Multi-farm picking and distribution integrated scheduling method based on improved artificial bee colony algorithm

Abstract

The invention provides a multi-farm picking and distribution integrated scheduling method based on an improved artificial bee colony algorithm, and relates to the technical field of agricultural product supply chain management and optimization, and the method comprises the steps: setting a constraint condition for a multi-farm picking and distribution integrated scheduling problem; defining an agricultural product freshness loss function; defining two objective functions, including an operation cost minimization function and a customer satisfaction maximization function; based on the constraint condition and the objective function, establishing a dual-objective model of multi-farm picking and distribution integrated scheduling; and solving the dual-objective optimization model to obtain an optimal solution set, and performing agricultural product scheduling according to picking and distribution information in the optimal solution set. According to the invention, picking and distribution links are effectively integrated, the operation cost is reduced, the freshness of agricultural products is guaranteed, the service satisfaction is improved, and an innovative and efficient solution is provided for an agricultural product supply chain in a community-supported agricultural mode.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural product supply chain management and optimization, and in particular to a multi-farm picking and distribution integrated scheduling method based on an improved artificial bee colony algorithm. Background Art

[0002] In recent years, as the quality of life continues to improve, people are increasingly concerned about healthy diets, and the demand for fresh organic agricultural products has increased dramatically. As an emerging agricultural product supply chain model, "community-supported agriculture" has attracted much attention. This model aims to establish direct links between urban community residents and local farms to form a risk-sharing and benefit-sharing partnership, aiming to provide residents with fresh and healthy fresh agricultural products. Under this operating framework, the farm provides a one-stop service from "picking to delivery", ensuring that fresh agricultural products can be picked, delivered and delivered on the same day.

[0003] However, as the "community-supported agriculture" model develops rapidly, it also faces challenges such as the difficulty in preserving agricultural products and the high cost of picking. Since farms are usually located on the outskirts of cities and their customers are widely distributed, the distribution efficiency is low and the distribution cost is high. At the same time, the freshness of fresh agricultural products is a key factor in determining their value. Once picked, their freshness gradually decreases over time. In addition, in order to meet the large demand, multiple farms often cooperate and operate together. Therefore, how to effectively integrate the picking and distribution processes of multiple farms to provide fresh agricultural products with high freshness at low cost has become a key issue that needs to be solved urgently.

[0004] However, most current research focuses on the single link of picking or distribution, and there is still a lack of discussion on the comprehensive optimization of these two stages. As for the research on incorporating the picking and distribution processes of multiple farms into a unified scheduling framework, it is even rarer. At the same time, most of the existing research on agricultural product picking and distribution problems uses traditional meta-heuristic algorithms. Summary of the invention

[0005] To this end, an embodiment of the present invention provides a multi-farm picking and distribution integrated scheduling method based on an improved artificial bee colony algorithm, which is used to solve the problems of insufficient integration of agricultural product picking and distribution processes, high costs and difficulty in ensuring freshness under the "community supported agriculture" model in the prior art.

[0006] In order to solve the above problems, an embodiment of the present invention provides a multi-farm picking and distribution integrated scheduling method based on an improved artificial bee colony algorithm, the method comprising:

[0007] For the problem of integrated scheduling of multi-farm picking and delivery, set constraints, including that multiple existing farms cooperate with each other to provide agricultural products to customers, managers receive customer orders and assign customer orders to each farm, arrange picking tasks and delivery tasks for each farm, that is, arrange the picking team to pick agricultural products according to the optimized picking order, and arrange vehicles to deliver agricultural products to customers from the farm according to the optimized route, and finally return to the farm;

[0008] A freshness loss function of agricultural products is defined, wherein the freshness loss function of agricultural products is used to describe the change of freshness of agricultural products over time from picking to delivery to customers;

[0009] Define two objective functions, including minimizing the operating cost function and maximizing the customer satisfaction function, where the operating cost includes the picking cost, transportation cost and vehicle usage cost, and customer satisfaction is related to the freshness of the delivered agricultural products;

[0010] Based on the constraints and the objective function, a dual-objective model for integrated scheduling of multi-farm picking and distribution is established;

[0011] Solve the dual-objective optimization model to obtain an optimal solution set, and dispatch agricultural products according to the picking and delivery information in the optimal solution set.

[0012] Preferably, the constraints also include:

[0013] Each farm grows a variety of agricultural products, and the types of agricultural products grown on each farm are the same;

[0014] Each type of agricultural product can only be picked by one picking team;

[0015] Each picking team can only pick one type of agricultural product at a time;

[0016] Each agricultural product has a specific freshness loss rate, and the freshness of agricultural products decreases over time after they are picked;

[0017] Each customer may need more than one agricultural product;

[0018] Each customer is assigned only one farm to provide him with agricultural products;

[0019] Each customer is delivered by only one vehicle;

[0020] The time it takes for the vehicle to depart from the farm is equal to the time it takes to complete the picking of the last produce that needs to be loaded;

[0021] The vehicle carrying capacity is limited, that is, the total vehicle load at any point on the route is not greater than the vehicle carrying capacity;

[0022] The vehicle's starting and ending points must be the same farm.

[0023] Preferably, the agricultural product freshness loss function is expressed as:

[0024]

[0025] Where F represents the initial freshness of agricultural products, that is, the maximum freshness; θ j is the freshness loss rate of agricultural product j; F j Represents the freshness of agricultural product j after time t.

[0026] Preferably, the minimization operation cost function is:

[0027]

[0028] In the formula, f1 represents the operating cost, b represents the picking cost per unit time, e represents the driving cost per unit time, r represents the fixed cost of each vehicle, and Y mg If customer m is assigned to farm g, then Y mg =1; otherwise, Y mg =0;d mj represents the demand of customer m for agricultural product j; t lj represents the picking time of agricultural product j by picking team l; U jgl If the picking team l of farm g picks agricultural product j, then U jgl =1; otherwise, U jgl =0;v mn represents the travel time from node m to node n; z mngh If vehicle h from farm g visits node m and then node n, then Z mngh =1; otherwise, Z mngh =0; m,n∈Q, representing the node index, where Q=J∪F, representing the node set, J={1,2,…,q}, representing the customer set, q represents the total number of customers, F={q+1,q+2,…,q+f}, representing the farm set, f represents the number of farms; h∈K g , represents the vehicle index, where K g ={1,2,…,k g}, represents the vehicle set, k g represents the number of vehicles in farm g; g∈F, represents the farm index; l∈M g , represents the picking team index, where M g ={1,2,…,m g}, represents the collection of picking teams, m grepresents the number of picking teams in farm g; j∈P represents the agricultural product index, where P={0,1,2,…,p}, represents the set of agricultural products, where 0 represents virtual agricultural products and p represents the number of types of agricultural products; P\{0} represents the set of agricultural products that does not contain 0.

[0029] Preferably, the maximization of customer satisfaction function is expressed by minimizing freshness loss:

[0030] minf2=∑ m∈J ψ m ;

[0031] Where f2 represents the freshness loss; ψ m Represents the maximum freshness loss of agricultural products obtained by customer m; m∈J, J={1,2,…,q}, represents the customer set, and q represents the total number of customers.

[0032] Preferably, the dual-objective model of multi-farm picking and distribution integrated scheduling is expressed as:

[0033]

[0034]

[0035]

[0036] Where i,j∈P represents the index of agricultural products, where P = {0,1,2,…,p}, represents the set of agricultural products, where 0 represents virtual agricultural products and p represents the number of agricultural product types; P\{0} represents the set of agricultural products that does not contain 0; m,n∈Q represents the node index, where Q = J∪F, represents the node set, J = {1,2,…,q}, represents the customer set, q represents the total number of customers, F = {q+1,q+2,…,q+f}, represents the farm set, and f represents the number of farms; h∈K g , represents the vehicle index, where K g ={1,2,…,k g}, represents the vehicle set, k g represents the number of vehicles in farm g; l∈M g , represents the picking team index, where M g ={1,2,…,m g}, represents the collection of picking teams, m g represents the number of picking teams in farm g; d mj represents the demand of customer m for agricultural product j; R mj If customer m needs agricultural product j, then R mj =1; otherwise, R mj =0;θ j is the freshness loss rate of agricultural product j; vnm represents the travel time from node m to node n; δ represents the maximum load of each vehicle; B represents infinity; Y mg If customer m is assigned to farm g, then Y mg =1; otherwise, Y mg =0; U jgl If the picking team l of farm g picks agricultural product j, then U jgl =1; otherwise, U jgl =0; Xi jgl If the picking team l of farm g picks agricultural product i and then picks agricultural product j, then X ijgl =1; otherwise, X ijgl =0;X 0jgl The picking team l representing farm g picks virtual product 0 and then picks agricultural product j; W mgh If vehicle h from farm g serves customer m, then W mgh =1; otherwise, W mgh =0; Z mngh If vehicle h from farm g visits node m and then node n, then Z mngh =1; otherwise, Z mngh =0; Z g′mgh where g′ and g represent two different farms, Z g′mgh Vehicle h representing farm g departs from farm g′ to customer m; Z mg′gh where g′ and g represent two different farms, Z mg′gh Vehicle h representing farm g returns from customer m to farm g′; Z g′g″gh where g″, g′ and g represent three different farms, Z g′g″gh Vehicle h representing farm g returns from farm g′ to farm g″; D gh represents the time when vehicle h departs from farm g; A m represents the time when the vehicle arrives at customer m; S gj represents the picking start time of agricultural product j in farm g; C gj represents the harvesting completion time of agricultural product j in farm g; ξ mj represents the freshness loss of agricultural product j when it is delivered to customer m; ψ m Get the maximum freshness loss in produce on behalf of customer m.

[0037] Preferably, the method for solving the dual-objective optimization model to obtain the optimal solution set is:

[0038] The improved artificial bee colony algorithm is used to solve the multi-objective optimization model to obtain the optimal solution set, wherein the improved artificial bee colony algorithm specifically includes:

[0039] Step S61: Initialize algorithm parameters, including population size N, maximum trial value number MaxTrial, Q table, initial state, and maximum running time; randomly generate an initial population, including solutions represented by N integer codes, and assign each solution a trial value number of 0; evaluate the target values ​​of N solutions in the population, and store the non-dominated solution set in an external archive;

[0040] Step S62: Execute the employed bee stage: the population performs a crossover operation, and if a solution is improved, the number of its test values ​​is increased by 1;

[0041] Step S63: Execute the spectator bee stage: select the optimal neighborhood structure using the Q learning method according to the current state, and the population executes the selected neighborhood structure. If a solution is improved, the number of its trial values ​​is increased by 1;

[0042] Step S64: Execute the scout bee stage: check whether the number of trial values ​​of each solution in the population reaches the maximum limit MaxTrial. If the maximum limit is reached, randomly select a solution from the external archive to replace the solution;

[0043] Step S65: the population updates the external archive, and the external archive executes the local search method;

[0044] Step S66: Calculate the reward value based on the change of state and update the Q table;

[0045] Step S67: determine whether the maximum running time has been reached, if so, terminate, otherwise return to step S62;

[0046] Step S68: Output the optimal solution set obtained from the external archive.

[0047] The embodiment of the present invention further provides a multi-farm picking and distribution integrated scheduling system based on an improved artificial bee colony algorithm, which is used to implement the multi-farm picking and distribution integrated scheduling method based on the improved artificial bee colony algorithm described above, specifically including:

[0048] The constraint setting module is used to set constraints for the integrated scheduling problem of multi-farm picking and delivery, including the cooperation of multiple existing farms to provide agricultural products to customers, managers receiving customer orders and assigning customer orders to various farms, arranging picking tasks and delivery tasks for each farm, that is, arranging picking teams to pick agricultural products in an optimized picking order, and arranging vehicles to deliver agricultural products to customers from the farms along the optimized routes, and finally returning to the farms;

[0049] A function definition module, used to define a freshness loss function of agricultural products, wherein the freshness loss function of agricultural products is used to describe the change of freshness of agricultural products over time from picking to delivery to customers;

[0050] An objective function definition module is used to define two objective functions, including minimizing the operating cost function and maximizing the customer satisfaction function, where the operating cost includes the picking cost, transportation cost and vehicle use cost, and the customer satisfaction is related to the freshness of the delivered agricultural products;

[0051] A dual-objective optimization model building module, used to build a dual-objective model for integrated scheduling of multi-farm picking and distribution based on the constraint conditions and the objective function;

[0052] The solution and scheduling module is used to solve the dual-objective optimization model, obtain the optimal solution set, and schedule agricultural products according to the picking and distribution information in the optimal solution set.

[0053] An embodiment of the present invention also provides an electronic device, comprising a processor, a memory and a bus system, wherein the processor and the memory are connected via the bus system, the memory is used to store instructions, and the processor is used to execute the instructions stored in the memory to implement the above-mentioned multi-farm picking and distribution integrated scheduling method based on the improved artificial bee colony algorithm.

[0054] An embodiment of the present invention also provides a computer storage medium, which stores a computer software product. The computer software product includes a number of instructions for enabling a computer device to execute the above-mentioned multi-farm picking and distribution integrated scheduling method based on the improved artificial bee colony algorithm.

[0055] It can be seen from the above technical solutions that the present invention has the following beneficial effects:

[0056] (1) Compared with previous studies that only focused on a single link in the fresh agricultural product supply chain, this invention has achieved an innovative breakthrough. It integrates the two key links of picking and distribution, and introduces a multi-farm collaborative operation model. By implementing a multi-farm two-stage integrated scheduling strategy, consumers can directly establish contact with farmers to obtain fresh agricultural products such as fruits and vegetables that are both economical and high-quality. This strategy actively responds to the concepts of community-supported agriculture and direct procurement and supply advocated by the country, and shows strong practical application value.

[0057] (2) In response to the challenges faced by the integrated scheduling of multi-farm harvesting and distribution, the present invention constructs a model framework with dual objectives. This framework not only takes into account the operating costs in the agricultural product supply chain, but also attaches great importance to consumer satisfaction with the freshness of the product. This model aims to help farmers reduce costs and expand profit margins while ensuring that consumers can enjoy high-quality and fresh agricultural products. Although there is a certain conflict between these two goals, by solving them, a Pareto optimal solution between the two can be found.

[0058] (3) In order to effectively solve the above dual-objective model, the present invention proposes an improved artificial bee colony algorithm. The algorithm is carefully designed in terms of coding rules, crossover strategy, neighborhood search structure and local search method, and incorporates reinforcement learning technology to improve the algorithm's solution efficiency. The effectiveness and superiority of this model and algorithm were verified by comparative experiments with three classic multi-objective algorithms. The Pareto optimal solution finally obtained helps to reduce operating costs and reduce the loss of freshness of agricultural products, thereby improving service satisfaction, providing a valuable reference for farmers and the fresh food e-commerce industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the implementation cases of the present invention or the technical solutions in the prior art, the following is a brief description of the drawings required for use in the embodiments. By referring to the drawings, the features and advantages of the present invention will be more clearly understood. The drawings are schematic and should not be understood as limiting the present invention in any way. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0060] Figure 1 A flowchart of a multi-farm picking and distribution integrated scheduling method based on an improved artificial bee colony algorithm provided in an embodiment;

[0061] Figure 2 Schematic diagram of the integrated scheduling problem of multi-farm picking and distribution in the embodiment;

[0062] Figure 3 Flow chart of the improved artificial bee colony algorithm in the embodiment;

[0063] Figure 4 Schematic diagram of encoding and decoding in the embodiment;

[0064] Figure 5 A schematic diagram of a crossover method in an embodiment;

[0065] Figure 6 It is a box plot of IGD and HV indicators obtained by the four algorithms in the embodiment on different examples;

[0066] Figure 7 A block diagram of a multi-farm picking and distribution integrated scheduling system based on an improved artificial bee colony algorithm provided in an embodiment. DETAILED DESCRIPTION

[0067] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0068] Embodiment 1

[0069] In order to solve the problems of insufficient integration of agricultural product picking and distribution processes, high costs and difficulty in ensuring freshness in the "community-supported agriculture" model in existing technologies. Figure 1 As shown, the embodiment of the present invention proposes a multi-farm picking and distribution integrated scheduling method based on an improved artificial bee colony algorithm, the method comprising:

[0070] For the problem of integrated scheduling of multi-farm picking and delivery, set constraints, including that multiple existing farms cooperate with each other to provide agricultural products to customers, managers receive customer orders and assign customer orders to each farm, arrange picking tasks and delivery tasks for each farm, that is, arrange the picking team to pick agricultural products according to the optimized picking order, and arrange vehicles to deliver agricultural products to customers from the farm according to the optimized route, and finally return to the farm;

[0071] Define the agricultural product freshness loss function, where the agricultural product freshness loss function is used to describe the change of freshness of agricultural products over time from picking to delivery to customers;

[0072] Define two objective functions, including minimizing the operating cost function and maximizing the customer satisfaction function, where the operating cost includes the picking cost, transportation cost and vehicle usage cost, and customer satisfaction is related to the freshness of the delivered agricultural products;

[0073] Based on constraints and objective functions, a dual-objective model for integrated scheduling of multi-farm harvesting and distribution is established;

[0074] Solve the dual-objective optimization model to obtain the optimal solution set, and dispatch agricultural products based on the picking and distribution information in the optimal solution set.

[0075] It can be seen from the above technical scheme that the present invention proposes a multi-farm picking and distribution integrated scheduling method based on an improved artificial bee colony algorithm, aiming to solve the problems of insufficient integration of agricultural product picking and distribution processes, high costs and difficulty in ensuring freshness under the existing "community supported agriculture" model. The method integrates the two major links of picking and distribution and introduces multi-farm collaboration to achieve full-chain optimization of agricultural products from picking to distribution. At the same time, the present invention defines the agricultural product freshness loss function and two objective functions, and constructs a dual-objective model including minimization of operating costs and maximization of customer satisfaction. By solving the model, the present invention obtains the Pareto optimal solution and achieves dual optimization of operating costs and customer satisfaction. In addition, the improved artificial bee colony algorithm proposed in the present invention is carefully designed in terms of encoding, crossover strategy, neighborhood search and local search, and incorporates reinforcement learning technology, which significantly improves the solution efficiency. The method not only reduces operating costs and reduces the loss of agricultural product freshness, but also improves service satisfaction, provides practical guidance and useful reference for farmers and the fresh food e-commerce industry, and shows strong practical application value and superiority.

[0076] The schematic diagram of the multi-farm picking and distribution integrated scheduling problem studied in this invention is as follows Figure 2 , which includes five decisions: (1) allocating customers (orders) to each farm; (2) allocating tasks to the picking teams in each farm, i.e. allocating the picking of agricultural products to the picking teams; (3) the order in which the picking teams pick agricultural products; (4) allocating between customer points and transport vehicles in each farm, i.e. allocating customer points to transport vehicles; and (5) the delivery routes of the vehicles.

[0077] Specifically, constraints are set for the integrated scheduling problem of multi-farm picking and distribution, including that multiple existing farms cooperate with each other to provide agricultural products (various vegetables and fruits) to customers, managers receive customer orders and assign customer orders to various farms, and arrange picking tasks and distribution tasks for each farm, that is, arrange picking teams to pick agricultural products according to the optimized picking order, and arrange vehicles to deliver agricultural products to customers from the farm according to the optimized route, and finally return to the farm; each farm grows a variety of agricultural products, and each farm grows the same type of agricultural products; each kind of agricultural product can only be picked by one picking team; each picking team can only pick one kind of agricultural product at the same time; each agricultural product has a specific freshness loss rate, and the freshness of the agricultural product decreases over time after it is picked; each customer may need more than one kind of agricultural product; each customer is only assigned to one farm to provide agricultural products for him; each customer is delivered by only one vehicle; the time when the vehicle departs from the farm is equal to the time when the last agricultural product to be loaded is completed; the vehicle carrying capacity is limited, that is, the total vehicle load at any point on the route is not greater than the vehicle carrying capacity; the starting point and end point of the vehicle must be the same farm.

[0078] Furthermore, the model symbols are defined, including the required collection, index, parameter, variable and other symbols, as shown in Table 1 below.

[0079] Table 1

[0080]

[0081]

[0082] Specifically, this embodiment defines an agricultural product freshness loss function. The agricultural product freshness loss function is used to describe the change of freshness over time in the process from picking to delivering agricultural products to customers. The freshness of agricultural products is one of the important factors affecting customer satisfaction. Therefore, this function is crucial for evaluating customer satisfaction. Generally speaking, the agricultural product freshness loss function can be expressed as a function of time. As time goes by, the freshness of agricultural products gradually decreases. Specifically, the agricultural product freshness loss function is expressed as:

[0083]

[0084] In the formula, F represents the initial freshness of agricultural products, that is, the maximum freshness; F j Represents the freshness of agricultural product j after time t.

[0085] Specifically, this embodiment defines two objective functions, including minimizing the operating cost function and maximizing the customer satisfaction function, where the operating cost is an important goal of model optimization, including picking cost, transportation cost and vehicle use cost. The picking cost is affected by the work efficiency of the picking team, while the transportation cost and vehicle use cost are related to the distribution route and vehicle arrangement. Therefore, by optimizing the work efficiency of the picking team and the distribution route, the operating cost can be reduced. Specifically, the minimizing operating cost function can be expressed as:

[0086]

[0087] Where f1 represents the operating cost.

[0088] Customer satisfaction is another important optimization objective, which is related to the freshness of the delivered produce. The higher the freshness of the produce, the more punctual the delivery time, and the higher the customer satisfaction. The freshness of the produce is affected by the produce freshness loss function. Specifically, maximizing the customer satisfaction function is expressed by minimizing the freshness loss:

[0089] minf2=∑ m∈J ψ m ;

[0090] Where f2 represents the freshness loss.

[0091] Specifically, this embodiment establishes a dual-objective model for integrated scheduling of multi-farm picking and distribution based on the above constraints and objective functions, where the dual-objective optimization model is expressed as:

[0092]

[0093]

[0094]

[0095] Where, X 0igl Picking team l representing farm g picks virtual product 0 and then picks product j; Z g′mgh where g′ and g represent two different farms, Z g′mgh Vehicle h representing farm g departs from farm g′ to customer m; Z mg′gh where g′ and g represent two different farms, Z mg′gh Vehicle h representing farm g returns from customer m to farm g′; Z g′g″gh where g″, g′ and g represent three different farms, and Z g′g″gh Vehicle h representing farm g returns from farm g′ to farm g″.

[0096] It should be noted that These three constraints are all equal to 0 to ensure that the starting point and end point of the vehicle must be the same farm.

[0097] Specifically, this embodiment uses an improved artificial bee colony algorithm to solve the multi-objective optimization model, obtains an optimal solution set (Pareto equilibrium solution), and performs agricultural product scheduling based on the picking and delivery information in the optimal solution set, including determining customer order allocation, picking task allocation, picking sequence, vehicle allocation, and delivery route. Figure 3 As shown, specifically including:

[0098] Step S61: Initialize algorithm parameters, including population size N, maximum trial value number MaxTrial, Q table, initial state, and maximum running time; randomly generate an initial population, including solutions represented by N integer codes, and assign each solution a trial value number of 0; evaluate the target values ​​of N solutions in the population, and store the non-dominated solution set in an external archive;

[0099] Step S62: Execute the employed bee stage: the population performs a crossover operation, and if a solution is improved, the number of its test values ​​is increased by 1;

[0100] Step S63: Execute the spectator bee stage: select the optimal neighborhood structure using the Q learning method according to the current state, and the population executes the selected neighborhood structure. If a solution is improved, the number of its trial values ​​is increased by 1;

[0101] Step S64: Execute the scout bee stage: check whether the number of trial values ​​of each solution in the population reaches the maximum limit MaxTrial. If the maximum limit is reached, randomly select a solution from the external archive to replace the solution;

[0102] Step S65: the population updates the external archive, and the external archive executes the local search method;

[0103] Step S66: Calculate the reward value based on the change of state and update the Q table;

[0104] Step S67: determine whether the maximum running time has been reached, if so, terminate, otherwise return to step S62;

[0105] Step S68: Output the optimal solution set obtained from the external archive.

[0106] In addition, this embodiment also uses integer coding to represent the solution of the problem, including 3 integer strings, integer string 1 (π′) represents the allocation of customers to farms, integer string 2 (π″) represents the picking tasks of each farm (including the picking order of agricultural products and the number of types of agricultural products assigned to the picking team), and integer string 3 (π″′) represents the delivery order of customers. Figure 4 , from integer string 1, we know that customers 1, 3, 5, and 9 are assigned to farm 1; the rest of the customers are assigned to farm 2. From integer string 2, we know that picking team 1 of farm 1 is responsible for picking two agricultural products, picking agricultural products 1 and agricultural products 2 in turn, and picking team 2 of farm 1 is responsible for picking one agricultural product, namely agricultural product 3; picking team 1 of farm 2 is responsible for picking two agricultural products, picking agricultural products 2 and agricultural products 1 in turn, and picking team 2 of farm 2 is responsible for picking one agricultural product, namely agricultural product 3. Finally, according to customer demand, vehicle loading limit and integer string 3, the decision of the distribution stage can be obtained, that is, according to integer string 3, customers of the same farm are assigned to the same vehicle in order until the loading capacity of a vehicle reaches the upper limit, then a vehicle is rearranged, and finally the distribution route is obtained.

[0107] In addition, if Figure 5As shown in the figure, in the process of solving the optimal solution set using the improved artificial bee colony algorithm, integer string 1 and integer string 2 use the uniform crossover method, and integer string 3 uses the sequential crossover method. The uniform crossover design is as follows: randomly generate the number 0 or 1, if the number 1 is generated, the gene is copied from parent 1, and if the number 0 is generated, the gene is copied from parent 2. The sequential crossover design is as follows: randomly select two different cutting points, and select the gene segment between the cutting points as the crossover segment; the crossover segment in parent 1 is copied to the corresponding gene position of the offspring individual, and the gene of the crossover segment of parent 1 is deleted in parent 2, and the remaining genes are assigned to the offspring individuals in sequence.

[0108] In order to verify the effectiveness and superiority of the improved artificial bee colony algorithm (denoted as Q-ABC-K) proposed in this embodiment, three algorithms are selected as comparison algorithms, namely, non-dominated sorting genetic algorithm II (NSGA-II), multi-objective evolutionary algorithm based on decomposition (MOEA / D) and multi-objective brainstorming optimization algorithm (MOBSO) are run 20 times on examples of different scales. The IGD index and HV index are used to measure the performance of the algorithm. It is worth noting that the smaller the IGD index value, the better the algorithm performance, while the larger the HV index value, the better the algorithm performance. Figure 6 The box plots obtained on the two indicators are given. It can be seen that the performance of the improved artificial bee colony algorithm is better than that of the other three algorithms.

[0109] Embodiment 2

[0110] like Figure 7 As shown, the present invention provides a multi-farm picking and distribution integrated scheduling system based on an improved artificial bee colony algorithm, which is used to implement the multi-farm picking and distribution integrated scheduling method based on the improved artificial bee colony algorithm of the above embodiment 1, specifically including:

[0111] The constraint condition setting module 100 is used to set constraint conditions for the integrated scheduling problem of multi-farm picking and distribution, including that multiple existing farms cooperate with each other to provide agricultural products to customers, managers receive customer orders and assign customer orders to each farm, and arrange picking tasks and distribution tasks for each farm, that is, arrange picking teams to pick agricultural products according to the optimized picking sequence, and arrange vehicles to deliver agricultural products to customers from the farm according to the optimized route, and finally return to the farm;

[0112] A function definition module 200 is used to define a freshness loss function of agricultural products, wherein the freshness loss function of agricultural products is used to describe the change of freshness of agricultural products over time from picking to delivery to customers;

[0113] An objective function definition module 300 is used to define two objective functions, including a function of minimizing operating costs and a function of maximizing customer satisfaction, wherein the operating costs include picking costs, transportation costs, and vehicle use costs, and customer satisfaction is related to the freshness of the delivered agricultural products;

[0114] A dual-objective optimization model building module 400 is used to build a dual-objective model for integrated scheduling of multi-farm harvesting and distribution based on constraints and objective functions;

[0115] The solution and scheduling module 500 is used to solve the dual-objective optimization model, obtain the optimal solution set, and schedule agricultural products according to the picking and delivery information in the optimal solution set.

[0116] A multi-farm picking and distribution integrated scheduling system based on an improved artificial bee colony algorithm in this embodiment is used to implement the aforementioned multi-farm picking and distribution integrated scheduling method based on the improved artificial bee colony algorithm. Therefore, the specific implementation method of the multi-farm picking and distribution integrated scheduling system based on the improved artificial bee colony algorithm can be seen from the embodiment part of the multi-farm picking and distribution integrated scheduling method based on the improved artificial bee colony algorithm in the previous text, for example, the constraint setting module 100, the function definition module 200, the objective function definition module 300, the dual-objective optimization model establishment module 400, the solution and scheduling module 500, are respectively used to implement steps S1, S2, S3, S4, and S5 in the above-mentioned multi-farm picking and distribution integrated scheduling method based on the improved artificial bee colony algorithm. Therefore, its specific implementation method can refer to the description of the corresponding embodiments of each part. In order to avoid redundancy, it will not be repeated here.

[0117] Embodiment 3

[0118] An embodiment of the present invention provides an electronic device, which includes a processor, a memory and a bus system. The processor and the memory are connected through the bus system. The memory is used to store instructions, and the processor is used to execute the instructions stored in the memory to realize the above-mentioned multi-farm picking and distribution integrated scheduling method based on the improved artificial bee colony algorithm.

[0119] Embodiment 4

[0120] An embodiment of the present invention provides a computer storage medium storing a computer software product. The computer software product includes a number of instructions for enabling a computer device to execute the above-mentioned multi-farm picking and distribution integrated scheduling method based on the improved artificial bee colony algorithm.

[0121] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0122] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0123] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide for implementing the process in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0124] Obviously, the above embodiments are merely examples for clear explanation and are not intended to limit the implementation methods. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived from them are still within the protection scope of the invention.

Claims

1. A multi-farm picking and distribution integrated scheduling method based on an improved artificial bee colony algorithm, characterized in that: include: For the problem of integrated scheduling of multi-farm picking and delivery, set constraints, including that multiple existing farms cooperate with each other to provide agricultural products to customers, managers receive customer orders and assign customer orders to each farm, arrange picking tasks and delivery tasks for each farm, that is, arrange the picking team to pick agricultural products according to the optimized picking order, and arrange vehicles to deliver agricultural products to customers from the farm according to the optimized route, and finally return to the farm; A freshness loss function of agricultural products is defined, wherein the freshness loss function of agricultural products is used to describe the change of freshness of agricultural products over time from picking to delivery to customers; Define two objective functions, including minimizing the operating cost function and maximizing the customer satisfaction function, where the operating cost includes the picking cost, transportation cost and vehicle usage cost, and customer satisfaction is related to the freshness of the delivered agricultural products; Based on the constraints and the objective function, a dual-objective model for integrated scheduling of multi-farm picking and distribution is established; Solve the dual-objective optimization model to obtain an optimal solution set, and dispatch agricultural products according to the picking and delivery information in the optimal solution set.

2. The multi-farm picking and distribution integrated scheduling method based on the improved artificial bee colony algorithm according to claim 1 is characterized in that: The constraints also include: Each farm grows a variety of agricultural products, and the types of agricultural products grown on each farm are the same; Each type of agricultural product can only be picked by one picking team; Each picking team can only pick one type of agricultural product at a time; Each agricultural product has a specific freshness loss rate, and the freshness of agricultural products decreases over time after they are picked; Each customer may need more than one agricultural product; Each customer is assigned only one farm to provide him with agricultural products; Each customer is delivered by only one vehicle; The time it takes for the vehicle to depart from the farm is equal to the time it takes to complete the picking of the last produce that needs to be loaded; The vehicle carrying capacity is limited, that is, the total vehicle load at any point on the route is not greater than the vehicle carrying capacity; The vehicle's starting and ending points must be the same farm.

3. The multi-farm picking and distribution integrated scheduling method based on the improved artificial bee colony algorithm according to claim 1 is characterized in that: The agricultural product freshness loss function is expressed as: Where F represents the initial freshness of agricultural products, that is, the maximum freshness; θ j is the freshness loss rate of agricultural product j; F j Represents the freshness of agricultural product j after time t.

4. The multi-farm picking and distribution integrated scheduling method based on the improved artificial bee colony algorithm according to claim 1 is characterized in that: The minimization operation cost function is: In the formula, f1 represents the operating cost, b represents the picking cost per unit time, e represents the driving cost per unit time, r represents the fixed cost of each vehicle, and Y mg If customer m is assigned to farm g, then Y mg =1; otherwise, Y mg =0;d mj represents the demand of customer m for agricultural product j; t lj represents the picking time of agricultural product j by picking team l; U jgl If the picking team l of farm g picks agricultural product j, then U jgl =1; otherwise , U jgl =0;v mn Represents the travel time from node m to node n; Z mngh If vehicle h from farm g visits node m and then node n, then Z mngh =1; otherwise ，Z mngh ＝0； m , n∈Q, represents the node index, where Q=J∪F, represents the node set, J={1,2,...,q}, represents the customer set, q represents the total number of customers, F={q+1,q+2,...,q+f}, represents the farm set, f represents the number of farms; h∈K g , represents the vehicle index, where K g ={1, 2, ..., k g }, represents the vehicle set, k g represents the number of vehicles in farm g; g∈F, represents the farm index; l∈M g , represents the picking team index, where M g ={1, 2, ..., m g }, represents the collection of picking teams, m g represents the number of picking teams in farm g; j∈P represents the agricultural product index, where P={0, 1, 2, ..., p}, represents the set of agricultural products, where 0 represents virtual agricultural products and p represents the number of types of agricultural products; P\{0} represents the set of agricultural products that does not contain 0.

5. The multi-farm picking and distribution integrated scheduling method based on the improved artificial bee colony algorithm according to claim 1 is characterized in that: The maximized customer satisfaction function is expressed by minimizing the freshness loss: minf2=∑ m∈J ψ m ; Where f2 represents the freshness loss; ψ m Represent customer m to obtain the maximum freshness loss in agricultural products; m∈J, J={1, 2, ..., q}, represents the customer set, and q represents the total number of customers.

6. The multi-farm picking and distribution integrated scheduling method based on the improved artificial bee colony algorithm according to claim 1 is characterized in that: The dual-objective model of multi-farm picking and distribution integrated scheduling is expressed as: Where i, j∈P represents the index of agricultural products, where P = {0, 1, 2, ..., p} represents the set of agricultural products, where 0 represents virtual agricultural products, and p represents the number of types of agricultural products; P\{0} represents the set of agricultural products that does not contain 0; m, n∈Q, represents the node index, where Q=J∪F, represents the node set, J={1, 2, ..., q}, represents the customer set, q represents the total number of customers, F={q+1, q+2, ..., q+f}, represents the farm set, f represents the number of farms; h∈K g , represents the vehicle index, where K g ={1, 2, ..., k g }, represents the vehicle set, k g represents the number of vehicles in farm g; l∈M g , represents the picking team index, where M g ={1, 2, ..., m g }, represents the collection of picking teams, m g represents the number of picking teams in farm g; d mj represents the demand of customer m for agricultural product j; R mj If customer m needs agricultural product j, then R mj =1; otherwise , R mj =0;θ j is the freshness loss rate of agricultural product j; v nm Represents the travel time from node m to node n; δ represents the maximum load of each vehicle; B represents infinity; Y mg If customer m is assigned to farm g, then Y mg =1; otherwise, Y mg =0; U jgl If the picking team l of farm g picks agricultural product j, then U jgl =1; otherwise , U jgl =0;X ijgl If the picking team l of farm g picks agricultural product i and then picks agricultural product j, then X ijgl =1; otherwise , X ijgl =0;X 0jgl The picking team l representing farm g picks virtual product 0 and then picks agricultural product j; W mgh If vehicle h from farm g serves customer m, then W mgh =1; otherwise, W mgh =0; Z mngh If vehicle h from farm g visits node m and then node n, then Z mngh =1; otherwise, Z mngh =0; Z g′mgh where g′ and g represent two different farms, Z g′mgh Vehicle h representing farm g departs from farm g′ to customer m; Z mg′gh where g′ and g represent two different farms, Z mg′gh Vehicle h representing farm g returns from customer m to farm g′; Z g′g″gh where g″, g′ and g represent three different farms, and Z g′g″gh Vehicle h representing farm g returns from farm g′ to farm g″; D gh represents the time when vehicle h departs from farm g; A m represents the time when the vehicle arrives at customer m; S gj represents the picking start time of agricultural product j in farm g; C gj represents the harvesting completion time of agricultural product j in farm g; ξ mj represents the freshness loss of agricultural product j when it is delivered to customer m; ψ m Get the maximum freshness loss in produce on behalf of customer m.

7. The multi-farm picking and distribution integrated scheduling method based on the improved artificial bee colony algorithm according to claim 1 is characterized in that: The method for solving the dual-objective optimization model to obtain the optimal solution set is: The improved artificial bee colony algorithm is used to solve the multi-objective optimization model to obtain the optimal solution set, wherein the improved artificial bee colony algorithm specifically includes: Step S61: Initialize algorithm parameters, including population size N, maximum trial value number MaxTrial, Q table, initial state, and maximum running time; randomly generate an initial population, including solutions represented by N integer codes, and assign each solution a trial value number of 0; evaluate the target values ​​of N solutions in the population, and store the non-dominated solution set in an external archive; Step S62: Execute the employed bee stage: the population performs a crossover operation, and if a solution is improved, the number of its test values ​​is increased by 1; Step S63: Execute the spectator bee stage: select the optimal neighborhood structure using the Q learning method according to the current state, and the population executes the selected neighborhood structure. If a solution is improved, the number of its trial values ​​is increased by 1; Step S64: Execute the scout bee stage: check whether the number of trial values ​​of each solution in the population reaches the maximum limit MaxTrial. If the maximum limit is reached, randomly select a solution from the external archive to replace the solution; Step S65: the population updates the external archive, and the external archive executes the local search method; Step S66: Calculate the reward value based on the change of state and update the Q table; Step S67: determine whether the maximum running time has been reached, if so, terminate, otherwise return to step S62; Step S68: Output the optimal solution set obtained from the external archive.

8. A multi-farm picking and distribution integrated scheduling system based on an improved artificial bee colony algorithm, characterized in that: The system is used to implement the multi-farm picking and distribution integrated scheduling method based on the improved artificial bee colony algorithm as described in any one of claims 1 to 7, specifically comprising: The constraint setting module is used to set constraints for the integrated scheduling problem of multi-farm picking and delivery, including the cooperation of multiple existing farms to provide agricultural products to customers, managers receiving customer orders and assigning customer orders to various farms, arranging picking tasks and delivery tasks for each farm, that is, arranging picking teams to pick agricultural products in an optimized picking order, and arranging vehicles to deliver agricultural products to customers from the farms along the optimized routes, and finally returning to the farms; A function definition module, used to define a freshness loss function of agricultural products, wherein the freshness loss function of agricultural products is used to describe the change of freshness of agricultural products over time from picking to delivery to customers; An objective function definition module is used to define two objective functions, including minimizing the operating cost function and maximizing the customer satisfaction function, where the operating cost includes the picking cost, transportation cost and vehicle use cost, and the customer satisfaction is related to the freshness of the delivered agricultural products; A dual-objective optimization model building module, used to build a dual-objective model for integrated scheduling of multi-farm picking and distribution based on the constraint conditions and the objective function; The solution and scheduling module is used to solve the dual-objective optimization model, obtain the optimal solution set, and schedule agricultural products according to the picking and distribution information in the optimal solution set.

9. An electronic device, characterized in that: The electronic device includes a processor, a memory and a bus system, the processor and the memory are connected through the bus system, the memory is used to store instructions, and the processor is used to execute the instructions stored in the memory to implement the multi-farm picking and distribution integrated scheduling method based on the improved artificial bee colony algorithm as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: The computer storage medium stores a computer software product, which includes a number of instructions for enabling a computer device to execute the multi-farm picking and distribution integrated scheduling method based on the improved artificial bee colony algorithm as described in any one of claims 1 to 7.

Images