Overseas small-batch order allocation method for multi-agent collaborative production, supply and marketing business chain

Abstract

The present invention provides a method for allocating overseas small-batch orders for a multi-agent collaborative production, supply, and marketing business chain, and relates to the technical field of order allocation. The present invention constructs a MAC‑PSM‑OA model based on order allocation resources and overseas small-batch orders, with the goal of minimizing the comprehensive cost of all overseas small-batch orders; and adopts an IAGA algorithm with an added initial population control strategy and an adaptive mechanism to solve the above model to obtain the allocation results of overseas small-batch orders. In the production, supply, and marketing business chain of a manufacturing enterprise, overseas small-batch orders have the typical characteristics of small product demand, large number of orders, and complex transportation conditions. A MAC‑PSM‑OA model is established to serve multi-agent collaboration, and an optimized genetic algorithm is used for solving the problem. The designed initial population control strategy makes the algorithm converge faster, and the adaptive mechanism ensures the rapid replacement search and global optimization of individuals in the early stages of evolution, which is conducive to finding a near-optimal solution, and ultimately realizes the optimization of the multi-agent collaborative production, supply, and marketing business chain for overseas small-batch orders of manufacturing enterprises.

Description

Technical Field

[0001] The present invention relates to the technical field of order distribution, and in particular to a method, system, storage medium and electronic equipment for distributing overseas small-batch orders in a multi-agent collaborative production, supply and marketing business chain. Background Art

[0002] With the growing trend of globalization, more and more manufacturing companies are shifting from centralized to decentralized production networks in order to improve production quality and customer satisfaction. How to arrange order planning and task allocation in a decentralized production network is a normal problem that companies need to face.

[0003] Currently, existing research focuses on three areas: multi-plant production and scheduling, production and transportation planning, and batch processing of small orders. However, manufacturing companies' orders are divided into domestic and overseas orders. While domestic orders are more mature, overseas orders, which involve ocean shipping, have received relatively less attention. Small orders are generated due to various reasons, such as the need for individual shipments of a small number of last-minute orders, or when some overseas customers place orders with low product quantities.

[0004] Although the product demand for each overseas small-batch order is relatively small, the number of orders is huge and the overall manufacturing demand is huge. Therefore, the reasonable and efficient allocation of overseas small-batch orders is crucial to achieving the optimization of the production, supply and marketing business chain under the collaboration of multiple entities. Summary of the Invention

[0005] (1) Technical problems solved

[0006] In response to the shortcomings of the existing technology, the present invention provides a method, system, storage medium and electronic equipment for allocating overseas small-batch orders in a multi-agent collaborative production, supply and marketing business chain, which solves the technical problem of how to reasonably and efficiently allocate and plan overseas small-batch orders.

[0007] (2) Technical solution

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0009] A method for allocating overseas small-batch orders in a multi-agent collaborative production, supply, and marketing business chain, comprising:

[0010] S1. Obtain order allocation resources and overseas small batch orders;

[0011] S2. Allocate resources and overseas small batch orders according to the orders, and build a MAC-PSM-OA model with the goal of minimizing the comprehensive cost of all overseas small batch orders;

[0012] S3. The IAGA algorithm with the added initial population control strategy and adaptive mechanism is used to solve the MAC-PSM-OA model to obtain the allocation results of overseas small batch orders.

[0013] Preferably, the MAC-PSM-OA model in S2 includes:

[0014] The objective function is to minimize the comprehensive cost of all overseas small batch orders:

[0015] minC=C pro +C sto +C tra +C P

[0016]

[0017]

[0018]

[0019]

[0020]

[0021]

[0022]

[0023] Among them, i represents overseas small-batch order i, i∈I={1, 2, ..., n}, and the total number of orders is n; j represents production base j, j∈J={1, 2, ..., m}, and the total number of production bases is m; r represents shipping port r, r∈R={1, 2, ..., g}, and the total number of ports is g; k represents shipping plan k, k∈K={1, 2, ..., l}, and the total number of plans is l;

[0024] C is the comprehensive cost;

[0025] C pro is the production cost; x ijk is a decision variable. If small batch order i is assigned to production base j and assigned to sea shipping plan k, then x ijk Take 1, otherwise take 0; q i is the demand quantity of the product in small batch order i; is the unit production cost of the product at production base j;

[0026] C sto is the storage cost; c h is the storage cost per unit volume per unit time; The product of the storage volume and storage time of all small batch order products at any production base j;

[0027] C tra is the transportation cost; if the shipping port of sea transport option k is r, then ρ rk Take 1, otherwise take 0; is the land transportation cost from production base j to shipping port r; is the container volume of small batch order i; is the unit shipping cost of shipping option k;

[0028] C P is the penalty cost; c p is the penalty cost per unit time; Estimated delivery time for ocean freight option k; Requested delivery time for customers who place small orders;

[0029] is the delivery time of small batch order i; is the loading time of shipping option k; is the land transportation time from production base j to shipping port r;

[0030] is the unit production time of the product at production base j; is the start time of production of small batch orders at production base j;

[0031] μ is the container volume per unit product.

[0032] Preferably, the MAC-PSM-OA model in S2 further includes:

[0033] Constraints:

[0034] (1) The production base j assigned to any small batch order i and the shipping port r corresponding to the ocean shipping plan k assigned to it belong to the same region;

[0035]

[0036] Among them, if the production base j is close to the shipping port r, then α jr Take 1, otherwise take 0;

[0037] (2) Each small batch order can only be assigned to one production base and one shipping plan;

[0038]

[0039] (3) It means that the total production demand of all small batch orders assigned to the same production base does not exceed its remaining production capacity;

[0040]

[0041] Among them, N j is the remaining production capacity of production base j;

[0042] (4) The total volume of all small-batch orders assigned to the same production base does not exceed the remaining warehouse capacity of the base;

[0043]

[0044] Among them, H j is the remaining capacity of the warehouse at production base j;

[0045] (5) The total container volume of all small batch orders assigned to the same shipping plan does not exceed the remaining available volume of the plan;

[0046]

[0047] in, is the remaining available volume of sea transport option k.

[0048] Preferably, the S3 specifically includes:

[0049] S31. Initialize a population of N individuals using a coding rule according to the MAC-PSM-OA model, where each row of the chromosome represents the number of the production base and shipping plan to which all small batch orders are assigned;

[0050] When generating the initial population, a first initial chromosome segment corresponding to the shipping plan is generated based on the principle of minimizing shipping costs. A second initial chromosome segment corresponding to the production base is generated based on the principle that the production base should be located in the same region as the shipping port specified in the shipping plan. The first and second chromosome segments are merged to obtain a complete initial chromosome.

[0051] S32. If the maximum number of iterations is reached, stop, decode the best individual in the population, and obtain the allocation planning result of the overseas small batch order; otherwise, continue the execution;

[0052] S33. Perform statistical analysis on the current population, record the fitness value of each individual and determine the optimal individual;

[0053] The objective function of the MAC-PSM-OA model is converted into a fitness function value using a linear conversion method;

[0054] F=aC+b

[0055] Where F represents the fitness function, a and b are the hyperparameters of the linear equation, and a < 0;

[0056] S34, independently select N mothers from the current population;

[0057] S35, adaptively adjust the crossover probability according to the population fitness, and perform a two-point crossover operation on the N mothers;

[0058] S36, adaptively adjust the mutation probability according to the population fitness, and perform integer mutation on the individuals after N crossovers;

[0059] S37, merging the parent population of the current generation and the population obtained by crossover mutation to obtain a population of size 2N;

[0060] S38. Use the roulette wheel selection method to select N individuals from the 2N population to obtain a new generation of population, and return to S32.

[0061] Preferably, the adaptive adjustment of the crossover probability according to the population fitness in S35 specifically refers to:

[0062]

[0063] Among them, P c is the crossover probability after update; f′ is the larger fitness value of the two individuals waiting for crossover; P c1 is the pre-set maximum crossover probability, P c2 is the pre-set minimum crossover probability; f max is the maximum fitness value of all individuals in the current population, f avg is the average fitness of all individuals in the current population;

[0064] Preferably, the adaptive adjustment of the mutation probability according to the population fitness in S36 specifically refers to:

[0065]

[0066] Among them, P m is the updated mutation probability; f represents the fitness value of the individual waiting for mutation; P m1 is the pre-set maximum mutation probability, P m2 is the pre-set minimum mutation probability.

[0067] An overseas small-batch order distribution system for a multi-agent collaborative production, supply, and marketing business chain, including:

[0068] Acquisition module, used to obtain order allocation resources and overseas small-batch orders;

[0069] A construction module is used to allocate resources and overseas small batch orders according to the orders, and to construct a MAC-PSM-OA model with the goal of minimizing the comprehensive cost of all overseas small batch orders;

[0070] The solution module is used to solve the MAC-PSM-OA model by using the IAGA algorithm with an added initial population control strategy and an adaptive mechanism to obtain the allocation planning results of overseas small batch orders.

[0071] A storage medium stores a computer program for allocating overseas small-batch orders for a multi-agent collaborative production, supply, and marketing business chain, wherein the computer program enables a computer to execute the method for allocating overseas small-batch orders for a multi-agent collaborative production, supply, and marketing business chain as described above.

[0072] An electronic device, comprising:

[0073] one or more processors;

[0074] Memory; and

[0075] One or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the programs include a method for allocating overseas small batch orders for executing the multi-agent collaborative production, supply and marketing business chain as described above.

[0076] (3) Beneficial effects

[0077] The present invention provides a method, system, storage medium, and electronic device for allocating small overseas orders in a multi-agent collaborative production, supply, and marketing business chain. Compared with existing technologies, it has the following advantages:

[0078] The present invention includes obtaining order allocation resources and overseas small-batch orders; constructing a MAC-PSM-OA model based on the order allocation resources and overseas small-batch orders, with the goal of minimizing the comprehensive cost of all overseas small-batch orders; and solving the MAC-PSM-OA model using an IAGA algorithm with an added initial population control strategy and adaptive mechanism to obtain the allocation results of the overseas small-batch orders. In view of the characteristics of overseas small-batch orders of manufacturing enterprises, such as small product demand, large number of orders, and complex transportation conditions, the MAC-PSM-OA model is established to serve the multi-agent collaboration of the production, supply, and marketing business chain. The model is solved using an optimized genetic algorithm, which facilitates the search for near-optimal solutions, helping manufacturing enterprises to centrally process large numbers of overseas small-batch orders and achieve optimization of the production, supply, and marketing business chain under multi-agent collaboration. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0080] Figure 1 A block diagram of a method for allocating overseas small-batch orders based on a multi-agent collaborative production, supply, and marketing business chain provided by an embodiment of the present invention;

[0081] Figure 2 A schematic diagram of a collaborative allocation scenario for overseas small-batch orders provided by an embodiment of the present invention;

[0082] Figure 3 A completion timeline for a small overseas order provided by an embodiment of the present invention;

[0083] Figure 4 A flowchart of an IAGA algorithm provided in an embodiment of the present invention;

[0084] Figure 5 A schematic diagram of IAGA coding provided by an embodiment of the present invention;

[0085] Figure 6 A schematic diagram of a two-point intersection method provided by an embodiment of the present invention;

[0086] Figure 7 A schematic diagram of an integer-valued mutation method provided by an embodiment of the present invention;

[0087] Figure 8 A schematic diagram of a roulette wheel selection method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0088] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention are clearly and completely described. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0089] The embodiments of the present application solve the technical problem of how to reasonably and efficiently allocate and plan overseas small-batch orders by providing a method, system, storage medium and electronic equipment for allocating overseas small-batch orders in a multi-agent collaborative production, supply and marketing business chain.

[0090] The technical solution in the embodiments of the present application is to solve the above technical problems, and the overall idea is as follows:

[0091] like Figure 1As shown, an embodiment of the present invention includes obtaining order allocation resources and overseas small-batch orders; constructing a Multi-Agent Cooperative-Production-Supply-Marketing-Orders Allocation (MAC-PSM-OA) model for the production, supply, and marketing business chain under multi-agent collaboration based on the order allocation resources and overseas small-batch orders, with the goal of minimizing the comprehensive cost of all overseas small-batch orders; and solving the unified order allocation model using an improved adaptive genetic algorithm (IAGA) with an added initial population control strategy and adaptive mechanism to obtain allocation results for overseas small-batch orders. In view of the characteristics of manufacturing companies' overseas small-batch orders, such as small product demand, large number of orders, and complex transportation conditions, a unified order allocation model is established to serve the multi-agent collaboration of the production, supply, and marketing business chain. The optimized genetic algorithm is used for solving the model, which is conducive to finding a near-optimal solution and helps manufacturing companies centrally process a large number of overseas small-batch orders.

[0092] In order to better understand the above technical solution, the above technical solution will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0093] Example:

[0094] An embodiment of the present invention provides a method for allocating overseas small-batch orders in a multi-agent collaborative production, supply, and marketing business chain, including:

[0095] S1. Obtain order allocation resources and overseas small batch orders;

[0096] S2. Allocate resources and overseas small batch orders according to the orders, and build a MAC-PSM-OA model with the goal of minimizing the comprehensive cost of all overseas small batch orders;

[0097] S3. The IAGA algorithm with the added initial population control strategy and adaptive mechanism is used to solve the MAC-PSM-OA model to obtain the allocation planning results of overseas small batch orders.

[0098] The embodiment of the present invention aims to establish a unified order allocation model based on the characteristics of manufacturing enterprises' overseas small-batch orders, such as small product demand, large number of orders, and complex transportation conditions, to serve the collaboration of multiple entities in the production, supply, and marketing business chain, and adopts an optimized genetic algorithm for solution, which is conducive to finding a near-optimal solution and helps manufacturing enterprises to centrally process a large number of overseas small-batch orders.

[0099] The following are the steps of the above technical solution:

[0100] First, it is necessary to explain and supplement the description of the allocation planning problem involved in the embodiment of the present invention, which is as follows:

[0101] A manufacturing company has n overseas small-batch orders, which need to be allocated to m production bases, and a shipping plan is assigned to each overseas small-batch order to ultimately achieve overseas delivery of all orders. Among them, the n overseas small-batch orders all have the same destination port, and the m production bases are distributed in different regions. There are a total of K shipping plans, which are abstractions of small-batch order consolidation and ship booking operations. Each shipping plan includes information such as the outbound time (also referred to as the shipping time in this article), loading time, expected delivery time, available volume, shipping costs, and shipping port. The overseas small-batch order allocation scenario of the multi-agent collaborative production, supply, and marketing business chain is as follows: Figure 2 shown.

[0102] For the same overseas small batch order, it will not be split. All overseas small batch orders that select the same production base will start production at the same time. After production is completed, if it is the delivery time, it will be shipped to the terminal for loading. If it is not the delivery time, it will be stored in the local finished product warehouse, incurring storage costs. Since the time of the warehousing process and the consolidation process is very short compared to the overall order completion time, it can be ignored. Therefore, the production off-line time = product warehousing time. The completion timeline of overseas small batch orders is as follows: Figure 3 shown.

[0103] In step S1, order allocation resources and overseas small batch orders are obtained.

[0104] The order allocation resources and overseas small batch orders specifically involve the following symbol system:

[0105] Input parameters

[0106]

[0107]

[0108] Decision variables

[0109]

[0110] In step S2, resources and overseas small batch orders are allocated according to the order, with the goal of minimizing the comprehensive cost of all overseas small batch orders, and a MAC-PSM-OA model is constructed.

[0111] The MAC-PSM-OA model in S2 includes:

[0112] The objective function is to minimize the comprehensive cost of all overseas small batch orders:

[0113] minC=C pro +Csto +C tra +C P

[0114]

[0115]

[0116]

[0117]

[0118]

[0119]

[0120]

[0121] Among them, C is the comprehensive cost; C pro is the production cost; C sto For storage costs; C is the product of the storage volume and storage time of all small batch order products at any production base j; tra is the transportation cost; C P For penalty costs.

[0122] The MAC-PSM-OA model in S2 also includes:

[0123] Constraints:

[0124] (1) The production base j assigned to any small batch order i and the shipping port r corresponding to the ocean shipping plan k assigned to it belong to the same region;

[0125]

[0126] (2) Each small batch order can only be assigned to one production base and one shipping plan;

[0127]

[0128] (3) It means that the total production demand of all small batch orders assigned to the same production base does not exceed its remaining production capacity;

[0129]

[0130] (4) The total volume of all small-batch orders assigned to the same production base does not exceed the remaining warehouse capacity of the base;

[0131]

[0132] (5) The total container volume of all small batch orders assigned to the same shipping plan does not exceed the remaining available volume of the plan;

[0133]

[0134] In step S3, the IAGA algorithm with the initial population control strategy and adaptive mechanism is used to solve the MAC-PSM-OA model to obtain the allocation planning results of overseas small batch orders; Figure 4 As shown, specifically including:

[0135] S31. According to the MAC-PSM-OA model, a population of N individuals is initialized using coding rules, where each row of the chromosome represents the number of the production base and shipping plan to which all small batch orders are assigned.

[0136] According to the genetic algorithm, a chromosome represents a solution. Chromosomes are encoded using multi-level integers, such as Figure 5 shown.

[0137] The first row of the chromosome represents the number of the production bases to which all small batch orders are assigned, and the second row represents the number of the shipping plans to which all small batch orders are assigned. The length of the chromosome is equal to the number of small batch orders. Figure 5 In the coding shown, small batch order 1 is assigned to production base 2 and shipping plan 5, small batch order 2 is assigned to production base 5 and shipping plan 11, and so on. The nth small batch order is assigned to production base 3 and shipping plan 39.

[0138] It should be emphasized that the embodiment of the present invention takes into account that the largest proportion of the comprehensive cost of overseas orders of manufacturing enterprises is the shipping cost. Therefore, the following initial population control strategy is adopted when generating the initial population:

[0139] Based on the principle of minimizing shipping costs, a first initial chromosome segment corresponding to the shipping plan is generated. Based on the principle that the production base should be located in the same region as the shipping port specified in the shipping plan, a second initial chromosome segment corresponding to the production base is generated. The first and second chromosome segments are merged to obtain a complete initial chromosome.

[0140] The initial population generated according to the above logic has better quality than the random initial population, so it can make the algorithm converge faster.

[0141] S32. If the maximum number of iterations is reached, stop, decode the best individual in the population, and obtain the allocation planning result of the overseas small batch order; otherwise, continue to execute.

[0142] S33. Perform statistical analysis on the current population, record the fitness value of each individual and determine the optimal individual;

[0143] The objective function of the MAC-PSM-OA model is converted into a fitness function using a linear transformation method;

[0144] F=aC+b

[0145] Where F represents the fitness function after linear scaling of the comprehensive cost C, a and b are the hyperparameters of the linear equation, and a < 0.

[0146] S34. Independently select N mothers from the current population.

[0147] S35. Adaptively adjust the crossover probability according to the population fitness, and perform a crossover operation on the N mothers.

[0148] Among them, the two-point crossover method is used for the crossover operation, which specifically refers to randomly determining two positions as one before and one after, determining the gene segments, and exchanging the corresponding gene segments of the two chromosomes.

[0149] The crossover operation changes the gene sequence of chromosomes by crossing gene segments between chromosomes, which can increase population diversity and improve the global search capability of the genetic algorithm. Here, the two-point crossover method is used for the crossover operation. Two positions are randomly determined as the front and back, and the gene segments are determined. Then, the corresponding gene segments of the two chromosomes are exchanged. Figure 6 As shown, the production bases and shipping plans for small batch orders 3, 4, and 5 are randomly determined as selected genes, and the positions of these two groups of genes are exchanged to obtain two daughter chromosomes.

[0150] The adaptive adjustment of the crossover probability according to the population fitness specifically refers to:

[0151]

[0152] Among them, P c is the crossover probability after update; f′ is the larger fitness value of the two individuals waiting for crossover; P c1 is the pre-set maximum crossover probability, P c2 is the pre-set minimum crossover probability; f max is the maximum fitness value of all individuals in the current population, f avg is the average fitness of all individuals in the current population. In the embodiment of the present invention, P c1 =0.9; P c2 =0.6.

[0153] S36. Adaptively adjust the mutation probability according to the population fitness and mutate the N individuals after crossover.

[0154] Among them, the mutation method using integer value mutation specifically refers to randomly determining a gene segment selected by a production base and a gene segment selected by a shipping plan on the chromosome, and performing mutations within the corresponding range respectively.

[0155] The mutation operation generates new chromosomes by changing the genes or gene positions in the chromosomes, increasing the diversity of the population and preventing the algorithm from falling into a local optimum. Here, we use the integer mutation method to randomly determine a mutation position on the chromosome and mutate the production base number and the shipping plan number within the corresponding range. Figure 7 As shown, the chromosome performs real-valued mutation on the production base and shipping plan of small batch order 4, that is, the production base and shipping plan number of small batch order 3 are regenerated.

[0156] The adaptive adjustment of the mutation probability according to the population fitness specifically refers to:

[0157]

[0158] Among them, P m is the updated mutation probability; f represents the fitness value of the individual waiting for mutation; P m1 is the pre-set maximum mutation probability, P m2 is the pre-set minimum mutation probability. In the embodiment of the present invention, P m1 =0.1; P m2 =0.001

[0159] The adaptive strategy adopted in the embodiment of the present invention ensures that all individuals have a large variation and crossover probability in the early stage of evolution. Even the optimal solution of the population has the minimum crossover probability P c2 and mutation probability P m2 , ensuring rapid replacement search and global optimization of individuals in the early stages of evolution.

[0160] S37. Merge the parent population of the current generation and the population obtained by crossover mutation to obtain a population of size 2N.

[0161] S38. Use the roulette wheel selection method to select N individuals from the 2N population to obtain a new generation of population, and return to S32.

[0162] like Figure 8 As shown, a roulette wheel selection method is used to select the population to be crossed. Individuals in the population are mapped to consecutive segments of the interval, with the length of each segment proportional to its fitness. A random number is generated, and the corresponding individual is selected based on the segment it falls into. This process is repeated until the required number of individuals is obtained, and the population is updated.

[0163] The embodiment of the present invention provides an overseas small-batch order distribution system for a multi-agent collaborative production, supply, and marketing business chain, including:

[0164] Acquisition module, used to obtain order allocation resources and overseas small-batch orders;

[0165] A construction module is used to allocate resources and overseas small batch orders according to the orders, and to construct a MAC-PSM-OA model with the goal of minimizing the comprehensive cost of all overseas small batch orders;

[0166] The solution module is used to solve the unified order allocation model by using the IAGA algorithm with an added initial population control strategy and an adaptive mechanism to obtain the allocation results of overseas small batch orders.

[0167] An embodiment of the present invention provides a storage medium storing a computer program for allocating overseas small-batch orders for a multi-subject collaborative production, supply, and marketing business chain, wherein the computer program enables a computer to execute the method for allocating overseas small-batch orders for a multi-subject collaborative production, supply, and marketing business chain as described above.

[0168] An embodiment of the present invention provides an electronic device, including:

[0169] one or more processors;

[0170] Memory; and

[0171] One or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the programs include a method for allocating overseas small batch orders for executing the multi-agent collaborative production, supply and marketing business chain as described above.

[0172] It can be understood that the overseas small-batch order allocation system, storage medium, and electronic device of the multi-subject collaborative production, supply, and marketing business chain provided by the embodiment of the present invention correspond to the overseas small-batch order allocation method of the multi-subject collaborative production, supply, and marketing business chain provided by the embodiment of the present invention. The explanation, examples, and beneficial effects of the relevant contents can refer to the corresponding parts of the overseas small-batch order allocation method of the multi-subject collaborative production, supply, and marketing business chain, and will not be repeated here.

[0173] In summary, compared with the existing technology, the present invention has the following beneficial effects:

[0174] 1. The present invention comprises obtaining order allocation resources and overseas small-batch orders; constructing a MAC-PSM-OA model based on these order allocation resources and overseas small-batch orders, with the goal of minimizing the overall cost of all overseas small-batch orders; and solving the MAC-PSM-OA model using an IAGA algorithm with an initial population control strategy and an adaptive mechanism to obtain an allocation planning result for overseas small-batch orders. Given the characteristics of overseas small-batch orders for manufacturing companies, such as low product demand, high numbers of orders, and complex transportation conditions, a unified order allocation model for overseas small-batch orders is established and solved using a preferred genetic algorithm, facilitating the search for near-optimal solutions and helping manufacturing companies centrally process large numbers of overseas small-batch orders.

[0175] 2. The embodiment of the present invention adopts an initial population control strategy to obtain an initial population, which has better quality than a random initial population and can make the algorithm converge faster.

[0176] 3. The adaptive strategy employed by the present invention ensures that all individuals have a high probability of mutation and crossover in the early stages of evolution. Even the optimal solution of the population has the minimum crossover and mutation probabilities, ensuring rapid replacement search and global optimization of individuals in the early stages of evolution.

[0177] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0178] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for allocating overseas small-batch orders in a multi-agent collaborative production, supply, and marketing business chain, characterized in that: include: S1. Obtain order allocation resources and overseas small batch orders; S2. Allocate resources and overseas small batch orders according to the orders, and build a MAC-PSM-OA model with the goal of minimizing the comprehensive cost of all overseas small batch orders; S3. Using the IAGA algorithm with an initial population control strategy and an adaptive mechanism to solve the MAC-PSM-OA model, the allocation results of overseas small batch orders are obtained; The MAC-PSM-OA model includes: The objective function is to minimize the comprehensive cost of all overseas small batch orders: minC=C pro +C sto +C tra +C P Where i represents overseas small-batch order i, i∈I={1,2,…,n}, and the total number of orders is n; j represents production base j, j∈J={1,2,…,m}, and the total number of production bases is m; r represents shipping port r, r∈R={1,2,…,g}, and the total number of ports is g; k represents shipping plan k, k∈K={1,2,…,l}, and the total number of plans is l; C is the comprehensive cost; C pro is the production cost; x ijk is a decision variable. If small batch order i is assigned to production base j and assigned to sea shipping plan k, then x ijk Take 1, otherwise take 0; q i is the demand quantity of the product in small batch order i; is the unit production cost of the product at production base j; C sto is the storage cost; c h is the storage cost per unit volume per unit time; The product of the storage volume and storage time of all small batch order products at any production base j; C tra is the transportation cost; if the shipping port of sea transport option k is r, then ρ rk Take 1, otherwise take 0; is the land transportation cost from production base j to shipping port r; is the container volume of small batch order i; is the unit shipping cost of shipping option k; C P is the penalty cost; c p is the penalty cost per unit time; Estimated delivery time for ocean freight option k; Requested delivery time for customers who place small orders; is the delivery time of small batch order i; is the loading time of shipping option k; is the land transportation time from production base j to shipping port r; is the unit production time of the product at production base j; is the start time of production of small batch orders at production base j; μ is the container volume per unit product.

2. The overseas small-batch order allocation method for a multi-agent collaborative production, supply, and marketing business chain as claimed in claim 1 is characterized in that: The MAC-PSM-OA model in S2 also includes: Constraints: (1) The production base j assigned to any small batch order i and the shipping port r corresponding to the ocean shipping plan k assigned to it belong to the same region; Among them, if the production base j is close to the shipping port r, then α jr Take 1, otherwise take 0; (2) Each small batch order can only be assigned to one production base and one shipping plan; (3) It means that the total production demand of all small batch orders assigned to the same production base does not exceed its remaining production capacity; Among them, N j is the remaining production capacity of production base j; (4) The total volume of all small-batch orders assigned to the same production base does not exceed the remaining warehouse capacity of the base; Among them, H j is the remaining capacity of the warehouse at production base j; (5) The total container volume of all small batch orders assigned to the same shipping plan does not exceed the remaining available volume of the plan; in, is the remaining available volume of sea transport option k.

3. The overseas small-batch order allocation method for a multi-agent collaborative production, supply, and marketing business chain according to any one of claims 1 to 2, characterized in that: The S3 specifically includes: S31. Initialize a population of N individuals using a coding rule according to the MAC-PSM-OA model, where each row of the chromosome represents the number of the production base and shipping plan to which all small batch orders are assigned; When generating the initial population, the first initial chromosome segment corresponding to the shipping plan is generated according to the principle of minimizing shipping costs; and the second initial chromosome segment corresponding to the production base is generated according to the principle that the production base should be located in the same region as the shipping port specified in the shipping plan; the first and second initial chromosome segments are merged to obtain a complete initial chromosome; S32. If the maximum number of iterations is reached, stop, decode the best individual in the population, and obtain the allocation planning result of the overseas small batch order; otherwise, continue the execution; S33. Perform statistical analysis on the current population, record the fitness value of each individual and determine the optimal individual; The objective function of the MAC-PSM-OA model is converted into a fitness function value using a linear conversion method; F=aC+b Where F represents the fitness function, a and b are the hyperparameters of the linear equation, and a<0; S34, independently select N mothers from the current population; S35, adaptively adjust the crossover probability according to the population fitness, and perform a two-point crossover operation on the N mothers; S36, adaptively adjust the mutation probability according to the population fitness, and perform integer mutation on the individuals after N crossovers; S37. Merge the parent population of the current generation and the population obtained by crossover mutation to obtain a population of size 2N; S38. Use the roulette wheel selection method to select N individuals from the 2N population to obtain a new generation of population, and return to S32.

4. The overseas small-batch order allocation method for a multi-agent collaborative production, supply, and marketing business chain as claimed in claim 3 is characterized in that: The adaptive adjustment of the crossover probability according to the population fitness in S35 specifically refers to: Among them, P c is the updated crossover probability; f ′ is the larger fitness value of the two individuals waiting for crossover; P c1 is the pre-set maximum crossover probability, P c2 is the pre-set minimum crossover probability; f max is the maximum fitness value of all individuals in the current population, f avg is the average fitness of all individuals in the current population; The adaptive adjustment of the mutation probability according to the population fitness in S36 specifically refers to: Among them, P m is the updated mutation probability; f represents the fitness value of the individual waiting for mutation; P m1 is the pre-set maximum mutation probability, P m2 is the pre-set minimum mutation probability.

5. A multi-agent collaborative production, supply and marketing business chain overseas small batch order distribution system, characterized by: include: Acquisition module, used to obtain order allocation resources and overseas small-batch orders; A construction module is used to allocate resources and overseas small batch orders according to the orders, and to construct a MAC-PSM-OA model with the goal of minimizing the comprehensive cost of all overseas small batch orders; A solution module is used to solve the MAC-PSM-OA model by using an IAGA algorithm with an initial population control strategy and an adaptive mechanism to obtain the allocation results of overseas small batch orders; The MAC-PSM-OA model includes: The objective function is to minimize the comprehensive cost of all overseas small batch orders: minC=C pro +C sto +C tra +C P Where i represents overseas small-batch order i, i∈I={1,2,…,n}, and the total number of orders is n; j represents production base j, j∈J={1,2,…,m}, and the total number of production bases is m; r represents shipping port r, r∈R={1,2,…,g}, and the total number of ports is g; k represents shipping plan k, k∈K={1,2,…,l}, and the total number of plans is l; C is the comprehensive cost; C pro is the production cost; x ijk is a decision variable. If small batch order i is assigned to production base j and assigned to sea shipping plan k, then x ijk Take 1, otherwise take 0; q i is the demand quantity of the product in small batch order i; is the unit production cost of the product at production base j; C sto is the storage cost; c h is the storage cost per unit volume per unit time; The product of the storage volume and storage time of all small batch order products at any production base j; C tra is the transportation cost; if the shipping port of sea transport option k is r, then ρ rk Take 1, otherwise take 0; is the land transportation cost from production base j to shipping port r; is the container volume of small batch order i; is the unit shipping cost of shipping option k; C P is the penalty cost; c p is the penalty cost per unit time; Estimated delivery time for ocean freight option k; Requested delivery time for customers who place small orders; is the delivery time of small batch order i; is the loading time of shipping option k; is the land transportation time from production base j to shipping port r; is the unit production time of the product at production base j; is the start time of production of small batch orders at production base j; μ is the container volume per unit product.

6. A storage medium, characterized in that It stores a computer program for allocating overseas small-batch orders for a multi-subject collaborative production, supply, and marketing business chain, wherein the computer program enables the computer to execute the method for allocating overseas small-batch orders for a multi-subject collaborative production, supply, and marketing business chain as described in any one of claims 1 to 4.

7. An electronic device, characterized in that: include: one or more processors; Memory; as well as One or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the programs include a method for allocating overseas small batch orders for executing the multi-agent collaborative production, supply and marketing business chain as described in any one of claims 1 to 4.

Images