Supply chain real-time monitoring and optimizing method and system based on artificial intelligence

Abstract

The invention discloses a supply chain real-time monitoring and optimizing method and system based on artificial intelligence, and the method comprises the steps: obtaining upstream and downstream enterprises of a supply chain, carrying out the node setting of the upstream and downstream enterprises of the supply chain, and obtaining supply chain nodes; a complete supply chain network is obtained; obtaining service data of each supply chain node in the supply chain network, and identifying a risk coefficient of each supply chain node; when the risk coefficient of one supply chain node is greater than a preset threshold value, taking the supply chain node as a risk node; acquiring information flow data, fund flow data and logistics data between each adjustment node and the risk node, and constructing a data transmission target; and performing iterative optimization of transmission and layout of the supply chain nodes according to a data transmission target in combination with the supply chain network, and generating a new transmission path of the risk nodes in the supply chain network, thereby realizing real-time monitoring and optimization of the supply chain.

Description

Technical Field

[0001] The present invention relates to the field of supply chain technology, and in particular to a supply chain real-time monitoring and optimization method and system based on artificial intelligence. Background Art

[0002] The node structure of the supply chain is usually presented as a network chain structure, which is composed of multiple node enterprises and the connection relationships between node enterprises. The connection relationships between node enterprises include logistics connections, information flow connections and capital flow connections. In order to monitor the production and product quality, product warehousing, product turnover and sales of enterprises, it is necessary to optimize the logistics connections on the supply chain nodes to reduce transportation distance and time and improve the circulation efficiency of enterprise products in the supply chain.

[0003] At present, the product supply relationship between supply chain nodes can be accurately identified and monitored. However, it is impossible to fully monitor the upstream and downstream nodes on the supply chain, making it impossible to identify and determine risky supply chain nodes (which may involve supply disruption risks, commercial credit risks, and market demand risks, etc.). As a result, risky nodes are prone to damage the interests of enterprises at various nodes on the supply chain network. At the same time, the inability to promptly discover risky supply chain nodes and adjust and optimize them will continue to damage enterprises on the supply chain network, making it impossible to ensure the stability and efficient operation of the supply chain. Summary of the invention

[0004] The present invention provides a real-time supply chain monitoring and optimization method and system based on artificial intelligence to solve the technical problem that the prior art is unable to identify and monitor risky supply chain enterprises, and then optimize the supply chain, resulting in the inability to ensure the stable and efficient operation of the supply chain.

[0005] In order to solve the above technical problems, an embodiment of the present invention provides a supply chain real-time monitoring and optimization method based on artificial intelligence, including: Acquire upstream and downstream enterprises in the supply chain, and set nodes for the upstream and downstream enterprises in the supply chain to obtain supply chain nodes; wherein the number of the supply chain nodes includes a plurality; The edges between supply chain nodes are regarded as supply chain links, and the supply chain links are adjusted to obtain a complete supply chain network; Acquire business data of each supply chain node in the supply chain network, monitor each supply chain node based on the business data, and identify the risk factor of each supply chain node; When there is a supply chain node whose risk coefficient is greater than a preset threshold, the supply chain node is regarded as a risk node, and the supply chain nodes in the supply chain network that have a supply chain link relationship with the risk node are regarded as adjustment nodes; Acquire information flow data, capital flow data and logistics data between each adjustment node and the risk node, and construct a data transmission target based on the information flow data, capital flow data and logistics data; According to the data transmission target, combined with the supply chain network, iterative optimization of the transmission and layout of the supply chain nodes is performed to generate a new transmission path for the risk node in the supply chain network, thereby achieving real-time monitoring and optimization of the supply chain.

[0006] As a preferred solution, the acquisition of upstream and downstream enterprises in the supply chain and setting nodes for the upstream and downstream enterprises in the supply chain to obtain supply chain nodes specifically includes: Obtain all upstream and downstream enterprises in the supply chain and obtain the nodes of corresponding suppliers, manufacturers, warehouses, logistics and retailers; According to the information relationship between the nodes of the supplier, manufacturer, warehouse, logistics and retailer, the nodes of the supplier, manufacturer, warehouse, logistics and retailer are set to obtain supplier nodes, manufacturer nodes, warehouse nodes, logistics nodes and retailer nodes; wherein the information relationship includes: information flow relationship, capital flow relationship and logistics relationship.

[0007] As a preferred solution, the edges between supply chain nodes are used as supply chain links, and the supply chain links are adjusted to obtain a complete supply chain network, which specifically includes: According to the information relationship between the nodes of the supplier, manufacturer, warehouse, logistics and retailer, each supply chain node is connected to obtain the edges between the supply chain nodes as the supply chain link; Obtain data throughput, transmission delay and load rate in the supply chain link between each supply chain node, and identify data information congestion points; The data information congestion point is taken as the adjustment target, and the optimal data transmission path is generated for each supply chain node in turn. The data transmission path of each supply chain node is connected as the adjusted supply chain link to obtain a complete supply chain network.

[0008] As a preferred solution, the acquiring of business data of each supply chain node in the supply chain network, monitoring each supply chain node according to the business data, and identifying the risk factor of each supply chain node specifically includes: Obtain business data about supplier nodes, manufacturer nodes, warehouse nodes, logistics nodes, and retailer nodes in the supply chain network; wherein the business data of the supplier nodes include inventory data, cost of goods sold data, order fulfillment rate, on-time delivery rate, and financial data; and the business data of the manufacturer nodes include inventory data, cost of goods sold data, order fulfillment rate, on-time delivery rate, and financial data. Input the supplier node and its inventory data, sales cost data, order fulfillment rate, on-time delivery rate and financial data into the risk detection model to obtain the risk coefficient of the supplier node; Input the manufacturer node and its production plan and actual progress data, equipment operation data, raw material inventory data and product quality inspection data into the risk detection model to obtain the risk coefficient of the supplier node; Input the warehouse node and its inventory level data, inventory turnover rate data, goods in and out of the warehouse data and warehouse space utilization rate data into the risk detection model to obtain the risk coefficient of the warehouse node; Input the logistics node and its logistics status data, logistics cost data, logistics timeliness data and logistics service quality data into the risk detection model to obtain the risk coefficient of the logistics node; Inputting the retailer node and its sales data, inventory data and customer feedback data into the risk detection model to obtain the risk coefficient of the retailer node; The risk detection model is generated by constructing and training based on the historical business data of the supplier node, manufacturer node, warehouse node, logistics node, and retailer node.

[0009] As a preferred solution, when there is a supply chain node whose risk coefficient is greater than a preset threshold, the supply chain node is used as a risk node, and the supply chain nodes in the supply chain network that have a supply chain link relationship with the risk node are used as adjustment nodes, specifically including: When there is a supply chain node whose risk coefficient is greater than a preset threshold, the supply chain node is regarded as a risk node; In the supply chain network, a supply chain node that has a supply chain link relationship with the corresponding risk node after the supply chain link is adjusted is obtained, and the supply chain node is used as an adjustment node.

[0010] As a preferred solution, the information flow data, capital flow data and logistics data between each adjustment node and the risk node are obtained, and a data transmission target is constructed according to the information flow data, capital flow data and logistics data, which specifically includes: Acquire information flow data, capital flow data and logistics data between each adjustment node and the risk node; wherein corresponding information flow data, capital flow data and logistics data exist in the supply chain link between each adjustment node and the risk node; According to the information flow data, identifying the supply chain nodes of the same type as the risk node, and calculating the information flow data of the supply chain links on the supply chain nodes of the same type to obtain the information flow delay loss between each adjustment node of the same type and the risk node; Calculate the capital flow risk and logistics cost of the supply chain links on the same type of supply chain nodes based on the capital flow data and logistics data; Based on the information flow delay loss, capital flow risk and logistics cost, the minimum comprehensive cost is constructed as the data transmission target.

[0011] As a preferred solution, the transmission and layout of supply chain nodes are iteratively optimized according to the data transmission target and combined with the supply chain network to generate a new transmission path for the risk node in the supply chain network, specifically including: Determine and initialize pheromones, and construct corresponding heuristic factors based on information flow data, capital flow data, and logistics data; According to the data transmission target, pheromones and heuristic factors, a transmission path is constructed, and the pheromones are updated according to the current transmission path until the maximum number of iterations is reached or the data transmission target is fitted, thereby obtaining a new transmission path for the risk node in the supply chain network.

[0012] Accordingly, the present invention also provides a supply chain real-time monitoring and optimization system based on artificial intelligence, comprising: a supply chain node module, a supply chain network module, a risk coefficient module, a risk identification module, a data transmission module and a transmission path module; The supply chain node module is used to obtain upstream and downstream enterprises in the supply chain, and set nodes for the upstream and downstream enterprises in the supply chain to obtain supply chain nodes; wherein the number of supply chain nodes includes several; The supply chain network module is used to use the edges between supply chain nodes as supply chain links and adjust the supply chain links to obtain a complete supply chain network; The risk coefficient module is used to obtain business data of each supply chain node in the supply chain network, monitor each supply chain node according to the business data, and identify the risk coefficient of each supply chain node; The risk identification module is used to, when there is a supply chain node whose risk coefficient is greater than a preset threshold, regard the supply chain node as a risk node, and regard the supply chain nodes in the supply chain network that have a supply chain link relationship with the risk node as adjustment nodes; The data transmission module is used to obtain information flow data, capital flow data and logistics data between each adjustment node and the risk node, and to construct a data transmission target based on the information flow data, capital flow data and logistics data; The transmission path module is used to iteratively optimize the transmission and layout of supply chain nodes according to the data transmission target and in combination with the supply chain network, and generate a new transmission path for the risk node in the supply chain network, thereby realizing real-time monitoring and optimization of the supply chain.

[0013] Correspondingly, the present invention also provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the artificial intelligence-based real-time supply chain monitoring and optimization method as described in any one of the above.

[0014] Accordingly, the present invention also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the artificial intelligence-based supply chain real-time monitoring and optimization methods described above.

[0015] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: The technical solution of the present invention acquires upstream and downstream enterprises in the supply chain, thereby constructing a supply chain network including supply chain nodes and supply chain links, and then acquires the business data of each supply chain node in the supply chain network, and then performs risk monitoring to obtain the risk coefficient of each supply chain node, so as to realize real-time monitoring of the supply chain nodes and avoid the inability to promptly and quickly identify supply chain nodes with risks.

[0016] Furthermore, when there is a supply chain node whose risk coefficient is greater than a preset threshold, the supply chain node in the supply chain network that has a supply chain link relationship with the risk node is used as an adjustment node, and the data transmission target is constructed through information flow data, capital flow data and logistics data, so as to finally realize the iterative optimization of the transmission and layout of the supply chain nodes, and generate a new transmission path for the risk node in the supply chain network, so as to avoid the impact of the risk node on the overall supply chain network. At the same time, by adjusting the relevant capital flow information, information flow data and logistics data of the risk node itself, the business relationship of the risk node is adjusted to the adjustment node, so as to optimize the link path of the supply chain and avoid the impact of the sudden interruption of the risk node on the overall supply chain. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 : A flow chart of a supply chain real-time monitoring and optimization method based on artificial intelligence provided by an embodiment of the present invention; Figure 2 : A structural diagram of a supply chain real-time monitoring and optimization system based on artificial intelligence provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Example

[0019] Please refer to Figure 1 , a supply chain real-time monitoring and optimization method based on artificial intelligence provided by an embodiment of the present invention, comprising the following steps S101-S106: Step S101: Acquire upstream and downstream enterprises in the supply chain, and set nodes for the upstream and downstream enterprises in the supply chain to obtain supply chain nodes; wherein the number of the supply chain nodes includes several.

[0020] As a preferred solution, the acquisition of upstream and downstream enterprises in the supply chain and setting nodes for the upstream and downstream enterprises in the supply chain to obtain supply chain nodes specifically includes: Obtain all upstream and downstream enterprises in the supply chain and obtain the nodes of corresponding suppliers, manufacturers, warehouses, logistics and retailers; According to the information relationship between the nodes of the supplier, manufacturer, warehouse, logistics and retailer, the nodes of the supplier, manufacturer, warehouse, logistics and retailer are set to obtain supplier nodes, manufacturer nodes, warehouse nodes, logistics nodes and retailer nodes; wherein the information relationship includes: information flow relationship, capital flow relationship and logistics relationship.

[0021] In this embodiment, all enterprise types upstream and downstream of the supply chain include suppliers, manufacturers, warehouses, logistics and retailers, where the number of suppliers, manufacturers, warehouses, logistics and retailers may be greater than or equal to one.

[0022] In this embodiment, the information relationship between nodes includes information flow relationship, capital flow relationship and logistics relationship. Among them, information flow is the process of commodity and transaction information, and the direction is a two-way flow between suppliers and customers. Capital flow is the process of money circulation, and the direction is from customers to suppliers via retailers, distributors, etc. Logistics is the flow process of materials (commodities), and the direction is from suppliers to customers via distributors, retailers, etc. Through the above information relationships, the nodes of suppliers, manufacturers, warehouses, logistics and retailers are set to obtain supplier nodes, manufacturer nodes, warehouse nodes, logistics nodes and retailer nodes. Step S102: taking the edges between supply chain nodes as supply chain links, and adjusting the supply chain links to obtain a complete supply chain network.

[0023] As a preferred solution, the edges between supply chain nodes are used as supply chain links, and the supply chain links are adjusted to obtain a complete supply chain network, which specifically includes: According to the information relationship between the nodes of the supplier, manufacturer, warehouse, logistics and retailer, each supply chain node is connected to obtain the edges between the supply chain nodes as the supply chain link; Obtain data throughput, transmission delay and load rate in the supply chain link between each supply chain node, and identify data information congestion points; The data information congestion point is taken as the adjustment target, and the optimal data transmission path is generated for each supply chain node in turn. The data transmission path of each supply chain node is connected as the adjusted supply chain link to obtain a complete supply chain network.

[0024] In this embodiment, in the supply chain nodes, the connection relationship between the nodes can be represented by a graph theory model. Through the information flow, capital flow and logistics relationship between these nodes, the nodes are connected to obtain the edges between the supply chain nodes as the supply chain links.

[0025] In this embodiment, in order to ensure the efficient operation of the supply chain, it is necessary to monitor and analyze the data transmission performance in the supply chain link. By real-time monitoring of these indicators, data information congestion points can be identified. Preferably, big data technology can be used to analyze the data in the link in real time to identify links with low throughput, high transmission delay, and high load rate. After identifying the data information congestion point, it is necessary to optimize the data transmission path of the supply chain node. For each node, a path optimization algorithm (such as Dijkstra algorithm, Floyd algorithm, etc., used to generate the shortest path from one node to other nodes) is used to generate the optimal path from the node to other nodes. Among them, the path should take into account factors such as data throughput, transmission delay and load rate to ensure the efficiency and reliability of data transmission; then, the optimal data transmission path of each node is connected to form an adjusted supply chain link, so that a complete and optimized supply chain network can be constructed.

[0026] Step S103: Acquire the business data of each supply chain node in the supply chain network, monitor each supply chain node according to the business data, and identify the risk coefficient of each supply chain node.

[0027] As a preferred solution, the acquiring of business data of each supply chain node in the supply chain network, monitoring each supply chain node according to the business data, and identifying the risk factor of each supply chain node specifically includes: Obtain business data about supplier nodes, manufacturer nodes, warehouse nodes, logistics nodes, and retailer nodes in the supply chain network; wherein the business data of the supplier nodes include inventory data, cost of goods sold data, order fulfillment rate, on-time delivery rate, and financial data; and the business data of the manufacturer nodes include inventory data, cost of goods sold data, order fulfillment rate, on-time delivery rate, and financial data. Input the supplier node and its inventory data, sales cost data, order fulfillment rate, on-time delivery rate and financial data into the risk detection model to obtain the risk coefficient of the supplier node; Input the manufacturer node and its production plan and actual progress data, equipment operation data, raw material inventory data and product quality inspection data into the risk detection model to obtain the risk coefficient of the supplier node; Input the warehouse node and its inventory level data, inventory turnover rate data, goods in and out of the warehouse data and warehouse space utilization rate data into the risk detection model to obtain the risk coefficient of the warehouse node; Input the logistics node and its logistics status data, logistics cost data, logistics timeliness data and logistics service quality data into the risk detection model to obtain the risk coefficient of the logistics node; Inputting the retailer node and its sales data, inventory data and customer feedback data into the risk detection model to obtain the risk coefficient of the retailer node; The risk detection model is generated by constructing and training based on the historical business data of the supplier node, manufacturer node, warehouse node, logistics node, and retailer node.

[0028] In this embodiment, the supplier node includes: inventory data, sales cost data, supplier performance data and supplier financial data. Among them, inventory data reflects the total amount of goods or raw materials accumulated by the enterprise in the supply chain. Too high or too low inventory levels may cause risks. The sales cost data is the direct cost incurred by the enterprise in the production process. By analyzing the changes in sales cost, the impact of supplier price fluctuations on enterprise costs can be evaluated. Supplier performance data includes on-time delivery rate, order fulfillment rate, etc., to evaluate the reliability and delivery ability of suppliers. Supplier financial data is the supplier's financial statements, credit ratings, etc., to understand the financial health of suppliers and prevent supply interruptions caused by supplier financial crises.

[0029] In this embodiment, the manufacturer node includes: production plan and actual progress data, equipment operation data, raw material inventory data and product quality inspection data. Among them, the production plan and actual progress data includes comparing the production plan and the actual production progress, timely discovering production delays and other problems, and evaluating the execution risk of the production plan. The equipment operation data includes the equipment startup time, number of failures, maintenance time, etc., evaluating the equipment's operating efficiency and reliability, and preventing production interruptions caused by equipment failures. The raw material inventory data includes mastering the inventory level and turnover rate of raw materials, avoiding inventory backlogs or out-of-stock, and optimizing inventory management. The product quality inspection data is the data for testing product quality during the production process, timely discovering and solving quality problems, and ensuring that the delivered products meet the standards.

[0030] In this embodiment, the warehouse node includes inventory level data, inventory turnover data, goods in and out data, and warehouse space utilization data; Inventory level data: real-time monitoring of inventory quantity, combined with indicators such as safety stock and economic order quantity, reasonable control of inventory, and reduction of inventory costs. Among them, inventory turnover data reflects the liquidity and sales of inventory. A high turnover rate indicates good inventory management, while a low turnover rate may mean an inventory backlog or insufficient demand. Goods in and out data includes recording the time, quantity, batch, and other information of goods in and out of the warehouse, which is convenient for tracing and managing inventory and improving warehousing operation efficiency. Warehouse space utilization data is used to evaluate the space usage of the warehouse, optimize the warehouse layout, and improve the storage capacity of the warehouse.

[0031] In this embodiment, the retailer node includes sales data, inventory data, and customer feedback data. Among them, sales data includes sales volume, sales growth rate, etc., which reflects the market demand and sales of products and provides a basis for production planning and inventory management. Inventory data includes understanding the inventory level and turnover rate of retailers to avoid out-of-stock or backlogs and ensure the timeliness and stability of product supply. Customer feedback data is to collect customer feedback on product quality, service, etc., to handle customer complaints and suggestions in a timely manner, and to improve customer satisfaction and loyalty.

[0032] In this embodiment, the logistics node includes logistics status data, logistics cost data, logistics timeliness data and logistics service quality data. The logistics status data includes real-time presentation of the location, transportation status, estimated arrival time and other information of the goods, realizing logistics visualization and facilitating timely adjustment of logistics plans. The logistics cost data includes transportation cost, warehousing cost, loading and unloading cost, etc. By analyzing the cost data, the logistics resource allocation is optimized and the logistics cost is reduced. The logistics timeliness data includes transportation time, delivery time, goods in transit time, etc., which evaluates the efficiency of logistics services, improves the logistics response speed, and meets customers' requirements for timeliness. The logistics service quality data includes the damage rate, loss rate, customer complaint rate, etc. of goods, reflecting the quality level of logistics services, timely discovering and solving problems in logistics services, and improving customer experience.

[0033] In this embodiment, the risk detection model is constructed and trained based on the historical business data of supplier nodes, manufacturer nodes, warehouse nodes, logistics nodes, and retailer nodes. By collecting the historical business data of suppliers, manufacturers, warehouses, logistics, and retailers, preliminary data cleaning is performed, including filling missing values, processing duplicate records, converting data types, etc., and features valuable for risk prediction are extracted from the original data, and a feature set is constructed. For example, key inventory management indicators such as inventory turnover rate, inventory holding days, inventory out-of-stock rate, replenishment cycle, and safety stock level are calculated. Select appropriate machine learning algorithms, such as random forests, gradient boosting trees, etc., to train the risk detection model, use historical business data to train the model, and ensure that the model can accurately predict the risk coefficient of nodes such as retailer nodes, thereby realizing risk monitoring of each node.

[0034] Step S104: When there is a supply chain node whose risk coefficient is greater than a preset threshold, the supply chain node is used as a risk node, and the supply chain nodes in the supply chain network that have a supply chain link relationship with the risk node are used as adjustment nodes.

[0035] As a preferred solution, when there is a supply chain node whose risk coefficient is greater than a preset threshold, the supply chain node is used as a risk node, and the supply chain nodes in the supply chain network that have a supply chain link relationship with the risk node are used as adjustment nodes, specifically including: When there is a supply chain node whose risk coefficient is greater than a preset threshold, the supply chain node is regarded as a risk node; In the supply chain network, a supply chain node that has a supply chain link relationship with the corresponding risk node after the supply chain link is adjusted is obtained, and the supply chain node is used as an adjustment node.

[0036] In the function of this embodiment, when the risk coefficient of a supply chain node is greater than a preset threshold, the supply chain node is regarded as a risk node, wherein the preset threshold can be set according to the actual situation.

[0037] Step S105: Acquire the information flow data, capital flow data and logistics data between each adjustment node and the risk node, and construct a data transmission target based on the information flow data, capital flow data and logistics data.

[0038] As a preferred solution, the information flow data, capital flow data and logistics data between each adjustment node and the risk node are obtained, and a data transmission target is constructed according to the information flow data, capital flow data and logistics data, which specifically includes: Acquire information flow data, capital flow data and logistics data between each adjustment node and the risk node; wherein corresponding information flow data, capital flow data and logistics data exist in the supply chain link between each adjustment node and the risk node; According to the information flow data, identifying the supply chain nodes of the same type as the risk node, and calculating the information flow data of the supply chain links on the supply chain nodes of the same type to obtain the information flow delay loss between each adjustment node of the same type and the risk node; Calculate the capital flow risk and logistics cost of the supply chain links on the same type of supply chain nodes based on the capital flow data and logistics data; Based on the information flow delay loss, capital flow risk and logistics cost, the minimum comprehensive cost is constructed as the data transmission target.

[0039] In this embodiment, by obtaining the information flow data, capital flow data and logistics data between each adjustment node and the risk node, the corresponding information flow delay loss, capital flow risk and logistics cost are calculated, and then the minimum comprehensive cost is constructed as the data transmission target, so that the risk nodes can be replaced at the lowest cost when optimizing the supply chain layout.

[0040] In this embodiment, supply chain nodes of the same type as the risk node are identified through information flow data, that is, when the risk node is a supplier node, the adjustment node is identified as the supplier's node, so that the related business of the risk node can be transferred to the adjustment node, thereby achieving the minimum negative impact caused by the supply chain network layout and node adjustment in a short time.

[0041] In this embodiment, the comprehensive cost to be minimized includes: logistics cost, capital risk cost and information delay cost, while maximizing network robustness, and its expression is:

[0042] in, is the logistics cost, which is calculated through transportation and inventory data. The capital flow risk is calculated by the default probability transaction amount. is the loss caused by information flow delay, α, β, γ are weight coefficients set by the enterprise strategy.

[0043] Step S106: According to the data transmission target, combined with the supply chain network, iterative optimization of the transmission and layout of the supply chain nodes is performed to generate a new transmission path for the risk node in the supply chain network, thereby achieving real-time monitoring and optimization of the supply chain.

[0044] As a preferred solution, the transmission and layout of supply chain nodes are iteratively optimized according to the data transmission target and combined with the supply chain network to generate a new transmission path for the risk node in the supply chain network, specifically including: Determine and initialize pheromones, and construct corresponding heuristic factors based on information flow data, capital flow data, and logistics data; According to the data transmission target, pheromones and heuristic factors, a transmission path is constructed, and the pheromones are updated according to the current transmission path until the maximum number of iterations is reached or the data transmission target is fitted, thereby obtaining a new transmission path for the risk node in the supply chain network.

[0045] In this embodiment, the pheromone is represented as the pheromone concentration of each edge (link) reflecting the historical optimization effect of the path, and the initial pheromone τ0 = 1 / initial path cost. The heuristic factors include logistics heuristic, capital flow heuristic and information flow heuristic.

[0046] Among them, the expression of logistics heuristic is: ; The expression of the capital flow heuristic is: ; The expression of information flow heuristic is: .

[0047] Through the importance of pheromone and heuristic factor, the state transition probability is calculated, and then iterative initialization is performed. Starting from the risk node, alternative paths are explored, and the next node is selected according to the state transition probability to avoid high-risk links, and then the pheromone update is performed. The pheromone update includes: local update and global update. Among them, the local update is to reduce the current edge pheromone after each move to avoid premature convergence. The global update is to increase the pheromone to the optimal path after the iteration is completed. When the maximum number of iterations is reached or the cost decreases and tends to be stable, the iteration is terminated, the optimal supply chain path is output, and the nodes on the supply chain path are determined, so as to adjust the relevant business of the risk node to the adjustment node, so as to optimize the supply chain network and layout with risk nodes.

[0048] Implementing the above embodiments has the following effects: The technical solution of the present invention acquires upstream and downstream enterprises in the supply chain, thereby constructing a supply chain network including supply chain nodes and supply chain links, and then acquires the business data of each supply chain node in the supply chain network, and then performs risk monitoring to obtain the risk coefficient of each supply chain node, so as to realize real-time monitoring of the supply chain nodes and avoid the inability to promptly and quickly identify supply chain nodes with risks.

[0049] Furthermore, when there is a supply chain node whose risk coefficient is greater than a preset threshold, the supply chain node in the supply chain network that has a supply chain link relationship with the risk node is used as an adjustment node, and the data transmission target is constructed through information flow data, capital flow data and logistics data, so as to finally realize the iterative optimization of the transmission and layout of the supply chain nodes, and generate a new transmission path for the risk node in the supply chain network, so as to avoid the impact of the risk node on the overall supply chain network. At the same time, by adjusting the relevant capital flow information, information flow data and logistics data of the risk node itself, the business relationship of the risk node is adjusted to the adjustment node, so as to optimize the link path of the supply chain and avoid the impact of the sudden interruption of the risk node on the overall supply chain. Example

[0050] See also Figure 2 , which is a supply chain real-time monitoring and optimization system based on artificial intelligence provided by the present invention, including: a supply chain node module 201, a supply chain network module 202, a risk coefficient module 203, a risk identification module 204, a data transmission module 205 and a transmission path module 206; The supply chain node module 201 is used to obtain upstream and downstream enterprises in the supply chain, and set nodes for the upstream and downstream enterprises in the supply chain to obtain supply chain nodes; wherein the number of supply chain nodes includes several; The supply chain network module 202 is used to use the edges between supply chain nodes as supply chain links and adjust the supply chain links to obtain a complete supply chain network; The risk coefficient module 203 is used to obtain business data of each supply chain node in the supply chain network, monitor each supply chain node according to the business data, and identify the risk coefficient of each supply chain node; The risk identification module 204 is used to, when there is a supply chain node whose risk coefficient is greater than a preset threshold, regard the supply chain node as a risk node, and regard the supply chain nodes in the supply chain network that have a supply chain link relationship with the risk node as adjustment nodes; The data transmission module 205 is used to obtain the information flow data, capital flow data and logistics data between each adjustment node and the risk node, and to construct a data transmission target according to the information flow data, capital flow data and logistics data; The transmission path module 206 is used to iteratively optimize the transmission and layout of supply chain nodes according to the data transmission target and in combination with the supply chain network, and generate a new transmission path for the risk node in the supply chain network, thereby realizing real-time monitoring and optimization of the supply chain.

[0051] As a preferred solution, the acquisition of upstream and downstream enterprises in the supply chain and setting nodes for the upstream and downstream enterprises in the supply chain to obtain supply chain nodes specifically includes: Obtain all upstream and downstream enterprises in the supply chain and obtain the nodes of corresponding suppliers, manufacturers, warehouses, logistics and retailers; According to the information relationship between the nodes of the supplier, manufacturer, warehouse, logistics and retailer, the nodes of the supplier, manufacturer, warehouse, logistics and retailer are set to obtain supplier nodes, manufacturer nodes, warehouse nodes, logistics nodes and retailer nodes; wherein the information relationship includes: information flow relationship, capital flow relationship and logistics relationship.

[0052] As a preferred solution, the edges between supply chain nodes are used as supply chain links, and the supply chain links are adjusted to obtain a complete supply chain network, which specifically includes: According to the information relationship between the nodes of the supplier, manufacturer, warehouse, logistics and retailer, each supply chain node is connected to obtain the edges between the supply chain nodes as the supply chain link; Obtain data throughput, transmission delay and load rate in the supply chain link between each supply chain node, and identify data information congestion points; The data information congestion point is taken as the adjustment target, and the optimal data transmission path is generated for each supply chain node in turn. The data transmission path of each supply chain node is connected as the adjusted supply chain link to obtain a complete supply chain network.

[0053] As a preferred solution, the acquiring of business data of each supply chain node in the supply chain network, monitoring each supply chain node according to the business data, and identifying the risk factor of each supply chain node specifically includes: Obtain business data about supplier nodes, manufacturer nodes, warehouse nodes, logistics nodes, and retailer nodes in the supply chain network; wherein the business data of the supplier nodes include inventory data, cost of goods sold data, order fulfillment rate, on-time delivery rate, and financial data; and the business data of the manufacturer nodes include inventory data, cost of goods sold data, order fulfillment rate, on-time delivery rate, and financial data. Input the supplier node and its inventory data, sales cost data, order fulfillment rate, on-time delivery rate and financial data into the risk detection model to obtain the risk coefficient of the supplier node; Input the manufacturer node and its production plan and actual progress data, equipment operation data, raw material inventory data and product quality inspection data into the risk detection model to obtain the risk coefficient of the supplier node; Input the warehouse node and its inventory level data, inventory turnover rate data, goods in and out of the warehouse data and warehouse space utilization rate data into the risk detection model to obtain the risk coefficient of the warehouse node; Input the logistics node and its logistics status data, logistics cost data, logistics timeliness data and logistics service quality data into the risk detection model to obtain the risk coefficient of the logistics node; Inputting the retailer node and its sales data, inventory data and customer feedback data into the risk detection model to obtain the risk coefficient of the retailer node; The risk detection model is generated by constructing and training based on the historical business data of the supplier node, manufacturer node, warehouse node, logistics node, and retailer node.

[0054] As a preferred solution, when there is a supply chain node whose risk coefficient is greater than a preset threshold, the supply chain node is used as a risk node, and the supply chain nodes in the supply chain network that have a supply chain link relationship with the risk node are used as adjustment nodes, specifically including: When there is a supply chain node whose risk coefficient is greater than a preset threshold, the supply chain node is regarded as a risk node; In the supply chain network, a supply chain node that has a supply chain link relationship with the corresponding risk node after the supply chain link is adjusted is obtained, and the supply chain node is used as an adjustment node.

[0055] As a preferred solution, the information flow data, capital flow data and logistics data between each adjustment node and the risk node are obtained, and a data transmission target is constructed according to the information flow data, capital flow data and logistics data, which specifically includes: Acquire information flow data, capital flow data and logistics data between each adjustment node and the risk node; wherein corresponding information flow data, capital flow data and logistics data exist in the supply chain link between each adjustment node and the risk node; According to the information flow data, identifying the supply chain nodes of the same type as the risk node, and calculating the information flow data of the supply chain links on the supply chain nodes of the same type to obtain the information flow delay loss between each adjustment node of the same type and the risk node; Calculate the capital flow risk and logistics cost of the supply chain links on the same type of supply chain nodes based on the capital flow data and logistics data; Based on the information flow delay loss, capital flow risk and logistics cost, the minimum comprehensive cost is constructed as the data transmission target.

[0056] As a preferred solution, the transmission and layout of supply chain nodes are iteratively optimized according to the data transmission target and combined with the supply chain network to generate a new transmission path for the risk node in the supply chain network, specifically including: Determine and initialize pheromones, and construct corresponding heuristic factors based on information flow data, capital flow data, and logistics data; According to the data transmission target, pheromones and heuristic factors, a transmission path is constructed, and the pheromones are updated according to the current transmission path until the maximum number of iterations is reached or the data transmission target is fitted, thereby obtaining a new transmission path for the risk node in the supply chain network.

[0057] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0058] Implementing the above embodiments has the following effects: The technical solution of the present invention acquires upstream and downstream enterprises in the supply chain, thereby constructing a supply chain network including supply chain nodes and supply chain links, and then acquires the business data of each supply chain node in the supply chain network, and then performs risk monitoring to obtain the risk coefficient of each supply chain node, so as to realize real-time monitoring of the supply chain nodes and avoid the inability to promptly and quickly identify supply chain nodes with risks.

[0059] Furthermore, when there is a supply chain node whose risk coefficient is greater than a preset threshold, the supply chain node in the supply chain network that has a supply chain link relationship with the risk node is used as an adjustment node, and the data transmission target is constructed through information flow data, capital flow data and logistics data, so as to finally realize the iterative optimization of the transmission and layout of the supply chain nodes, and generate a new transmission path for the risk node in the supply chain network, so as to avoid the impact of the risk node on the overall supply chain network. At the same time, by adjusting the relevant capital flow information, information flow data and logistics data of the risk node itself, the business relationship of the risk node is adjusted to the adjustment node, so as to optimize the link path of the supply chain and avoid the impact of the sudden interruption of the risk node on the overall supply chain. Example

[0060] Correspondingly, the present invention also provides a terminal device, comprising: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, it implements the artificial intelligence-based real-time supply chain monitoring and optimization method as described in any one of the above embodiments.

[0061] The terminal device of this embodiment includes: a processor, a memory, and a computer program and a computer instruction stored in the memory and executable on the processor. When the processor executes the computer program, each step in the above-mentioned embodiment 1 is implemented, for example: Figure 1 Alternatively, when the processor executes the computer program, the functions of each module / unit in the above device embodiment, such as the risk identification module 204, are implemented.

[0062] Exemplarily, the computer program may be divided into one or more modules / units, and the one or more modules / units are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program in the terminal device. For example, the risk identification module 204 is used to treat a supply chain node as a risk node when there is a supply chain node whose risk coefficient is greater than a preset threshold, and to treat the supply chain node in the supply chain network that has a supply chain link relationship with the risk node as an adjustment node.

[0063] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the schematic diagram is merely an example of a terminal device and does not constitute a limitation on the terminal device. The terminal device may include more or fewer components than shown in the diagram, or may combine certain components, or different components. For example, the terminal device may also include an input / output device, a network access device, a bus, etc.

[0064] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.

[0065] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the terminal device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function, etc.; the data storage area can store data created according to the use of the mobile terminal, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0066] Wherein, if the module / unit integrated in the terminal device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals. Example

[0067] Accordingly, the present invention also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the artificial intelligence-based real-time supply chain monitoring and optimization method as described in any one of the above embodiments.

[0068] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A supply chain real-time monitoring and optimization method based on artificial intelligence, characterized in that: include: Acquire upstream and downstream enterprises in the supply chain, and set nodes for the upstream and downstream enterprises in the supply chain to obtain supply chain nodes; wherein the number of the supply chain nodes includes a plurality; The edges between supply chain nodes are regarded as supply chain links, and the supply chain links are adjusted to obtain a complete supply chain network; Acquire business data of each supply chain node in the supply chain network, monitor each supply chain node based on the business data, and identify the risk factor of each supply chain node; When there is a supply chain node whose risk coefficient is greater than a preset threshold, the supply chain node is regarded as a risk node, and the supply chain nodes in the supply chain network that have a supply chain link relationship with the risk node are regarded as adjustment nodes; Acquire information flow data, capital flow data and logistics data between each adjustment node and the risk node, and construct a data transmission target based on the information flow data, capital flow data and logistics data; According to the data transmission target, combined with the supply chain network, iterative optimization of the transmission and layout of the supply chain nodes is performed to generate a new transmission path for the risk node in the supply chain network, thereby achieving real-time monitoring and optimization of the supply chain.

2. The method for real-time monitoring and optimization of a supply chain based on artificial intelligence as claimed in claim 1, characterized in that: The obtaining of upstream and downstream enterprises in the supply chain and setting nodes for the upstream and downstream enterprises in the supply chain to obtain supply chain nodes specifically includes: Obtain all upstream and downstream enterprises in the supply chain and obtain the nodes of corresponding suppliers, manufacturers, warehouses, logistics and retailers; According to the information relationship between the nodes of the supplier, manufacturer, warehouse, logistics and retailer, the nodes of the supplier, manufacturer, warehouse, logistics and retailer are set to obtain supplier nodes, manufacturer nodes, warehouse nodes, logistics nodes and retailer nodes; wherein the information relationship includes: information flow relationship, capital flow relationship and logistics relationship.

3. The method for real-time monitoring and optimization of a supply chain based on artificial intelligence as claimed in claim 2, characterized in that: The edges between supply chain nodes are used as supply chain links, and the supply chain links are adjusted to obtain a complete supply chain network, which specifically includes: According to the information relationship between the nodes of the supplier, manufacturer, warehouse, logistics and retailer, each supply chain node is connected to obtain the edges between the supply chain nodes as the supply chain link; Obtain data throughput, transmission delay and load rate in the supply chain link between each supply chain node, and identify data information congestion points; The data information congestion point is taken as the adjustment target, and the optimal data transmission path is generated for each supply chain node in turn. The data transmission path of each supply chain node is connected as the adjusted supply chain link to obtain a complete supply chain network.

4. The method for real-time monitoring and optimization of a supply chain based on artificial intelligence as claimed in claim 3, characterized in that: The obtaining of business data of each supply chain node in the supply chain network, monitoring each supply chain node according to the business data, and identifying the risk factor of each supply chain node specifically includes: Obtain business data about supplier nodes, manufacturer nodes, warehouse nodes, logistics nodes, and retailer nodes in the supply chain network; wherein the business data of the supplier nodes include inventory data, cost of goods sold data, order fulfillment rate, on-time delivery rate, and financial data; and the business data of the manufacturer nodes include inventory data, cost of goods sold data, order fulfillment rate, on-time delivery rate, and financial data. Input the supplier node and its inventory data, sales cost data, order fulfillment rate, on-time delivery rate and financial data into the risk detection model to obtain the risk coefficient of the supplier node; Input the manufacturer node and its production plan and actual progress data, equipment operation data, raw material inventory data and product quality inspection data into the risk detection model to obtain the risk coefficient of the supplier node; Input the warehouse node and its inventory level data, inventory turnover rate data, goods in and out of the warehouse data and warehouse space utilization rate data into the risk detection model to obtain the risk coefficient of the warehouse node; Input the logistics node and its logistics status data, logistics cost data, logistics timeliness data and logistics service quality data into the risk detection model to obtain the risk coefficient of the logistics node; Inputting the retailer node and its sales data, inventory data and customer feedback data into the risk detection model to obtain the risk coefficient of the retailer node; The risk detection model is generated by constructing and training based on the historical business data of the supplier node, manufacturer node, warehouse node, logistics node, and retailer node.

5. The method for real-time monitoring and optimization of a supply chain based on artificial intelligence as claimed in claim 4, characterized in that: When there is a supply chain node whose risk coefficient is greater than a preset threshold, the supply chain node is used as a risk node, and the supply chain nodes in the supply chain network that have a supply chain link relationship with the risk node are used as adjustment nodes, specifically including: When there is a supply chain node whose risk coefficient is greater than a preset threshold, the supply chain node is regarded as a risk node; In the supply chain network, a supply chain node that has a supply chain link relationship with the corresponding risk node after the supply chain link is adjusted is obtained, and the supply chain node is used as an adjustment node.

6. The method for real-time monitoring and optimization of a supply chain based on artificial intelligence as claimed in claim 5, characterized in that: The acquiring of information flow data, capital flow data and logistics data between each adjustment node and the risk node, and constructing a data transmission target according to the information flow data, capital flow data and logistics data, specifically includes: Acquire information flow data, capital flow data and logistics data between each adjustment node and the risk node; wherein corresponding information flow data, capital flow data and logistics data exist in the supply chain link between each adjustment node and the risk node; According to the information flow data, identifying the supply chain nodes of the same type as the risk node, and calculating the information flow data of the supply chain links on the supply chain nodes of the same type to obtain the information flow delay loss between each adjustment node of the same type and the risk node; Calculate the capital flow risk and logistics cost of the supply chain links on the same type of supply chain nodes based on the capital flow data and logistics data; Based on the information flow delay loss, capital flow risk and logistics cost, the minimum comprehensive cost is constructed as the data transmission target.

7. The method for real-time monitoring and optimization of a supply chain based on artificial intelligence as claimed in claim 6, characterized in that: The iterative optimization of the transmission and layout of the supply chain nodes is performed according to the data transmission target and in combination with the supply chain network, so as to generate a new transmission path of the risk node in the supply chain network, specifically including: Determine and initialize pheromones, and construct corresponding heuristic factors based on information flow data, capital flow data, and logistics data; According to the data transmission target, pheromones and heuristic factors, a transmission path is constructed, and the pheromones are updated according to the current transmission path until the maximum number of iterations is reached or the data transmission target is fitted, thereby obtaining a new transmission path for the risk node in the supply chain network.

8. A supply chain real-time monitoring and optimization system based on artificial intelligence, characterized in that: include: Supply chain node module, supply chain network module, risk coefficient module, risk identification module, data transmission module and transmission path module; The supply chain node module is used to obtain upstream and downstream enterprises in the supply chain, and set nodes for the upstream and downstream enterprises in the supply chain to obtain supply chain nodes; wherein the number of supply chain nodes includes several; The supply chain network module is used to use the edges between supply chain nodes as supply chain links and adjust the supply chain links to obtain a complete supply chain network; The risk coefficient module is used to obtain business data of each supply chain node in the supply chain network, monitor each supply chain node according to the business data, and identify the risk coefficient of each supply chain node; The risk identification module is used to, when there is a supply chain node whose risk coefficient is greater than a preset threshold, regard the supply chain node as a risk node, and regard the supply chain nodes in the supply chain network that have a supply chain link relationship with the risk node as adjustment nodes; The data transmission module is used to obtain information flow data, capital flow data and logistics data between each adjustment node and the risk node, and to construct a data transmission target based on the information flow data, capital flow data and logistics data; The transmission path module is used to iteratively optimize the transmission and layout of supply chain nodes according to the data transmission target and in combination with the supply chain network, and generate a new transmission path for the risk node in the supply chain network, thereby realizing real-time monitoring and optimization of the supply chain.

9. A terminal device, characterized in that: It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the real-time monitoring and optimization method of the supply chain based on artificial intelligence as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein, when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the artificial intelligence-based real-time supply chain monitoring and optimization method as described in any one of claims 1 to 7.

Images