Decision Method and Service Platform for Material Ordering and Replenishment Based on GA-PSO

Abstract

The present application relates to a decision-making method and service platform for material ordering and replenishment based on GA-PSO. The method includes: obtaining the material ordering quantities corresponding to multiple target materials in each ordering cycle; encoding the number of delivery cycles and the material ordering quantities corresponding to multiple target materials in each ordering cycle to generate multiple first matrix-type encoded individuals; after performing at least one genetic operation using a genetic algorithm based on the multiple first matrix-type encoded individuals, determining the fitness of the second sub-encoded body corresponding to each second matrix-type encoded individual generated in the current iteration, and performing iterative genetic operations based on the fitness and the second matrix-type encoded individuals until multiple candidate matrix-type encoded individuals are generated; after using the candidate sub-encoded bodies in the candidate matrix-type encoded individuals as candidate particles, performing iterative processing on the multiple candidate particles based on a particle swarm optimization algorithm, and selecting a target particle including target material replenishment decision information from the multiple generated alternative particles.

Description

Technical Field

[0001] This application relates to the field of intelligent manufacturing technology, in particular to a decision-making method and service platform for material ordering and replenishment based on GA-PSO. Background Art

[0002] In the related art, for paint manufacturing manufacturers, they not only need to continuously innovate products and improve service quality, but also must effectively control the material ordering cost, so the optimization of procurement management is crucial.

[0003] In the related art, material procurement involves multiple complex decision points and constraint conditions. In the batch ordering link, the manufacturer needs to decide the order quantity of each material and which supplier to choose. This not only needs to consider the price and demand of the material, but also needs to weigh the price discounts provided by the supplier; at the same time, in the batch delivery link, the manufacturer also needs to accurately plan the delivery quantity of each material and the delivery vehicle according to multiple factors such as the order quantity in the current cycle, vehicle type, and warehouse capacity to ensure the timeliness and efficiency of supply.

[0004] In the related art, existing optimization algorithms for material inventory replenishment decision-making have deficiencies in solving speed when dealing with such complex problems and cannot meet the needs of rapid decision-making; at the same time, due to the large amount of data and calculations involved in the material inventory replenishment decision-making problem, traditional optimization algorithms often have defects such as low calculation efficiency and poor solution quality.

[0005] Currently, for the problems in the related art of material inventory replenishment decision-making, such as the inability to meet the needs of rapid decision-making, low decision-making efficiency, and poor material inventory replenishment effect, no effective solution has been proposed. Summary of the Invention

[0006] The embodiments of this application provide a decision-making method and service platform for material ordering and replenishment based on GA-PSO to at least solve the problems in the related art of material inventory replenishment decision-making, such as the inability to meet the needs of rapid decision-making, low decision-making efficiency, and poor material inventory replenishment effect.

[0007] In a first aspect, an embodiment of the present application provides a decision-making method for material ordering and replenishment based on GA-PSO, including: in a plurality of preset ordering cycles, determining a plurality of delivery cycles agreed upon in each of the ordering cycles, and obtaining the material ordering quantities corresponding to multiple target materials to be replenished in each of the ordering cycles, where the material ordering quantity is used to represent the total quantity of materials to be delivered for each target material in the corresponding multiple delivery cycles; encoding the number of the delivery cycles and the material ordering quantities corresponding to the multiple target materials respectively to generate a plurality of first matrix-type encoded individuals, where the first matrix-type encoded individual includes a plurality of first matrix-type sub-encoded bodies each having a plurality of first sub-encoded bodies, and the first sub-encoded body is used to represent the material replenishment decision information of a target material in the multiple delivery cycles corresponding to one of the ordering cycles, and the material replenishment decision information includes a replenishment supply object and a replenishment supply quantity; after performing at least one genetic operation on the basis of the plurality of first matrix-type encoded individuals by using a preset genetic algorithm GA, determining the fitness of each second sub-encoded body corresponding to the second matrix-type encoded individual generated in the current iteration, and performing genetic operation iteration based on the fitness and the second matrix-type encoded individual until a plurality of candidate matrix-type encoded individuals are generated, where the genetic evolution operation includes: individual selection based on the roulette method and the elite retention strategy, self-adaptive crossover based on gene positions, and dynamic mutation, and the fitness is determined according to the ordering cost, transportation cost, storage cost, and emergency transfer cost generated by the replenishment supply object corresponding to the second sub-encoded body when replenishing the target material of the replenishment supply quantity; after using the candidate sub-encoded bodies in the candidate matrix-type encoded individuals as candidate particles, performing particle swarm search iteration processing on the plurality of candidate particles based on a preset particle swarm optimization algorithm PSO, and selecting a target particle from the generated plurality of alternative particles to obtain a decision result, where the decision result includes the material replenishment decision information corresponding to the target particle, and the particle swarm optimization algorithm PSO uses a dynamic self-adaptive inertia factor and dynamically adjusted acceleration coefficients.

[0008] In a second aspect, an embodiment of the present application provides a service platform, including a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the computer program, the steps of the decision-making method for material ordering and replenishment based on GA-PSO as described in the first aspect are implemented.

[0009] Compared with the related art, the decision-making method and service platform for material ordering and replenishment based on GA-PSO provided by the embodiments of the present application determine, in a plurality of preset ordering cycles, the plurality of delivery cycles agreed upon in each ordering cycle, and obtain the material ordering quantities corresponding to multiple target materials to be replenished in each ordering cycle, where the material ordering quantity is used to represent the total amount of materials to be delivered for each target material in the corresponding multiple delivery cycles; encode the number of delivery cycles and the material ordering quantities corresponding to multiple target materials respectively to generate a plurality of first matrix-type coded individuals, where each first matrix-type coded individual includes a plurality of first matrix-type sub-coded bodies each having a plurality of first sub-coded bodies, and the first sub-coded body is used to represent the material replenishment decision information of a target material in the corresponding multiple delivery cycles of an ordering cycle, and the material replenishment decision information includes a replenishment supply object and a replenishment supply quantity; after performing at least one genetic operation on the basis of the plurality of first matrix-type coded individuals by using a preset genetic algorithm GA, determine the fitness of each second sub-coded body corresponding to each second matrix-type coded individual generated in the current iteration, and perform genetic operation iteration based on the fitness and the second matrix-type coded individual until a plurality of candidate matrix-type coded individuals are generated; after using the candidate sub-coded bodies in the candidate matrix-type coded individuals as candidate particles, perform particle swarm search iteration processing on the plurality of candidate particles based on a preset particle swarm optimization algorithm PSO, and select a target particle from the plurality of generated alternative particles to obtain a decision result, where the decision result includes the material replenishment decision information corresponding to the target particle, which solves the problems that the decision on material inventory replenishment cannot meet the requirement of rapid decision-making, the decision-making efficiency is low, and the effect of material inventory replenishment is not good. By combining the global search ability of the genetic algorithm and the group learning characteristics of the particle swarm optimization algorithm PSO, it is possible to more effectively explore the solution space, find a solution closer to the global optimum, and improve the solution efficiency.

[0010] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more concise and understandable. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The drawings described herein are used to provide a further understanding of the present application and form a part of the present application. The illustrative embodiments and descriptions thereof of the present application are used to explain the present application and do not constitute an improper limitation of the present application. In the drawings:

[0012] Figure 1 is a hardware structure block diagram of a terminal of the decision-making method for material ordering and replenishment based on GA-PSO according to an embodiment of the present application;

[0013] Figure 2It is a flowchart of a decision-making method for material ordering and replenishment based on GA-PSO according to an embodiment of the present application;

[0014] Figure 3 It is a schematic diagram of an individual with matrix coding provided by an embodiment of the present application;

[0015] Figure 4 It is a schematic diagram of a genetic operation based on position crossover according to an embodiment of the present application;

[0016] Figure 5 It is a schematic diagram of a dynamic mutation operation for random variation according to an embodiment of the present application;

[0017] Figure 6 It is a schematic diagram of a dynamic mutation operation for adjacent cycle exchange according to an embodiment of the present application;

[0018] Figure 7 It is a schematic diagram of a dynamic mutation operation for random sharing according to an embodiment of the present application;

[0019] Figure 8 It is a schematic diagram of a dynamic mutation operation for random merging according to an embodiment of the present application;

[0020] Figure 9 It is a schematic diagram of particle search based on the particle swarm optimization algorithm according to an embodiment of the present application;

[0021] Figure 10 It is a structural block diagram of a decision-making device for material ordering and replenishment based on GA-PSO according to an embodiment of the present application. Detailed implementation manners

[0022] In order to make the objectives, technical solutions and advantages of the present application more clear and understandable, the present application will be described and explained below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments provided in the present application without making creative efforts belong to the scope of protection of the present application. In addition, it can also be understood that although the efforts made in this development process may be complex and lengthy, for those of ordinary skill in the art related to the content disclosed in the present application, some design, manufacturing or production changes based on the technical content disclosed in the present application are only conventional technical means and should not be understood as insufficient disclosure of the content of the present application.

[0023] References to "embodiments" in this application mean that specific features, structures, or characteristics described in connection with the embodiments can be included in at least one embodiment of this application. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those of ordinary skill in the art will explicitly and implicitly understand that the embodiments described in this application can be combined with other embodiments without conflict.

[0024] Unless otherwise defined, the technical terms or scientific terms involved in this application shall have the ordinary meaning understood by those of ordinary skill in the technical field to which this application belongs. The words such as "a", "an", "one kind", "the" and the like involved in this application do not indicate a limitation in quantity and can represent a singular or plural number. The terms "including", "comprising", "having" and any variations thereof involved in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may further include steps or units not listed, or may further include other steps or units inherent to these processes, methods, products or devices. The "multiple links" involved in this application refer to two or more links. "And / or" describes the association relationship of associated objects and indicates that there can be three relationships. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, and B exists alone. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific order for the objects.

[0025] The method embodiments provided in this embodiment can be executed on a terminal, a computer, or a similar computing device. Taking running on a terminal as an example, Figure 1 is a hardware structure block diagram of a terminal for the decision-making method of material ordering and replenishment based on GA-PSO according to an embodiment of this application. As Figure 1 shown, the terminal may include one or more ( Figure 1 only one is shown in the figure) processors 102 (the processor 102 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data. Optionally, the above terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those of ordinary skill in the art can understand that Figure 1 the structure shown is only schematic and does not limit the structure of the above terminal. For example, the terminal may further include more or fewer components than those shown in Figure 1 the figure, or have a different configuration from that shown in Figure 1 the figure.

[0026] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the decision-making method for material ordering and replenishment based on GA-PSO in the embodiments of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, implements the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some instances, the memory 104 may further include a memory remotely disposed relative to the processor 102, and these remote memories can be connected to the terminal 10 through a network. Examples of the above network include but are not limited to the Internet, intranet, local area network, mobile communication network, and combinations thereof.

[0027] The transmission device 106 is used to receive or send data via a network. Specific examples of the above network may include the wireless network provided by the communication provider of the terminal 10. In one instance, the transmission device 106 includes a network adapter (abbreviated as NIC), which can be connected to other network devices through a base station and thus communicate with the Internet. In one instance, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0028] This embodiment provides a decision-making method for material ordering and replenishment based on GA-PSO running on the above terminal. Figure 2 It is a flowchart of the decision-making method for material ordering and replenishment based on GA-PSO according to the embodiments of the present application, as Figure 2 shown, and the process includes the following steps:

[0029] Step S201, in a plurality of preset ordering cycles, determine the multiple delivery cycles agreed upon in each ordering cycle, and obtain the material ordering quantities corresponding to multiple target materials to be replenished in each ordering cycle, where the material ordering quantity is used to represent the total amount of materials to be delivered for each target material in the corresponding multiple delivery cycles.

[0030] The execution entity of the embodiment of the present application corresponds to a manufacturer that processes materials for inventory replenishment (for example, a manufacturer in the paint industry). It should be understood that the material inventory replenishment decision-making method described in the embodiment of the present application corresponds to the process of batch ordering and batch delivery by the manufacturer. During the decision-making period of the embodiment of the present application, there are multiple ordering cycles, and each ordering cycle includes multiple delivery cycles. Allocation delivery means that the supplier delivers the corresponding target materials within each negotiated delivery cycle. At the same time, it should also be understood that the manufacturer determines the material order quantity during the ordering cycle. That is, the decision-making point for each ordering cycle is the order quantity of each target material and the selected supplier, and it needs to comprehensively consider the material inventory, material price, material demand, and supplier price discount. Each ordering cycle contains multiple delivery cycles, and the manufacturer determines the delivery quantity of the target materials that the supplier needs to deliver during the delivery cycle. That is, the decision-making point for each delivery cycle is the delivery quantity of each target material by the supplier and the selected current cycle order quantity, vehicle type, supplier distance, warehouse capacity, storage cost, and stock-out cost. In this embodiment, the target materials include, but are not limited to, emulsions, resins, and titanium dioxide required for producing paint.

[0031] In this embodiment, within each ordering cycle, the manufacturer expects to deliver multiple target materials corresponding to each delivery cycle. The smallest data unit of the decision result of the embodiment of the present application is the quantity of each target material delivered in each delivery cycle and who (the supplier) delivers it. The decision result includes the delivery data of the target materials (including the replenishment supply object and replenishment supply quantity) in all delivery cycles of all ordering cycles within the preset decision-making period.

[0032] Step S202: Encode the number of delivery cycles and the material order quantities corresponding to multiple target materials respectively to generate multiple first matrix-type coding individuals. The first matrix-type coding individual includes multiple first matrix-type sub-coding bodies each having multiple first sub-coding bodies. The first sub-coding body is used to represent the material replenishment decision-making information of a target material in multiple delivery cycles corresponding to one ordering cycle. The material replenishment decision-making information includes the replenishment supply object and the replenishment supply quantity.

[0033] In this embodiment, after determining the delivery cycles and material order quantities corresponding to one ordering cycle, the material order quantity is allocated to each delivery cycle in a manner that meets the production demand (the material replenishment demand determined according to the initial inventory demand). Refer to Figure 3, 170 units of resin are allocated to Delivery Cycle 1, Delivery Cycle 2, and Delivery Cycle 3, and all 170 units of resin are allocated to Delivery Cycle 1. The replenishment supply quantities for Delivery Cycle 2 and Delivery Cycle 3 are 0, thus completing the initialization of one dimension (replenishment supply quantity, delivery quantity) during the population initialization process. Then, using the exhaustive method, the target material cost for supplying the corresponding replenishment supply quantity with the lowest cost is selected from multiple alternative replenishment supply objects as the corresponding replenishment supply object, thereby associating the corresponding replenishment supply object (supplier), and then generating the first matrix-type coding individual; reference Figure 3 , one first matrix-type sub-coding body in this embodiment represents the delivery situation of each target material within all delivery cycles (e.g., Delivery Cycle 1 to Delivery Cycle 3) within one ordering cycle (e.g., Ordering Cycle 1); meanwhile, one first sub-coding body represents the delivery situation of one target material within one ordering cycle. For example, taking titanium dioxide as the target material, one first sub-coding body correspondingly represents: Delivery Cycle 1: 0 units of titanium dioxide, Delivery Cycle 2: 200 units of titanium dioxide, Delivery Cycle 3: 170 units of titanium dioxide. At the same time, the corresponding replenishment supply quantity will be associated with the corresponding replenishment supply object ( Figure 3 not shown in

[0034] Step S203, after performing at least one genetic operation on multiple first matrix-type coding individuals using the preset genetic algorithm GA, determine the fitness of each second sub-coding body corresponding to the second matrix-type coding individual generated in the current iteration, and based on the fitness and the second matrix-type coding individual, perform genetic operation iteration until multiple candidate matrix-type coding individuals are generated. Among them, the genetic evolution operations include: individual selection based on the roulette wheel method and the elite retention strategy, self-adaptive crossover based on gene position, and dynamic mutation. The fitness is determined according to the ordering cost, transportation cost, storage cost, and emergency replenishment cost generated by the replenishment supply object corresponding to the second sub-coding body when replenishing the target material with this replenishment supply quantity.

[0035] In this embodiment, the fitness of each corresponding character coding body is calculated, and then the fitness of multiple target materials within the same ordering cycle is summed to calculate the individual fitness corresponding to the first matrix-type sub-coding individual. Then, the individual fitness within multiple ordering cycles is summed to obtain the total fitness corresponding to a corresponding matrix-type coding individual.

[0036] It can be understood that performing genetic operations is a means well-known to those skilled in the art. However, this application adopts genetic operations that are different from existing genetic operations, including individual selection based on the roulette wheel method and the elite retention strategy, self-adaptive crossover based on gene position, and dynamic mutation. This part of the genetic operations maintains the effectiveness and diversity of the solutions and simultaneously accelerates the convergence process of the algorithm.

[0037] Step S204, after taking the candidate sub-encoders in the candidate matrix-type coding individuals as candidate particles, based on the preset particle swarm optimization algorithm PSO, perform particle swarm search iterative processing on multiple candidate particles, and select a target particle from the generated multiple alternative particles to obtain a decision result, where the decision result includes the target material replenishment decision information corresponding to the target particle, and the particle swarm optimization algorithm PSO adopts a dynamic self-adaptive inertia factor and a dynamically adjusted acceleration coefficient.

[0038] In this embodiment, the implementation means of using the particle swarm optimization algorithm is understandable and known to those skilled in the art. However, this application adopts a processing method different from the conventional particle swarm optimization algorithm, that is, adopting a dynamic self-adaptive inertia factor and a dynamically adjusted acceleration coefficient. The dynamic self-adaptive inertia factor and the dynamically adjusted acceleration coefficient are configured and adjusted during the search process so that they can adaptively change according to the fitness value of the chromosome and the number of iterations. Compared with the fixed inertia factor, the dynamic self-adaptive inertia factor can better balance the global and local search capabilities. By dynamically adjusting the acceleration factor, the diversity of the particle swarm in the early search stage and the convergence of the algorithm in the later search stage are achieved.

[0039] Through the above steps S201 to S204, in a plurality of preset ordering cycles, determine the multiple delivery cycles agreed upon in each ordering cycle, and obtain the material order quantities corresponding to multiple target materials to be replenished in each ordering cycle. The material order quantity is used to represent the total amount of materials to be delivered for each target material in the corresponding multiple delivery cycles; encode the number of delivery cycles and the material order quantities corresponding to the multiple target materials respectively to generate multiple first matrix-type coding individuals. The first matrix-type coding individual includes multiple first matrix-type sub-coding bodies with multiple first sub-coding bodies. The first sub-coding body is used to represent the material replenishment decision information of a target material in the multiple delivery cycles corresponding to one ordering cycle. The material replenishment decision information includes the replenishment supply object and the replenishment supply quantity; after performing at least one genetic operation on the basis of the multiple first matrix-type coding individuals using the preset genetic algorithm GA, determine the fitness of the second sub-coding body corresponding to each second matrix-type coding individual generated in the current iteration, and based on the fitness and the second matrix-type coding individuals, perform genetic operation iteration until multiple candidate matrix-type coding individuals are generated; after using the candidate sub-coding bodies in the candidate matrix-type coding individuals as candidate particles, based on the preset particle swarm optimization algorithm PSO, perform particle swarm search iteration processing on the multiple candidate particles, and select a target particle from the generated multiple alternative particles to obtain a decision result. The decision result includes the target material replenishment decision information corresponding to the target particle, which solves the problems that the decision on material inventory replenishment cannot meet the requirements of rapid decision-making, has low decision-making efficiency, and poor material inventory replenishment effect. By combining the global search ability of the genetic algorithm and the group learning characteristics of the particle swarm optimization algorithm PSO, it is possible to more effectively explore the solution space, find a solution closer to the global optimum, and improve the solution efficiency.

[0040] It should be noted that the decision-making method of the embodiment of the present application can obtain the optimal solution of the "batch ordering - batch delivery" process in the coating manufacturing enterprise and achieve rapid convergence; the decision-making method of the embodiment of the present application has high flexibility and adaptability. The parameters in the GA-PSO algorithm (such as crossover probability, mutation probability, inertia weight, etc.) are all adaptively adjusted and dynamically adjusted to be adjusted according to the complexity and scale of the specific problem, so that the algorithm can maintain high efficiency and stability in various scenarios; the embodiment of the present application optimizes and adjusts key steps such as the coding method, chromosome crossover, and mutation; in terms of the coding method, matrix-type coding is adopted to more effectively represent the decision variables of inventory replenishment. In terms of chromosome crossover and mutation, individual selection based on the roulette wheel method and elitist retention strategy, self-adaptive crossover based on gene position, and dynamic mutation are adopted to maintain the effectiveness and diversity of the solution while accelerating the convergence process of the algorithm.

[0041] It should be further noted that the purpose of this method is to solve the problems of low solution efficiency and poor convergence quality faced by traditional meta-heuristic algorithms when dealing with complex operations research models, especially the dilemma that it is difficult to reach the optimal solution in the process optimization of "batch ordering - batch delivery" in coating manufacturing enterprises. By combining the global search ability of GA and the swarm learning characteristics of PSO, the method of the embodiment of the present invention can more effectively explore the solution space and find a solution closer to the global optimum. This method not only improves the solution efficiency but also significantly enhances the convergence quality.

[0042] In some of these embodiments, the number of delivery cycles and the material order quantities corresponding to various target materials are encoded to generate a plurality of first matrix-type encoded individuals, which are achieved through the following steps:

[0043] Step 21, determine the target information of multiple alternative supply objects, and randomly allocate the material order quantity corresponding to each target material within multiple delivery cycles of one order cycle to obtain the first delivery quantity of each target material within one delivery cycle. Among them, the target information includes the material discount rate and the transportation cost parameter.

[0044] In this embodiment, after determining the delivery cycle and the material order quantity corresponding to one order cycle, the material order quantity is allocated to each delivery cycle in a manner that meets the production demand (the material replenishment demand determined according to the initial inventory demand). Refer to Figure 3 , allocate 170 units of resin to delivery cycle 1, delivery cycle 2, and delivery cycle 3, and allocate all 170 units of resin to delivery cycle 1, and the replenishment supply quantities of delivery cycle 2 and delivery cycle 3 are 0, to obtain the first delivery quantity of resin within each delivery cycle

[0045] Step 22, based on the material discount rate and the transportation cost parameter, use the exhaustive method to determine, among multiple alternative supply objects, the alternative supply object for delivering the first delivery quantity of the target material. Take the determined alternative supply object and the first delivery quantity as the replenishment supply object and the replenishment supply quantity respectively, and generate a first sub-encoded body corresponding to the corresponding target material. Among them, the replenishment supply object is the alternative supply object with the lowest first cost for supplying the first delivery quantity of the target material, and the first cost is the sum of the ordering cost and the transportation cost determined according to the material discount rate and the transportation cost parameter respectively.

[0046] In this embodiment, the method of exhaustive search for the optimal supplier is adopted to determine the replenishment supply object, which specifically includes the following steps:

[0047] Step 1, calculate the ordering cost according to the gene value of the first sub-encoded body. For example: Refer to Figure 3, for the emulsion, first calculate the sum of the delivery volumes in three delivery cycles under the ordering period Q1, that is, 150 + 200 = 350. Then, according to the discount rates of each alternative supplier s corresponding to this delivery volume, calculate the ordering costs of each alternative supplier s. , subsequently, determine the vehicle models according to the delivery volumes of each delivery cycle, and then calculate the corresponding transportation costs of each alternative supplier s according to the distances of each alternative supplier s. , sum up these two costs, and select the alternative supplier with the minimum total cost as the option.

[0048] Step 2, repeat Step 1, and keep calculating all the purchasing periods Q of the emulsion. Similarly, calculate the ordering costs of target raw materials such as resin, and determine the alternative suppliers for different target materials in different ordering periods. Finally, sum up all the costs respectively to obtain the ordering costs. and .

[0049] Step 3, calculate the storage costs

[0050] Since there is a lead time for the materials, the target materials delivered in the previous delivery cycle can only arrive in the next cycle. Therefore, the ending inventory = beginning inventory + the ordered quantity in the previous delivery cycle - the demand quantity. For example: the ending inventory of resin in the previous production cycle is the beginning inventory of 50 minus the production demand of 10. The ending inventory in the second production cycle of resin is the beginning inventory of 40 plus the ordered quantity of 170 in the previous delivery cycle minus the production demand of 200, which equals the ending inventory of 10. Similarly, calculate the ending inventories of all materials in all production cycles, and calculate the warehousing costs according to the ending inventories. In addition, when the ending inventory is greater than the maximum storage capacity of the warehouse, the warehouse rental costs for the additional stored materials need to be calculated. Finally, obtain the storage costs.

[0051] Step 4, when the sum of the beginning inventory and the ordered quantity in the previous delivery cycle is less than the production demand, emergency replenishment will occur, and the emergency replenishment costs will be determined according to the shortage quantity of the materials.

[0052] Step 23, encode all the first sub - coding bodies corresponding to multiple target materials in the same ordering period into a first matrix - type sub - coding body, encode the first matrix - type sub - coding bodies corresponding to multiple ordering periods into a first matrix - type coding individual, and generate multiple first matrix - type coding individuals through population initialization.

[0053] In this embodiment, multiple first matrix - type coding individuals form the initial population. Each first matrix - type coding individual represents a potential strategy for the material inventory replenishment decision. A first matrix - type coding individual, such as Figure 3As shown, the values in the table represent the delivery quantities of each target raw material in each delivery cycle. The material order quantity in one order cycle is equal to the sum of the delivery quantities in the corresponding delivery cycles. Figure 3 For the emulsion shown, the delivery quantity in delivery cycle 1 is 0, the delivery quantity in delivery cycle 2 is 150, and the delivery quantity in delivery cycle 3 is 200. Then the delivery quantity in order cycle 1 is the sum of the three, which is 350. Similarly, for the resin, the delivery quantities in delivery cycles 1, 2, and 3 are 170, 0, and 0 respectively, and the delivery quantity in order cycle 1 is 170.

[0054] Through the above steps 21 to 23, the initialization of the initial population is achieved.

[0055] In some embodiments, after generating a plurality of first matrix - type encoded individuals, the following steps are implemented:

[0056] Step 31: Determine the current matrix - type encoded individual for individual selection based on the roulette - wheel method and the elitist retention strategy, and calculate the total fitness of each current matrix - type encoded individual according to a preset objective function based on the fitness of all current sub - encoded bodies corresponding to each current matrix - type encoded individual. Here, the current matrix - type encoded individual includes one of the following: the first matrix - type encoded individual, the second matrix - type encoded individual.

[0057] In this embodiment, the preset objective function is: Min(PC + SC + TC + EC), and the calculated total fitness is: F = Min(PC + SC + TC + EC), where,

[0058]

[0059]

[0060]

[0061]

[0062] Among them, PC represents the total material ordering cost corresponding to a corresponding matrix - type coded individual; SC represents the total target material storage cost corresponding to a corresponding matrix - type coded individual; TC represents the total material transportation cost corresponding to a corresponding matrix - type coded individual; EC represents the total material emergency replenishment cost corresponding to a corresponding matrix - type coded individual; i represents the i - th target material, I represents the set of target materials, i ∈ I; j represents the j - th replenishment supply object, J represents the set of replenishment supply objects, j ∈ J; q represents the q - th ordering cycle, Q represents the set of ordering cycles, q ∈ Q; k represents the k - th discount plan for the target material, K represents the set of discount plans, k ∈ K; m represents the m - th delivery cycle, M represents the set of delivery cycles, m ∈ M; v represents the v - th vehicle, V represents the set of vehicles, v ∈ V; is the discount rate corresponding to the k - th discount plan k of the i - th target material for the j - th replenishment supply object in the q - th ordering cycle; is the material base price of the i - th target material for the j - th replenishment supply object in the q - th ordering cycle; is the unit storage cost of the i - th target material; is the actual storage quantity of the i - th target material in the m - th delivery cycle under the q - th ordering cycle; in the m - th delivery cycle under the q - th ordering cycle; is the unit rental warehouse storage cost of the i - th target material; is the rental warehouse storage quantity of the i - th material in the m - th delivery cycle under the q - th ordering cycle; in the m - th delivery cycle under the q - th ordering cycle; is the distance cost corresponding to the replenishment supply object ; is the vehicle rental cost corresponding to the v - th vehicle; is the unit emergency transfer cost of the i - th target material; is the stock - out quantity of the i - th target material in the m - th delivery cycle under the q - th ordering cycle; in the m - th delivery cycle under the q - th ordering cycle; is a decision variable, indicating whether the v - th vehicle is selected for delivering the i - th target material from the j - th replenishment supply object in the m - th delivery cycle under the q - th ordering cycle; is a decision variable, indicating the quantity of the i - th target material ordered from the j - th replenishment supply object in the q - th ordering cycle; is a decision variable, indicating whether to select replenishment of the i - th target material from the j - th replenishment supply object in the m - th delivery cycle under the q - th ordering cycle; is a decision variable, indicating whether the v-th vehicle is selected for replenishing the i-th target material in the m-th delivery cycle of the q-th ordering cycle from the j-th replenishment supply object.

[0063] Step 32: According to the total fitness, select the current matrix-encoded individuals with a total fitness less than a preset fitness threshold from multiple current matrix-encoded individuals to obtain the first alternative encoded individuals, where the first alternative encoded individuals are used to represent the optimal individuals in the current population.

[0064] In this embodiment, the roulette wheel method can retain excellent individuals to a certain extent. However, in complex optimization problems, it is still possible that the optimal individuals in the current population are lost in the next generation, resulting in the genetic algorithm being unable to converge to the global optimal solution. In this embodiment, an elite retention strategy is introduced, that is, the best first alternative encoded individuals that appear among multiple current matrix-encoded individuals during the evolution process are directly copied to the next generation without genetic operations, that is, the remaining offspring are directly obtained by retaining the optimal individuals in the previous generation, so as to ensure that the algorithm can continuously approach the global optimal solution.

[0065] Step 33: After calculating the first selection probability based on the transposed fitness generated by transposing each total fitness, use the first selection probability to perform individual selection on all current matrix-encoded individuals except the first alternative encoded individuals based on the roulette wheel method to obtain a preset number of second alternative encoded individuals, and use all the first alternative encoded individuals and all the second alternative encoded individuals as the first intended encoded individuals corresponding to the selection result of completing the individual selection based on the roulette wheel method and the elite retention strategy.

[0066] In this embodiment, the total fitness is transposed according to the following formula:

[0067]

[0068] where gen represents the number of iterations, n represents the encoding of the n-th matrix-encoded individual in the corresponding population, N represents the set of individual encodings, n ∈ N, represents the n-th current matrix-encoded individual, represents the transposed fitness of the n-th current matrix-encoded individual after gen iterations, represents the total fitness of the n-th current matrix-encoded individual after gen iterations.

[0069] In this embodiment, the first selection probability is calculated according to the following formula:

[0070]

[0071] where, Denote the nth current matrix - coded individual in the population after gen iterations The first selection probability of being selected.

[0072] In this embodiment, selection is continuously performed according to the first selection probability until the number of second alternative coded individuals is filled to at least 95% of the individuals, that is, a preset number of second alternative coded individuals are obtained.

[0073] Through the above - mentioned steps 31 to 33, the genetic operation of individual selection based on the roulette - wheel method and the elitist retention strategy is realized, enabling the algorithm to continuously approach the global optimal solution.

[0074] In some of these embodiments, after generating the first intended coded individuals, the following steps are further implemented:

[0075] Step 41: Select the maximum total fitness, minimum total fitness, and average total fitness from the total fitnesses corresponding to all the first intended coded individuals, and calculate the current crossover probability corresponding to each first intended coded individual in the current iteration based on the total fitness of each first intended coded individual and the maximum total fitness, minimum total fitness, and average total fitness.

[0076] In this embodiment, the current crossover probability corresponding to each first intended coded individual in the current iteration is adaptively updated according to the following formula:

[0077]

[0078] Where, is the current crossover probability of the nth first intended coded individual in the population at the iteration, , are the minimum and maximum crossover probabilities respectively, is the total fitness of the ith first intended coded individual in the population at the iteration, , , are the maximum total fitness, minimum total fitness, and average total fitness in the population respectively; it can be understood that in this embodiment, the influence of the evolutionary generation and the individual fitness function value is considered to maintain the diversity of the population and reduce the exhaustive search process in GA - PSO; at the same time, an adaptive update mechanism is introduced to promote the regeneration of the population. In the context of adaptive crossover operation, the crossover probability decreases adaptively during the iteration process to increase the possibility of retaining high - quality solutions.

[0079] Step 42: Randomly select a preset number of intention sub-coding bodies from all the intention sub-coding bodies corresponding to the first intention-coded individuals as the first cross-sub-coding body group corresponding to each first intention-coded individual, and use the intention sub-coding bodies other than the first cross-sub-coding body group as the second cross-sub-coding body group corresponding to the first intention-coded body.

[0080] Step 43: After successively selecting two first intention-coded individuals from all the first intention-coded individuals based on the current crossover probability to obtain the first parental coded individual and the second parental coded individual, fill the first cross-sub-coding body group corresponding to the first parental coded individual and the second cross-sub-coding body group corresponding to the second parental coded individual into the first offspring coded individual according to the corresponding coding positions in the first parental coded individual and the second parental coded individual, and fill the first cross-sub-coding body group corresponding to the second parental coded individual and the second cross-sub-coding body group corresponding to the first parental coded individual into the second offspring coded individual according to the corresponding coding positions in the first parental coded individual and the second parental coded individual.

[0081] Step 44: Take the first offspring coded individual and the second offspring coded individual generated each time as the second intention-coded individuals, and use the corresponding second intention-coded individuals as the results of completing the genetic operation of the current position-based adaptive crossover.

[0082] In this embodiment, a crossover operation process based on order-based crossover (OBX for short) is adopted. Refer to Figure 4 , randomly select several positions (corresponding to the first cross-sub-coding body group) in two parental chromosomes (two first intention-coded individuals, refer to Figure 4 for Parent 1 and Parent 2). The positions can be discontinuous. First, find the positions of the genes selected in Parent 1 in Parent 2, and then generate the offspring with the remaining genes in Parent 2, ensuring that the positions correspond. Put the selected genes in Parent 1 into the remaining positions of the offspring in order. The other offspring is obtained in a similar way. Specifically, refer to Figure 4 , for Parent 1, it randomly selects the genes at positions 1, 2, and 6. Naturally, Parent 2 selects the genes at positions 3, 4, and 5. For the first offspring (refer to Figure 4 for Offspring 1), it finds the positions of the selected genes (1, 2, 6) in Parent 1 and the positions of the selected genes (3, 4, 5) in Parent 2, and fills in the selected genes correspondingly to generate the corresponding Offspring 1. For the second offspring (refer to Figure 4 for Offspring 2), it is the opposite of Offspring 1. It finds the positions of the selected genes (1, 2, 6) in Parent 2 and the positions of the selected genes (3, 4, 5) in Parent 1, and fills in the selected genes correspondingly to generate the corresponding Offspring 2.

[0083] Through the above steps 41 to 44, a genetic operation of adaptive crossover based on gene positions is realized.

[0084] In some of these embodiments, after generating the second intended coding individual, the following steps are further implemented:

[0085] Step 51, determine the current mutation probability corresponding to the current mutation operation according to a preset dynamic adjustment method.

[0086] Step 52, based on the current mutation probability, select the second intended coding individual currently undergoing dynamic mutation from all the second intended coding individuals, and randomly select a target mutation operation from a preset variety of mutation operations, where the mutation operation includes one of the following: random change, adjacent cycle exchange, random sharing, random merging.

[0087] Step 53, perform an edge operation corresponding to the target mutation operation on the selected second intended coding individual to generate the current matrix-type coding individual that completes the genetic operation, where the current matrix-type coding individual includes a plurality of third sub-coding bodies, and the third sub-coding body includes one of the second sub-coding body and the candidate sub-coding body.

[0088] In some of these embodiments, when the mutation operation is random change, referring to Figure 5 , step 53 of performing an edge operation corresponding to the target mutation operation on the selected second intended coding individual to generate the current matrix-type coding individual that completes the genetic operation is realized through the following steps:

[0089] Step 531-1, randomly select one fourth sub-coding body corresponding to at least one target material from all the fourth sub-coding bodies corresponding to the selected second intended coding individual;

[0090] Step 531-2, randomly select at least one delivery cycle from the multiple delivery cycles corresponding to the selected fourth sub-coding body, randomly change the first delivery quantity corresponding to the corresponding delivery cycle to obtain a new delivery quantity, and determine the alternative supply objects of the target material for delivering the new delivery quantity by using the exhaustive method based on the material discount rate and the transportation cost parameter;

[0091] Step 531-3, update the selected fourth sub-coding body based on the new delivery quantity and the determined alternative supply objects to generate a third sub-coding body at the same coding position.

[0092] In this embodiment, the delivery quantity 150 in delivery cycle 2 of order cycle 1 is randomly changed to 50 to generate a new delivery quantity, realizing the dynamic mutation operation based on random change.

[0093] In some of these embodiments, when the mutation operation is adjacent cycle exchange, refer to Figure 6 , in step 53, for the selected second-intention coded individual, perform the edge operation corresponding to the target mutation operation to generate the current matrix-type coded individual that has completed the genetic operation, which is achieved through the following steps:

[0094] Step 532-1: Randomly select one fourth sub-coded body corresponding to at least one target material from all the fourth sub-coded bodies corresponding to the selected second-intention coded individual.

[0095] Step 532-2: Randomly select two adjacent delivery cycles from the multiple delivery cycles corresponding to the selected fourth sub-coded body, and exchange the replenishment supply objects and replenishment supply quantities corresponding to the two adjacent delivery cycles to generate a third sub-coded body at the same coding position.

[0096] In this embodiment, an operation of swapping the delivery quantity 150 of delivery cycle 1 in order cycle 1 and the delivery quantity 0 of delivery cycle 2 in order cycle 1 is adopted. Then, in the new third sub-coded body, the delivery quantity of delivery cycle 1 in order cycle 1 is 0, and the delivery quantity of delivery cycle 2 in order cycle 1 is 150, realizing the dynamic mutation operation based on adjacent cycle exchange.

[0097] In some of these embodiments, when the mutation operation is random sharing, refer to Figure 7 , in step 53, for the selected second-intention coded individual, perform the edge operation corresponding to the target mutation operation to generate the current matrix-type coded individual that has completed the genetic operation, which is achieved through the following steps:

[0098] Step 533-1: Randomly select one fourth sub-coded body corresponding to at least one target material from all the fourth sub-coded bodies corresponding to the selected second-intention coded individual.

[0099] Step 533-2: Randomly select a target delivery cycle and a sharing delivery cycle from the multiple delivery cycles corresponding to the selected fourth sub-coded body, randomly share a first shared delivery quantity from the first delivery quantity corresponding to the target delivery cycle, and share the first shared delivery quantity to the sharing delivery cycle;

[0100] Step 533-3: Based on the material discount rate and transportation cost parameters, use the exhaustive method to respectively determine the target material for the remaining delivery quantity of the target delivery cycle and the alternative supply objects for the first shared delivery quantity to obtain the first supply object and the second supply object.

[0101] Step 533-4: Update the selected fourth sub-code body according to the remaining delivery quantity of the target delivery cycle, the first supply object, the first shared delivery quantity, and the second supply object, so as to generate a third sub-code body at the same coding position.

[0102] In this embodiment, in order to implement the re-batch operation of the delivery quantity during the batch delivery process, a mutation operator that can randomly allocate the delivery quantity of a certain delivery cycle to other delivery cycles is adopted. That is, the delivery quantity of 150 in delivery cycle 2 of order cycle 1 is randomly allocated to two delivery cycles, so that the delivery quantity in delivery cycle 1 under order cycle 1 is 100, and the delivery quantity in delivery cycle 2 under order cycle 1 is 50, realizing the dynamic mutation operation based on random sharing.

[0103] In some of these embodiments, when the mutation operation is random merging, refer to Figure 8 , in step 53, perform edge operations corresponding to the target mutation operation on the selected second intended coding individual to generate the current matrix-type coding individual that has completed the genetic operation, which is realized through the following steps:

[0104] Step 534-1: Randomly select one fourth sub-code body corresponding to at least one target material from all the fourth sub-code bodies corresponding to the selected second intended coding individual.

[0105] Step 534-2: Randomly select two delivery cycles from the multiple delivery cycles corresponding to the selected fourth sub-code body, merge the first delivery quantity of one of the two delivery cycles into the other delivery cycle, and determine the merged delivery quantity and the remaining delivery quantity corresponding to the two delivery cycles respectively after random merging.

[0106] Step 534-3: Based on the material discount rate and the transportation cost parameter, use the exhaustive method to respectively determine the alternative supply objects corresponding to the target materials of the merged delivery quantity and the remaining delivery quantity, and obtain the third supply object and the fourth supply object.

[0107] Step 534-4: Update the selected fourth sub-code body according to the remaining delivery quantity and the third supply object, and the remaining delivery quantity and the second supply object, so as to generate a third sub-code body at the same coding position.

[0108] In this embodiment, in order to implement the merging operation of the delivery quantity during the batch delivery process, a mutation operator that can randomly merge the delivery quantities of two delivery cycles into one delivery cycle is adopted. That is, the delivery quantity of 50 in delivery cycle 1 under order cycle 1 and the delivery quantity of 100 in delivery cycle 2 under order cycle 1 are merged, and they are merged into one delivery cycle, so that the delivery quantity in delivery cycle 2 under order cycle 1 is 150, realizing the dynamic mutation operation based on random merging.

[0109] Through the above steps 51 to 53, a genetic operation with dynamic mutation is implemented.

[0110] In some of these embodiments, after taking the candidate sub-coding bodies in the candidate matrix-type coding individuals as candidate particles, based on the preset particle swarm optimization algorithm PSO, particle swarm search processing is performed on multiple candidate particles, which is achieved through the following steps:

[0111] Step 61: Obtain an initial particle population including multiple candidate particles, and determine the initial particle position and preset initial particle velocity of each candidate particle. Among them, the initial particle position is used to characterize the material replenishment decision information corresponding to the candidate sub-coding body.

[0112] Step 62: Based on the preset dynamic adaptive change method, respectively determine the dynamic self-adaptive inertia factor, the first acceleration coefficient, and the second acceleration coefficient corresponding to the current particle search. Among them, the dynamic sub-adaptive inertia factor, the first acceleration coefficient, and the second acceleration coefficient are generated with self-adaptive changes according to the fitness corresponding to each candidate sub-coding body and the search iteration times.

[0113] Step 63: Based on the initial particle position, the initial particle velocity, the dynamic self-adaptive inertia factor, the first acceleration coefficient, and the second acceleration coefficient, use the particle swarm optimization algorithm to perform at least one population search iteration on the initial particle population until the total fitness corresponding to the matrix-type coding individual corresponding to the generated particle population is not greater than the preset fitness threshold, and obtain at least one target matrix-type coding individual including multiple alternative particles.

[0114] In this embodiment, the parameters of the particle swarm are adaptively changed. It can be understood that the particle swarm algorithm does not have mass and direction at the time of initialization. Each independent particle moves according to its own velocity within the optimal solution space. The mass of each particle is determined by the adaptive fitness function, and the direction and displacement of the particle are determined by its velocity variable. During the movement of the particle, it continuously adjusts its own movement path and direction through its own movement experience and by borrowing the movement experience of other particles. Usually, the particle can find its own optimal position in the space and obtain the optimal solution.

[0115] In this embodiment, the corresponding sub-coding body is processed as a particle in the particle swarm optimization algorithm, thereby realizing population search based on the particle swarm optimization algorithm PSO; in this embodiment, the particle swarm search process needs to use including the dynamic self-adaptive inertia factor and acceleration coefficients c1 and c2, which affect the global and local search capabilities of the particle. c1 and c2 respectively determine the degree of attention of the particle to the individual optimal solution and the global optimal solution; in this embodiment, the dynamic self-adaptive inertia factor The acceleration coefficients c1 and c2 are configured and adjusted during the search process to be adaptively variable according to the fitness value of the chromosome and the number of iterations. Compared with a fixed inertia factor, the dynamic self-adaptive inertia factor can better balance the global and local search capabilities. The adaptability is reflected by the acceleration coefficients c1 and c2. By dynamically adjusting the acceleration factors, the diversity of the particle swarm in the early search stage and the convergence of the algorithm in the later search stage are achieved dynamically can better balance the global and local search capabilities; in this embodiment, the dynamic self-adaptive inertia factor and the acceleration coefficients c1 and c2 are calculated by the following formulas:

[0116]

[0117]

[0118]

[0119] wherein, represents the maximum dynamic self-adaptive inertia factor , represents the minimum dynamic self-adaptive inertia factor , genmax represents the maximum number of iterations, is the total fitness of the nth candidate matrix-encoded individual in the population at the iteration, , are the maximum total fitness and the minimum total fitness in the population respectively.

[0120] In this embodiment, after adaptively updating the dynamic self-adaptive inertia factor , the acceleration coefficients c1 and c2, then each candidate particle is iterated according to the following formula one by one:

[0121]

[0122] wherein, represents the initial velocity of the nth candidate matrix-encoded individual and all its corresponding candidate particles in the population at the gen iteration, represents the position of the nth candidate matrix-encoded individual in the population at the gen iteration; represents the inertia weight; r1, r2 represent random numbers in the range of (0, 1), Wbest represents the optimal position of the candidate matrix-encoded individual, and GWbest represents the global optimal position.

[0123] In this embodiment, the position of the candidate particle is updated according to the speed. In this embodiment, the position can also be regarded as the structure of the matrix-type encoded individual. Then, the position update refers to the change of the gene value on the corresponding sub-encoded body, denoted by W n,gen+1 represents the position of the nth matrix-type encoded individual in the population at the (gen + 1)-th iteration. Then:

[0124] .

[0125] In this embodiment, referring to Figure 9 , the particle position update operation in this embodiment includes: First, it is the inertial position of the particle, which is determined by the speed of the particle itself, that is ; Second, it is the historical optimal position of the particle, which can be expressed as Wbest; Finally, it is the position GWbest of the global optimal solution of the particles in the current population. The updated position of the particle is jointly contributed by these three factors. The particle will be weighted by the dynamic self-adaptive inertia factor , acceleration coefficient and and summed up to finally obtain a new particle.

[0126] In some embodiments, from the generated multiple alternative particles, a target particle is selected to obtain a decision result, which is achieved through the following steps:

[0127] Step 71, obtain the alternative particles corresponding to at least one target matrix-type encoded individual, and calculate the fitness of each alternative sub-encoded body corresponding to the alternative particle;

[0128] Step 72, according to the fitness of the alternative sub-encoded body, select the alternative particle with the minimum fitness from the multiple alternative particles to obtain the target particle. Among them, the material replenishment decision information corresponding to the alternative sub-encoded body corresponding to the target particle is the target material replenishment decision information.

[0129] This embodiment also provides a decision-making device for material ordering and replenishment based on GA-PSO. This device is used to implement the above embodiments and preferred implementation manners, and those that have been described will not be repeated. As used below, terms such as "module", "unit", "sub-unit", etc. can be a combination of software and / or hardware that can achieve a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0130] Figure 10 is a structural block diagram of the decision-making device for material ordering and replenishment based on GA-PSO according to an embodiment of the present application. As Figure 10 shown, the device includes an acquisition module 101, an encoding module 102, an iteration module 103, and a processing module 104, where

[0131] An acquisition module 101 is configured to determine, in a plurality of preset ordering cycles, the multiple delivery cycles agreed upon in each ordering cycle, and acquire the material order quantities corresponding to multiple target materials to be replenished in each ordering cycle, where the material order quantity is used to represent the total amount of materials to be delivered for each target material in the corresponding multiple delivery cycles;

[0132] An encoding module 102, which is coupled to the acquisition module 101, is configured to encode the number of delivery cycles and the material order quantities corresponding to multiple target materials respectively to generate a plurality of first matrix-type encoding individuals, where each first matrix-type encoding individual includes a plurality of first matrix-type sub-encoding bodies each having a plurality of first sub-encoding bodies, and the first sub-encoding body is used to represent the material replenishment decision information of a target material in the multiple delivery cycles corresponding to one ordering cycle, and the material replenishment decision information includes a replenishment supply object and a replenishment supply quantity;

[0133] An iteration module 103, which is coupled to the encoding module 102, is configured to determine the fitness of the second sub-encoding body corresponding to each second matrix-type encoding individual generated in the current iteration after performing at least one genetic operation on the basis of a plurality of first matrix-type encoding individuals by using a preset genetic algorithm GA, and perform genetic operation iteration based on the fitness and the second matrix-type encoding individuals until a plurality of candidate matrix-type encoding individuals are generated, where the genetic evolution operations include: individual selection based on the roulette wheel method and the elite retention strategy, self-adaptive crossover based on gene positions, and dynamic mutation, and the fitness is determined according to the ordering cost, transportation cost, storage cost, and emergency replenishment cost generated by the replenishment supply object corresponding to the second sub-encoding body for replenishing the target material of the replenishment supply quantity;

[0134] A processing module 104, which is coupled to the iteration module 103, is configured to, after using the candidate sub-encoding bodies in the candidate matrix-type encoding individuals as candidate particles, perform particle swarm search iteration processing on the plurality of candidate particles based on a preset particle swarm optimization algorithm PSO, and select a target particle from the plurality of generated alternative particles to obtain a decision result, where the decision result includes the target material replenishment decision information corresponding to the target particle, and the particle swarm optimization algorithm PSO uses a dynamic self-adaptive inertia factor and dynamically adjusted acceleration coefficients.

[0135] In some embodiments, the encoding module 102 further includes:

[0136] An allocation unit is configured to determine the target information of a plurality of alternative supply objects, and randomly allocate the material order quantity corresponding to each target material within the multiple delivery cycles of one ordering cycle to obtain the first delivery quantity of each target material within one delivery cycle, where the target information includes a material discount rate and a transportation cost parameter.

[0137] A selection unit, which is coupled to the allocation unit, is configured to use the exhaustive method to determine, from multiple alternative supply objects, an alternative supply object for delivering the target material of the first delivery volume based on the material discount rate and the transportation cost parameter, and use the determined alternative supply object and the first delivery volume as the replenishment supply object and the replenishment supply quantity respectively, and generate a first sub-coding body corresponding to the corresponding target material. The replenishment supply object is the alternative supply object with the lowest first cost for supplying the target material of the first delivery volume, and the first cost is the sum of the ordering cost and the transportation cost determined according to the material discount rate and the transportation cost parameter respectively.

[0138] A coding unit, which is coupled to the selection unit, is configured to code all the first sub-coding bodies corresponding to multiple target materials within the same ordering cycle into a first matrix-type sub-coding body, code the first matrix-type sub-coding bodies corresponding to multiple ordering cycles into a first matrix-type coding individual, and generate multiple first matrix-type coding individuals through population initialization.

[0139] In some embodiments, after generating multiple first matrix-type coding individuals, the iteration module 93 is further configured to determine a current matrix-type coding individual for individual selection based on the roulette wheel method and the elitist retention strategy, and calculate the total fitness of each current matrix-type coding individual according to a preset objective function based on the fitness of all the current sub-coding bodies corresponding to each current matrix-type coding individual. The current matrix-type coding individual includes one of the following: the first matrix-type coding individual, the second matrix-type coding individual; according to the total fitness, screen out the current matrix-type coding individuals with a total fitness less than a preset fitness threshold from multiple current matrix-type coding individuals to obtain first alternative coding individuals, where the first alternative coding individuals are used to represent the optimal individuals in the current population; after calculating a first selection probability based on the transposed fitness generated by transposing each total fitness, use the first selection probability to perform individual selection on all current matrix-type coding individuals except the first alternative coding individuals based on the roulette wheel method to obtain a preset number of second alternative coding individuals, and use all the first alternative coding individuals and all the second alternative coding individuals as the first intended coding individuals corresponding to the selection result of completing individual selection based on the roulette wheel method and the elitist retention strategy.

[0140] In some embodiments, the iteration module 103 is further configured to calculate the total fitness F according to the following formula:

[0141] F = Min(PC + SC + TC + EC)

[0142]

[0143]

[0144]

[0145]

[0146] Among them, PC represents the total material ordering cost corresponding to a corresponding matrix-coded individual; SC represents the total target material storage cost corresponding to a corresponding matrix-coded individual; TC represents the total material transportation cost corresponding to a corresponding matrix-coded individual; EC represents the total material emergency replenishment cost corresponding to a corresponding matrix-coded individual; i represents the i-th target material, I represents the set of target materials, i∈I; j represents the j-th replenishment supply object, J represents the set of replenishment supply objects, j∈J; q represents the q-th ordering cycle, Q represents the set of ordering cycles, q∈Q; k represents the k-th discount plan of the target material, K represents the set of discount plans, k∈K; m represents the m-th delivery cycle, M represents the set of delivery cycles, m∈M; v represents the v-th vehicle, V represents the set of vehicles, v∈V; is the discount rate corresponding to the kth discount scheme k for the i-th target material by the j-th replenishment supply object in the q-th ordering period; is the base price of the i-th target material for the j-th replenishment supply object in the q-th ordering cycle; It is Unit storage cost of the target material; It is Order cycle Delivery cycle The actual storage quantity of the target material; is the unit rental warehouse storage cost of the i-th target material; It is Order cycle Delivery cycle Storage capacity of rented warehouses for various materials; Replenishment supply object The corresponding distance cost; is the rental cost corresponding to the vth vehicle; It is Unit emergency transfer cost of the target material; It is Order cycle Delivery cycle The out-of-stock quantity of the target material; is a decision variable, indicating whether the vth vehicle is selected when the i-th target material in the m-th delivery cycle under the q-th ordering cycle is delivered to the j-th replenishment supply object; is a decision variable, representing the quantity of the i-th target material selected to be ordered from the j-th replenishment supplier in the q-th ordering cycle; is a decision variable, representing whether the i-th target material in the m-th delivery cycle in the q-th ordering cycle selects to be replenished from the j-th replenishment supplier; is a decision variable, representing whether the v-th vehicle is selected when the i-th target material in the m-th delivery cycle in the q-th ordering cycle is replenished from the j-th replenishment supplier.

[0147] In some of these embodiments, after generating the first intended coding individuals, the iterative module 103 is further configured to select the maximum total fitness, the minimum total fitness, and the average total fitness from the total fitness corresponding to all the first intended coding individuals, and calculate the current crossover probability corresponding to each first intended coding individual in the current iteration based on the total fitness corresponding to each first intended coding individual and the maximum total fitness, the minimum total fitness, and the average total fitness; randomly select a preset number of intended sub-coding bodies from all the intended sub-coding bodies corresponding to the first intended coding individuals as the first crossover sub-coding body group corresponding to each first intended coding individual, and use the intended sub-coding bodies other than the first crossover sub-coding body group as the second crossover sub-coding body group corresponding to the first intended coding body; after successively selecting two first intended coding individuals from all the first intended coding individuals based on the current crossover probability to obtain a first parental coding individual and a second parental coding individual, fill the first crossover sub-coding body group corresponding to the first parental coding individual and the second crossover sub-coding body group corresponding to the second parental coding individual into the first offspring coding individual according to the corresponding coding positions in the first parental coding individual and the second parental coding individual, and fill the first crossover sub-coding body group corresponding to the second parental coding individual and the second crossover sub-coding body group corresponding to the first parental coding individual into the second offspring coding individual according to the corresponding coding positions in the first parental coding individual and the second parental coding individual; use the first offspring coding individual and the second offspring coding individual generated each time as the second intended coding individuals, and use the corresponding second intended coding individuals as the results of completing the genetic operation of self-adaptive crossover based on the gene positions in the current iteration.

[0148] In some of these embodiments, after generating the second intended coding individuals, the iterative module 103 is further configured to determine the current mutation probability corresponding to the current mutation operation according to a preset dynamic adjustment method; based on the current mutation probability, select the second intended coding individuals currently undergoing dynamic mutation from all the second intended coding individuals, and randomly select a target mutation operation from a preset variety of mutation operations, where the mutation operations include one of the following: random change, adjacent cycle exchange, random sharing, and random merging; perform an edge operation corresponding to the target mutation operation on the selected second intended coding individuals to generate the current matrix-type coding individuals that have completed the genetic operation, where the current matrix-type coding individuals include multiple third sub-coding bodies, and the third sub-coding bodies include one of the second sub-coding bodies and the candidate sub-coding bodies.

[0149] In some of these embodiments, when the mutation operation is a random change, the iterative module 103 is further configured to randomly select a fourth sub-coding body corresponding to at least one target material from all the fourth sub-coding bodies corresponding to the selected second intended coding individuals; randomly select at least one delivery cycle from the multiple delivery cycles corresponding to the selected fourth sub-coding body, randomly change the first delivery quantity corresponding to the corresponding delivery cycle to obtain a new delivery quantity, and determine alternative supply objects of the target material for delivering the new delivery quantity by using the exhaustive method based on the material discount rate and the transportation cost parameter; update the selected fourth sub-coding body based on the new delivery quantity and the determined alternative supply objects to generate a third sub-coding body at the same coding position.

[0150] In some of these embodiments, when the mutation operation is an adjacent cycle exchange, the iterative module 103 is further configured to randomly select a fourth sub-coding body corresponding to at least one target material from all the fourth sub-coding bodies corresponding to the selected second intended coding individuals; randomly select two adjacent delivery cycles from the multiple delivery cycles corresponding to the selected fourth sub-coding body, and exchange the replenishment supply objects and the replenishment supply quantities corresponding to the two adjacent delivery cycles to generate a third sub-coding body at the same coding position;

[0151] In some of these embodiments, when the mutation operation is random sharing, the iteration module 103 is further configured to randomly select one fourth sub-coding body corresponding to at least one target material from all the fourth sub-coding bodies corresponding to the selected second intended coding individual; among the multiple delivery cycles corresponding to the selected fourth sub-coding body, randomly select a target delivery cycle and a sharing delivery cycle, and randomly share a first shared delivery quantity from the first delivery quantity corresponding to the target delivery cycle, and allocate the first shared delivery quantity to the sharing delivery cycle; based on the material discount rate and the transportation cost parameter, use the exhaustive method to respectively determine the target material for delivering the remaining delivery quantity of the target delivery cycle and the alternative supply objects for the first shared delivery quantity, to obtain a first supply object and a second supply object; according to the remaining delivery quantity of the target delivery cycle and the first supply object, the first shared delivery quantity and the second supply object, update the selected fourth sub-coding body to generate a third sub-coding body at the same coding position.

[0152] In some of these embodiments, when the mutation operation is random merging, the iteration module 103 is further configured to randomly select one fourth sub-coding body corresponding to at least one target material from all the fourth sub-coding bodies corresponding to the selected second intended coding individual; among the multiple delivery cycles corresponding to the selected fourth sub-coding body, randomly select two delivery cycles, and merge the first delivery quantity of one of the two delivery cycles into the other delivery cycle, and determine the merged delivery quantity and the remaining delivery quantity corresponding to the two delivery cycles after random merging; based on the material discount rate and the transportation cost parameter, use the exhaustive method to respectively determine the alternative supply objects corresponding to the target materials for delivering the merged delivery quantity and the remaining delivery quantity, to obtain a third supply object and a fourth supply object; according to the remaining delivery quantity and the third supply object, the remaining delivery quantity and the second supply object, update the selected fourth sub-coding body to generate a third sub-coding body at the same coding position.

[0153] In some of these embodiments, the processing module 104 further includes:

[0154] An acquisition unit, configured to acquire an initial particle population including a plurality of candidate particles, and determine the initial particle position and a preset initial particle velocity of each candidate particle, where the initial particle position is used to characterize the material replenishment decision information corresponding to the candidate sub-coding body.

[0155] A determination unit, coupled to the acquisition unit, configured to respectively determine a dynamic adaptive inertia factor, a first acceleration coefficient, and a second acceleration coefficient corresponding to the current particle search based on a preset dynamic adaptive change method, where the dynamic sub-adaptive inertia factor, the first acceleration coefficient, and the second acceleration coefficient are adaptively changed and generated according to the fitness corresponding to each candidate sub-coding body and the search iteration times.

[0156] A search unit, coupled to the determination unit, is configured to perform at least one population search iteration on the initial particle population using the particle swarm optimization algorithm based on the initial particle position, initial particle velocity, dynamic self-adaptive inertia factor, first acceleration coefficient, and second acceleration coefficient until the total fitness corresponding to the matrix-type encoded individuals of the generated particle population is not greater than a preset fitness threshold, so as to obtain at least one target matrix-type encoded individual including a plurality of alternative particles.

[0157] In some embodiments, the processing module 104 is further configured to obtain the alternative particles corresponding to at least one target matrix-type encoded individual, and calculate the fitness of the alternative sub-encoded bodies corresponding to each alternative particle; according to the fitness of the alternative sub-encoded bodies, select the alternative particle with the minimum fitness from the plurality of alternative particles to obtain a target particle, where the material replenishment decision information corresponding to the alternative sub-encoded body corresponding to the target particle is the target material replenishment decision information.

[0158] This embodiment also provides a service platform, including a memory and a processor. A computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0159] Optionally, the above service platform may further include a transmission device and an input / output device, where the transmission device is connected to the above processor, and the input / output device is connected to the above processor.

[0160] Optionally, in this embodiment, the above processor may be configured to execute the following steps through a computer program:

[0161] S1. In a preset plurality of ordering cycles, determine the plurality of delivery cycles agreed upon in each ordering cycle, and obtain the material ordering quantities corresponding to multiple target materials to be replenished in each ordering cycle. The material ordering quantity is used to represent the total amount of materials to be delivered for each target material in the corresponding plurality of delivery cycles.

[0162] S2. Encode the number of delivery cycles and the material ordering quantities corresponding to multiple target materials respectively to generate a plurality of first matrix-type encoded individuals. The first matrix-type encoded individual includes a plurality of first matrix-type sub-encoded bodies each having a plurality of first sub-encoded bodies. The first sub-encoded body is used to represent the material replenishment decision information of a target material in the corresponding plurality of delivery cycles of an ordering cycle. The material replenishment decision information includes a replenishment supply object and a replenishment supply quantity.

[0163] S3. After performing at least one genetic operation on multiple first matrix - type encoded individuals using the preset genetic algorithm GA, determine the fitness of the second sub - encoded body corresponding to each second matrix - type encoded individual generated in the current iteration, and perform iterative genetic operations based on the fitness and the second matrix - type encoded individuals until multiple candidate matrix - type encoded individuals are generated.

[0164] S4. After using the candidate sub - encoded bodies in the candidate matrix - type encoded individuals as candidate particles, perform particle swarm search iterative processing on multiple candidate particles based on the preset particle swarm optimization algorithm PSO, and select a target particle from the generated multiple alternative particles to obtain a decision result. The decision result includes the target material replenishment decision information corresponding to the target particle. The particle swarm optimization algorithm PSO uses a dynamic self - adaptive inertia factor and dynamically adjusted acceleration coefficients.

[0165] It should be noted that the specific examples in this embodiment can refer to the examples described in the above - mentioned embodiment and alternative implementation manners, and will not be elaborated here.

[0166] In addition, in combination with the above - mentioned decision - making method for material ordering and replenishment based on GA - PSO in the embodiment, the embodiment of the present application can be implemented by providing a storage medium. A computer program is stored on the storage medium; when the computer program is executed by a processor, it implements any one of the above - mentioned decision - making methods for material ordering and replenishment based on GA - PSO.

[0167] Those skilled in the art should understand that the technical features of the above - mentioned embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above - mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0168] The above - mentioned embodiments only represent several implementation manners of the present application. Their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the invention patent. It should be pointed out that for those of ordinary skill in the art, without departing from the concept of the present application, several deformations and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A decision-making method for material ordering and replenishment based on GA-PSO, characterized in that, Including: In a plurality of preset ordering cycles, determine the plurality of delivery cycles agreed upon in each ordering cycle, and obtain the material order quantities corresponding to multiple target materials to be replenished in each ordering cycle, where the material order quantity is used to represent the total amount of materials to be delivered for each target material in the corresponding multiple delivery cycles; Encode the number of delivery cycles and the material order quantities corresponding to multiple target materials respectively to generate a plurality of first matrix-type coding individuals, where the first matrix-type coding individual includes a plurality of first matrix-type sub-coding bodies each having a plurality of first sub-coding bodies, and the first sub-coding body is used to represent the material replenishment decision information of a target material in the multiple delivery cycles corresponding to one ordering cycle, and the material replenishment decision information includes a replenishment supply object and a replenishment supply quantity; After performing at least one genetic operation on the basis of the plurality of first matrix-type coding individuals using a preset genetic algorithm GA, determine the fitness of the second sub-coding body corresponding to each second matrix-type coding individual generated in the current iteration, and perform genetic operation iteration based on the fitness and the second matrix-type coding individual until a plurality of candidate matrix-type coding individuals are generated, where the genetic operation includes: individual selection based on roulette wheel method and elitist retention strategy, self-adaptive crossover based on gene position, and dynamic mutation, and the fitness is determined according to the ordering cost, transportation cost, storage cost, and emergency replenishment cost generated by the replenishment supply object corresponding to the second sub-coding body when replenishing the target material of the replenishment supply quantity; After taking the candidate sub-coding bodies in the candidate matrix-type coding individuals as candidate particles, perform particle swarm search iteration processing on the plurality of candidate particles based on a preset particle swarm optimization algorithm PSO, and select a target particle from the generated plurality of alternative particles to obtain a decision result, where the decision result includes the material replenishment decision information corresponding to the target particle, and the particle swarm optimization algorithm PSO uses a dynamic self-adaptive inertia factor and a dynamically adjusted acceleration coefficient.

2. The method according to claim 1, characterized in that Encoding the number of delivery cycles and the material order quantities corresponding to multiple target materials respectively to generate a plurality of first matrix-type coding individuals includes: Determine the target information of multiple alternative supply objects, and randomly allocate the material order quantity corresponding to each target material within the multiple delivery cycles of one ordering cycle to obtain the first delivery quantity of each target material in one delivery cycle, where the target information includes a material discount rate and a transportation cost parameter; Based on the material discount rate and the transportation cost parameter, using the exhaustive method, among multiple alternative supply objects, determine the alternative supply object for delivering the target material of the first delivery quantity, and use the determined alternative supply object and the first delivery quantity as the replenishment supply object and the replenishment supply quantity respectively, and generate one first sub-coding body corresponding to the corresponding target material, where the replenishment supply object is the alternative supply object with the lowest first cost for supplying the target material of the first delivery quantity, and the first cost is the sum of the ordering cost and the transportation cost determined according to the material discount rate and the transportation cost parameter respectively; Encode all the first sub-coding bodies corresponding to multiple target materials within the same ordering cycle into one first matrix-type sub-coding body, encode the first matrix-type sub-coding bodies corresponding to multiple ordering cycles into one first matrix-type coding individual, and generate multiple first matrix-type coding individuals through population initialization.

3. The method according to claim 2, wherein After generating multiple first matrix-type coding individuals, the method further includes: Determine the current matrix-type coding individual for individual selection based on the roulette wheel method and the elite retention strategy, and calculate the total fitness of each current matrix-type coding individual according to a preset objective function based on the fitness of all current sub-coding bodies corresponding to each current matrix-type coding individual, where the current matrix-type coding individual includes one of the following: the first matrix-type coding individual, the second matrix-type coding individual; According to the total fitness, screen out the current matrix-type coding individuals with a total fitness less than a preset fitness threshold from multiple current matrix-type coding individuals to obtain first alternative coding individuals, where the first alternative coding individuals are used to represent the optimal individuals in the current population; After calculating the first selection probability based on the transposed fitness generated by transposing each total fitness, use the first selection probability to perform individual selection on all current matrix-type coding individuals except the first alternative coding individuals based on the roulette wheel method to obtain a preset number of second alternative coding individuals, and use all the first alternative coding individuals and all the second alternative coding individuals as the first intended coding individuals corresponding to the selection result of completing individual selection based on the roulette wheel method and the elite retention strategy.

4. The method according to claim 3, wherein Calculate the total fitness F according to the following formula: F = Min(PC + SC + TC + EC) Among them, PC represents the total material ordering cost corresponding to a corresponding matrix - type coded individual; SC represents the total target material storage cost corresponding to a corresponding matrix - type coded individual; TC represents the total material transportation cost corresponding to a corresponding matrix - type coded individual; EC represents the total material emergency replenishment cost corresponding to a corresponding matrix - type coded individual; i represents the i - th target material, I represents the set of target materials, i ∈ I; j represents the j - th replenishment supply object, J represents the set of replenishment supply objects, j ∈ J; q represents the q - th ordering cycle, Q represents the set of ordering cycles, q ∈ Q; k represents the k - th discount plan for the target material, K represents the set of discount plans, k ∈ K; m represents the m - th delivery cycle, M represents the set of delivery cycles, m ∈ M; v represents the v - th vehicle, V represents the set of vehicles, v ∈ V; is the discount rate corresponding to the k - th discount plan k of the i - th target material for the j - th replenishment supply object in the q - th ordering cycle; is the material base price of the i - th target material for the j - th replenishment supply object in the q - th ordering cycle; is the unit storage cost of the i - th target material; is the actual storage quantity of the i - th target material in the m - th delivery cycle in the q - th ordering cycle; ; is the unit rental warehouse storage cost of the i - th target material; is the rental warehouse storage quantity of the i - th material in the m - th delivery cycle in the q - th ordering cycle; ; is the distance cost corresponding to the replenishment supply object ; is the vehicle rental cost corresponding to the v - th vehicle; is the unit emergency transfer cost of the i - th target material; is the stock - out quantity of the i - th target material in the m - th delivery cycle in the q - th ordering cycle; ; is a decision variable, indicating whether the v - th vehicle is selected for delivering the i - th target material from the j - th replenishment supply object in the m - th delivery cycle of the q - th ordering cycle; is a decision variable, indicating the quantity of the i - th target material ordered from the j - th replenishment supply object in the q - th ordering cycle; is a decision variable, indicating whether to select replenishment of the i - th target material from the j - th replenishment supply object in the m - th delivery cycle of the q - th ordering cycle; is a decision variable, indicating whether the v-th vehicle is selected for replenishing the i-th target material in the m-th delivery period of the q-th ordering cycle from the j-th replenishment supply object.

5. The method according to claim 3, characterized in that, After generating the first intended coding individuals, the method further includes: Select the maximum total fitness, the minimum total fitness, and the average total fitness from the total fitness corresponding to all the first intended coding individuals, and calculate the current crossover probability corresponding to each first intended coding individual for the current iteration based on the total fitness corresponding to each first intended coding individual and the maximum total fitness, the minimum total fitness, and the average total fitness; Randomly select a preset number of the intention sub-coding bodies from all the intention sub-coding bodies corresponding to the first intention coding individuals as the first cross-sub-coding body group corresponding to each of the first intention coding individuals, and use the intention sub-coding bodies other than the first cross-sub-coding body group as the second cross-sub-coding body group corresponding to the first intention coding individuals; After successively selecting two of the first intention coding individuals from all the first intention coding individuals based on the current crossover probability to obtain a first parent coding individual and a second parent coding individual, fill the first cross-sub-coding body group corresponding to the first parent coding individual and the second cross-sub-coding body group corresponding to the second parent coding individual into the first offspring coding individual according to the corresponding coding positions in the first parent coding individual and the second parent coding individual, and fill the first cross-sub-coding body group corresponding to the second parent coding individual and the second cross-sub-coding body group corresponding to the first parent coding individual into the second offspring coding individual according to the corresponding coding positions in the first parent coding individual and the second parent coding individual; Use the first offspring coding individual and the second offspring coding individual generated each time as the second intention coding individuals, and use the corresponding second intention coding individuals as the results of completing the genetic operation of the current self-adaptive crossover based on the gene position.

6. The method according to claim 5, characterized in that, After generating the second intention coding individuals, the method further includes: Determine the current mutation probability corresponding to the current mutation operation according to a preset dynamic adjustment method; Based on the current mutation probability, select the second intention coding individual currently undergoing dynamic mutation from all the second intention coding individuals, and randomly select a target mutation operation from a preset variety of mutation operations, where the mutation operations include one of the following: random change, adjacent cycle exchange, random sharing, random merging; Perform an edge operation corresponding to the target mutation operation on the selected second intention coding individual to generate the matrix-type coding individual of the current time that completes the genetic operation, where the matrix-type coding individual of the current time includes a plurality of third sub-coding bodies, and the third sub-coding body includes one of the second sub-coding body and the candidate sub-coding body.

7. The method according to claim 6, wherein when the mutation operation is a random change, the method includes: Randomly select one of the fourth sub-coding bodies corresponding to at least one target material from all the fourth sub-coding bodies corresponding to the selected second intention coding individual; Randomly select at least one of the delivery cycles corresponding to the selected fourth sub-coding body, randomly change the first delivery quantity corresponding to the corresponding delivery cycle to obtain a new delivery quantity, and use the exhaustive method to determine the alternative supply object of the target material for delivering the new delivery quantity based on the material discount rate and the transportation cost parameter; Update the selected fourth sub - coding body based on the new delivery volume and the determined alternative supply object to generate the third sub - coding body at the same coding position; When the mutation operation is adjacent - cycle exchange, the method includes: Randomly select one fourth sub - coding body corresponding to at least one target material from all the fourth sub - coding bodies corresponding to the selected second - intention coding individual; Among the multiple delivery cycles corresponding to the selected fourth sub - coding body, randomly select two adjacent delivery cycles, and exchange the replenishment supply object and the replenishment supply volume corresponding to the two adjacent delivery cycles to generate the third sub - coding body at the same coding position; When the mutation operation is random sharing, the method includes: Randomly select one fourth sub - coding body corresponding to at least one target material from all the fourth sub - coding bodies corresponding to the selected second - intention coding individual; Among the multiple delivery cycles corresponding to the selected fourth sub - coding body, randomly select a target delivery cycle and a sharing delivery cycle, randomly share a first sharing delivery volume from the first delivery volume corresponding to the target delivery cycle, and allocate the first sharing delivery volume to the sharing delivery cycle; Based on the material discount rate and the transportation cost parameter, use the exhaustive method to respectively determine the target material for delivering the remaining delivery volume of the target delivery cycle and the alternative supply object for the first sharing delivery volume, obtaining the first supply object and the second supply object; Update the selected fourth sub - coding body according to the remaining delivery volume of the target delivery cycle, the first supply object, the first sharing delivery volume, and the second supply object to generate the third sub - coding body at the same coding position; When the mutation operation is random merging, the method includes: Randomly select one fourth sub - coding body corresponding to at least one target material from all the fourth sub - coding bodies corresponding to the selected second - intention coding individual; Among the multiple delivery cycles corresponding to the selected fourth sub - coding body, randomly select two delivery cycles, merge the first delivery volume of one of the two delivery cycles into the other delivery cycle, and determine the combined delivery volume and the remaining delivery volume corresponding to the two delivery cycles after random merging; Based on the material discount rate and the transportation cost parameter, use the exhaustive method to respectively determine the alternative supply objects corresponding to the target materials for delivering the combined delivery volume and the remaining delivery volume, obtaining the third supply object and the fourth supply object; Update the selected fourth sub - coding body according to the remaining delivery volume and the third supply object, the remaining delivery volume and the second supply object to generate the third sub - coding body at the same coding position.

8. The method according to claim 5, characterized in that, After taking the candidate sub - coding bodies in the candidate matrix - type coding individual as candidate particles, based on the preset particle swarm optimization algorithm PSO, perform particle swarm search processing on the multiple candidate particles, including: Obtain an initial particle population including a plurality of the candidate particles, and determine the initial particle positions and preset initial particle velocities of each of the candidate particles, wherein the initial particle positions are used to characterize the material replenishment decision information corresponding to the candidate sub-encoding bodies; Based on a preset dynamic adaptive change method, respectively determine the dynamically adaptive inertia factor, the first acceleration coefficient, and the second acceleration coefficient corresponding to the current particle search, wherein the dynamically adaptive inertia factor, the first acceleration coefficient, and the second acceleration coefficient are adaptively changed and generated according to the fitness corresponding to each candidate sub-encoding body and the search iteration times; Based on the initial particle positions, the initial particle velocities, the dynamically adaptive inertia factor, the first acceleration coefficient, and the second acceleration coefficient, use the particle swarm optimization algorithm to perform at least one population search iteration on the initial particle population until the total fitness corresponding to the matrix-type encoding individuals corresponding to the generated particle population is not greater than a preset fitness threshold, to obtain at least one target matrix-type encoding individual including a plurality of the alternative particles.

9. The method according to claim 8, characterized in that, Select a target particle from the generated plurality of alternative particles to obtain a decision result, including: Obtain the alternative particles corresponding to at least one of the target matrix-type encoding individuals, and calculate the fitness of the alternative sub-encoding bodies corresponding to each of the alternative particles; According to the fitness of the alternative sub-encoding bodies, select the alternative particle with the minimum fitness from the plurality of alternative particles to obtain the target particle, wherein the material replenishment decision information corresponding to the alternative sub-encoding body corresponding to the target particle is the target material replenishment decision information.

10. A service platform, comprising a memory and a processor, characterized in that, A computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps of the decision method for material ordering and replenishment based on GA-PSO according to any one of claims 1 to 9.

Images