A supply chain enterprise risk assessment method based on multi-data fusion analysis

Abstract

The present application relates to the technical field of supply chain risk assessment, and relates to a supply chain enterprise risk assessment method based on multi-data fusion analysis.The present application obtains the business operation data of each level enterprise in the supply chain network within the current statistical period, when the business operation data is valid, the business performance information and business transaction frequency between each level enterprise are called, the business transaction dependence between each level enterprise is analyzed, the historical business operation data of each level enterprise and the business operation reference data of enterprises in the same industry are combined to determine the year-on-year change parameter and the horizontal change parameter of the same industry, the transmission identifier is generated through the direction consistency judgment, the supply chain risk transmission strength is evaluated combined with the deviation amount, the risk transmission strength transmission direction is analyzed based on the time sequence change, the risk influence transmission path is determined, the business transaction dependence evaluation and risk transmission path identification between supply chain enterprises are realized, and the accuracy and forward-looking of the supply chain enterprise risk assessment are improved.

Description

Technical Field

[0001] This invention relates to the field of supply chain risk assessment technology, and specifically to a supply chain enterprise risk assessment method based on multi-data fusion analysis. Background Technology

[0002] Supply chain networks are formed by multi-level upstream and downstream enterprises linked through business transactions. The inter-enterprise business transaction dependencies serve as the carriers of risk transmission. Risks spread and propagate along the transaction chain between upstream and downstream enterprises, and the intensity and path of this transmission directly affect the operational stability and resilience of the entire supply chain network. In supply chain management practice, how to assess the business transaction dependencies between enterprises at each level based on actual business operation data, and promptly identify potential risk transmission paths within the supply chain, has become a pressing issue in the field of supply chain risk management.

[0003] The existing technology has the following technical defects: (1) The existing technology usually regards enterprises in the supply chain as isolated individuals, only focusing on the enterprise's own financial indicators or static operating data, failing to use the frequency of business transactions and performance deviations between enterprises to assess the business dependence between upstream and downstream enterprises, ignoring the transaction transmission relationship of risk in the supply chain network, resulting in the assessment results failing to reflect the actual impact of an enterprise on its upstream and downstream enterprises when an operational anomaly occurs, making the risk assessment lack globality and relevance, and affecting the accuracy of the risk transmission intensity determination.

[0004] (2) The assessment results of existing technologies are all static risk levels or scores, lacking tracking and analysis of the transmission path and evolution trend of risks in the supply chain network. Since it is impossible to identify whether the risk is transmitted from the enterprise to the upstream supplier or the downstream distributor, it is also difficult to judge the rate of change of risk intensity over time. As a result, enterprise managers can only know that there is a risk now, but cannot predict which node the risk will spread to next. This results in the lack of pertinence in the formulation of prevention and control measures, which can easily lead to resource misallocation and delay in prevention and control. It is difficult to provide forward-looking path prediction and accurate intervention node positioning for supply chain risk prevention and control. Summary of the Invention

[0005] This invention aims to overcome the shortcomings of existing technologies and provide a supply chain enterprise risk assessment method based on multi-data fusion analysis. This method enables dynamic quantitative assessment of the dependence of business transactions among supply chain enterprises and accurate identification of risk transmission paths, thereby improving the accuracy and foresight of supply chain enterprise risk assessment.

[0006] The technical solution adopted by the present invention to solve its technical problem is as follows: The present invention provides a supply chain enterprise risk assessment method based on multi-data fusion analysis, including: S1, based on the business operation data of enterprises at each level in the supply chain network in the current statistical period, determining whether the business operation data is valid through data matching.

[0007] S2. When the business operation data is valid, retrieve the business performance information and business transaction frequency between enterprises at each level, compare them with the corresponding business operation data, and analyze the business transaction dependence between enterprises at each level.

[0008] S3. Retrieve historical business operation data of enterprises at all levels and business operation reference data of enterprises in the same industry, and combine them with the business transaction dependence within the current statistical period to determine the month-on-month change parameter and the horizontal change parameter of peers in business transaction dependence.

[0009] S4. Determine the directional consistency between the month-on-month change parameter and the horizontal change parameter of the peers, generate corresponding transmission indicators, and assess the strength of supply chain risk transmission between enterprises at each level by combining the deviation amount.

[0010] S5. Conduct time-series change analysis on the intensity of supply chain risk transmission between enterprises at all levels, determine the direction of risk transmission intensity, and determine the transmission path of risk impact in the supply chain network in combination with the corresponding business transaction dependence.

[0011] Compared with the prior art, the present invention has the following beneficial effects: (1) The present invention is based on the business operation data of enterprises at all levels in the supply chain network within the current statistical period. By matching the data, it judges whether the business operation data is valid, realizes the verification of the authenticity and integrity of the business operation data, effectively eliminates false transactions and abnormal data, provides a reliable data foundation for subsequent business transaction dependence analysis and risk transmission intensity assessment, and improves the authenticity and credibility of the assessment results.

[0012] (2) This invention retrieves business performance information and business transaction frequency between enterprises at all levels, compares them with the business operation data of the corresponding enterprises, analyzes the business transaction dependence between enterprises at all levels, effectively overcomes the defect of isolated assessment of individual enterprise risk, realizes quantitative assessment of the degree of business transaction dependence between supply chain enterprises from multi-dimensional data, accurately reflects the actual business dependence relationship between enterprises at different levels, and improves the accuracy of identifying high-risk dependence relationships.

[0013] (3) Based on the historical business operation data of enterprises at all levels and the business operation reference data of enterprises in the same industry, this invention determines the month-on-month change parameter of business transaction dependence and the horizontal change parameter of peers. By judging the consistency of direction, corresponding transmission indicators are generated. Combined with the deviation, the strength of supply chain risk transmission between enterprises at all levels is evaluated. This enables a comprehensive evaluation of dependence changes from the time dimension and industry dimension, effectively distinguishes between common industry fluctuations and enterprise-specific anomalies, accurately locates the risk source and quantifies the risk transmission strength, avoids misjudgment or omission caused by industry cyclical fluctuations, and improves the accuracy and timeliness of risk warning.

[0014] (4) The application analyzes the time sequence change of the supply chain risk transmission intensity between enterprises at each level, identifies the risk transmission intensity trend characteristics, determines the risk influence transmission path of the supply chain network in combination with the corresponding business transaction dependence, realizes the automatic identification and visual presentation of the supply chain risk transmission path, improves the accuracy of the risk propagation direction prediction and intervention node positioning of the supply chain risk prevention and control, and provides forward-looking decision support for the preventive risk control of the supply chain network. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the application, the following will briefly introduce the drawings needed to be used in the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0016] Figure 1 The method step flowchart of the application is shown in the figure.

[0017] Figure 2 The business transaction dependence analysis step diagram between enterprises at each level in the application is shown in the figure.

[0018] Figure 3 The risk influence transmission path determination step diagram of the supply chain network in the application is shown in the figure. DETAILED DESCRIPTION

[0019] Various exemplary embodiments of the application will now be described in detail with reference to the accompanying drawings. Note that the relative arrangement, numerical expressions, and values of the components and steps set forth in these embodiments are not limiting to the scope of the application unless specifically stated otherwise. It should also be understood that the sizes of the various parts shown in the drawings are not drawn to scale for ease of description.

[0020] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way limiting to the scope of the application and its applications or uses. Techniques, methods, and devices known to those of ordinary skill in the relevant art can not be discussed in detail, but should be considered part of the specification, where appropriate.

[0021] In all examples shown and discussed herein, any specific values should be interpreted as merely illustrative, and not as limiting. Thus, other examples of the exemplary embodiments can have different values.

[0022] Reference should be made to Figure 1As shown, the present application provides a supply chain enterprise risk assessment method based on multi-data fusion analysis, comprising: S1, based on the business operation data of each level enterprise in the supply chain network within the current statistical period, judging whether the business operation data is effective through data matching.

[0023] S2, when the business operation data is effective, the business performance information and business transaction frequency between each level enterprise are called, and the corresponding business operation data is compared to analyze the business transaction dependence between each level enterprise.

[0024] S3, the historical business operation data of each level enterprise and the business operation reference data of enterprises in the same industry are called, and the business transaction dependence in the current statistical period is combined to determine the relative change parameter of business transaction dependence and the horizontal change parameter of enterprises in the same industry.

[0025] S4, the relative change parameter and the horizontal change parameter of enterprises in the same industry are judged for direction consistency, the corresponding conduction identifier is generated, and the deviation amount is used to evaluate the supply chain risk conduction strength between each level enterprise.

[0026] S5, the supply chain risk conduction strength between each level enterprise is analyzed for time sequence change, the risk conduction strength transmission direction is determined, and the risk influence transmission path of the supply chain network is determined combined with the corresponding business transaction dependence.

[0027] Considering that the business operation data uploaded by each level enterprise in the supply chain network is from various sources, there may be data omission, record error or even fraud. If the business operation data without validity verification is directly used for risk assessment, the calculation result of transaction dependence between enterprises deviates from the real business situation, and then misjudgment of risk conduction strength is caused. It is necessary to match the transaction flow records, bill certificate information and inventory turnover data of each level enterprise to judge whether the business operation data is effective, and ensure that the business operation data participating in the evaluation is real and reliable.

[0028] Based on this, the specific implementation content of judging the effectiveness of the business operation data in the present application comprises: S11, extracting the business operation data of each level enterprise in the current statistical period, the business operation data comprising transaction flow records, bill certificate information and inventory turnover data.

[0029] It should be noted that the business operation data is uniformly extracted through a data interface of the supply chain management platform, wherein the transaction flow record is a business transaction detail record between the enterprises at each level and the upstream and downstream enterprises in the current statistical period, including transaction enterprise identification, transaction time, transaction amount and transaction subject information; the bill voucher information is invoice information corresponding to the transaction flow record, including invoice number, invoice date, purchase and sale enterprise identification, invoice amount and invoice subject information; and the inventory turnover data is the material warehousing quantity, the material out-of-warehouse quantity and the inventory balance change amount of the enterprises at each level in the current statistical period.

[0030] S12, matching the transaction flow record of the enterprise at each level with the corresponding bill voucher information, verifying whether the transaction enterprise and the transaction amount in the transaction flow record are consistent with the bill voucher information.

[0031] Specifically, when the transaction enterprise identification, the transaction time, the transaction amount and the transaction subject in the transaction flow record are consistent with the purchase and sale enterprise identification, the invoice date, the invoice amount and the invoice subject in the bill voucher information respectively, it is determined that the transaction flow record is consistent with the bill voucher information; otherwise, it is determined that the transaction flow record is inconsistent with the bill voucher information.

[0032] S13, when the transaction flow record is consistent with the bill voucher information, the inventory turnover data of the enterprise at each level is extracted, and the quantity deviation between the in-and-out warehouse quantity in the transaction flow record and the actual inventory change amount in the inventory turnover data is obtained.

[0033] S14, if the quantity deviation is in the preset quantity deviation interval, and the transaction flow record is consistent with the bill voucher information, it is determined that the business operation data of the enterprise at each level is valid, otherwise it is determined that the business operation data of the enterprise at each level is invalid.

[0034] Preferably, in one specific embodiment of the present application, the in-and-out warehouse quantity recorded in the transaction flow record and the actual inventory change amount of the corresponding material in the current statistical period in the inventory turnover data are subjected to difference operation, so as to obtain the quantity deviation, which represents the difference degree between the in-and-out warehouse quantity and the actual inventory change amount in the transaction flow record.

[0035] The preset quantity deviation interval is set according to the material measurement error in the supply chain enterprise, for example, it is set to ±2%, which represents the allowed reasonable inventory error range. When the quantity deviation exceeds the preset quantity deviation interval, it indicates that there is a difference between the in-and-out warehouse quantity and the actual inventory change amount in the transaction flow record, and there may be data recording error or abnormal goods turnover, so it is determined that the business operation data is invalid.

[0036] This invention is based on the business operation data of enterprises at all levels within the supply chain network during the current statistical period. By matching data, it determines whether the business operation data is valid, thereby verifying the authenticity and completeness of the business operation data. It effectively eliminates false transactions and abnormal data, providing a reliable data foundation for subsequent business transaction dependency analysis and risk transmission intensity assessment, and improving the authenticity and credibility of the assessment results.

[0037] Given that current technologies typically treat companies in the supply chain as isolated entities, focusing only on their own financial indicators or static operating data, they fail to analyze the strength of business dependence between upstream and downstream companies by utilizing the frequency of business transactions and performance deviations, and neglect the transaction transmission relationship of risk in the supply chain network. Therefore, it is necessary to analyze the degree of business transaction dependence between companies at each level by comparing business performance information and transaction frequency with the corresponding companies' business operation data.

[0038] Based on this, such as Figure 2 As shown, the specific implementation of the analysis of business transaction dependence between enterprises at different levels in this invention includes: S21, based on the business performance information between enterprises at different levels, extracting the actual performance time and delivery quantity of the performance target of each enterprise in the current statistical period, and determining the performance time deviation and the completion degree of the performance target between enterprises at different levels.

[0039] S22. Based on the business operation data of enterprises at each level, determine the comprehensive frequency of business transactions of enterprises at each level in the current statistical period, and compare it with the frequency of business transactions between enterprises at each level to obtain the matching degree of transaction frequency between enterprises at each level.

[0040] In this invention, for example, the transaction frequency matching degree between the i-th level enterprise and the j-th level enterprise is obtained by: performing a ratio calculation between the business transaction frequency between the i-th level enterprise and the j-th level enterprise and the comprehensive business transaction frequency of the i-th level enterprise to obtain the transaction frequency matching degree of the i-th level enterprise to the j-th level enterprise. The transaction frequency matching degree characterizes the degree of dependence of the i-th level enterprise's business transactions on the j-th level enterprise.

[0041] S23. Integrate the performance time deviation, the completion rate of the performance target, and the matching degree of transaction frequency to calculate the business transaction dependence between enterprises at each level.

[0042] Preferably, in a specific embodiment of the present invention, the method for determining the performance time deviation and the completion degree of the performance target between enterprises at each level is as follows: S211, based on the transaction flow records between enterprises at each level, extract the actual performance time and the planned performance time of each business transaction record between enterprises at each level, calculate the difference between the actual performance time and the planned performance time, and obtain the performance time deviation value of each business transaction.

[0043] It should be noted that the actual performance time refers to the actual time when the target or service is delivered between enterprises at each level, while the planned performance time refers to the delivery time agreed upon in the contract between the two parties. A positive deviation value indicates early delivery, while a negative value indicates a delay. For example, if the planned performance time is September 1st and the actual performance time is September 5th, the deviation value is -4 days, indicating a 4-day delay in performance; conversely, if the actual performance time is August 30th, the deviation value is +2 days, indicating 2 days of early performance.

[0044] S212. Extract the quantity of the contracted goods delivered and the planned quantity of the contracted goods delivered from each business transaction record between enterprises at each level. Calculate the ratio of the quantity of the contracted goods delivered to the planned quantity of the contracted goods delivered to obtain the completion rate of the contracted goods for each business transaction.

[0045] S213. Adjust the performance time deviation and performance target completion rate of each business transaction according to the corresponding transaction amount to determine the performance time deviation and performance target completion rate between enterprises at each level.

[0046] It should be noted that the method for adjusting the performance time deviation value of each business transaction according to the corresponding transaction amount is as follows: A weighted average is calculated by taking the performance time deviation value of each business transaction and the transaction amount of each business transaction. The larger the transaction amount, the greater the weight of the performance time deviation value in the performance time deviation degree. The calculation formula is as follows: ;in For the deviation in delivery time, For the first The time deviation of the next business transaction. For the first The transaction amount of this business transaction , This represents the total number of business transactions within the current statistical period.

[0047] Similarly, the method for adjusting the completion rate of each business transaction according to the corresponding transaction amount is as follows: ;in To assess the degree of completion of the contract, For the first The completion rate of the contractual obligations for each business transaction.

[0048] Preferably, in a specific embodiment of the present invention, the method for calculating the business transaction dependency between enterprises at each level is as follows: S231, configuring the corresponding influence weight coefficients of the performance time deviation, the completion degree of the performance target, and the matching degree of transaction frequency between enterprises at each level in the supply chain network.

[0049] The influence weighting coefficients are determined based on the business transaction characteristics between upstream and downstream enterprises in the supply chain network. For example, in this invention, for an upstream supply chain mainly engaged in component supply, the completion rate of the fulfillment target affects production continuity, and its weighting coefficient is set to 0.45; the transaction frequency matching coefficient is set to 0.35; and the fulfillment time deviation coefficient is set to 0.20. For a downstream supply chain mainly engaged in bulk commodity trading, the transaction frequency matching reflects the stability of market supply and demand, and its weighting coefficient is set to 0.50; the completion rate of the fulfillment target is set to 0.30; and the fulfillment time deviation coefficient is set to 0.20. Implementers can adjust the influence weighting coefficients according to the specific business characteristics of the supply chain network. For example, for a fast-moving consumer goods supply chain with high timeliness requirements, the weighting coefficient for fulfillment time deviation can be increased.

[0050] S232. The normalized performance time deviation, performance target completion rate, and transaction frequency matching rate are weighted by the corresponding influence weight coefficients to obtain the initial business transaction dependency.

[0051] It should be noted that the normalization process uses the min-max standardization method to map the performance time deviation, performance target completion rate, and transaction frequency matching rate to the [0,1] numerical range, so as to eliminate the dimensional differences between different indicators.

[0052] The normalized performance time deviation, performance target completion, and transaction frequency matching degree are multiplied by their corresponding influence weight coefficients to obtain the coupling components corresponding to the performance time deviation, performance target completion, and transaction frequency matching degree. The initial business transaction dependency degree is obtained by summing these components.

[0053] S233. Based on the hierarchical position of each level of enterprise in the supply chain network, obtain the hierarchical decay factor between each level position, and multiply the initial business transaction dependence between each level of enterprise with the hierarchical decay factor of the corresponding level position to obtain the business transaction dependence between each level of enterprise.

[0054] It should be noted that the hierarchical attenuation factor characterizes the characteristic that risk in the supply chain network decreases as the hierarchical distance increases. Specifically, the greater the hierarchical distance between upstream and downstream enterprises in the supply chain network, the greater the degree of attenuation of business transaction dependence.

[0055] The hierarchical distance is divided according to the supply chain trade transmission level: the core enterprise is the level 0, the upstream suppliers or downstream customers who have direct transactions with the core enterprise are the level 1, the enterprises that have direct transactions with the level 1 enterprises but not with the core enterprise are the level 2, and so on; the hierarchical distance between two enterprises is the absolute value of the difference between their levels.

[0056] In a supply chain network, the business transaction dependence between directly upstream and downstream enterprises is the highest. As the supply chain extends, the business transaction dependence between indirectly related enterprises gradually decreases. The hierarchical attenuation factor is preset according to the hierarchical structure of the supply chain network. For example, when the hierarchical distance is 1, the hierarchical attenuation factor is set to 1.0; when the hierarchical distance is 2, it is set to 0.8; when the hierarchical distance is 3, it is set to 0.6, and so on. For every increase of 1 in the hierarchical distance, the attenuation factor decreases by 0.2. Implementers can also adjust it according to the actual supply chain network structure.

[0057] This invention analyzes the business transaction dependence between enterprises at different levels by retrieving business performance information and transaction frequency between enterprises at each level and comparing them with the corresponding enterprises' business operation data. This effectively overcomes the shortcomings of assessing individual enterprise risks in isolation and achieves a quantitative assessment of the degree of business transaction dependence between supply chain enterprises from multiple dimensions of data. It accurately reflects the actual business dependence relationship between enterprises at different levels and improves the accuracy of identifying high-risk dependence relationships.

[0058] Assessing the intensity of supply chain risk transmission requires not only considering changes in business transaction dependence within the current statistical period but also combining historical data over time and cross-industry comparative data to distinguish between common industry fluctuations and unique company-specific anomalies. Relying solely on dependence changes in a single dimension cannot effectively differentiate between cyclical industry fluctuations and changes in dependence caused by company-specific operational anomalies, easily leading to misjudgments or omissions. Therefore, it is necessary to determine month-on-month and cross-industry variation parameters by retrieving historical business operation data and reference data from peer companies to improve the accuracy and timeliness of risk warnings.

[0059] Based on this, the specific implementation of determining the month-on-month change parameter and the peer-to-peer change parameter of business transaction dependence in this invention includes: S31, determining the historical business transaction dependence between enterprises at each level in the previous statistical period based on the historical business operation data of each level of enterprises in the previous statistical period.

[0060] The time window length of the previous statistical period and the current statistical period is the same, for example, both are monthly or quarterly. The calculation method for historical business transaction dependence is the same as the calculation method for business transaction dependence in the current statistical period in step S2.

[0061] S32. Calculate the difference between the business transaction dependence of enterprises at each level within the current statistical period and the historical business transaction dependence within the previous statistical period to obtain the month-on-month change parameter of business transaction dependence. The positive or negative sign of the month-on-month change parameter indicates the direction of change in business transaction dependence; a positive value indicates a month-on-month increase in business transaction dependence, and a negative value indicates a month-on-month decrease in business transaction dependence.

[0062] S33. Retrieve reference data on the business operations of companies in the same industry within the current statistical period to determine the reference distribution range of business transaction dependence among companies in the same industry.

[0063] It should be noted that the "competing companies" refers to the set of companies in other supply chain networks that are under the same industry classification code as the target supply chain company. The reference distribution interval for business transaction dependence is determined by: statistically analyzing the business transaction dependence data between all upstream and downstream related companies in the same industry, calculating the confidence interval of its statistical distribution, for example, taking the interval between the 25th quantile and the 75th quantile as the reference distribution interval, representing the normal fluctuation range of business transaction dependence among companies in the same industry.

[0064] S34. Compare the business transaction dependence within the current statistical period with the corresponding reference distribution interval to determine the relative position of the business transaction dependence within the corresponding reference distribution interval and generate peer horizontal variation parameters.

[0065] The horizontal variation parameter of peers represents the positional relationship between the business transaction dependence of enterprises at each level and the reference distribution range of enterprises in the same industry. Specifically, when the business transaction dependence is greater than the upper boundary of the reference distribution range, an upward deviation horizontal variation parameter of peers is generated; when the business transaction dependence is less than the lower boundary of the reference distribution range, a downward deviation horizontal variation parameter of peers is generated; and when the business transaction dependence is within the reference distribution range, an undevised horizontal variation parameter of peers is generated.

[0066] Considering that the month-on-month change parameter reflects the time evolution trend of an individual company's dependence, while the peer-to-peer change parameter reflects the company's relative position in the industry, when the two parameters are in the same direction, it indicates that the company's dependence change is synchronized with industry trends; when they are in different directions, it indicates that the company's dependence change is mainly driven by common industry fluctuations or short-term disturbances. It is necessary to judge the strength of supply chain risk transmission by assessing the consistency of the month-on-month change parameter and the peer-to-peer change parameter, and combining this with the deviation.

[0067] Based on this, the specific implementation of the present invention for assessing the intensity of supply chain risk transmission between enterprises at different levels includes: S41, determining the consistency of the month-on-month change parameter with the horizontal change parameter of the peers, and generating a first transmission indicator when the month-on-month change parameter is positive and the horizontal change parameter of the peers is outside the upper boundary of the corresponding reference distribution interval.

[0068] S42. When the month-on-month change parameter is negative and the horizontal change parameter of the same line is outside the lower boundary of the corresponding reference distribution interval, a second transmission indicator is generated; when the month-on-month change parameter and the horizontal change parameter of the same line are not in the same direction, a third transmission indicator is generated.

[0069] S43. Determine the intensity of supply chain risk transmission based on the generated transmission identifiers and their corresponding deviations.

[0070] Among them, the first transmission indicator represents a month-on-month increase in business transaction dependence, which has exceeded the upper limit of the normal industry level. This indicates that the increase in dependence is mainly driven by enterprise factors rather than common industry fluctuations, which will lead to increased business transaction dependence and exacerbate the intensity of risk transmission.

[0071] The second transmission indicator represents a month-on-month decrease in business transaction dependence, which has fallen below the lower limit of the industry's normal level. This indicates that the decrease in dependence is also driven by corporate factors, and the weakening of business transaction dependence will change the risk transmission path or reduce the transmission intensity.

[0072] The third transmission indicator represents a change in the direction of business transaction dependence that is not synchronized with industry trends. For example, if the dependence increases month-on-month but is still within the normal range of the industry, or if the dependence decreases month-on-month but is still within the normal range of the industry, it indicates that the change may be due to the company's own normal operational adjustments.

[0073] In a preferred embodiment of the present invention, the method for determining the intensity of supply chain risk transmission is as follows: S431, based on the generated transmission identifier, the business transaction dependence in the current statistical period is compared with the corresponding reference distribution interval to determine the deviation corresponding to the generated transmission identifier.

[0074] Specifically, when the transmission identifier is the first transmission identifier, the deviation is the difference between the business transaction dependency and the upper boundary of the reference distribution interval; when the transmission identifier is the second transmission identifier, the deviation is the difference between the lower boundary of the reference distribution interval and the business transaction dependency; and when the transmission identifier is the third transmission identifier, the deviation is the difference between the business transaction dependency and the nearest boundary of the reference distribution interval.

[0075] S432. When the transmission identifier is the first transmission identifier or the second transmission identifier, the deviation amount is compared with the deviation threshold corresponding to each transmission intensity in the preset deviation threshold set to match the transmission intensity of supply chain risk.

[0076] It should be noted that the deviation threshold set includes strong transmission intensity, medium transmission intensity, and weak transmission intensity. When the deviation amount reaches the deviation threshold corresponding to strong transmission intensity, the supply chain risk transmission intensity is determined to be strong transmission intensity; when the deviation amount reaches the deviation threshold corresponding to medium transmission intensity but does not reach the deviation threshold corresponding to strong transmission intensity, the supply chain risk transmission intensity is determined to be medium transmission intensity; when the deviation amount is less than the deviation threshold corresponding to medium transmission intensity, the supply chain risk transmission intensity is determined to be weak transmission intensity.

[0077] In one specific embodiment of the present invention, the deviation threshold set is determined as follows: Sample data corresponding to the deviation of business transaction dependence and the risk transmission intensity in historical risk events are obtained, and the deviation threshold corresponding to each transmission intensity is determined through quantile statistics. For example, risk events with deviations greater than the 75th quantile are marked as having strong transmission intensity, risk events with deviations between the 25th and 75th quantiles are marked as having medium transmission intensity, and risk events with deviations less than the 25th quantile are marked as having weak transmission intensity.

[0078] S433. When the transmission indicator is the third transmission indicator, the deviation amount is compared with the set disturbance transmission deviation threshold. If the deviation amount reaches the disturbance transmission deviation threshold, the supply chain risk transmission intensity is determined to be strong transmission intensity; otherwise, the supply chain risk transmission intensity is determined to be weak transmission intensity.

[0079] It should be noted that the disturbance transmission deviation threshold is determined based on the statistical analysis of the magnitude of cyclical fluctuations in the industry supply chain. Specifically, it is the average of the maximum deviations in the business transaction dependence of historical peer companies during cyclical fluctuations. When the transmission indicator is the third transmission indicator and the deviation reaches the disturbance transmission deviation threshold, it indicates that although the change in dependence is inconsistent with the industry trend, the deviation has exceeded the normal fluctuation range, resulting in a strong risk transmission effect.

[0080] This invention, based on historical business operation data of enterprises at all levels and reference data of business operation of enterprises in the same industry, determines the month-on-month change parameter and the horizontal change parameter of business transaction dependence. It generates corresponding transmission indicators by judging directional consistency, and evaluates the intensity of supply chain risk transmission between enterprises at all levels by combining deviation. It realizes a comprehensive evaluation of dependence changes from time and industry dimensions, effectively distinguishes between common industry fluctuations and enterprise-specific anomalies, accurately locates risk sources and quantifies the intensity of risk transmission, avoids misjudgment or omission caused by industry cyclical fluctuations, and improves the accuracy and timeliness of risk warning.

[0081] Given that the impact of supply chain risks is not limited to a single enterprise but spreads tier by tier along the supply chain network through transaction relationships, assessing only the intensity of transmission between enterprises while ignoring the direction of transmission makes it difficult to predict which node the risk will spread to, resulting in a lack of targeted prevention and control measures. Therefore, it is necessary to conduct time-series analysis of the intensity of risk transmission to identify trend characteristics and, in conjunction with business transaction dependencies, determine the direction and path of risk transmission between enterprises at each level.

[0082] Based on this, such as Figure 3As shown, the specific implementation of determining the risk transmission path of the supply chain network in this invention includes: S51, retrieving the supply chain risk transmission intensity between enterprises at each level within each statistical period of a preset time window, and constructing a time series sequence of risk transmission intensity between enterprises at each level. The preset time window includes the current statistical period and several previous historical statistical periods, for example, the most recent three statistical periods.

[0083] S52. Conduct trend analysis on the time series of risk transmission intensity, identify the trend characteristics of risk transmission intensity, and determine the transmission direction of risk transmission intensity among enterprises at all levels.

[0084] In one specific embodiment of the present invention, for example, when the trend characteristic of the time series of risk transmission intensity between enterprise A and enterprise B is an upward trend, if enterprise A is an upstream enterprise and enterprise B is a downstream enterprise, then the transmission direction between enterprise A and enterprise B is from A to B.

[0085] For example, when the time series of risk transmission intensity is (weak transmission intensity, medium transmission intensity, strong transmission intensity) or (weak transmission intensity, medium transmission intensity, medium transmission intensity), the trend characteristic is an upward trend.

[0086] If the time series of risk transmission intensity between company A and company B shows a downward or stable trend, then there is no transmission direction between company A and company B.

[0087] S53. Based on the transmission direction and combined with the business transaction dependence between enterprises at each level, a risk impact transmission path is formed.

[0088] In a preferred embodiment of the present invention, the method of forming the risk impact transmission path is as follows: S531, based on the business transaction dependence between enterprises at each level, filter enterprise nodes between enterprises at the corresponding level whose business transaction dependence exceeds a preset dependence threshold, and record them as marked nodes.

[0089] It should be noted that the preset dependency threshold is set based on the historical business transaction dependency distribution of enterprises in the supply chain network. Specifically, the 75th percentile of the historical distribution of business transaction dependency among enterprises at all levels is taken as the preset dependency threshold. This indicates that enterprises at all levels whose business transaction dependency exceeds the preset dependency threshold have the attribute of risk transmission carriers in the supply chain network and are potential links for risk transmission.

[0090] S532. Based on the supply chain risk transmission intensity between enterprises at each level, determine the supply chain risk transmission intensity corresponding to the marked node, and record the marked node whose risk transmission intensity exceeds the preset risk transmission intensity as a risk node. In this invention, the preset risk transmission intensity is a strong transmission intensity.

[0091] S533. Calculate the transmission direction corresponding to all risk nodes, and splice them together according to the transmission direction to form the risk impact transmission path.

[0092] For example, if the risk transmission strength between company A and company B is labeled as strong transmission strength, and the transmission direction is from A to B; and the risk transmission strength between company B and company C is also labeled as strong transmission strength, and the transmission direction is from B to C; then the risk impact transmission path can be represented as follows: This indicates that the risk is being transmitted step by step along the supply chain.

[0093] This invention analyzes the temporal changes in the intensity of supply chain risk transmission between enterprises at different levels, identifies the trend characteristics of risk transmission intensity, and determines the risk impact transmission path of the supply chain network by combining the corresponding business transaction dependence. It realizes the automatic identification and visualization of the supply chain risk transmission path, improves the accuracy of predicting the risk propagation direction and positioning the intervention node corresponding to supply chain risk prevention and control, and provides forward-looking decision support for the preventive risk management of the supply chain network.

[0094] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, in the form of a computer program product.

[0095] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0096] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0097] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0098] Finally, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A supply chain enterprise risk assessment method based on multi-data fusion analysis, characterized in that, include: Based on the business operation data of enterprises at each level within the supply chain network during the current statistical period, the validity of the business operation data is determined through data matching. When the business operation data is valid, retrieve the business performance information and business transaction frequency between enterprises at each level, compare them with the corresponding business operation data, and analyze the business transaction dependence between enterprises at each level. By retrieving historical business operation data of enterprises at all levels and business operation reference data of enterprises in the same industry, and combining the business transaction dependence within the current statistical period, the month-on-month change parameter and the horizontal change parameter of peers in business transaction dependence are determined. The month-on-month change parameter is compared with the horizontal change parameter of the peers to determine the directional consistency, and the corresponding transmission indicator is generated. The deviation is combined to assess the strength of supply chain risk transmission between enterprises at each level. A time-series analysis of the intensity of supply chain risk transmission between enterprises at different levels is conducted to determine the direction of risk transmission intensity and, in conjunction with the corresponding business transaction dependence, to determine the transmission path of risk impact in the supply chain network.

2. The supply chain enterprise risk assessment method based on multi-data fusion analysis according to claim 1, characterized in that, The method for determining the validity of business operation data is as follows: Extract business operation data of enterprises at all levels within the current statistical period. The business operation data includes transaction records, invoice and voucher information, and inventory turnover data. Match the transaction records of enterprises at each level with the corresponding invoices and vouchers to verify whether the transaction enterprises and transaction amounts in the transaction records are consistent with the invoices and vouchers. When the transaction record is consistent with the invoice information, extract the inventory turnover data of the enterprise at that level and obtain the quantity deviation between the inbound and outbound quantities in the transaction record and the actual inventory change in the inventory turnover data. If the quantity deviation is within the preset quantity deviation range and the transaction record is consistent with the invoice information, the business operation data of the enterprise at that level is deemed valid; otherwise, the business operation data of the enterprise at that level is deemed invalid.

3. The supply chain enterprise risk assessment method based on multi-data fusion analysis according to claim 1, characterized in that, The method for analyzing the business transaction dependencies between enterprises at different levels is as follows: Based on the business performance information between enterprises at each level, the actual performance time and the quantity of performance targets delivered by each enterprise in the current statistical period are extracted to determine the performance time deviation and the completion rate of performance targets between enterprises at each level. Based on the business operation data of enterprises at each level, determine the comprehensive frequency of business transactions of enterprises at each level in the current statistical period, and compare it with the business transaction frequency among enterprises at each level to obtain the matching degree of transaction frequency among enterprises at each level. By integrating and analyzing the deviation in performance time, the completion rate of the performance target, and the matching degree of transaction frequency, the business transaction dependence between enterprises at each level is calculated.

4. The supply chain enterprise risk assessment method based on multi-data fusion analysis according to claim 3, characterized in that, The method for determining the time deviation and completion rate of the contractual obligations among enterprises at different levels is as follows: Based on the transaction records between enterprises at all levels, the actual performance time and planned performance time of each business transaction between enterprises at all levels are extracted. The difference between the actual performance time and the planned performance time is calculated to obtain the performance time deviation value of each business transaction. Extract the quantity of the contracted goods delivered and the planned quantity of the contracted goods delivered from each business transaction record between enterprises at each level, calculate the ratio of the quantity of the contracted goods delivered to the planned quantity of the contracted goods delivered, and obtain the contracted goods completion rate of each business transaction. The time deviation and completion rate of each business transaction are adjusted according to the corresponding transaction amount to determine the time deviation and completion rate of each level of enterprise.

5. The supply chain enterprise risk assessment method based on multi-data fusion analysis according to claim 3, characterized in that, The method for calculating the business transaction dependency between enterprises at each level is as follows: Configure the weighting coefficients corresponding to the deviation in delivery time, the completion rate of the delivery target, and the matching rate of transaction frequency among enterprises at each level of the supply chain network; The normalized performance time deviation, performance target completion rate, and transaction frequency matching rate are weighted by the corresponding influence weight coefficients to obtain the initial business transaction dependence. Based on the hierarchical position of each enterprise in the supply chain network, the hierarchical decay factor between each position is obtained. The initial business transaction dependence between enterprises at each level is multiplied by the hierarchical decay factor of the corresponding position to obtain the business transaction dependence between enterprises at each level.

6. The supply chain enterprise risk assessment method based on multi-data fusion analysis according to claim 1, characterized in that, The method for determining the month-on-month change parameter and the peer-to-peer horizontal change parameter of business transaction dependence is as follows: Based on the historical business operation data of enterprises at each level in the previous statistical period, the historical business transaction dependence between enterprises at each level in the previous statistical period is determined. The difference between the business transaction dependence of enterprises at all levels in the current statistical period and the historical business transaction dependence in the previous statistical period is calculated to obtain the month-on-month change parameter of business transaction dependence. Retrieve reference data on the business operations of companies in the same industry within the current statistical period to determine the reference distribution range of business transaction dependence among companies in the same industry; By comparing the business transaction dependence within the current statistical period with the corresponding reference distribution interval, the relative position of the business transaction dependence within the corresponding reference distribution interval is determined, and a peer horizontal variation parameter is generated.

7. A supply chain enterprise risk assessment method based on multi-data fusion analysis according to claim 6, characterized in that, The method for assessing the strength of supply chain risk transmission among enterprises at different levels is as follows: The month-on-month change parameter and the horizontal change parameter of the same peer are judged to be consistent in direction. When the month-on-month change parameter is positive and the horizontal change parameter of the same peer is outside the upper boundary of the corresponding reference distribution interval, the first transmission indicator is generated. A second transmission indicator is generated when the month-on-month change parameter is negative and the horizontal change parameter of the same peer is outside the lower boundary of the corresponding reference distribution interval; a third transmission indicator is generated when the direction of the month-on-month change parameter is inconsistent with that of the horizontal change parameter of the same peer. The intensity of supply chain risk transmission is determined based on the generated transmission identifiers and their corresponding deviations.

8. The supply chain enterprise risk assessment method based on multi-data fusion analysis according to claim 7, characterized in that, The method for determining the intensity of supply chain risk transmission is as follows: Based on the generated transmission identifier, the business transaction dependence within the current statistical period is compared with the corresponding reference distribution interval to determine the deviation corresponding to the generated transmission identifier; When the transmission identifier is the first transmission identifier or the second transmission identifier, the deviation amount is compared with the deviation threshold corresponding to each transmission intensity in the preset deviation threshold set to match the transmission intensity of supply chain risk. When the transmission indicator is the third transmission indicator, the deviation amount is compared with the set disturbance transmission deviation threshold. If the deviation amount reaches the disturbance transmission deviation threshold, the supply chain risk transmission strength is determined to be strong transmission strength. Conversely, if the transmission strength of supply chain risk is determined to be weak, then the transmission strength is determined to be weak.

9. The supply chain enterprise risk assessment method based on multi-data fusion analysis according to claim 1, characterized in that, The method for determining the risk impact transmission path of the supply chain network is as follows: The intensity of supply chain risk transmission between enterprises at each level within each statistical period in a preset time window is retrieved, and a time series sequence of the intensity of risk transmission between enterprises at each level is constructed. Trend analysis is performed on the time series of risk transmission intensity to identify the trend characteristics of risk transmission intensity and determine the transmission direction of risk transmission intensity among enterprises at different levels; Based on the transmission direction and the degree of business transaction dependence between enterprises at different levels, a risk impact transmission path is formed.

10. A supply chain enterprise risk assessment method based on multi-data fusion analysis according to claim 9, characterized in that, The method for forming the risk impact transmission path is as follows: Based on the business transaction dependency between enterprises at each level, enterprise nodes between enterprises at the corresponding level whose business transaction dependency exceeds a preset dependency threshold are selected and marked as labeled nodes. Based on the intensity of supply chain risk transmission between enterprises at each level, determine the intensity of supply chain risk transmission corresponding to the marked node, and record the marked node whose risk transmission intensity exceeds the preset risk transmission intensity as a risk node; Analyze the transmission direction of all risk nodes and piece them together according to the transmission direction to form the risk impact transmission path.

Images