and labels of the experts. Based on the expert risk evaluation data, data collation and in-depth analysis are carried out. Through expert opinions, risk event incidence, impact severity and other factors, the risk is weighted and evaluated to build a scientific risk assessment system. Weight evaluation can adopt weighted average, expert system or fuzzy logic and other methods. Assume that a manufacturing company faces multiple risks in supply chain management, including supplier delivery delays, raw material quality problems, logistics and transportation problems, etc. The company hopes to establish a comprehensive risk assessment system to better manage and respond to these potential risks. The manufacturing company has collected supply chain-related data over the past year, including supplier delivery records, product quality reports, customer feedback, etc. After data cleaning and formatting, these historical data are organized into a unified database form to form the first risk data. The first risk data is stored in the company's risk database and updated regularly. The database includes risk information for each link in the supply chain, such as delivery delay rate, product quality problem ratio, supplier performance evaluation and other data, which is convenient for the company to access and analyze at any time. The company also surveyed supply chain management experts in professional fields and selected experts with rich experience and knowledge from the expert archives for risk assessment. Based on expert opinions and historical data, the company conducted in-depth data collation and weight assessment. By analyzing expert opinions, the incidence and severity of historical risk events and other factors, a supply chain risk assessment system was developed. For example, the weight of delivery delay is set to 30%, the weight of product quality problems is set to 25%, and the weight of logistics and transportation problems is set to 20%. This embodiment comprehensively considers the factors of objective risk events and subjective evaluation of experts, which can improve the accuracy of risk assessment. Through continuous data collection, collation and weight assessment, enterprises can establish their own supply chain risk assessment system to facilitate subsequent risk warning and control.

[0086] In one embodiment, the step of performing risk scoring on the supplier based on the pre-processed enterprise operation data and the risk assessment system, wherein the risk score is calculated based on the risk factor corresponding to each risk indicator and the enterprise operation data of the supplier, comprises:

[0087] S31. Constructing a risk scoring model based on the risk indicators and risk factors in the risk assessment system;

[0088] S32, inputting the pre-processed enterprise operation data into the risk scoring model to obtain a preliminary risk score of the supplier;

[0089] S33. According to the preliminary risk score and in combination with the preset requirements of the supply chain risk assessment, weight adjustment or score optimization is performed to obtain a final risk score result.

[0090] In this embodiment, a risk scoring model is constructed based on the risk indicators (such as on-time delivery rate, quality control ability, financial stability, etc.) and corresponding risk factors (such as different degrees of late delivery, product defect rate, etc.) determined in the risk assessment system. For example, each risk indicator is divided into multiple levels, corresponding to different risk factors and scores. The pre-processed enterprise operation data (such as the supplier's actual delivery record, quality control data, financial statements, etc.) is input into the risk scoring model. According to the supplier's performance on each risk indicator, a preliminary risk score is calculated. For example, a supplier scored 85 points in terms of on-time delivery rate, 90 points in terms of quality control ability, and 78 points in terms of financial stability. According to the preliminary risk scoring results, combined with the requirements of supply chain risk management, weight adjustment or score optimization is performed. This step takes into account the importance differences between different risk indicators. For example, if the supply chain has higher requirements for on-time delivery rate, the weight of this indicator can be increased. After the weight adjustment, the final risk score of the supplier is recalculated. At the same time, the risk score can also be optimized according to the specific needs of supply chain risk management. For example, on the basis of the preliminary score, the stability factor of the supplier's past performance is added, or the supplier's continuous improvement ability is considered. The optimized risk score can better meet the actual needs of the enterprise.

[0091] Assume that an electronics company wants to assess the risk of its key suppliers to ensure the smooth operation of its supply chain. The company uses the following steps to score the risk of suppliers based on pre-processed operational data and risk assessment system:

[0092] First, the company identified three key risk indicators based on its risk assessment system: delivery timeliness, product quality, and financial health. A corresponding risk factor was assigned to each indicator:

[0093] Timely delivery:

[0094] Level 1: 95%-100% on-time delivery rate (score: 5 points)

[0095] Level 2: 90%-94% on-time delivery rate (score: 4 points)

[0096] Level 3: 80%-89% on-time delivery rate (score: 3 points)

[0097] Level 4: On-time delivery rate below 80% (score: 2 points)

[0098] Product Quality:

[0099] Level 1: Product defect rate less than 0.5% (score: 5 points)

[0100] Level 2: 0.5%-1% product defect rate (score: 4 points)

[0101] Level 3: 1%-2% product defect rate (score: 3 points)

[0102] Level 4: Product defect rate higher than 2% (score: 2 points)

[0103] Financial health:

[0104] Level 1: Strong financial statements, no debt default risk (score: 5 points)

[0105] Level 2: Good financial condition, small amount of debt (score: 4 points)

[0106] Level 3: Moderate financial status, moderate debt (score: 3 points)

[0107] Level 4: Poor financial situation, high debt (score: 2 points)

[0108] The company has three main suppliers: Supplier A, Supplier B, and Supplier C. The pre-processed operational data is input into the risk scoring model to obtain the following preliminary risk score:

[0109] Supplier A:

[0110] Timely delivery: Level 2 (4 points)

[0111] Product quality: Level 1 (5 points)

[0112] Financial health: Level 2 (4 points)

[0113] Preliminary total score: 13 points

[0114] Supplier B:

[0115] Timely delivery: Level 3 (3 points)

[0116] Product quality: Level 2 (4 points)

[0117] Financial health: Level 3 (3 points)

[0118] Preliminary total score: 10 points

[0119] Supplier C:

[0120] Timely delivery: Level 4 (2 points)

[0121] Product quality: Level 3 (3 points)

[0122] Financial health: Level 4 (2 points)

[0123] Preliminary total score: 9 points

[0124] Weight adjustment and score optimization: The company's supply chain manager learned that product quality is the company's biggest concern. Therefore, she decided to increase the weight of product quality and optimize the initial risk score. The new weights are: delivery timeliness: 30%, product quality: 40%, financial health: 30%.

[0125] Based on the new weights, the final risk score of the supplier is recalculated:

[0126] Supplier A: 13x 30% + 15x 40% + 12x 30% = 14.4 points

[0127] Supplier B: 10x 30% + 12x 40% + 9x 30% = 11.4 points

[0128] Supplier C: 9x 30% + 11x 40% + 8x 30% = 10.2 points

[0129] After weight adjustment and score optimization, the company obtained the final risk scores of the suppliers: Supplier A scored 14.4 points, Supplier B scored 11.4 points, and Supplier C scored 10.2 points.

[0130] In summary, this embodiment establishes a risk scoring model based on data, and obtains the final risk scoring result by comprehensively evaluating the performance of suppliers on different risk indicators, combining weight adjustment and scoring optimization. This helps to comprehensively evaluate supplier risks, warn of potential problems in advance, optimize supplier selection and management, stabilize the supply chain, and improve transparency and comparability, thereby improving supply chain efficiency, resilience and reliability.

[0131] In one embodiment, the step of sorting the risk scores and screening out high-risk suppliers and low-risk suppliers according to the sorting results includes:

[0132] S40, sorting the risk scores in descending order;

[0133] S41. According to the preset risk threshold, the sorted risk scores are divided into three levels: high risk, medium risk and low risk;

[0134] S42. Suppliers belonging to a high-risk level shall be determined as high-risk suppliers, suppliers belonging to a medium-risk level shall be determined as medium-risk suppliers, and suppliers belonging to a low-risk level shall be determined as low-risk suppliers.

[0135] In this embodiment, by sorting and screening the supplier risk scores, it is helpful for enterprises to quickly identify high-risk suppliers and take corresponding measures according to the degree of risk. Sorting the risk scores from high to low can intuitively show which suppliers are more likely to bring risks, making it convenient for enterprises to focus on them. The sorted risk scores are graded by preset risk thresholds, and suppliers are divided into high, medium and low risk levels, which can make supplier management and resource allocation more clear. Enterprises can focus their main efforts on high-risk suppliers, closely monitor their operations, and promptly identify and respond to potential risks. At the same time, they also pay attention to medium-risk suppliers to help them improve their performance and reduce risks. For low-risk suppliers, simple high-frequency monitoring or incentives can be adopted to ensure that they maintain good performance.

[0136] Take a certain automobile manufacturing company as an example. The company has dozens of suppliers that provide raw materials, parts, etc. The company's supply chain management department uses the above method to score, sort and grade the suppliers' risks.

[0137] First, based on the supplier performance data of the past year, the supply chain management department ranks suppliers with high risk scores at the top. For example, if the risk score of supplier X is 10, supplier Y is 8, and supplier Z is 5, then the ranking of suppliers X, Y, and Z is X>Y>Z.

[0138] Subsequently, the sorted suppliers are divided into three categories according to the preset risk threshold. If the risk score is higher than 8 points, it is judged as a high-risk supplier and needs to be paid special attention; if the score is between 5 and 8 points, it is a medium-risk supplier and needs general attention; if it is lower than 5 points, it is a low-risk supplier and can be simply monitored. According to the sorting and grading results, the supply chain management department can formulate corresponding supplier management strategies, such as for high-risk suppliers: in-depth communication with suppliers, analysis of their risk reasons, and formulation of detailed risk reduction plans and backup plans. For example, if the high-risk reason of a high-risk supplier is that it cannot deliver products in time, the supplier can be required to increase alternative logistics channels or provide more raw material backups. At the same time, some orders are transferred to other qualified suppliers to diversify risks. For medium-risk suppliers: help these suppliers improve their performance and enhance risk awareness. The supply chain management department can provide relevant training and support to help them improve delivery timeliness, product quality, etc. In addition, these suppliers can also be encouraged to take risk management measures, such as inventory optimization, diversified logistics, etc. For low-risk suppliers: conduct high-frequency and brief monitoring of these suppliers and give them certain incentives to maintain their good performance. For example, small batch orders can be provided as rewards, or guidance and assistance can be provided when suppliers encounter minor problems. This embodiment helps automobile manufacturers effectively identify and manage supplier risks and ensure the stable operation of the supply chain. By actively responding to high-risk suppliers and discovering potential problems early, companies can reduce production delays and cost increases caused by supplier risks. At the same time, support and incentives are provided to medium and low-risk suppliers to improve their performance and maintain a stable and sustainable cooperative relationship with suppliers.

[0139] In one embodiment, the step of generating a corresponding risk warning report based on each high-risk supplier and performing risk control on the high-risk supplier includes:

[0140] S50. For each high-risk supplier, generate a detailed risk warning report based on the risk score and risk factors in the risk assessment system;

[0141] S51, sending the risk warning report to relevant personnel or systems for risk response and processing;

[0142] S52. Formulate risk control measures based on the content of the risk warning report and focus on and monitor high-risk suppliers;

[0143] S53. Regularly evaluate and adjust the risk control effects of high-risk suppliers to ensure the effectiveness of risk control.

[0144] In this embodiment, supply chain risks are actively and effectively managed by conducting in-depth analysis of high-risk suppliers, generating risk warning reports, and taking corresponding risk control measures. First, a detailed risk warning report can be generated for each high-risk supplier based on its risk score and risk factors, such as delivery delays, product quality issues, financial risks, etc. The report should include basic information of the supplier, risk score details, risk factor analysis, historical risk events, etc., to fully display the risk status of the supplier. For example, a supplier has a high risk score due to multiple delivery delays. Its risk warning report should include the specific circumstances of delayed delivery, analysis of the reasons for the delay, and the supplier's response measures. After the risk warning report is generated, the report is sent to relevant personnel or systems, such as the supply chain management department, procurement department, financial department, etc., or a decision-making system related to supplier risk management. Sending a risk warning report allows relevant personnel to understand the situation of high-risk suppliers in a timely manner, facilitating subsequent risk response and processing. After receiving the risk warning report, the supply chain management department, etc., can formulate targeted risk control measures based on the content of the report. For example, if the supplier's risk stems from the stability of its raw material supplier, the supplier can be required to develop a new alternative source of raw materials or establish a cooperative relationship with a reliable raw material supplier. If the supply chain risk is caused by the supplier's financial risk, you can work with the financial department to jointly develop a financial risk control plan, or provide financial support in a timely manner to ensure the supplier's operational stability. In order to ensure the effectiveness of risk control measures, the system can continuously monitor and regularly evaluate the corresponding risk changes of suppliers, so that relevant departments can adjust corresponding measures. For example, hold regular meetings and communications with high-risk suppliers to understand their latest operating conditions and risk control progress. According to the supplier's risk control effect, timely adjust the risk control strategy to ensure the stable operation of the supply chain. If necessary, suppliers can be required to provide detailed risk control reports.

[0145] refer to Figure 2 , a supply chain risk assessment device based on big data, comprising:

[0146] The preprocessing module 100 is used to obtain the enterprise operation data of the supplier and preprocess the enterprise operation data;

[0147] The risk assessment system establishment module 200 is used to establish a risk assessment system based on a preset risk database and expert archive, wherein the risk assessment system includes a plurality of risk indicators, each of which corresponds to one or more risk factors;

[0148] A risk scoring module 300, configured to perform risk scoring on the supplier based on the pre-processed enterprise operation data and the risk assessment system, wherein the risk score is calculated based on the risk factor corresponding to each risk indicator and the enterprise operation data of the supplier;

[0149] A sorting and screening module 400 is used to sort the risk scores and screen out suppliers with corresponding risk levels according to the sorting results;

[0150] The risk control module 500 is used to generate a corresponding risk warning report based on each high-risk supplier and perform risk control on the high-risk suppliers.

[0151] Furthermore, the preprocessing module 100 includes:

[0152] A data collection unit, used to collect enterprise operation data of suppliers;

[0153] A data cleaning unit, configured to clean and process the enterprise operation data to obtain first data;

[0154] A format conversion unit, used for performing format conversion and standardization processing on the first data to obtain pre-processed enterprise operation data;

[0155] A feature extraction unit is used to extract key features and indicators from the pre-processed enterprise operation data based on the goal of supply chain risk assessment to obtain feature data;

[0156] The data storage unit is used to store the characteristic data and the pre-processed enterprise operation data.

[0157] Furthermore, the risk assessment system establishment module 200 includes:

[0158] A historical data cleaning unit, used for collecting historical data on the supply chain, and cleaning and formatting the historical data to obtain first risk data;

[0159] A storage and updating unit, used for storing the first risk data, forming a risk database and updating it regularly;

[0160] The expert data collection module is used to collect risk assessment data of people with preset domain expert labels from the expert archive;

[0161] The weight assessment module is used to perform data sorting and weight assessment based on the risk assessment data to form the risk assessment system.

[0162] Furthermore, the above-mentioned sorting and screening module 400 includes:

[0163] A model building unit, used to build a risk scoring model based on the risk indicators and risk factors in the risk assessment system;

[0164] A scoring input unit, used to input the pre-processed enterprise operation data into the risk scoring model to obtain a preliminary risk score of the supplier;

[0165] The weight adjustment unit is used to adjust the weight or optimize the score according to the preliminary risk score and the preset requirements of the supply chain risk assessment to obtain the final risk score result.

[0166] Furthermore, the risk control module 500 includes:

[0167] A sorting unit, used to sort the risk scores in order from high to low;

[0168] A grading unit is used to classify the sorted risk scores into three levels: high risk, medium risk and low risk according to a preset risk threshold;

[0169] The determination unit is used to determine suppliers belonging to a high risk level as high risk suppliers, suppliers belonging to a medium risk level as medium risk suppliers, and suppliers belonging to a low risk level as low risk suppliers.

[0170] Reference Figure 3 In an embodiment of the present application, a computer device is also provided. The computer device may be a server, and its internal structure may be as follows: Figure 3As shown. The computer device includes a processor, a memory, a network interface and a database connected by a bus. Among them, the processor designed by the computer is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores operations, computer programs and databases. The memory provides an environment for the operation of the operations and computer programs in the non-volatile storage medium. The database of the computer device is used to store data such as a supply chain risk assessment method based on big data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by a processor, a supply chain risk assessment method based on big data is implemented, including the following steps: obtaining the enterprise operation data of the supplier and preprocessing the enterprise operation data; establishing a risk assessment system based on a preset risk database and expert archive, wherein the risk assessment system includes multiple risk indicators, each of which corresponds to one or more risk factors; performing risk scoring on the supplier based on the preprocessed enterprise operation data and the risk assessment system, wherein the risk score is calculated based on the risk factor corresponding to each risk indicator and the enterprise operation data of the supplier; sorting the risk scores, and screening out suppliers of corresponding risk levels based on the sorting results; generating a corresponding risk warning report based on each high-risk supplier, and performing risk control on the high-risk suppliers.

[0171] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, a supply chain risk assessment method based on big data is implemented, including the following steps: obtaining the enterprise operation data of a supplier and preprocessing the enterprise operation data; establishing a risk assessment system based on a preset risk database and an expert archive, wherein the risk assessment system includes a plurality of risk indicators, each of which corresponds to one or more risk factors; performing risk scoring on the supplier based on the preprocessed enterprise operation data and the risk assessment system, wherein the risk score is calculated based on the risk factor corresponding to each risk indicator and the enterprise operation data of the supplier; sorting the risk scores, and screening out suppliers of corresponding risk levels based on the sorting results; generating a corresponding risk warning report based on each high-risk supplier, and performing risk control on the high-risk suppliers.

[0172] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided in the present application and used in the embodiments can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0173] The above description is only a preferred embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A supply chain risk assessment method based on big data, characterized in that: include: Acquire the enterprise operation data of the supplier and pre-process the enterprise operation data; Establishing a risk assessment system based on a preset risk database and expert archive, wherein the risk assessment system includes a plurality of risk indicators, each of which corresponds to one or more risk factors; According to the pre-processed enterprise operation data and risk assessment system, the supplier is given a risk score, wherein the risk score is calculated based on the risk factor corresponding to each risk indicator and the enterprise operation data of the supplier; Sorting the risk scores, and selecting suppliers with corresponding risk levels according to the sorting results; Generate corresponding risk warning reports for each high-risk supplier and perform risk control on high-risk suppliers.

2. The supply chain risk assessment method based on big data according to claim 1 is characterized in that: The step of obtaining the supplier's enterprise operation data and preprocessing the enterprise operation data includes: Collect supplier’s business operation data; Cleaning and processing the enterprise operation data to obtain first data; Performing format conversion and standardization processing on the first data to obtain pre-processed enterprise operation data; Based on the goal of supply chain risk assessment, key features and indicators are extracted from the pre-processed enterprise operation data to obtain feature data; The characteristic data and the pre-processed enterprise operation data are stored.

3. The supply chain risk assessment method based on big data according to claim 1 is characterized in that: The steps of establishing a risk assessment system based on a preset risk database and expert archive library include: Collecting historical data on the supply chain, and cleaning and formatting the historical data to obtain first risk data; Storing the first risk data to form a risk database and updating it regularly; Collect risk assessment data from people with preset domain expert labels in the expert archive; Data collation and weight assessment are performed based on the risk assessment data to form the risk assessment system.

4. The supply chain risk assessment method based on big data according to claim 1 is characterized in that: The step of performing risk scoring on the supplier based on the pre-processed enterprise operation data and the risk assessment system, wherein the risk score is calculated based on the risk factor corresponding to each risk indicator and the enterprise operation data of the supplier, comprises: Constructing a risk scoring model based on the risk indicators and risk factors in the risk assessment system; Inputting the pre-processed enterprise operation data into the risk scoring model to obtain a preliminary risk score of the supplier; Based on the preliminary risk score, combined with the preset requirements of the supply chain risk assessment, weight adjustment or score optimization is performed to obtain the final risk score result.

5. The supply chain risk assessment method based on big data according to claim 1 is characterized in that: The step of sorting the risk scores and screening out high-risk suppliers and low-risk suppliers according to the sorting results includes: sorting the risk scores from high to low; According to the preset risk threshold, the sorted risk scores are divided into three levels: high risk, medium risk and low risk; Suppliers belonging to a high-risk level will be judged as high-risk suppliers, suppliers belonging to a medium-risk level will be judged as medium-risk suppliers, and suppliers belonging to a low-risk level will be judged as low-risk suppliers.

6. The supply chain risk assessment method based on big data according to claim 1 is characterized in that: The steps of generating a corresponding risk warning report based on each high-risk supplier and performing risk control on the high-risk supplier include: For each high-risk supplier, generate a detailed risk warning report based on the risk score and risk factors in the risk assessment system; Send the risk warning report to relevant personnel or systems for risk response and processing; Formulate risk control measures based on the content of the risk warning report and focus on and monitor high-risk suppliers; Regular evaluation and adjustment are conducted on the risk control effects of high-risk suppliers to ensure the effectiveness of risk control.

7. A supply chain risk assessment device based on big data, characterized in that: include: A preprocessing module, used to obtain the enterprise operation data of the supplier and preprocess the enterprise operation data; A risk assessment system establishment module, used to establish a risk assessment system based on a preset risk database and expert archive, wherein the risk assessment system includes a plurality of risk indicators, each of which corresponds to one or more risk factors; A risk scoring module, used to perform risk scoring on the supplier based on the pre-processed enterprise operation data and the risk assessment system, wherein the risk score is calculated based on the risk factor corresponding to each risk indicator and the enterprise operation data of the supplier; A sorting and screening module, used to sort the risk scores and screen out suppliers with corresponding risk levels according to the sorting results; The risk control module is used to generate corresponding risk warning reports based on each high-risk supplier and perform risk control on high-risk suppliers.

8. The supply chain risk assessment device based on big data according to claim 7 is characterized in that: The risk assessment system establishment module includes: A historical data cleaning unit, used for collecting historical data on the supply chain, and cleaning and formatting the historical data to obtain first risk data; A storage and updating unit, used for storing the first risk data, forming a risk database and updating it regularly; The expert data collection module is used to collect risk assessment data of people with preset domain expert labels from the expert archive; The weight assessment module is used to perform data sorting and weight assessment based on the risk assessment data to form the risk assessment system.

9. A supply chain risk assessment device based on big data, characterized in that: include: processor; Memory for storing computer programs; Wherein, when the processor executes the computer program, the supply chain risk assessment method based on big data described in any one of claims 1 to 6 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the supply chain risk assessment method based on big data described in any one of claims 1 to 6 is implemented.

Images