A supplier management method and system based on risk assessment

Abstract

The present invention belongs to the field of data processing technology, and specifically relates to a supplier management method and system based on risk assessment. The method comprises: obtaining a supplier's own risk indicators based on the supplier's quality risk, delivery risk, financial risk, and compliance risk; constructing a risk propagation directed graph based on the upstream and downstream relationships between suppliers, thereby obtaining the risk propagation index between any two suppliers; and further introducing an ant colony algorithm to construct a procurement path. During each iteration, the ant colony algorithm comprehensively considers the potential supplier's own risk index, the risk propagation index from existing nodes in the current path to the potential supplier, and the distribution of risk and cost-oriented pheromones in historical paths, thereby dynamically calculating the selection probability of each potential supplier and guiding the ants to gradually construct an optimal path that meets procurement needs. The present invention improves the objectivity and accuracy of risk identification and enhances the enterprise's early warning capabilities for systemic risks.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and more particularly to a supplier management method and system based on risk assessment. Background Art

[0002] Currently, companies generally rely on empirical judgment or simple scoring mechanisms when managing suppliers and selecting procurement paths, lacking the ability to systematically assess and dynamically optimize overall supply chain risks. Traditional approaches often make decisions based on a single metric (such as price, lead time, or quality compliance), ignoring the complex dependencies between suppliers and the propagation of risk within the supply chain. This makes procurement strategies incapable of responding to unexpected risk events, such as the disruption of key suppliers, the spread of quality issues, and financial crises.

[0003] In addition, existing technologies mostly use static scoring methods to assess supplier risks, and fail to dynamically model them in combination with upstream and downstream impacts, thereby ignoring certain "invisible high-risk nodes" that appear to be low-risk but have high transmission capabilities. Once an anomaly occurs, it may cause the entire supply chain to be disrupted.

[0004] Therefore, there is an urgent need for an intelligent path construction mechanism that can integrate multi-dimensional risk indicators and cost control objectives to enhance the resilience and sustainability of the supply chain. Summary of the Invention

[0005] In order to solve the technical problem that the above-mentioned existing technologies ignore the propagation characteristics of risks, resulting in procurement strategies being unable to cope with sudden risk events, the present invention provides solutions in the following aspects.

[0006] In a first aspect, the present invention provides a supplier management method based on risk assessment, comprising:

[0007] Obtain suppliers' own risk indicators based on their quality risk, delivery risk, financial risk, and compliance risk. Construct a risk propagation directed graph based on the upstream and downstream relationships between suppliers, and obtain the risk propagation index between any two suppliers based on the risk propagation directed graph.

[0008] The procurement path is constructed using the ant colony algorithm. In each iteration of the ant colony algorithm, the heuristic factor of the optional supplier is determined based on the optional supplier's own risk index and the risk propagation index from the supplier of each node in the current path to the optional supplier; the risk-oriented pheromone of the edge between the supplier corresponding to the current node in the current path and the optional supplier is determined based on the sum of the supplier's own risk coefficients contained in each path obtained in the previous iteration; the cost-oriented pheromone of the edge between the supplier corresponding to the current node in the current path and the optional supplier is determined based on the sum of the unit procurement costs of the suppliers contained in each path obtained in the previous iteration; the selection probability of the optional supplier is determined based on the risk-oriented pheromone, cost-oriented pheromone and heuristic factor; and according to the selection probability, one supplier is selected from all the optional suppliers as the next node of the current path.

[0009] Preferably, the method for obtaining the supplier's own risk indicator is:

[0010] The supplier's quality risk is obtained based on the supplier's product qualification rate; the supplier's delivery risk is obtained based on the supplier's on-time delivery rate, the number of delayed deliveries, and the delay time of each delayed delivery; the supplier's financial risk is obtained based on the supplier's financial status; the supplier's compliance risk is obtained based on the number of violations committed by the supplier; the quality risk, delivery risk, financial risk, and compliance risk are weighted and summed to obtain the supplier's own risk indicator.

[0011] Preferably, constructing the risk propagation directed graph includes:

[0012] Take each supplier as a node, and for any two suppliers and , in response to suppliers For suppliers Upstream suppliers, in suppliers With suppliers Establish a supplier relationship Point to suppliers Directed edges of Point to suppliers The weight of the directed edge : , Indicates supplier Supply Supplier No. the number of products; Indicates supplier All upstream suppliers supply suppliers No. The total quantity of the product; Indicates supplier Supply Supplier The number of product types; Represents the maximum function; a directed graph is formed according to all nodes, directed edges and the weights of directed edges, which is recorded as the risk propagation directed graph.

[0013] Preferably, the method for obtaining the risk propagation index is:

[0014] For any two suppliers and , obtain suppliers in the risk propagation directed graph To suppliers All paths are regarded as a risk transmission path;

[0015] supplier To suppliers Risk Communication Index Satisfies the expression: , Indicates supplier own risk index; Represents the supplier in the risk propagation directed graph To suppliers No. The first of the risk transmission paths The weight of a directed edge; Represents the supplier in the risk propagation directed graph To suppliers No. The number of directed edges in the risk propagation path; Represents the supplier in the risk propagation directed graph To suppliers The number of risk transmission paths.

[0016] Preferably, the heuristic factor satisfies the expression:

[0017] ;

[0018] in, Indicates the Heuristic factors for alternative suppliers, Indicates the The risk index of each potential supplier; Indicates the current path The supplier corresponding to the node Risk propagation index of the selected suppliers; Indicates the number of nodes in the current path; Represents an exponential function with a natural constant as its base.

[0019] Preferably, the risk-oriented pheromone satisfies the expression:

[0020] ;

[0021] Let the current iteration be Round iteration, record the supplier corresponding to the current node in the current path as supplier , where Indicates the After rounds of iteration, suppliers To Risk-oriented pheromones between alternative suppliers; Indicates the After rounds of iteration, suppliers To Risk-oriented pheromones between alternative suppliers; represents the pheromone volatility coefficient; Indicates the After rounds of iteration, suppliers To The incremental risk-oriented pheromone between optional suppliers: , Indicates the The results of the round of iterations include To The number of paths between edges of optional suppliers, Indicates the total amount of pheromone; Indicates the The results of the round of iterations include To The first edge between the optional suppliers The sum of the risk coefficients of suppliers corresponding to all nodes in the path.

[0022] Preferably, the cost-oriented pheromone satisfies the expression:

[0023] ;

[0024] Let the current iteration be Round iteration, record the supplier corresponding to the current node in the current path as supplier , where Indicates the After rounds of iteration, suppliers To Cost-oriented pheromones on the edges between alternative suppliers; Indicates the After rounds of iteration, suppliers To Cost-oriented pheromones on the edges between alternative suppliers; represents the pheromone volatility coefficient; Indicates the After rounds of iteration, suppliers To The cost-oriented pheromone increment between the edges of optional suppliers is: , Indicates the The results of the round of iterations include To The number of paths between edges of optional suppliers, Indicates the total amount of pheromone; Indicates the The results of the round of iterations include To The first edge between the optional suppliers The sum of the unit procurement costs of suppliers corresponding to all nodes in the path.

[0025] Preferably, the selection probability of the optional supplier satisfies the expression:

[0026] ;

[0027] Let the current iteration be In round iteration, the supplier corresponding to the current node in the current path is recorded as the supplier , where Indicates the The probability of selecting an optional supplier as the next node of the path; Indicates the After rounds of iteration, suppliers To Risk-oriented pheromones between alternative suppliers; Indicates the After rounds of iteration, suppliers To Cost-oriented pheromones on the edges between alternative suppliers; Indicates the heuristic factors for alternative suppliers; Indicates the number of optional suppliers; 、 、 is a hyperparameter.

[0028] Preferably, the delivery risk satisfies the expression:

[0029] ;

[0030] Where, Indicates the supplier's delivery risk; Indicates the supplier's on-time delivery rate; Indicates the number of delayed deliveries, Indicates the The delay time for the delayed delivery; Represents the maximum function.

[0031] In a second aspect, the present invention provides an artificial intelligence-based video data optimization acquisition system, comprising a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned supplier management method based on risk assessment is implemented.

[0032] By adopting the above technical solution, the above-mentioned supplier management method based on risk assessment is generated into a computer program and stored in a memory so as to be loaded and executed by a processor, thereby making a terminal device based on the memory and the processor for easy use.

[0033] The beneficial effects of the present invention are as follows: by constructing a comprehensive assessment model for supplier quality risk, delivery risk, financial risk and compliance risk, the present invention realizes quantitative analysis of supplier's own risks, thereby breaking through the limitations of relying on subjective experience or single indicator judgment in traditional procurement decisions, and improving the objectivity and accuracy of risk identification; on this basis, a risk propagation directed graph is established in combination with the upstream and downstream relationships between suppliers, further revealing the transmission path and impact range of risks in the supply chain network, helping to identify key nodes and high-risk links, and enhancing the company's early warning capabilities for systemic risks.

[0034] The present invention optimizes the procurement path by introducing the ant colony algorithm, combining risk control with cost control. In each round of iteration, the risk level, risk propagation intensity and historical path pheromone distribution of each optional supplier are dynamically calculated, forming a path selection mechanism with "heuristic factor + risk-oriented pheromone + cost-oriented pheromone" as the core, guiding the algorithm to give priority to supplier combination paths with controllable risks, reasonable costs and strong stability. This not only improves the overall robustness of the procurement path, but also enhances the company's responsiveness and anti-interference capabilities in a complex market environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 The flowchart schematically illustrates a supplier management method based on risk assessment in the present invention. DETAILED DESCRIPTION

[0036] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work shall fall within the scope of protection of the present invention.

[0037] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0038] The embodiment of the present invention discloses a supplier management method based on risk assessment, referring to Figure 1 , including steps S1 to S4:

[0039] S1. Obtain basic information and historical delivery data of suppliers.

[0040] Specifically, the basic information includes the supplier name, product type, industry, financial status, upstream suppliers, downstream suppliers, number of violations, etc., among which the financial status includes debt ratio, cash flow, current ratio, etc., and the number of violations is the number of records of administrative penalties, regulatory notifications, legal disputes, etc. imposed on the supplier.

[0041] The historical delivery data includes product qualification rate, on-time delivery rate, number of delayed deliveries, and the delay time of each delayed delivery (in days), etc.

[0042] S2. Determine the supplier’s own risk indicators based on the supplier’s basic information and historical delivery data.

[0043] Specifically, the supplier's quality risk is obtained based on the supplier's product qualification rate; the supplier's delivery risk is obtained based on the supplier's on-time delivery rate, the number of delayed deliveries, and the delay time of each delayed delivery; the supplier's financial risk is obtained based on the supplier's financial status; the supplier's compliance risk is obtained based on the number of supplier violations; and the supplier's own risk indicators are obtained based on quality risk, delivery risk, financial risk, and compliance risk.

[0044] In one embodiment, the quality risk satisfies the expression:

[0045] ;

[0046] Where, Indicates the supplier's quality risk; It indicates the supplier's product qualification rate; when the product qualification rate is higher, the supplier's quality risk is lower; conversely, when the product qualification rate is lower, the supplier's quality risk is higher.

[0047] In one embodiment, the delivery risk satisfies the expression:

[0048] ;

[0049] Where, Indicates the supplier's delivery risk; Indicates the supplier's on-time delivery rate; Indicates the number of delayed deliveries, Indicates the The delay time for the delayed delivery; represents the maximum function, Indicates selection The maximum value of 1 and 1, when the number of delayed deliveries When it is 0, it is specified ,therefore Used to prevent the denominator from being 0.

[0050] Where, Indicates the rate of late delivery, when the on-time delivery rate The lower it is, the higher the rate of delayed delivery is and the greater the delivery risk is; It represents the average delay time of delayed delivery. When the average delay time is longer, the impact on delivery is greater. Therefore, the present invention will As the rate of late delivery The gamma transform is used to increase the delivery risk to a certain extent. When the average delay time is smaller, the impact on delivery is smaller. The closer it is to 1, the closer the delivery risk result is to the on-time delivery rate. ,When the average delay time is longer, the impact on delivery is greater, The smaller the delivery risk is, the higher the rate of late delivery Therefore, when the on-time delivery rate is smaller and the delay time of each delayed delivery is longer, the delivery risk is greater.

[0051] In one embodiment, the method for obtaining the financial risk is:

[0052] Setting up an ideal healthy financial situation ,in, It represents the debt ratio under an ideal healthy financial situation. When the debt ratio is higher, the supplier's debt repayment pressure is higher and the financial risk is greater. When the debt ratio is lower, the supplier's capital structure is more stable and the risk resistance is stronger. Therefore, in this embodiment, It is set to 0, indicating that the ideal healthy financial status is no debt; It represents the cash flow under an ideal and healthy financial situation. When the cash flow is larger, the supplier's ability to cope with sudden demands or short-term debts is stronger, and the risk of capital chain rupture is smaller. When the cash flow is smaller, the supplier may face the risk of insufficient income and operational difficulties. Therefore, this embodiment will Set to the maximum of the cash flows of all suppliers in the industry, indicating the level of the most well-funded supplier in the industry; It represents the current ratio under an ideal healthy financial condition. When the current ratio is larger, the supplier's liquidity is stronger and its short-term debt repayment ability is stronger. When the current ratio is smaller, the supplier's liquidity is weaker and its short-term debt repayment ability is weaker. There may be a risk of being unable to repay short-term debts. The generally accepted healthy current ratio standard in the industry is 2, so this embodiment will Set to 2. In other embodiments, the implementer can set the ideal healthy financial status according to actual implementation conditions.

[0053] Furthermore, the supplier's financial risk is obtained based on the difference between the supplier's financial status and the ideal healthy financial status:

[0054] ;

[0055] Where, Indicates the financial risk to the supplier; Indicates the supplier's debt ratio; represents the supplier's cash flow; Indicates the supplier's current ratio; Indicates the debt ratio under ideal healthy financial status, Represents the cash flow under ideal healthy financial conditions; The current ratio represents an ideal healthy financial situation; Represents the linear rectification function, the expression is .

[0056] Where, Indicates the supplier's debt ratio Debt ratio under ideal healthy financial status The difference between the supplier's debt ratio Compared to the debt ratio under ideal healthy financial status When the value is larger, the supplier's debt repayment pressure is higher and the financial risk is greater. On the contrary, when near When a company is close to debt-free, it indicates that its financial structure is sound and its financial risk is low; Represents the supplier's cash flow Cash flow under ideal healthy financial status The difference between Differences Normalize it so that it falls within the range of [0,1], when the supplier's cash flow Compared to the cash flow under ideal healthy financial conditions When the value is larger, the supplier's cash flow is smaller, and the supplier may face the risk of not making ends meet and having operational difficulties. At this time, the financial risk is greater. Represents the supplier's current ratio Current ratio compared to ideal healthy financial condition When the supplier's current ratio Compared to the current ratio under ideal healthy financial conditions The smaller the current ratio is, the worse the supplier's liquidity and short-term debt repayment ability are. There may be a risk of not being able to repay short-term debts. At this time, the financial risk is greater. When the current ratio of the supplier is Achieve an ideal current ratio for healthy financial conditions When , it indicates that the supplier has strong liquidity and short-term debt repayment ability, so this embodiment uses Differences Perform non-negative truncation to prevent the risk score from being lowered when the current ratio is higher than the ideal value. right Normalize it to fall within the range [0,1].

[0057] In one embodiment, the compliance risk satisfies the expression:

[0058] ;

[0059] in, Indicates the supplier’s compliance risk; Indicates the number of violations by the supplier, that is, the number of administrative penalties, regulatory notifications, legal disputes, etc. Represents the hyperbolic tangent function, which is used to calculate the number of violations Normalization is performed; the more violations a supplier has, the weaker its compliance awareness is as indicated by its historical behavior, the higher the possibility of violations occurring again in the future, and the greater the supplier's compliance risk.

[0060] In one embodiment, the self-risk index satisfies the expression:

[0061] ;

[0062] Where, Indicates the supplier's own risk index; Indicates the supplier's quality risk; Indicates the supplier's delivery risk; Indicates the financial risk to the supplier; Indicates the supplier’s compliance risk; represents a normalization function. In this embodiment, linear normalization is used to linearly normalize the financial risk of the current supplier based on the financial risks of all suppliers. In other embodiments, the implementer may select a normalization method based on actual implementation conditions. 、 、 、 Represent the weights of quality risk, delivery risk, financial risk, and compliance risk respectively. In this embodiment, the attention levels to quality risk, delivery risk, financial risk, and compliance risk are the same, so In other embodiments, the implementers can adjust the weights of quality risk, delivery risk, financial risk, and compliance risk according to the characteristics of the industry. For example, the weight of quality risk can be increased in the medical industry, and the weight of delivery risk can be increased in the electronic manufacturing industry. The greater the supplier's quality risk, delivery risk, financial risk, and compliance risk, the more likely the supplier will experience key risk events such as supply interruption, quality problems, broken capital chain, and legal disputes. At this time, the supplier's own risk index is R The larger it is, the worse the supplier's overall operational stability is.

[0063] S3. Based on the upstream and downstream relationships between suppliers, a risk propagation directed graph is constructed, and the risk propagation index between any two suppliers is obtained based on the risk propagation directed graph.

[0064] Specifically, based on the upstream and downstream relationships between suppliers, a risk propagation directed graph is constructed, including:

[0065] Take each supplier as a node, and for any two suppliers and , in response to suppliers For suppliers Upstream suppliers (i.e. suppliers) To suppliers Provide raw materials, parts, etc.) Corresponding nodes and suppliers A supplier link is established between the corresponding nodes Point to suppliers Directed edges, according to suppliers Supply Supplier Product proportion, determine the supplier Point to suppliers The weight of the directed edge.

[0066] By judging the upstream and downstream relationship between any two suppliers, all directed edges are obtained, and a directed graph is formed according to the nodes, directed edges and the weights of directed edges, which is recorded as the risk propagation directed graph.

[0067] Among them, the weight of the directed edge satisfies the expression:

[0068] ;

[0069] in, Indicates supplier Point to suppliers The weight of the directed edge; Indicates supplier Supply Supplier No. the number of products; Indicates supplier All upstream suppliers supply suppliers No. The total quantity of the product; Indicates supplier Supply Supplier The number of product types; Represents the maximum function.

[0070] when near When the supplier is a supplier No. The main source of supply of this product, Much smaller than When the supplier supplier No. The secondary source of supply for this product. is a supplier When a product is the main source of supply, The closer it is to 1, the greater the weight of the directed edge, indicating that the supplier To suppliers The stronger the supply dependence, the more likely the supplier If there is a supply interruption, quality or delivery problem, The more serious the impact; if the supplier Supply Supplier Across all product categories, suppliers Just a supplier When the secondary source of supply is The closer it is to 0, the smaller the weight of the directed edge is, indicating that the supplier To suppliers The weaker the impact, even if the supplier If there is a problem, the supplier It is also easier to replace through other channels and has a lower risk transmission capacity.

[0071] Furthermore, the risk propagation index between any two suppliers is obtained based on the risk propagation directed graph, including:

[0072] For any two suppliers and , obtain suppliers in the risk propagation directed graph To suppliers All paths are regarded as a risk transmission path, according to The risk index of the supplier and the weights of all directed edges in each risk propagation path are obtained. To suppliers Risk Communication Index:

[0073] ;

[0074] Where, Indicates supplier To suppliers Risk Communication Index; Indicates supplier own risk index; Represents the supplier in the risk propagation directed graph To suppliers No. The first of the risk transmission paths The weight of a directed edge; Represents the supplier in the risk propagation directed graph To suppliers No. The number of directed edges in the risk propagation path; Represents the supplier in the risk propagation directed graph To suppliers The number of risk transmission paths. Represents the supplier in the risk propagation directed graph To suppliers No. The risk propagation attenuation coefficient of the risk propagation path, Represents the supplier in the risk propagation directed graph To suppliers No. The risk propagation intensity of the risk propagation path; when the supplier To suppliers The greater the risk transmission intensity of each risk transmission path, the greater the risk of suppliers To suppliers The greater the risk propagation index, the greater the risk propagation index. To suppliers The smaller the risk transmission intensity of each risk transmission path, the greater the risk of suppliers To suppliers The smaller the risk transmission index.

[0075] It should be noted that when the risk propagation directed graph has suppliers To suppliers When there is no risk transmission path, suppliers are required to To suppliers The risk transmission index is 0.

[0076] S4. Based on the supplier’s own risk index and the risk propagation index between suppliers, the ant colony algorithm is used to construct the procurement path.

[0077] Each supplier is treated as a node, and a procurement path is constructed using the ant colony algorithm. In each iteration of the ant colony algorithm, all suppliers not yet added to the current path are considered as alternative suppliers. The heuristic factor for the alternative supplier is determined based on the risk index of the alternative supplier and the risk propagation index from the supplier corresponding to each node in the current path to the alternative supplier. The risk-oriented pheromone for the edge between the supplier corresponding to the current node and the alternative supplier in the current path is determined based on the sum of the risk coefficients of the suppliers included in each path obtained in the previous iteration. The cost-oriented pheromone for the edge between the supplier corresponding to the current node and the alternative supplier in the current path is determined based on the sum of the unit procurement costs of the suppliers included in each path obtained in the previous iteration. The probability of selecting an alternative supplier is determined based on the risk-oriented pheromone, cost-oriented pheromone, and heuristic factor. Based on the selection probability, an unequal probability sampling method is used to select a supplier from all the alternative suppliers as the next node in the current path. This path expansion process is repeated until the product variety and quantity provided by the suppliers in the current path meet the current procurement demand, or when there are no more alternative suppliers left to visit. At this point, the current path construction stops.

[0078] The optimal path obtained after several rounds of iteration is used as the procurement path, and structured procurement decisions and order allocation are made based on the set of suppliers included in the procurement path.

[0079] It should be noted that the present invention uses the total amount of pheromone in the ant colony algorithm Set to 1 to increase the pheromone volatility coefficient Set it to 0.5 and set the maximum number of iterations to 100. Implementers can also set it according to actual implementation conditions.

[0080] In one embodiment, the heuristic factor satisfies the expression:

[0081] ;

[0082] in, Indicates the Heuristic factors for alternative suppliers, Indicates the The risk index of each potential supplier; Indicates the current path The supplier corresponding to the node Risk propagation index of the selected suppliers; Indicates the number of nodes in the current path; Represents an exponential function with a natural constant as the base, used for Perform negative correlation mapping.

[0083] When The risk index of each supplier The larger the value, the higher the probability of the supplier having quality problems, delivery delays or supply interruptions and other risk events. The smaller the size, the more likely the ants are to choose suppliers with lower risks and more stable performance. The larger the risk propagation index of an optional supplier is, the more it indicates that if a supplier in the current path encounters a risk event such as quality problems, delivery delays, or supply interruption, the supplier in the next path may be affected through the risk propagation mechanism. The negative impact on the number of alternative suppliers is The joint risk of the third supplier is higher. The smaller the heuristic factor of the optional supplier is, the ants are encouraged to choose suppliers that are less affected by existing nodes in the path and have higher independence and anti-interference ability.

[0084] In one embodiment, the risk-oriented pheromone satisfies the expression:

[0085] ;

[0086] Let the current iteration be In round iteration, the supplier corresponding to the current node in the current path is recorded as the supplier , then Indicates the After rounds of iteration, suppliers To Risk-oriented pheromones between alternative suppliers; Indicates the After rounds of iteration, suppliers To Risk-oriented pheromones between alternative suppliers; Indicates the After rounds of iteration, suppliers To The incremental risk-oriented pheromone between the optional suppliers; Indicates the pheromone volatility coefficient.

[0087] Among them, the risk-oriented information increment satisfies the expression:

[0088] ;

[0089] Where, Indicates the After rounds of iteration, suppliers To The incremental risk-oriented pheromone between the optional suppliers; Indicates the The results of the round of iterations include To The number of paths between edges of optional suppliers, Indicates the total amount of pheromone; Indicates the The results of the round of iterations include To The first edge between the optional suppliers The sum of the risk coefficients of suppliers corresponding to all nodes in the path; Indicates the The risk-oriented pheromone increment brought by the first path The sum of the risk coefficients of suppliers corresponding to all nodes in the path The smaller the hour, the The greater the risk-oriented pheromone increment brought by the path, the greater the risk-oriented pheromone increment brought by the path. To The greater the risk-oriented pheromone increment brought by all paths between optional suppliers, the greater the supplier To The greater the increment of risk-oriented pheromone between the edges of the optional suppliers, the greater the risk-oriented pheromone increment will be, which will encourage ants to prioritize paths with lower risks and stronger node stability.

[0090] It should be noted that, in this embodiment, the initial risk-oriented pheromone between any two suppliers is 1. In other embodiments, the implementer may set the initial risk-oriented pheromone according to the actual implementation situation.

[0091] In one embodiment, the cost-oriented pheromone satisfies the expression:

[0092] ;

[0093] Let the current iteration be Round iteration, record the supplier corresponding to the current node in the current path as supplier , then Indicates the After rounds of iteration, suppliers To Cost-oriented pheromones on the edges between alternative suppliers; Indicates the After rounds of iteration, suppliers To Cost-oriented pheromones on the edges between alternative suppliers; Indicates the After rounds of iteration, suppliers To Cost-oriented pheromone increment between the edges of the optional suppliers; Indicates the pheromone volatility coefficient.

[0094] Among them, the cost-oriented information increment satisfies the expression:

[0095] ;

[0096] Where, Indicates the After rounds of iteration, suppliers To Cost-oriented pheromone increment between the edges of the optional suppliers; Indicates the The results of the round of iterations include To The number of paths between edges of optional suppliers, Indicates the total amount of pheromone; Indicates the The results of the round of iterations include To The first edge between the optional suppliers The sum of the unit purchase costs of suppliers corresponding to all nodes in the path; Indicates the The cost-oriented pheromone increment brought by the path, when the The sum of the unit purchase costs of suppliers corresponding to all nodes in the path The smaller the hour, the The cost-oriented pheromone increment brought by the path is larger when it includes To The greater the cost-oriented pheromone increment brought by all paths between optional suppliers, the greater the supplier To The larger the cost-oriented pheromone increment between the edges of the optional suppliers, the greater the cost-oriented pheromone increment, which encourages ants to give priority to paths with lower unit procurement costs and more economical and efficient supply chain links.

[0097] It should be noted that, in this embodiment, the initial cost-oriented pheromone of the edge between any two suppliers is 1. In other embodiments, the implementer may set the initial cost-oriented pheromone according to the actual implementation situation.

[0098] In one embodiment, the selection probability satisfies the expression:

[0099] ;

[0100] Let the current iteration be Round iteration, record the supplier corresponding to the current node in the current path as supplier , then Indicates the The probability of selecting an optional supplier as the next node of the path; Indicates the After rounds of iteration, suppliers To Risk-oriented pheromones between alternative suppliers; Indicates the After rounds of iteration, suppliers To Cost-oriented pheromones on the edges between alternative suppliers; Indicates the heuristic factors for alternative suppliers; Indicates the number of optional suppliers; 、 、 is a hyperparameter, Used to control the relative importance of risk-oriented pheromones, Used to control the relative importance of cost-oriented pheromones, It is used to control the relative importance of the heuristic factors. In this embodiment, the relative importance of risk-oriented pheromone, cost-oriented pheromone and heuristic factors are the same, so it is set In other embodiments, the implementer can set the hyperparameters according to the actual implementation situation. 、 、 .

[0101] An embodiment of the present invention also discloses an artificial intelligence-based video data optimization acquisition system, including a processor and a memory, wherein the memory stores computer program instructions. When the computer program instructions are executed by the processor, a supplier management method based on risk assessment according to the present invention is implemented.

[0102] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface. The configuration and functions of these components are known in the art and will not be described in detail here.

Claims

1. A supplier management method based on risk assessment, characterized in that: include: Obtain the supplier's own risk indicators based on the supplier's quality risk, delivery risk, financial risk, and compliance risk; Based on the upstream and downstream relationships between suppliers, a risk propagation directed graph is constructed, and the risk propagation index between any two suppliers is obtained based on the risk propagation directed graph; The method for obtaining the risk transmission index is as follows: for any two suppliers and , obtain suppliers in the risk propagation directed graph To suppliers All paths are regarded as a risk transmission path; suppliers To suppliers Risk Communication Index Satisfies the expression: , Indicates supplier own risk index; Represents the supplier in the risk propagation directed graph To suppliers No. The first of the risk transmission paths The weight of a directed edge; Represents the supplier in the risk propagation directed graph To suppliers No. The number of directed edges in the risk propagation path; Represents the supplier in the risk propagation directed graph To suppliers the number of risk transmission pathways; The ant colony algorithm is used to construct the procurement path. In each round of the ant colony algorithm, the heuristic factor of the optional supplier is determined based on the risk index of the optional supplier and the risk propagation index from the supplier corresponding to each node in the current path to the optional supplier: ;in, Indicates the Heuristic factors for alternative suppliers, Indicates the The risk index of each potential supplier; Indicates the current path The supplier corresponding to the node Risk propagation index of the selected suppliers; Indicates the number of nodes in the current path; represents an exponential function with a natural constant as the base; based on the sum of the risk coefficients of the suppliers contained in each path obtained in the previous round of iteration, the risk-oriented pheromone of the edge between the supplier corresponding to the current node in the current path and the optional supplier is determined; based on the sum of the unit procurement costs of the suppliers contained in each path obtained in the previous round of iteration, the cost-oriented pheromone of the edge between the supplier corresponding to the current node in the current path and the optional supplier is determined; based on the risk-oriented pheromone, the cost-oriented pheromone and the heuristic factor, the selection probability of the optional supplier is determined; based on the selection probability, one supplier is selected from all the optional suppliers as the next node of the current path.

2. A supplier management method based on risk assessment according to claim 1, characterized in that: The method for obtaining the supplier's own risk indicators is as follows: Obtain supplier quality risk based on the supplier's product qualification rate; obtain supplier delivery risk based on the supplier's on-time delivery rate, number of delayed deliveries, and the delay time of each delayed delivery; obtain supplier financial risk based on the supplier's financial status; obtain supplier compliance risk based on the number of supplier violations; The quality risk, delivery risk, financial risk and compliance risk are weighted and summed to obtain the supplier's own risk index.

3. A supplier management method based on risk assessment according to claim 1, characterized in that: The step of constructing a risk propagation directed graph includes: Take each supplier as a node, and for any two suppliers and , in response to suppliers For suppliers Upstream suppliers, in suppliers With suppliers Establish a supplier relationship Point to suppliers Directed edges of Point to suppliers The weight of the directed edge : , Indicates supplier Supply Supplier No. the number of products; Indicates supplier All upstream suppliers supply suppliers No. The total quantity of the product; Indicates supplier Supply Supplier The number of product types; Represents the maximum function; a directed graph is formed according to all nodes, directed edges and the weights of directed edges, which is recorded as the risk propagation directed graph.

4. A supplier management method based on risk assessment according to claim 1, characterized in that: The risk-oriented pheromone satisfies the expression: ； Let the current iteration be Round iteration, record the supplier corresponding to the current node in the current path as supplier , where Indicates the After rounds of iteration, suppliers To Risk-oriented pheromones between alternative suppliers; Indicates the After rounds of iteration, suppliers To Risk-oriented pheromones between alternative suppliers; represents the pheromone volatility coefficient; Indicates the After rounds of iteration, suppliers To The incremental risk-oriented pheromone between optional suppliers: , Indicates the The results of the round of iterations include To The number of paths between edges of optional suppliers, Indicates the total amount of pheromone; Indicates the The results of the round of iterations include To The first edge between the optional suppliers The sum of the risk coefficients of suppliers corresponding to all nodes in the path.

5. The supplier management method based on risk assessment according to claim 1, characterized in that: The cost-oriented pheromone satisfies the expression: ； Let the current iteration be In round iteration, the supplier corresponding to the current node in the current path is recorded as the supplier , where Indicates the After rounds of iteration, suppliers To Cost-oriented pheromones on the edges between alternative suppliers; Indicates the After rounds of iteration, suppliers To Cost-oriented pheromones on the edges between alternative suppliers; represents the pheromone volatility coefficient; Indicates the After rounds of iteration, suppliers To The cost-oriented pheromone increment between the edges of optional suppliers is: , Indicates the The results of the round of iterations include To The number of paths between edges of optional suppliers, Indicates the total amount of pheromone; Indicates the The results of the round of iterations include To The first edge between the optional suppliers The sum of the unit procurement costs of suppliers corresponding to all nodes in the path.

6. A supplier management method based on risk assessment according to claim 1, characterized in that: The selection probability of the optional supplier satisfies the expression: ； Let the current iteration be Round iteration, record the supplier corresponding to the current node in the current path as supplier , where Indicates the The probability of selecting an optional supplier as the next node of the path; Indicates the After rounds of iteration, suppliers To Risk-oriented pheromones between alternative suppliers; Indicates the After rounds of iteration, suppliers To Cost-oriented pheromones on the edges between alternative suppliers; Indicates the heuristic factors for alternative suppliers; Indicates the number of optional suppliers; 、 、 is a hyperparameter.

7. A supplier management method based on risk assessment according to claim 2, characterized in that: The delivery risk satisfies the expression: ； Where, Indicates the supplier's delivery risk; Indicates the supplier's on-time delivery rate; Indicates the number of delayed deliveries, Indicates the The delay time for the delayed delivery; Represents the maximum function.

8. A video data optimization acquisition system based on artificial intelligence, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a supplier management method based on risk assessment according to any one of claims 1 to 7 is implemented.

Images