A scheduling method and system for coordinated distribution of processed raw materials and finished products

Abstract

The present invention relates to the technical field of logistics and distribution, and provides a scheduling method and system for the coordinated distribution of processed raw materials and finished products, comprising: collecting multi-dimensional data from the distribution of processed raw materials and finished products; the multi-dimensional data includes logistics information and node information; decomposing the logistics information to obtain logistics feature information; the logistics feature information includes trend feature information, period feature information and random feature information; constructing a logistics matrix containing logistics nodes based on the node information, and calculating the node feature information; the node feature information includes the average number of connections and the degree of aggregation; based on the logistics feature information and the node feature information, designing a scheduling strategy to perform coordinated distribution scheduling for processed raw materials and finished products; so as to improve the utilization rate of logistics resources, enhance the ability to respond to market demand, effectively reduce logistics costs, improve the overall efficiency and benefits of logistics distribution, and provide a more competitive solution for the field of logistics and distribution.

Description

Technical Field

[0001] The present invention relates to the field of logistics distribution technology, and in particular to a scheduling method and system for the coordinated distribution of processed raw materials and finished products. Background Art

[0002] With the booming e-commerce and manufacturing industries, logistics and distribution, as a critical link connecting production and consumption, have a crucial impact on business competitiveness and customer satisfaction. In traditional logistics and distribution models, the distribution of raw materials and finished products is often separated, planned and executed independently. Companies typically manage the procurement and transportation of raw materials and the sales and distribution of finished products separately, employing relatively simple inventory management strategies and fixed transportation routes to meet basic production and sales needs. However, this traditional model has several significant drawbacks: Low resource utilization: Due to a lack of coordinated planning, the transport of raw materials and finished products has a high idle rate, and storage space is difficult to allocate rationally, resulting in significant waste of logistics resources and high transportation and storage costs. Slow market responsiveness: Independent distribution models fail to fully and timely account for dynamic market demand changes, easily leading to inventory backlogs or shortages of raw materials and finished products. Lack of deep data drive: The traditional model only processes logistics information superficially, focusing only on basic data such as transportation volume and inventory quantity. It fails to deeply explore the trends, cycles and other characteristics in logistics information, as well as the connection relationship and aggregation degree of logistics nodes, making it difficult to achieve accurate optimization of distribution scheduling.

[0003] In view of this, and to overcome the shortcomings of the above-mentioned traditional logistics distribution model, this application proposes a scheduling method and system for the coordinated distribution of processed raw materials and finished products. By collecting multi-dimensional data, deeply decomposing logistics characteristic information, constructing a logistics matrix to analyze node characteristics, and then designing a scientific scheduling strategy, the coordinated distribution scheduling of processed raw materials and finished products can be achieved. This solution aims to improve the utilization rate of logistics resources, enhance the ability to respond to market demand, optimize distribution scheduling through in-depth data analysis, effectively reduce logistics costs, and improve the overall efficiency and benefits of logistics distribution, providing a more competitive solution for the logistics distribution field. Summary of the Invention

[0004] The object of the present invention is to provide a scheduling method for the coordinated distribution of processed raw materials and finished products, comprising: collecting multi-dimensional data in the distribution of processed raw materials and finished products; the multi-dimensional data includes logistics information and node information; decomposing the logistics information to obtain logistics characteristic information; the logistics characteristic information includes trend characteristic information, periodic characteristic information and random characteristic information; constructing a logistics matrix containing logistics nodes based on the node information, and calculating the node characteristic information; the node characteristic information includes the average number of connections and the degree of aggregation; based on the logistics characteristic information and the node characteristic information, designing a scheduling strategy to perform coordinated distribution scheduling for processed raw materials and finished products.

[0005] Furthermore, a logistics matrix including logistics nodes is constructed based on the node information, including: based on the node information, the nodes in the logistics network for distributing processed raw materials and finished products are classified to obtain multiple types of logistics nodes; based on historical transportation routes, the connection relationship between logistics nodes is determined; based on the logistics nodes and their connection relationship, an adjacency matrix is created, and the adjacency matrix is used as the logistics matrix; the adjacency matrix is a square matrix, the order of which is the total number of logistics nodes, and the matrix elements represent the connection status between logistics nodes.

[0006] Furthermore, the node feature information is calculated, including: determining the node degree of each logistics node; the node degree represents the number of other logistics nodes directly connected to the logistics node; averaging the node degrees of all logistics nodes to obtain the average number of connections; determining the edge degree between logistics nodes; the edge degree represents the number of edges with connection relationships between other logistics nodes connected to the logistics node; calculating the clustering coefficient of the logistics node based on the average number of connections and the edge degree; averaging the clustering coefficients of all logistics nodes to obtain the degree of aggregation.

[0007] Furthermore, based on the logistics characteristic information and the node characteristic information, a scheduling strategy is designed to coordinate the distribution scheduling of processed raw materials and finished products, including: constructing a scheduling objective function based on the node characteristic information and the distribution volume; constructing scheduling constraints based on the logistics characteristic information; solving the scheduling objective function to obtain the processing raw material inventory and the finished product inventory of the logistics node; optimizing the scheduling objective function through a scheduling optimization algorithm to obtain an optimized distribution volume; adjusting the optimized distribution volume based on the random characteristic information to obtain an adjusted distribution volume; bringing the adjusted distribution volume into the scheduling objective function to obtain a new scheduling objective function; repeating the solving and optimization operations of the scheduling objective function until the change values of the processing raw material inventory and the finished product inventory are respectively less than the preset raw material inventory threshold and the preset finished product inventory threshold, and taking the final distribution volume, processing raw material inventory and finished product inventory as the scheduling strategy.

[0008] Furthermore, the expression of the scheduling objective function is:

[0009] ;

[0010] ;

[0011] ;

[0012] ;

[0013] Among them, min means taking the minimum value; Z represents the value of the scheduling objective function; represents the first scheduling target parameter; represents the second scheduling target parameter; represents the third scheduling target parameter; i and j represent different logistics node variables, representing the first logistics node variable and the second logistics node variable respectively; N represents the total number of logistics nodes; It indicates the influence of the degree of aggregation on the basic transportation cost; D represents the degree of aggregation; and They represent the basic transportation cost of processed raw materials and the basic transportation cost of finished products from logistics node i to logistics node j respectively; and They represent the amount of processed raw materials delivered from logistics node i to logistics node j and the amount of finished product delivered, respectively; Indicates the degree of influence of the average number of connections on the basic transportation time; Indicates the average number of connections; represents the basic transportation time from logistics node i to logistics node j; k represents the warehouse node variable; K represents the total number of warehouse nodes; and They represent the unit storage cost of processed raw materials and the unit storage cost of finished products at warehouse node k respectively; and They represent the inventory of processed raw materials and finished products at warehouse node k respectively;

[0014] Scheduling constraints include:

[0015] Demand matching constraints:

[0016] ;

[0017] ;

[0018] in, and They represent the total amount of processed raw materials delivered and the total amount of finished products delivered from logistics node i to all connected logistics nodes j; and They represent the demand for processing raw materials and finished products of node i respectively; and They represent the fluctuation of processing raw material demand and finished product demand at node i, respectively. The demand fluctuation is related to trend characteristic information and period characteristic information; represents the conversion coefficient of processing raw materials into finished products; S represents the set of logistics nodes that supply processing raw materials; represents the total amount of processed raw materials transported from logistics node j to logistics node i;

[0019] Transport capacity constraints:

[0020] ;

[0021] in, It represents the maximum delivery volume that can be carried by logistics node i to logistics node j;

[0022] Inventory capacity constraints:

[0023] ;

[0024] ;

[0025] in, and They represent the maximum storage capacity of processed raw materials and finished products of warehouse node k respectively;

[0026] Non-negativity constraints:

[0027] ;

[0028] Delivery time constraints:

[0029] ;

[0030] in, represents the time when delivery starts; t represents the actual delivery time; Indicates the time when delivery ends.

[0031] Furthermore, the scheduling objective function is optimized through a scheduling optimization algorithm to obtain an optimized distribution volume, including: determining an initial distribution volume based on logistics characteristic information; using the initial distribution volume to calculate the scheduling objective function value to provide an initial evaluation basis for particle swarm optimization; bringing the position of each particle into the scheduling objective function to calculate the fitness value; the fitness value represents the quality of the distribution combination; the position of each particle is represented as a set of distribution volume combinations; according to the average number of connections and the degree of aggregation of logistics nodes, the exploration range of particles in different areas is adjusted; when the preset number of iterations is met or the fitness value converges, the iteration is terminated, and the distribution volume combination corresponding to the global optimal position at this time is used as the final distribution volume.

[0032] Furthermore, according to the average number of connections and the degree of aggregation of logistics nodes, the exploration range of particles in different areas is adjusted as follows: at logistics nodes where the average number of connections is higher than the connection threshold, the search range of particles is narrowed; at logistics nodes where the degree of aggregation is higher than the aggregation threshold, particles are guided to search along the local optimal solution at the logistics node.

[0033] Furthermore, the calculation formula for updating the individual optimal position and global optimal position of particles through particle swarm optimization is:

[0034] ;

[0035] ;

[0036] ;

[0037] ;

[0038] in, and Represent the particles at time ti and ti+1 respectively In dimension speed; Represents the original inertia weight of the particle; represents the self-recognition coefficient of the particle; Represents the first random number in the [0,1] interval; Represents particles In dimension The best position in history; and Represent the particles at time ti and ti+1 respectively In dimension location; represents the social cognition coefficient of the particle; Represents the second random number in the interval [0,1]; Indicates that all particles are in dimension The global optimal position of Indicates the average number of connections; represents the connection threshold; D represents the degree of aggregation; represents the aggregation threshold; Represents the modified inertia weight of the particle; represents the modified self-recognition coefficient of the particle; Indicates the maximum value of node degree; Indicates the maximum edge degree.

[0039] Furthermore, the expression for adjusting the delivery quantity is obtained as follows:

[0040] ;

[0041] ;

[0042] ;

[0043] in, and Represents the adjusted delivery quantities of processed raw materials and finished products respectively; Indicates the adjustment coefficient dynamically adjusted according to random feature information; and They represent the actual residual standard deviations of the processed raw materials and finished products respectively; and They represent the standard deviation of the prediction residuals of the processed raw materials and finished products respectively; and Respectively represent the minimum adjustment coefficient and the maximum adjustment coefficient; Fr, and They represent random feature information, the maximum value of random feature information, and the minimum value of random feature information respectively.

[0044] The present invention also provides a scheduling system for a scheduling method for coordinated distribution of processed raw materials and finished products using any of the above-mentioned scheduling methods, comprising an acquisition module, a decomposition module, a calculation module and a scheduling module; the acquisition module is used to collect multi-dimensional data in the distribution of processed raw materials and finished products; the multi-dimensional data includes logistics information and node information; the decomposition module is used to decompose the logistics information to obtain logistics characteristic information; the logistics characteristic information includes trend characteristic information, periodic characteristic information and random characteristic information; the calculation module is used to construct a logistics matrix containing logistics nodes based on the node information, and calculate the node characteristic information; the node characteristic information includes the average number of connections and the degree of aggregation; the scheduling module is used to design a scheduling strategy for coordinated distribution scheduling of processed raw materials and finished products based on the logistics characteristic information and the node characteristic information.

[0045] The technical solutions of the embodiments of the present invention have at least the following advantages and beneficial effects:

[0046] The present invention decomposes logistics information to obtain trend feature information, period feature information and random feature information, can accurately explore the inherent laws of logistics activities, and reveal the characteristics of logistics nodes from the network structure level through node feature information. By analyzing logistics feature information and node feature information and designing scheduling strategies, the optimization of coordinated distribution scheduling of processed raw materials and finished products is achieved, which helps to improve distribution efficiency, reduce logistics costs, enhance the overall utilization efficiency of logistics resources, and enhance the adaptability of logistics systems to complex business scenarios.

[0047] The present invention classifies the nodes in the logistics network, which can clarify the roles and functions of different types of nodes in logistics activities, making scheduling more targeted. The connection relationship between logistics nodes is determined based on historical transportation routes, ensuring an accurate grasp of the actual operation mode of the logistics network. An adjacency matrix is created as a logistics matrix, which intuitively presents the logistics nodes and their connection status in the form of a square matrix, providing a clear model basis for analyzing the degree of correlation between nodes and the rationality of transportation routes. This method makes the design of scheduling strategies more in line with the actual structure of the logistics network, helps to optimize transportation routes, reduce ineffective transportation, enhance the scientific nature and effectiveness of scheduling plans, and improve the overall operating efficiency of the logistics network.

[0048] This invention uses node degree to provide a key indicator of a node's importance and influence in a logistics network. By calculating node characteristics based on this indicator, it can more accurately identify core nodes and densely populated areas within the logistics network, providing a solid foundation for subsequent scheduling strategies. For example, narrowing the search range near nodes with high average connection counts can concentrate resources and improve distribution efficiency in key areas. For nodes with high aggregation levels, guiding particles to search for local optimal solutions can accelerate optimization by leveraging regional density. This improves the efficiency and effectiveness of overall logistics distribution and enhances the stability and reliability of the logistics system.

[0049] This invention uses a particle swarm optimization algorithm to optimize the scheduling objective function to obtain the optimal delivery quantity. Leveraging the algorithm's efficient global search capabilities, it can quickly identify optimal delivery solutions in complex delivery scenarios, improving both the quality and efficiency of delivery solutions. Furthermore, by determining the initial delivery quantity based on logistics characteristics, the initial solution closely aligns with the patterns and characteristics of actual logistics operations (such as trends and cycles). This provides a more rational and targeted starting point for particle swarm optimization, effectively reducing ineffective algorithm iterations, accelerating algorithm convergence, and more quickly approaching the optimal solution.

[0050] By narrowing the particle search range at logistics nodes where the average number of connections is higher than the connection threshold, the present invention can avoid meaningless and extensive searches of particles in node areas with rich but complex connections, concentrate computing resources on the effective area near the node, quickly lock in high-quality distribution paths or resource allocation methods, and improve search efficiency. It is particularly suitable for the precise scheduling of key nodes such as logistics hubs.

[0051] This method guides particles along the search path for local optimal solutions at logistics nodes with a degree of aggregation above a threshold. This leverages the close connections and strong collaboration within the region where these nodes reside, allowing particles to accelerate the optimization process by leveraging the stability and representativeness of the local optimal solution. This allows for rapid adaptation to demand fluctuations within highly aggregated areas, such as dense urban distribution zones, improving the accuracy and efficiency of localized dispatch scheduling for processed raw materials and finished products, and better addressing the complex node structures and demand distribution in collaborative distribution. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 An exemplary flow chart of a scheduling method for coordinated distribution of processed raw materials and finished products provided by the present invention;

[0053] Figure 2 This is an exemplary module diagram of a scheduling system for the coordinated distribution of processed raw materials and finished products provided by the present invention. DETAILED DESCRIPTION

[0054] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of 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. Generally, the components of the embodiments of the present invention described and shown in the drawings herein can be arranged and designed in various different configurations.

[0055] Figure 1 This is an exemplary flow chart of a scheduling method for the coordinated distribution of processed raw materials and finished products provided by the present invention. Figure 1 As shown, the scheduling method for coordinated distribution of processed raw materials and finished products provided by the present invention includes the following contents:

[0056] Step 110 collects multi-dimensional data on the distribution of processed raw materials and finished products; the multi-dimensional data includes logistics information and node information. Processed raw materials may include raw sugar, sweeteners, and preservatives, and finished products may include syrup. Multi-dimensional data may refer to various data related to the distribution of raw materials and finished products, which can be obtained by extracting historical distribution data for processed raw materials and finished products. Logistics information may refer to information related to logistics and transportation, and logistics information may include demand fluctuations, transportation time efficiency, raw material inventory, finished product inventory, and processing equipment status. Logistics information may be daily logistics information. Node information may refer to information related to logistics nodes, and logistics information may include factory coordinates, warehouse coordinates, demand supplier coordinates, raw material supplier coordinates, transportation routes, and transportation frequency.

[0057] Step 120 decomposes the logistics information to obtain logistics characteristic information; the logistics characteristic information includes trend characteristic information, periodic characteristic information, and random characteristic information. Logistics characteristic information refers to systematic information obtained after processing logistics information that can be used to represent the logistics situation. Trend characteristic information can reflect the overall direction of change in logistics over a long period of time. For example, the procurement volume of processing raw materials has shown a steady annual growth trend as the market expands, and the distribution volume of finished products has increased over the long term due to the improvement of brand influence. Cyclic characteristic information refers to information that shows regular and recurring fluctuations in logistics. For example, weekly peaks in raw material demand and congestion in finished product distribution during daily peak hours in the morning and evening. Random characteristic information refers to irregular and sudden fluctuations in logistics. For example, sudden natural disasters may cause the interruption of raw material transportation during a certain period, or temporary policy adjustments may cause changes in finished product distribution routes.

[0058] In some embodiments, decomposing logistics information to obtain logistics characteristic information involves segmenting the logistics information and extracting time series characteristics for each time period. These time series characteristics may include the mean, variance, slope, and cyclical fluctuation amplitude of the logistics information. In conjunction with logistics business scenarios, prior rules related to logistics trends and cycles are analyzed. These prior rules may include promotional activity cycles, holiday shipping peaks, and seasonal supply and demand fluctuations. Current logistics data is matched against historical logistics data for similarity, and the matching results are compared with the prior rules to isolate trend and cycle characteristic information that meets the rules. The difference between the original logistics data and the isolated trend and cycle characteristic information is used as random feature information. Time series characteristics are used to reflect the changing patterns and statistical characteristics of logistics information at different time points. For example, daily processing raw material purchase data and product shipment data for the past 30 days can be segmented into daily time periods. The segmented logistics data is processed and arranged chronologically to obtain time series characteristics for each time period. Logistics business scenarios may include goods storage, transportation, and distribution, as well as related processes such as order processing and supply chain collaboration. Prior rules refer to regularities related to logistics trends and cycles, summarized and summarized based on past experience, industry principles, or domain knowledge before analyzing logistics data. Current logistics data refers to various data related to the transportation of processed materials and products within the current time period. Historical logistics data refers to various data related to the transportation of processed materials and products within a historical time period. For example, current logistics data is a logistics company's cargo transportation volume data for this week, while historical logistics data is weekly cargo transportation volume data for the past two years. Various distance methods can be used to calculate the similarity between this week's transportation volume data and the weekly transportation volume data for the past two years. It is found that this week's transportation volume data is highly similar to the transportation volume data for a certain week last year. By comparing it with the prior rules (for example, the cyclical pattern for this period is that transportation volume gradually increases in the first three days and then increases and then decreases in the last four days), the trend characteristic information isolated is that this week's transportation volume shows a trend of first increasing and then decreasing.

[0059] Step 130 constructs a logistics matrix containing logistics nodes based on the node information and calculates node characteristic information; this node characteristic information includes the average number of connections and the degree of aggregation. Logistics nodes can include processing plants, transportation hubs, warehouses, suppliers, distribution centers, and raw material suppliers. The logistics matrix can be used to represent the transportation logistics of processed raw materials and finished products. Node characteristic information can be used to represent the connectivity between logistics nodes. The average number of connections can reflect the richness of the logistics node's connections within the network. The degree of aggregation can reflect the closeness of the region where the logistics node is located.

[0060] In some embodiments, a logistics matrix including logistics nodes is constructed based on node information, including: based on the node information, the nodes in the logistics network for distributing processed raw materials and finished products are classified to obtain multiple types of logistics nodes. The multiple types of logistics nodes may include processing plant nodes, transportation hub nodes, warehouse nodes, demander nodes, distribution center nodes, and raw material supplier nodes, etc. Based on historical transportation routes, the connection relationship between logistics nodes is determined. Historical transportation routes may refer to historical transportation routes for processed raw materials and products. The connection relationship may refer to the connectivity between logistics nodes. Based on the logistics nodes and their connection relationships, an adjacency matrix is created, and the adjacency matrix is used as the logistics matrix; the adjacency matrix is a square matrix, the order is the total number of logistics nodes, and the matrix elements represent the connection status between logistics nodes.

[0061] In some embodiments, calculating node feature information includes: determining the node degree of each logistics node; the node degree represents the number of other logistics nodes directly connected to the logistics node. averaging the node degrees of all logistics nodes to obtain the average number of connections. Determining the edge degrees between logistics nodes; the edge degrees represent the number of edges with connection relationships between other logistics nodes connected to the logistics node. Based on the average number of connections and the edge degrees, calculating the clustering coefficient of the logistics node, for the target logistics node (the node currently being processed), its clustering coefficient is equal to twice its edge degree divided by the product of the node degree and the node degree minus one, and when the node degree is less than 2, the clustering coefficient of the target logistics node is 0. averaging the clustering coefficients of all logistics nodes to obtain the degree of aggregation.

[0062] Step 140: Based on the logistics and node characteristics, a scheduling strategy is designed to coordinate the distribution of raw materials and finished products. The scheduling strategy may be a strategy for coordinating the distribution of raw materials and finished products. For example, the scheduling strategy may include adjusting the distribution volume of raw materials and finished products, or adjusting the storage volume of raw materials and finished products in warehouses.

[0063] In some embodiments, a scheduling strategy is designed based on logistics characteristic information and node characteristic information to coordinate the delivery of processed raw materials and finished products. The strategy includes: constructing a scheduling objective function based on the node characteristic information and the delivery volume. The delivery volume may include the amount of processed raw materials and the amount of finished products transported from one node to another. Scheduling constraints are established based on the logistics characteristic information. The scheduling objective function is solved to obtain the inventory of processed raw materials and the inventory of finished products at the logistics node. The inventory of processed raw materials may refer to the amount of processed raw materials stored in a warehouse node; the inventory of finished products may refer to the amount of finished products stored in a warehouse node. The scheduling objective function is optimized using a scheduling optimization algorithm to obtain an optimized delivery volume. The optimized delivery volume is adjusted based on the random characteristic information to obtain an adjusted delivery volume. The adjusted delivery volume is substituted into the scheduling objective function to obtain a new scheduling objective function. The solving and optimization of the scheduling objective function are repeated until the changes in the inventory of processed raw materials and the inventory of finished products are less than preset raw material inventory thresholds and preset finished product inventory thresholds, respectively. The resulting delivery volume of processed raw materials, delivery volume of finished products, inventory of processed raw materials, and inventory of finished products are used as the scheduling strategy. The change in raw material inventory and finished product inventory refers to the difference between the raw material inventory and finished product inventory obtained from the previous solution of the scheduling objective function and the raw material inventory and finished product inventory obtained from the next solution of the scheduling objective function. The preset raw material inventory threshold refers to the maximum change in raw material inventory between two consecutive optimizations. The preset finished product inventory threshold refers to the maximum change in finished product inventory between two consecutive optimizations.

[0064] In some embodiments, the scheduling objective function is expressed as:

[0065] ;

[0066] ;

[0067] ;

[0068] ;

[0069] Among them, min means taking the minimum value; Z represents the value of the scheduling objective function; represents the first scheduling target parameter; represents the second scheduling target parameter; represents the third scheduling target parameter; i and j represent different logistics node variables, representing the first logistics node variable and the second logistics node variable respectively; N represents the total number of logistics nodes; It indicates the influence of the degree of aggregation on the basic transportation cost; D represents the degree of aggregation; and They represent the basic transportation cost of processed raw materials and the basic transportation cost of finished products from logistics node i to logistics node j respectively; and They represent the amount of processed raw materials delivered from logistics node i to logistics node j and the amount of finished product delivered, respectively; Indicates the degree of influence of the average number of connections on the basic transportation time; Indicates the average number of connections; represents the basic transportation time from logistics node i to logistics node j; k represents the warehouse node variable; K represents the total number of warehouse nodes; and They represent the unit storage cost of processed raw materials and the unit storage cost of finished products at warehouse node k respectively; and They represent the inventory of processed raw materials and finished products of warehouse node k respectively.

[0070] Scheduling constraints include:

[0071] Demand matching constraints:

[0072] ;

[0073] ;

[0074] in, and They represent the total amount of processed raw materials delivered and the total amount of finished products delivered from logistics node i to all connected logistics nodes j; and They represent the demand for processing raw materials and finished products of node i respectively; and They represent the fluctuation of processing raw material demand and finished product demand at node i, respectively. The demand fluctuation is related to trend characteristic information and period characteristic information; represents the conversion coefficient of processing raw materials into finished products; S represents the set of logistics nodes that supply processing raw materials; Represents the total amount of processed raw materials transported from logistics node j to logistics node i.

[0075] In some embodiments, the expressions for the processing raw material demand and finished product demand of node i can be:

[0076] ;

[0077] ;

[0078] in, represents the trend component of the processed raw materials at logistics node i in time period t; represents the periodic component of the processed raw materials at node i in time period t; represents the trend component of finished products at logistics node i in time period t; represents the periodic component of the finished product of node i in time period t.

[0079] In some embodiments, the expressions for the fluctuation of processing raw material demand and the fluctuation of finished product demand at node i can be:

[0080] ;

[0081] ;

[0082] in, shows the trend component of the processed raw materials of logistics node i in time period t-1; represents the periodic component of the processed raw materials of node i in time period t-1; represents the trend component of finished products at logistics node i in time period t-1; represents the periodic component of the finished product of node i in time period t-1.

[0083] Transport capacity constraints:

[0084] ;

[0085] in, It represents the maximum delivery volume that can be carried from logistics node i to logistics node j.

[0086] Inventory capacity constraints:

[0087] ;

[0088] ;

[0089] in, and They represent the maximum storage capacity of processed raw materials and finished products of warehouse node k respectively.

[0090] Non-negativity constraints:

[0091] .

[0092] Delivery time constraints:

[0093] ;

[0094] in, represents the time when delivery starts; t represents the actual delivery time; Indicates the time when delivery ends.

[0095] In some embodiments, the scheduling optimization algorithm may be a particle swarm optimization algorithm. The scheduling objective function is optimized by the scheduling algorithm to obtain an optimized delivery quantity, including:

[0096] Based on logistics characteristics, the initial delivery volume is determined. The initial delivery volume refers to the delivery volume before optimization. For example, the initial delivery volume can be determined by analyzing past logistics delivery data from the same or similar time periods and calculating relevant indicators. The initial delivery volume is used to calculate the scheduling objective function value, providing an initial evaluation basis for particle swarm optimization. For example, the initial delivery volume can be used to determine the initial storage capacity. The optimized delivery volume based on the initial storage capacity is then substituted into the scheduling objective function to obtain the objective function value. The position of each particle is substituted into the scheduling objective function to calculate the fitness value; the fitness value indicates the quality of the delivery combination; each particle position represents a set of delivery volume combinations. The particle's exploration range in different areas is adjusted based on the average number of connections and the degree of aggregation of logistics nodes. The iteration terminates when the preset number of iterations is met or the fitness value converges, and the delivery volume combination corresponding to the global optimal position at that time is used as the final delivery volume. For example, there are three warehouses (Warehouse A, Warehouse B, Warehouse C), two factories (Factory X, Factory Y), and two product demanders (Demander M, Demander N). Warehouses store both raw materials and finished products. Factories X and Y require the raw materials for production, while customers M and N need the products for sale or use. In a particle swarm optimization algorithm, each particle represents a combination of raw material delivery quantities from each warehouse to the factories and product delivery quantities to the product demanders. After multiple rounds of iterative search, the optimal global position is determined to correspond to the following delivery quantity combination: Raw material delivery: Warehouse A delivers 60 tons to Factory X and 50 tons to Factory Y; Warehouse B delivers 40 tons to Factory X and 30 tons to Factory Y; Warehouse C delivers 20 tons to Factory X and 25 tons to Factory Y. Product delivery: Warehouse A delivers 40 units to customer M, Warehouse B delivers 30 units to customer M, and Warehouse C delivers 50 units to customer N.

[0097] In some embodiments, based on the average number of connections and degree of aggregation of logistics nodes, the particle's exploration range in different regions is adjusted as follows: at logistics nodes where the average number of connections exceeds a connection threshold, the particle's search range is narrowed; at logistics nodes where the degree of aggregation exceeds the aggregation threshold, the particle is guided to search for the local optimal solution at that logistics node. The connection threshold is a benchmark value for the average number of connections at a logistics node. When the average number of connections at a logistics node exceeds this value, it indicates that the node is well-connected and important in the logistics network. The aggregation threshold is a benchmark value for the degree of aggregation of logistics nodes. If the degree of aggregation of a logistics node exceeds this value, it indicates that the node is located in a region with close nodes and a compact structure. For example, in a regional logistics network, based on historical data and network structure analysis, the connection threshold is set to 5 and the aggregation threshold is set to 0.6. Logistics node A has an average number of connections of 6, which means it can be considered a regional logistics hub, connected to multiple warehouses and transshipment centers. In the particle swarm optimization search, the particle originally searches for the optimal delivery route within a 10-kilometer radius centered on node A. Because the search range exceeds the connection threshold, the search range is narrowed to 5 kilometers, focusing on exploring efficient routes near node A. Logistics node B has a degree of aggregation of 0.7, indicating that it is located in a dense urban distribution area with close connections to surrounding nodes. When particle search involves this area, it guides the particles along the local optimal distribution path discovered near node B (such as the route with the shortest delivery time) and fine-tunes the distribution sequence and vehicle scheduling parameters on this path, rather than blindly searching across a large area. This allows for rapid optimization of the distribution plan for this area.

[0098] In some embodiments, the calculation formula for updating the individual optimal position and the global optimal position of the particle through particle swarm optimization is:

[0099] ;

[0100] ;

[0101] ;

[0102] ;

[0103] in, and Represent the particles at time ti and ti+1 respectively In dimension speed; Represents the original inertia weight of the particle; represents the self-recognition coefficient of the particle; Represents the first random number in the [0,1] interval; Represents particles In dimension The best position in history; and Represent the particles at time ti and ti+1 respectively In dimension location; represents the social cognition coefficient of the particle; Represents the second random number in the interval [0,1]; Indicates that all particles are in dimension The global optimal position of Indicates the average number of connections; It represents the connection threshold, which is greater than 0 and less than the maximum value of the node degree; D represents the degree of aggregation; Represents the aggregation threshold, the value is greater than 0 and less than the maximum edge degree; Represents the modified inertia weight of the particle; represents the modified self-recognition coefficient of the particle; Indicates the maximum value of node degree; Indicates the maximum edge degree.

[0104] In some embodiments, the expression for the adjusted delivery amount is:

[0105] ;

[0106] ;

[0107] ;

[0108] in, and Represents the adjusted delivery quantities of processed raw materials and finished products respectively; Indicates the adjustment coefficient dynamically adjusted according to random feature information; and They represent the actual residual standard deviations of the processed raw materials and finished products respectively; and They represent the standard deviation of the prediction residuals of the processed raw materials and finished products respectively; and Respectively represent the minimum adjustment coefficient and the maximum adjustment coefficient; Fr, and They represent random feature information, the maximum value of random feature information, and the minimum value of random feature information respectively.

[0109] Figure 2 This is an exemplary module diagram of a scheduling system for the coordinated distribution of processed raw materials and finished products provided by the present invention. Figure 2As shown, the scheduling system for coordinated distribution of processed raw materials and finished products provided by the present invention includes a collection module 210 , a decomposition module 220 , a calculation module 230 and a scheduling module 240 .

[0110] The acquisition module is used to collect multi-dimensional data on the distribution of processed raw materials and finished products; the multi-dimensional data includes logistics information and node information.

[0111] The decomposition module is used to decompose the logistics information to obtain logistics feature information; the logistics feature information includes trend feature information, period feature information and random feature information.

[0112] The calculation module is used to construct a logistics matrix containing logistics nodes based on node information and calculate node feature information; the node feature information includes the average number of connections and the degree of aggregation.

[0113] The scheduling module is used to design scheduling strategies for coordinated distribution scheduling of processed raw materials and finished products based on logistics characteristic information and node characteristic information.

[0114] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A scheduling method for the coordinated distribution of processed raw materials and finished products, characterized in that: include: Collect multi-dimensional data on raw materials and finished products during distribution; The multi-dimensional data includes logistics information and node information; Decomposing the logistics information to obtain logistics characteristic information; the logistics characteristic information includes trend characteristic information, periodic characteristic information and random characteristic information; trend Characteristic information reflects the overall direction of change in logistics over time, including trends in the purchase volume of processed raw materials and the delivery volume of finished products. Cyclic characteristic information refers to information showing regular, recurring fluctuations in logistics, including peaks in raw material demand and congestion in finished product delivery during peak hours in the morning and evening. Random characteristic information refers to irregular, sudden fluctuations in logistics, including interruptions in raw material transportation during a certain period due to sudden natural disasters and changes in finished product delivery routes caused by temporary policy adjustments. Obtaining logistics characteristic information includes: segmenting logistics information and extracting time series characteristics for each time period; the time series characteristics include the mean, variance, slope, and cyclical fluctuation amplitude of the logistics information; analyzing prior rules related to logistics trends and cycles in combination with logistics business scenarios; the prior rules include promotional activity cycle rules, holiday transportation peak rules, and seasonal supply and demand fluctuation rules; matching the similarity between current logistics data and historical logistics data, comparing the similarity matching results with the prior rules, and separating trend characteristic information and cycle characteristic information that meet the rules; and using the difference between the original logistics data and the separated trend characteristic information and cycle characteristic information as random characteristic information; Constructing a logistics matrix containing logistics nodes based on the node information and calculating node feature information; the node feature information includes the average number of connections and the degree of aggregation; Based on logistics and node feature information, a scheduling strategy is designed to coordinate the distribution of processed raw materials and finished products, including: Constructing a scheduling objective function based on the node characteristic information and the delivery volume; Constructing scheduling constraints based on the logistics characteristic information; Solving the scheduling objective function to obtain the inventory of processed raw materials and finished products at the logistics node; The scheduling objective function is optimized by a scheduling optimization algorithm to obtain an optimized delivery volume, including: determining an initial delivery volume based on logistics feature information; using the initial delivery volume to calculate the scheduling objective function value to provide an initial evaluation basis for particle swarm optimization; bringing the position of each particle into the scheduling objective function to calculate the fitness value; the fitness value represents the quality of the delivery combination; the position of each particle is represented as a set of delivery volume combinations; according to the average number of connections and the degree of aggregation of the logistics nodes, adjusting the exploration range of the particles in different areas, including: at logistics nodes where the average number of connections is higher than the connection threshold, narrowing the search range of the particles; at logistics nodes where the degree of aggregation is higher than the aggregation threshold, guiding the particles to search along the local optimal solution at the logistics nodes; when the preset number of iterations is met or the fitness value converges, terminating the iteration, and taking the delivery volume combination corresponding to the global optimal position at this time as the final delivery volume; adjusting the optimized delivery quantity based on the random feature information to obtain an adjusted delivery quantity; Substituting the adjusted delivery quantity into the scheduling objective function to obtain a new scheduling objective function; Repeat the solution and optimization operations of the scheduling objective function until the change values of the processing raw material inventory and the finished product inventory are less than the preset raw material inventory threshold and the preset finished product inventory threshold respectively, and use the final distribution quantity, processing raw material inventory and finished product inventory as the scheduling strategy.

2. The scheduling method for coordinated distribution of processed raw materials and finished products according to claim 1 is characterized in that: Construct a logistics matrix containing logistics nodes based on node information, including: Based on node information, nodes in the logistics network for distributing processed raw materials and finished products are classified to obtain multiple types of logistics nodes; Determine the connection relationship between logistics nodes based on historical transportation routes; Based on the logistics nodes and their connection relationships, an adjacency matrix is created, and the adjacency matrix is used as the logistics matrix; the adjacency matrix is a square matrix, the order is the total number of logistics nodes, and the matrix elements represent the connection status between logistics nodes.

3. The method for coordinating the distribution of processed raw materials and finished products according to claim 2, characterized in that: Compute node characteristic information, including: Determine the node degree of each logistics node; the node degree represents the number of other logistics nodes directly connected to the logistics node; averaging the node degrees of all logistics nodes to obtain the average number of connections; Determining the edge degree between logistics nodes; the edge degree represents the number of edges having a connection relationship between other logistics nodes connected to the logistics node; Calculating a clustering coefficient of a logistics node based on the average number of connections and the edge degree; The clustering coefficients of all logistics nodes are averaged to obtain the degree of aggregation.

4. The method for coordinating the distribution of processed raw materials and finished products according to claim 1, characterized in that: The expression of the scheduling objective function is: ； ; ； ; Among them, min means taking the minimum value; Z represents the value of the scheduling objective function; represents the first scheduling target parameter; represents the second scheduling target parameter; represents the third scheduling target parameter; i and j represent different logistics node variables, representing the first logistics node variable and the second logistics node variable respectively; N represents the total number of logistics nodes; It indicates the influence of the degree of aggregation on the basic transportation cost; D represents the degree of aggregation; and They represent the basic transportation cost of processed raw materials and the basic transportation cost of finished products from logistics node i to logistics node j respectively; and They represent the amount of processed raw materials delivered from logistics node i to logistics node j and the amount of finished product delivered, respectively; Indicates the degree of influence of the average number of connections on the basic transportation time; Indicates the average number of connections; represents the basic transportation time from logistics node i to logistics node j; k represents the warehouse node variable; K represents the total number of warehouse nodes; and They represent the unit storage cost of processed raw materials and the unit storage cost of finished products at warehouse node k respectively; and They represent the inventory of processed raw materials and finished products at warehouse node k respectively; Scheduling constraints include: Demand matching constraints: ； ； in, and They represent the total amount of processed raw materials delivered and the total amount of finished products delivered from logistics node i to all connected logistics nodes j; and They represent the demand for processing raw materials and finished products of node i respectively; and They represent the fluctuation of processing raw material demand and finished product demand at node i, respectively. The demand fluctuation is related to trend characteristic information and period characteristic information; represents the conversion coefficient of processing raw materials into finished products; S represents the set of logistics nodes that supply processing raw materials; represents the total amount of processed raw materials transported from logistics node j to logistics node i; Transport capacity constraints: ； in, It represents the maximum delivery volume that can be carried by logistics node i to logistics node j; Inventory capacity constraints: ； ； in, and They represent the maximum storage capacity of processed raw materials and finished products of warehouse node k respectively; Non-negativity constraints: ； Delivery time constraints: ； in, represents the time when delivery starts; t represents the actual delivery time; Indicates the time when delivery ends.

5. The method for coordinating the distribution of processed raw materials and finished products according to claim 1, characterized in that: The calculation formula for updating the individual optimal position and global optimal position of particles through particle swarm optimization is: ; ; ; ; in, and Represent the particles at time ti and ti+1 respectively In dimension speed; Represents the original inertia weight of the particle; represents the self-recognition coefficient of the particle; Represents the first random number in the [0,1] interval; Represents particles In dimension The best position in history; and Represent the particles at time ti and ti+1 respectively In dimension location; represents the social cognition coefficient of the particle; Represents the second random number in the interval [0,1]; Indicates that all particles are in dimension The global optimal position of Indicates the average number of connections; represents the connection threshold; D represents the degree of aggregation; represents the aggregation threshold; Represents the modified inertia weight of the particle; represents the modified self-recognition coefficient of the particle; Indicates the maximum value of node degree; Indicates the maximum edge degree.

6. The method for coordinating the distribution of processed raw materials and finished products according to claim 1, characterized in that: The expression for adjusting the delivery quantity is: ; ; ; in, and Represents the adjusted delivery quantities of processed raw materials and finished products respectively; Indicates the adjustment coefficient dynamically adjusted according to random feature information; and They represent the actual residual standard deviations of the processed raw materials and finished products respectively; and They represent the standard deviation of the prediction residuals of the processed raw materials and finished products respectively; and Respectively represent the minimum adjustment coefficient and the maximum adjustment coefficient; Fr, and They represent random feature information, the maximum value of random feature information, and the minimum value of random feature information respectively.

7. A scheduling system using the scheduling method for coordinated distribution of processed raw materials and finished products according to any one of claims 1 to 6, characterized in that: It includes acquisition module, decomposition module, calculation module and scheduling module; The acquisition module is used to collect multi-dimensional data of the distribution processing raw materials and finished products; the multi-dimensional data includes logistics information and node information; The decomposition module is used to decompose the logistics information to obtain logistics feature information; the logistics feature information includes trend feature information, period feature information and random feature information; The calculation module is used to construct a logistics matrix containing logistics nodes based on node information and calculate node feature information; the node feature information includes the average number of connections and the degree of aggregation; The scheduling module is used to design a scheduling strategy to coordinate the distribution of processed raw materials and finished products based on logistics feature information and node feature information.

Images