Method and system for supplying goods

Abstract

The application discloses a material supply method and system, wherein the method comprises the following steps: acquiring scene parameters and generating an initial population; calculating a first fitness value of the initial population; performing pretreatment on the initial population to obtain a first population and calculating a second fitness value of the first population; combining the initial population and the first population to obtain a second population, performing screening on the second population to obtain a third population; performing neighborhood search on feasible solutions of the third population to obtain a fourth population and calculating a third fitness value of the fourth population; combining the third population and the fourth population to obtain a fifth population, performing screening on the fifth population to obtain a sixth population, and calculating a fourth fitness value of the sixth population; acquiring a current iteration number, repeating the above steps until the current iteration number is equal to a preset iteration number if the current iteration number is less than the preset iteration number; selecting a minimum value from all the fitness values, acquiring pareto front data corresponding to the minimum value, and obtaining a target supply scheme.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of material supply, and in particular to a material supply method and system. BACKGROUND

[0002] In reality, a logistics system for material transmission at least includes a node requiring material, a vehicle distributing material, and a material transfer station. The existing technical scheme for material supply planning mostly focuses on the shortest path, the shortest time, etc. In a specific scenario, the material transfer station in the logistics system may fail. The existing technical scheme needs to exclude the failed material transfer station and then perform material supply planning focusing on the shortest path, the shortest time, etc., that is, to perform a new scheme planning, and thus the logistics system exhibits problems such as reaction lag, mismatch between supply and demand, and low distribution efficiency. SUMMARY

[0003] Therefore, it is necessary to propose a material supply method and system to solve the technical problems of reaction lag, mismatch between supply and demand, and low distribution efficiency of the existing logistics system when the transfer station fails.

[0004] In a first aspect, a material supply method is provided, and the method includes:

[0005] Obtaining scene parameters of a target material supply scene, and generating an initial population by gene coding according to the scene parameters;

[0006] Calculating a first fitness value of the initial population under a preset constraint condition by a preset objective function;

[0007] Selecting, crossing, and mutating individuals in the initial population to obtain a first population, and calculating a second fitness value of the first population under the preset constraint condition by the preset objective function;

[0008] Merging the initial population and the first population to obtain a second population, and performing a first population screening on the second population to obtain a third population;

[0009] Performing neighborhood search on feasible solutions of the third population according to a preset rule to obtain a fourth population, and calculating a third fitness value of the fourth population under the preset constraint condition by the preset objective function;

[0010] Merging the third population and the fourth population to obtain a fifth population, performing a second population screening on the fifth population to obtain a sixth population, and calculating a fourth fitness value of the sixth population under the preset constraint condition by the preset objective function;

[0011] acquire the current iteration number, if the current iteration number is less than the preset iteration number, the sixth population is taken as the initial population, the steps of selecting, crossing and mutating the individuals in the initial population are continued, and the fitness value set when the sixth population is taken as the initial population is recorded, until the current iteration number is equal to the preset iteration number;

[0012] select the minimum value from the first fitness value, the second fitness value, the third fitness value, the fourth fitness value and the fitness value set, acquire the pareto front data corresponding to the minimum value, and obtain the target supply scheme according to the pareto front data.

[0013] Optionally, the step of acquiring the scene parameters of the target material supply scene and generating the initial population in the form of gene coding according to the scene parameters comprises:

[0014] acquire the scene parameters of the target material supply scene, and the scene parameters comprise: a matching relationship between demand points and distribution vehicles, a matching relationship between vehicles and transfer stations, a distribution sequence matrix of the demand points, a number of warehouses of the secondary supply network, a number of optional transfer stations, and a number of demand points to be distributed;

[0015] generate the initial population in the form of gene coding according to the matching relationship between the demand points and the distribution vehicles, the matching relationship between the vehicles and the transfer stations, the distribution sequence matrix of the demand points, the number of warehouses of the secondary supply network, the number of optional transfer stations and the number of demand points to be distributed.

[0016] Optionally, the step of generating the initial population in the form of gene coding according to the matching relationship between the demand points and the distribution vehicles, the matching relationship between the vehicles and the transfer stations, the distribution sequence matrix of the demand points, the number of warehouses of the secondary supply network, the number of optional transfer stations and the number of demand points to be distributed comprises:

[0017] generate a first individual set in the form of gene coding according to the matching relationship between the demand points and the distribution vehicles, the matching relationship between the vehicles and the transfer stations, the distribution sequence matrix of the demand points, the number of warehouses of the secondary supply network, the number of optional transfer stations and the number of demand points to be distributed according to a random generation strategy;

[0018] generate a second individual set in the form of gene coding according to the matching relationship between the demand points and the distribution vehicles, the matching relationship between the vehicles and the transfer stations, the distribution sequence matrix of the demand points, the number of warehouses of the secondary supply network, the number of optional transfer stations and the number of demand points to be distributed according to a greedy generation strategy;

[0019] generate the initial population based on the first set of individuals and the second set of individuals.

[0020] Optionally, the step of calculating the first fitness value of the initial population under the preset constraint condition by the preset objective function comprises:

[0021] by the preset objective function:

[0022]

[0023]

[0024] calculating the first fitness value of the initial population under the preset constraint condition, wherein ω is a failure scenario, P ω is a probability of a failure scenario, is a failure scenario total cost after temporary adjustment, failure scenario satisfaction after temporary adjustment, the preset constraint condition comprises a demand amount condition of the material, a loading amount condition of the vehicle, a condition of limiting departure and return of the vehicle at the same node, a vehicle travel continuity condition, a time condition of arriving at a node, a condition of a transfer station forbidden to the vehicle, and a loading amount condition of the vehicle on an effective path.

[0025] Optionally, the step of selecting, crossing, and mutating the individuals in the initial population to obtain the first population comprises:

[0026] selecting parent individuals from the initial population by a tournament selection method;

[0027] selecting exchange individuals from the initial population by a uniform crossing method according to a preset crossing probability, and constructing an intermediate population according to the parent individuals and the exchange individuals;

[0028] mutating the intermediate population according to a preset mutation rule to obtain the first population.

[0029] Optionally, the step of performing neighborhood search on the feasible solutions of the third population according to a preset rule to obtain the fourth population comprises:

[0030] deleting routes in the feasible solutions of the third population that only distribute one node according to a first rule in the preset rule to obtain a first initial feasible solution;

[0031] redistributing the farthest node on each route in the initial feasible solution according to a second rule in the preset rule to obtain a second initial feasible solution;

[0032] According to a third rule in the preset rules, a shortest path search is performed on each path in the second initial feasible solution to obtain a fourth population.

[0033] Optionally, the step of performing first population screening on the second population to obtain a third population comprises:

[0034] The first population screening on the second population is performed by an elitist strategy and a crowding degree allocation strategy to obtain a third population.

[0035] In a second aspect, the present application provides a material supply device, which comprises:

[0036] A data acquisition module is configured to acquire scene parameters of a target material supply scene and generate an initial population by gene coding according to the scene parameters;

[0037] A first calculation module is configured to calculate a first fitness value of the initial population under a preset constraint condition by a preset target function;

[0038] A second calculation module is configured to perform selection, crossover and mutation processing on individuals in the initial population to obtain a first population, and calculate a second fitness value of the first population under the preset constraint condition by the preset target function;

[0039] A third calculation module is configured to combine the initial population and the first population to obtain a second population, and perform first population screening on the second population to obtain a third population;

[0040] A fourth calculation module is configured to perform neighborhood search on feasible solutions of the third population according to a preset rule to obtain a fourth population, and calculate a third fitness value of the fourth population under the preset constraint condition by the preset target function;

[0041] A fifth calculation module is configured to combine the third population and the fourth population to obtain a fifth population, perform second population screening on the fifth population to obtain a sixth population, and calculate a fourth fitness value of the sixth population under the preset constraint condition by the preset target function;

[0042] An iteration module is configured to acquire a current iteration number, if the current iteration number is less than a preset iteration number, take the sixth population as the initial population, continue the step of performing selection, crossover and mutation processing on individuals in the initial population, and record a fitness value set when the sixth population is taken as the initial population, until the current iteration number is equal to the preset iteration number.

[0043] The scheme output module is configured to select a minimum value from the first fitness value, the second fitness value, the third fitness value, the fourth fitness value and the fitness value set, and obtain pareto frontier data corresponding to the minimum value, and obtain a target supply scheme according to the pareto frontier data.

[0044] In a fourth aspect, a computer readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, the steps of the above-mentioned material supply method are implemented.

[0045] The application obtains scene parameters of a target material supply scene, and generates an initial population by genetic coding according to the scene parameters. A first fitness value of the initial population under a preset constraint condition is calculated by a preset objective function. Individuals in the initial population are selected, crossed and mutated to obtain a first population. A second fitness value of the first population under the preset constraint condition is calculated by the preset objective function. The initial population and the first population are merged to obtain a second population, and the second population is screened for the first time to obtain a third population. A feasible solution of the third population is searched in a neighborhood according to a preset rule to obtain a fourth population, and a third fitness value of the fourth population under the preset constraint condition is calculated by the preset objective function. The third population and the fourth population are merged to obtain a fifth population, and the fifth population is screened for the second time to obtain a sixth population, and a fourth fitness value of the sixth population under the preset constraint condition is calculated by the preset objective function. A current iteration number is obtained. If the current iteration number is less than a preset iteration number, the sixth population is taken as the initial population, the steps of selecting, crossing and mutating individuals in the initial population are continued, and a fitness value set when the sixth population is taken as the initial population is recorded, until the current iteration number is equal to the preset iteration number. A minimum value is selected from the first fitness value, the second fitness value, the third fitness value, the fourth fitness value and the fitness value set, and pareto frontier data corresponding to the minimum value is obtained. A target supply scheme is obtained according to the pareto frontier data. In the process of formulating a material supply scheme, the scenario of transfer station failure is considered, and by overall planning, the human and material resources are reasonably arranged to reduce costs on the basis of ensuring timeliness. At the same time, when the transfer station failure occurs, the material supply scheme considering the transfer station failure in formulating the material supply scheme can be directly output without re-planning, thereby avoiding problems such as slow response of the logistics system, mismatch between supply and demand, and low distribution efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0047] Wherein:

[0048] Figure 1 A flow chart of a material supply method in an embodiment;

[0049] Figure 2 A schematic diagram of a coding result in a material supply method in an embodiment;

[0050] Figure 3 A flow chart of an adaptive value calculation in a material supply method in an embodiment;

[0051] Figure 4 A structural block diagram of a material supply device in an embodiment;

[0052] Figure 5 A structural block diagram of a computer device in an embodiment;

[0053] Figure 6 A structural block diagram of a computer device in another embodiment. DETAILED DESCRIPTION

[0054] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0055] The present application will be described in detail below through specific embodiments.

[0056] Please refer to Figure 1 as shown, Figure 1 A flow chart of a material supply method provided by an embodiment of the present application, comprising the following steps:

[0057] S101, acquire scene parameters of a target material supply scene, and generate an initial population by gene coding according to the scene parameters;

[0058] In a possible implementation, the step of acquiring scene parameters of a target material supply scene and generating an initial population by gene coding according to the scene parameters comprises:

[0059] obtaining scene parameters of a target material supply scene, the scene parameters comprising: a matching relationship between demand points and distribution vehicles, a matching relationship between vehicles and transfer stations, a distribution sequence matrix of the demand points, a number of warehouses of a two-level supply network, a number of optional transfer stations, and a number of demand points to be distributed;

[0060] According to the matching relationship between the demand points and the distribution vehicles, the matching relationship between the vehicles and the transfer stations, the distribution sequence matrix of the demand points, the number of warehouses of the two-level supply network, the number of optional transfer stations, and the number of demand points to be distributed, an initial population is generated in a gene coding manner.

[0061] Exemplarily, the scene parameters comprise: a number of warehouses of a two-level supply network, a number of optional transfer stations, a number of demand points to be distributed, and two-dimensional coordinates of each node position; the parameters comprise: a demand amount of each demand point, a current infection rate, a satisfaction time threshold, a capacity of a first-level and a second-level distribution vehicle, a use cost, a transportation cost, an average speed, and an operation cost of a transfer station. The scene parameters further comprise: a failure probability of a transfer station calculated by the current infection rate; a distance matrix of the first-level and the second-level network calculated by the two-dimensional coordinates of the nodes, the distance matrix being used for calculating a calculation cost.

[0062] Exemplarily, a combination of the matching relationship between the demand points and the distribution vehicles and the matching relationship between the vehicles and the transfer stations is adopted, and then a distribution sequence matrix of the demand points is coded according to the matching relationship between the demand points and the distribution vehicles and the matching relationship between the vehicles and the transfer stations, as shown in the following table. Figure 2 According to the gene coding manner, N individuals (an initial population) are initially generated, and gene decoding is to convert a chromosome represented by a gene into an overall scheme of emergency warehouse location and distribution path. The matching gene between a vehicle and an emergency warehouse is decoded to obtain a selected emergency warehouse node, and then a complete distribution path of each vehicle after starting from the emergency warehouse and a distribution sequence of demand points are decoded according to the demand point distribution sequence gene.

[0063] S102, calculating a first fitness value of the initial population under a preset constraint condition through a preset objective function;

[0064] In a possible implementation, the step of calculating the first fitness value of the initial population under the preset constraint condition through the preset objective function comprises:

[0065] The preset objective function is:

[0066]

[0067]

[0068] calculating a first fitness value of the initial population under preset constraints, wherein ω is a failure scenario, P ω is a probability of a failure scenario, is a failure scenario a total cost after temporary adjustment, a failure scenario a satisfaction degree after temporary adjustment, the preset constraints include a demand amount condition of the materials, a loading amount condition of the vehicles, a condition of limiting the departure and return of the vehicles at the same node, a vehicle travel continuity condition, a time condition of arriving at a node, a condition of a failure of a transfer station for the vehicles, and a loading amount condition of the vehicles on an effective path.

[0069] For example, a mathematical representation of the preset constraints is:

[0070]

[0071]

[0072]

[0073]

[0074]

[0075]

[0076]

[0077]

[0078]

[0079]

[0080]

[0081]

[0082]

[0083]

[0084]

[0085]

[0086]

[0087]

[0088] The constraints are respectively the demand amount of the goods, the loading amount of the vehicle, the limitation of the departure and return of the vehicle at the same node, the continuity of the vehicle trip, the time of arriving at the node, the transfer station of the vehicle no-go invalidity, and the loading amount of the vehicle on the valid path.

[0089] S103, selecting, crossing and mutating the individuals in the initial population to obtain a first population, and calculating a second fitness value of the first population under the preset constraint condition through the preset target function;

[0090] In a possible implementation, the step of selecting, crossing and mutating the individuals in the initial population to obtain the first population includes:

[0091] The parent individuals are selected from the initial population through a tournament selection method;

[0092] According to a preset crossing probability, the exchange individuals are selected from the initial population through a uniform crossing method, and the intermediate population is constructed according to the parent individuals and the exchange individuals;

[0093] The intermediate population is mutated according to a preset mutation rule to obtain the first population.

[0094] For example, the parent individuals are first selected from the population through a tournament selection method, and then each group of genes is crossed with a crossing probability It is determined whether to exchange, and then a mutation operation is adopted to generate a new population (the first population). The mutation operation specifically includes: first randomly selecting an operation to be executed from a set of to-be-selected operations, and then determining whether other operations are executed with a probability of 50%.

[0095] The set of to-be-selected operations includes:

[0096] Randomly exchange the demand points and the starting transfer station of two vehicles.

[0097] Randomly exchange the starting transfer stations of two vehicles.

[0098] Randomly exchange the distribution demand points of two vehicles.

[0099] Randomly change the distribution vehicle of a demand point.

[0100] After the crossing and mutation operations, the feasibility of the solution needs to be repaired, the overloaded and over-threshold demand points are re-allocated, and then the distribution sequence of the first-level and second-level networks is generated according to the shortest tour path algorithm.

[0101] S104, merging the initial population and the first population to obtain a second population, and performing first population screening on the second population to obtain a third population.

[0102] In a possible implementation, the step of performing the first population screening on the second population to obtain a third population comprises:

[0103] The first population screening on the second population is performed by an elitist strategy and a crowding degree allocation strategy to obtain the third population.

[0104] For example, the first population screening is a non-dominated elitist screening, and specifically, a fast non-dominated sorting is used to obtain each level of the Pareto front of the population, and then the first N individuals are screened out by the elitist strategy and the crowding degree allocation strategy.

[0105] S105, performing a neighborhood search on the feasible solutions of the third population according to a preset rule to obtain a fourth population, and calculating a third fitness value of the fourth population under the preset constraint condition by using the preset target function;

[0106] In a possible implementation, the step of performing the neighborhood search on the feasible solutions of the third population according to a preset rule to obtain a fourth population comprises:

[0107] According to a first rule in the preset rule, a route that only delivers one node in the feasible solutions of the third population is deleted to obtain a first initial feasible solution;

[0108] According to a second rule in the preset rule, the farthest node on each route in the initial feasible solution is re-allocated to obtain a second initial feasible solution;

[0109] According to a third rule in the preset rule, a shortest path search is performed on each path in the second initial feasible solution to obtain the fourth population.

[0110] For example, the destruction operation: deleting the route that only delivers one node, setting the state of the demand point to empty; and deleting the farthest node on each path from the route and setting the state to empty. The repair operator: minimum cost insertion. After the destruction operation, the demand point with the state set to empty is inserted into the path with the minimum cost according to the capacity to determine the secondary network distribution route. After the state of all demand points set to empty is re-allocated, the primary network distribution route is re-planned according to the new transfer station. The exact algorithm of the shortest tour path is used to solve each route of the secondary network.

[0111] S106, merging the third population and the fourth population to obtain a fifth population, performing a second population screening on the fifth population to obtain a sixth population, and calculating a fourth fitness value of the sixth population under the preset constraint condition by using the preset target function;

[0112] For example, the second population screening is a non-dominated elitist screening, in particular, the fast non-dominated sorting is used to obtain the Pareto front of each level of the population, and then the elite reservation strategy and the crowding degree distribution strategy are used to screen the first N individuals

[0113] S107, obtaining a current iteration number, if the current iteration number is less than the preset iteration number, taking the sixth population as the initial population, continuing the steps of selecting, crossing and mutating the individuals in the initial population, and recording the fitness value set when the sixth population is taken as the initial population, until the current iteration number is equal to the preset iteration number;

[0114] S108, selecting a minimum value from the first fitness value, the second fitness value, the third fitness value, the fourth fitness value and the fitness value set, obtaining pareto front data corresponding to the minimum value, and obtaining a target supply scheme according to the pareto front data.

[0115] The scene parameters of the target material supply scene are acquired, and an initial population is generated in a gene coding manner according to the scene parameters; a first fitness value of the initial population under a preset constraint condition is calculated through a preset target function; individuals in the initial population are selected, crossed and mutated to obtain a first population, and a second fitness value of the first population under the preset constraint condition is calculated through the preset target function; the initial population and the first population are merged to obtain a second population, and a third population is obtained by performing first population screening on the second population; a neighborhood search is performed on feasible solutions of the third population according to a preset rule to obtain a fourth population, and a third fitness value of the fourth population under the preset constraint condition is calculated through the preset target function; the third population and the fourth population are merged to obtain a fifth population, and a sixth population is obtained by performing second population screening on the fifth population, and a fourth fitness value of the sixth population under the preset constraint condition is calculated through the preset target function; a current iteration number is acquired, if the current iteration number is less than a preset iteration number, the sixth population is taken as the initial population, the step of selecting, crossing and mutating individuals in the initial population is continued, and a fitness value set when the sixth population is taken as the initial population is recorded, until the current iteration number is equal to the preset iteration number; a minimum value is selected from the first fitness value, the second fitness value, the third fitness value, the fourth fitness value and the fitness value set, pareto front data corresponding to the minimum value is acquired, and a target supply scheme is obtained according to the pareto front data. In the process of formulating the material supply scheme, the scene of the failure of the transfer station is considered, the global plan is overall arranged, the human and transport capacity is reasonably arranged on the basis of ensuring the timeliness to reduce the cost. Meanwhile, when the failure of the transfer station occurs, the material supply scheme considering the failure of the transfer station in formulating the material supply scheme can be directly output without again performing the scheme planning, so that the problems of slow response of the logistics system, mismatch between supply and demand, and low distribution efficiency are avoided.

[0116] In a possible implementation, the step of generating the initial population in a gene coding manner according to the matching relationship between the demand points and the distribution vehicles, the matching relationship between the vehicles and the transfer stations, the distribution sequence matrix of the demand points, the number of warehouses of the secondary supply network, the number of optional transfer stations and the number of demand points to be distributed includes:

[0117] The first individual set is generated in a gene coding manner according to the matching relationship between the demand points and the distribution vehicles, the matching relationship between the vehicles and the transfer stations, the distribution sequence matrix of the demand points, the number of warehouses of the secondary supply network, the number of optional transfer stations and the number of demand points to be distributed according to a random generation strategy;

[0118] According to the matching relationship between the demand points and the delivery vehicles, the matching relationship between the vehicles and the transfer stations, the delivery sequence matrix of the demand points, the number of warehouses of the secondary supply network, the number of optional transfer stations, and the number of demand points to be delivered, a second individual set is generated in a greedy generation strategy through gene coding.

[0119] The initial population is generated based on the first individual set and the second individual set.

[0120] For example, 30% of the initial individuals are generated in an orderly manner using the greedy strategy to ensure the effectiveness and quality of the initial population. Then, the remaining 70% of the initial individuals are generated using a random generation strategy to maintain the diversity of the initial population.

[0121] The greedy generation strategy includes the following steps:

[0122] The matching gene between the demand points and the vehicles is generated. Each demand point is assigned to a vehicle for delivery without exceeding the capacity limit and the delivery threshold of the vehicle.

[0123] The transfer stations are selected and the secondary network path planning is completed. The shortest tour route is solved using the greedy algorithm, the minimum transfer station is selected according to the distance cost, and the demand point delivery sequence gene matrix is coded.

[0124] The primary network path planning is completed. The demand amount of each transfer station is obtained through the above arrangement of the secondary supply network, and the shortest tour route is solved using the dynamic programming method.

[0125] The random generation strategy includes the following steps:

[0126] The matching gene between the vehicles and the transfer stations is generated. Each vehicle of the secondary network is randomly assigned to a transfer station. (Set a probability limit of not more than 25% for the use of vehicles)

[0127] The matching gene between the demand points and the vehicles is generated. Each demand point is assigned to a vehicle for delivery without exceeding the capacity limit and the delivery threshold of the vehicle in the above list of vehicles.

[0128] The secondary network path planning is completed. The shortest tour route is solved using the greedy algorithm, and the demand point delivery sequence gene matrix is coded.

[0129] The primary network path planning is completed. The demand amount of each transfer station is obtained through the above arrangement of the secondary supply network, and the shortest tour route is solved using the dynamic programming method.

[0130] In one possible implementation, in the face of emergency supplies, the cost is controlled on the basis of pursuing the highest possible time efficiency. The dual-objective optimization of maximizing the final demand satisfaction and minimizing the total cost is realized.

[0131] Total costs include transportation costs for primary and secondary distribution, vehicle usage costs for primary and secondary distribution, and fixed costs for transit station operations.

[0132]

[0133] The satisfaction level at each demand point is obtained by considering the relationship between arrival time and time threshold. The sum of the satisfaction ratings for all demand points is used as the overall satisfaction index.

[0134]

[0135]

[0136] First, calculate the total cost and satisfaction of each solution after temporary adjustments under various failure scenarios. Then, combine the failure probability of each failure scenario to obtain the expected total cost and expected satisfaction of the solution as evaluation indicators.

[0137] In one possible implementation, the probability of failure scenario ω occurring is:

[0138]

[0139] Failure Scenario Total cost and satisfaction after temporary adjustments.

[0140] In one possible implementation, such as Figure 3 As shown, a fitness calculation process includes: determining whether all feasible solutions in the population have completed fitness calculation; if so, outputting the fitness values ​​of all solutions; if not, reading a solution from the population and determining whether the selected solution has completed all failure scenarios; if the selected solution has completed all failure scenarios, calculating the expected total cost and expected satisfaction of the selected solution; if the selected solution has not completed all failure scenarios, selecting the failure scenarios that the selected solution has not completed, making temporary adjustments for the failure scenarios, and calculating the total cost and satisfaction of the failure scenarios, until the selected solution has completed all failure scenarios.

[0141] Secondly, such as Figure 4 As shown, this application provides a material supply device, the device comprising:

[0142] The data acquisition module 201 is used to acquire scene parameters of the target material supply scenario and generate an initial population based on the scene parameters through gene encoding.

[0143] The first calculation module 202 is used to calculate the first fitness value of the initial population under preset constraints through a preset objective function;

[0144] The second calculation module 203 is configured to select, cross and mutate individuals in the initial population to obtain a first population, and calculate a second fitness value of the first population under the preset constraint condition through the preset target function;

[0145] The third calculation module 204 is configured to merge the initial population and the first population to obtain a second population, and perform a first population screening on the second population to obtain a third population;

[0146] The fourth calculation module 205 is configured to perform a neighborhood search on the feasible solutions of the third population according to a preset rule to obtain a fourth population, and calculate a third fitness value of the fourth population under the preset constraint condition through the preset target function;

[0147] The fifth calculation module 206 is configured to merge the third population and the fourth population to obtain a fifth population, perform a second population screening on the fifth population to obtain a sixth population, and calculate a fourth fitness value of the sixth population under the preset constraint condition through the preset target function;

[0148] The iteration module 207 is configured to obtain a current iteration number, if the current iteration number is less than a preset iteration number, take the sixth population as the initial population, continue the steps of selecting, crossing and mutating individuals in the initial population, and record a fitness value set when the sixth population is taken as the initial population, until the current iteration number is equal to the preset iteration number.

[0149] The scheme output module 208 is configured to select a minimum value from the first fitness value, the second fitness value, the third fitness value, the fourth fitness value and the fitness value set, obtain pareto front data corresponding to the minimum value, and obtain a target supply scheme according to the pareto front data.

[0150] In one embodiment, a computer device is provided, which can be a server, and an internal structure diagram of the computer device can be as shown in Figure 5As shown in the figure. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes non-volatile and / or volatile storage media, internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with the external client through the network connection. The computer program is executed by the processor to realize the function or step of the server side of the material supply method.

[0151] In one embodiment, a computer device is provided, which can be a client, and its internal structure diagram can be as shown in the figure. Figure 6 As shown in the figure. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes non-volatile storage media, internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with the external server through the network connection. The computer program is executed by the processor to realize the function or step of the client side of the material supply method.

[0152] In one embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor implementing the following steps when executing the computer program: calculating a first fitness value of the initial population under a preset constraint condition by a preset objective function; selecting, crossing, and mutating individuals in the initial population to obtain a first population, calculating a second fitness value of the first population under the preset constraint condition by the preset objective function; merging the initial population and the first population to obtain a second population, and performing a first population screening on the second population to obtain a third population; performing a neighborhood search on feasible solutions of the third population according to a preset rule to obtain a fourth population, and calculating a third fitness value of the fourth population under the preset constraint condition by the preset objective function; merging the third population and the fourth population to obtain a fifth population, and performing a second population screening on the fifth population to obtain a sixth population, and calculating a fourth fitness value of the sixth population under the preset constraint condition by the preset objective function; obtaining a current iteration number, if the current iteration number is less than a preset iteration number, taking the sixth population as the initial population, continuing the steps of selecting, crossing, and mutating individuals in the initial population, and recording a fitness value set when the sixth population is taken as the initial population, until the current iteration number is equal to the preset iteration number; selecting a minimum value from the first fitness value, the second fitness value, the third fitness value, the fourth fitness value, and the fitness value set, obtaining pareto front data corresponding to the minimum value, and obtaining a target supply scheme according to the pareto front data.

[0153] In one embodiment, a computer readable storage medium is provided, which stores a computer program. The computer program is executed by a processor to implement the following steps: calculating a first fitness value of the initial population under a preset constraint condition by a preset objective function; selecting, crossing and mutating individuals in the initial population to obtain a first population, calculating a second fitness value of the first population under the preset constraint condition by the preset objective function; merging the initial population and the first population to obtain a second population, and performing a first population screening on the second population to obtain a third population; performing a neighborhood search on feasible solutions of the third population according to a preset rule to obtain a fourth population, and calculating a third fitness value of the fourth population under the preset constraint condition by the preset objective function; merging the third population and the fourth population to obtain a fifth population, and performing a second population screening on the fifth population to obtain a sixth population, and calculating a fourth fitness value of the sixth population under the preset constraint condition by the preset objective function; obtaining a current iteration number, if the current iteration number is less than a preset iteration number, taking the sixth population as the initial population, continuing the steps of selecting, crossing and mutating individuals in the initial population, and recording a fitness value set when the sixth population is taken as the initial population, until the current iteration number is equal to the preset iteration number; selecting a minimum value from the first fitness value, the second fitness value, the third fitness value, the fourth fitness value and the fitness value set, obtaining pareto front data corresponding to the minimum value, and obtaining a target supply scheme according to the pareto front data.

[0154] It should be noted that the functions or steps that the computer readable storage medium or the computer device can implement can be referred to the related descriptions of the server side and the client side in the foregoing method embodiments. To avoid repetition, they will not be described one by one here.

[0155] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiment methods. Any reference to memory, storage, database or other medium used in the embodiments provided by the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0156] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is exemplified, and in actual application, the above-mentioned functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above.

[0157] The above-mentioned embodiments are only used to illustrate the technical solutions of the present application, but not limit it. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features. The modification or replacement does not make the essence of the corresponding technical solution deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A method for supplying materials, characterized in that, The method includes: Obtain the scenario parameters of the target material supply scenario, and generate an initial population based on the scenario parameters through gene encoding; The first fitness value of the initial population under preset constraints is calculated using a preset objective function; The step of calculating the first fitness value of the initial population under preset constraints using a preset objective function includes: Through the preset objective function: Calculate the first fitness value of the initial population under preset constraints, where ω represents the failure scenario and P ω Let be the probability of the failure scenario. Failure scenario The total cost after the temporary adjustment is completed. Failure scenarios The satisfaction level after the temporary adjustment is completed. The preset constraints include the demand for materials, the loading capacity of vehicles, the restriction that vehicles depart and return at the same node, the continuity of vehicle journey, the time of arrival at the node, the transfer station where the vehicle prohibition is invalid, and the loading capacity of vehicles on the effective path. Individuals in the initial population are selected, crossovered, and mutated to obtain a first population. The second fitness value of the first population under the preset constraints is calculated using the preset objective function. The initial population and the first population are merged to obtain the second population, and the second population is subjected to the first population screening to obtain the third population; According to the preset rules, a neighborhood search is performed on the feasible solutions of the third population to obtain the fourth population, and the third fitness value of the fourth population under the preset constraints is calculated by the preset objective function. The third and fourth populations are merged to obtain the fifth population, and the fifth population is subjected to a second population screening to obtain the sixth population. The fourth fitness value of the sixth population under the preset constraints is calculated using the preset objective function. Obtain the current iteration number. If the current iteration number is less than the preset iteration number, then use the sixth population as the initial population, continue the steps of selecting, crossing over, and mutating individuals in the initial population, and record the fitness value set when the sixth population is used as the initial population, until the current iteration number is equal to the preset iteration number. The minimum value is selected from the first fitness value, the second fitness value, the third fitness value, the fourth fitness value and the fitness value set, and the Pareto front data corresponding to the minimum value is obtained. The target supply plan is obtained based on the Pareto front data.

2. The material supply method according to claim 1, characterized in that, The step of obtaining scenario parameters of the target material supply scenario and generating an initial population based on the scenario parameters through genetic encoding includes: Obtain scenario parameters for the target material supply scenario, including: the matching relationship between demand points and delivery vehicles, the matching relationship between vehicles and transfer stations, the delivery order matrix of demand points, the number of warehouses in the secondary supply network, the number of optional transfer stations, and the number of demand points to be delivered. An initial population is generated through genetic coding based on the matching relationship between demand points and delivery vehicles, the matching relationship between vehicles and transfer stations, the delivery order matrix of demand points, the number of warehouses in the secondary supply network, the number of optional transfer stations, and the number of demand points to be delivered.

3. The material supply method according to claim 2, characterized in that, The step of generating an initial population through genetic coding based on the matching relationship between demand points and delivery vehicles, the matching relationship between vehicles and transfer stations, the delivery order matrix of demand points, the number of warehouses in the secondary supply network, the number of optional transfer stations, and the number of demand points to be delivered includes: Based on the matching relationship between the demand points and delivery vehicles, the matching relationship between the vehicles and transfer stations, the delivery order matrix of the demand points, the number of warehouses in the secondary supply network, the number of optional transfer stations, and the number of demand points to be delivered, the first set of entities is generated using a gene encoding method and a random generation strategy. Based on the matching relationship between the demand points and delivery vehicles, the matching relationship between the vehicles and transfer stations, the delivery order matrix of the demand points, the number of warehouses in the secondary supply network, the number of optional transfer stations, and the number of demand points to be delivered, a second set of entities is generated using a gene encoding method and a greedy generation strategy. The initial population is generated based on the first set of individuals and the second set of individuals.

4. The material supply method according to claim 1, characterized in that, The step of selecting, crossovering, and mutating individuals in the initial population to obtain the first population includes: Parent individuals are selected from the initial population through a tournament selection process; Based on a preset crossover probability, exchange individuals are selected from the initial population through uniform crossover, and an intermediate population is constructed based on the parent individuals and the exchange individuals. The intermediate population is subjected to mutation processing according to the preset mutation rules to obtain the first population.

5. The material supply method according to claim 1, characterized in that, The step of performing a neighborhood search on the feasible solutions of the third group according to preset rules to obtain the fourth group includes: According to the first rule in the preset rules, delete the routes that only deliver one node in the feasible solutions of the third group to obtain the first initial feasible solution; According to the second rule in the preset rules, the farthest node on each route in the initial feasible solution is reallocated to obtain the second initial feasible solution; According to the third rule in the preset rules, the shortest path is searched for each path in the second initial feasible solution to obtain the fourth group.

6. The material supply method according to claim 1, characterized in that, The step of performing a first population screening on the second population to obtain a third population includes: The second population was subjected to a first population screening using an elite retention strategy and a crowding allocation strategy, resulting in a third population.

7. A material supply device, characterized in that, The device includes: The data acquisition module is used to acquire scene parameters of the target material supply scenario and generate an initial population based on the scene parameters through gene encoding. A first calculation module is used to calculate the first fitness value of the initial population under preset constraints using a preset objective function; the step of calculating the first fitness value of the initial population under preset constraints using a preset objective function includes: Through the preset objective function: Calculate the first fitness value of the initial population under preset constraints, where ω represents the failure scenario and P ω Let be the probability of the failure scenario. Failure scenario The total cost after the temporary adjustment is completed. Failure scenarios The satisfaction level after the temporary adjustments is determined. The preset constraints include the demand for materials, the vehicle loading capacity, restrictions on vehicle departure and return to the same node, the continuity of vehicle journeys, the time of arrival at nodes, the transfer station where vehicle access restrictions are lifted, and the vehicle loading capacity on the effective path. The second calculation module is used to select, crossover, and mutate individuals in the initial population to obtain a first population, and to calculate the second fitness value of the first population under the preset constraints through the preset objective function. The third calculation module is used to merge the initial population and the first population to obtain the second population, and to perform a first population screening on the second population to obtain the third population. The fourth calculation module is used to perform a neighborhood search on the feasible solutions of the third population according to a preset rule to obtain a fourth population, and to calculate the third fitness value of the fourth population under the preset constraints using the preset objective function. The fifth calculation module is used to merge the third population and the fourth population to obtain the fifth population, and to perform a second population screening on the fifth population to obtain the sixth population, and to calculate the fourth fitness value of the sixth population under the preset constraint conditions through the preset objective function; The iteration module is used to obtain the current iteration number. If the current iteration number is less than the preset iteration number, the sixth population is used as the initial population, and the steps of selecting, crossing over, and mutating individuals in the initial population are continued. The fitness value set when the sixth population is used as the initial population is recorded until the current iteration number is equal to the preset iteration number. The solution output module is used to select the minimum value from the first fitness value, the second fitness value, the third fitness value, the fourth fitness value and the fitness value set, and obtain the Pareto front data corresponding to the minimum value, and obtain the target supply solution based on the Pareto front data.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the material supply method as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the material supply method as described in any one of claims 1 to 6.

Images