A catering supply chain scheduling method and system based on intelligent optimization algorithm

Abstract

The present application relates to the technical field of supply chain resource allocation, and a catering supply chain scheduling method and system based on an intelligent optimization algorithm, comprising: identifying a set of deliverable vehicle terminals based on a distribution center terminal, constructing a vehicle supply matrix according to the set of deliverable vehicle terminals and a set of stores to be delivered, setting a scheduling energy consumption objective function and matrix generation constraint conditions by using a set of delivery locations, a set of scheduling demand quantities, and the vehicle supply matrix, generating a current genetic population based on the matrix generation constraint conditions, performing genetic iteration on the current genetic population by using the scheduling energy consumption objective function, obtaining an optimal vehicle scheduling scheme, performing terminal control on the set of deliverable vehicle terminals based on the optimal vehicle scheduling scheme, and obtaining a set of controlled vehicle terminals. The present application can improve the scheduling efficiency and intelligent level of the catering supply chain and reduce the overall energy consumption in the scheduling process.

Description

Technical Field

[0001] This invention relates to the field of supply chain resource allocation technology, and in particular to a catering supply chain scheduling method and system based on intelligent optimization algorithms. Background Technology

[0002] In modern restaurant chain operations, supply chain scheduling is a core element in ensuring the timely and accurate delivery of ingredients to each store and guaranteeing daily operations. This problem is essentially a complex multivariate dynamic optimization problem, involving multiple constraints such as store location, real-time delivery demand, available vehicle load capacity, driving route planning, and time window. Therefore, an efficient and intelligent scheduling solution is crucial for improving the response speed, resource utilization efficiency, and operational stability of the entire supply chain.

[0003] Traditional technologies typically rely on the experience of human dispatchers or simple rules (such as by region or fixed route) for vehicle allocation and route planning. The drawback is that human experience cannot simultaneously take into account all global variables, which can easily lead to suboptimal scheduling solutions. This manifests as more empty or detours by vehicles, higher overall delivery energy consumption, and static rules that cannot flexibly adapt to daily fluctuations in store demand and real-time road conditions, resulting in low scheduling efficiency and resource utilization. Summary of the Invention

[0004] This invention provides a catering supply chain scheduling method based on intelligent optimization algorithms and a computer-readable storage medium. Its main purpose is to improve the scheduling efficiency and intelligence level of the catering supply chain and reduce the overall energy consumption in the scheduling process.

[0005] To achieve the above objectives, this invention provides a catering supply chain scheduling method based on intelligent optimization algorithms, comprising:

[0006] Based on the pre-built distribution center terminal, the catering dispatch request is received, and based on the catering dispatch request, the set of store terminals to be delivered is determined, wherein the set of store terminals to be delivered includes multiple store terminals to be delivered.

[0007] Based on the catering dispatch request, query the set of locations to be delivered and the set of dispatch demand corresponding to the set of stores to be delivered;

[0008] Based on the distribution center terminal identification of the deliverable vehicle terminal set, the deliverable vehicle terminal set includes multiple deliverable vehicle terminals;

[0009] A vehicle supply matrix is ​​constructed based on the set of deliverable vehicle terminals and the set of store terminals to be delivered. The objective function of scheduling energy consumption and the matrix generation constraints are set using the set of locations to be delivered, the set of scheduling demand, and the vehicle supply matrix.

[0010] The current genetic population is generated based on matrix generation constraints. The current genetic population consists of multiple current chromosomes, and each current chromosome corresponds to a vehicle scheduling scheme.

[0011] By using the scheduling energy consumption objective function to perform genetic iteration on the current genetic population, the optimal vehicle scheduling scheme is obtained. Based on the optimal vehicle scheduling scheme, the set of deliverable vehicle terminals is controlled to obtain the set of controlled vehicle terminals, thus completing the catering supply chain scheduling based on intelligent optimization algorithms.

[0012] Optionally, constructing a vehicle supply matrix based on the set of deliverable vehicle terminals and the set of store terminals to be delivered includes:

[0013] Sequentially extract deliverable vehicle terminals from the deliverable vehicle terminal set and record the extracted deliverable vehicle terminals as vehicle terminals to be dispatched.

[0014] Obtain the number of stores to be delivered in the set of stores to be delivered, and generate a vehicle supply vector based on the number of stores to be delivered. The vehicle supply vector contains multiple supply codes, and each supply code corresponds one-to-one with a store terminal to be delivered. The supply code is either the value 1 or the value 0.

[0015] Summarize the vehicle supply vectors corresponding to each vehicle terminal to be dispatched to obtain a vehicle supply vector set;

[0016] The vehicle supply matrix is ​​obtained by concatenating the vehicle supply vector set. The vehicle supply matrix contains multiple supply row vectors, and each supply row vector corresponds one-to-one with a vehicle supply vector.

[0017] Optionally, the step of setting the scheduling energy consumption objective function and matrix generation constraints using the set of locations to be delivered, the set of scheduling demand, and the vehicle supply matrix includes:

[0018] Perform the following operation on each supply row vector in the vehicle supply matrix:

[0019] Obtain the non-zero encoded sequence from the supply row vector, where the non-zero encoded sequence includes multiple non-zero codes;

[0020] Identify the coded store terminal corresponding to each non-zero code in the non-zero coded sequence to obtain the coded store terminal sequence;

[0021] Based on the scheduling demand set and the delivery location set, the coding demand and coding location of each coded store terminal in the coded store terminal sequence are obtained, resulting in the coding demand sequence and the coding location sequence.

[0022] Vehicle scheduling energy consumption is calculated using the coded demand sequence and coded location sequence to obtain the current vehicle energy consumption value;

[0023] Summarize the current vehicle energy consumption values ​​corresponding to each supply row vector to obtain the current vehicle energy consumption value sequence. Perform a summation operation based on the current vehicle energy consumption value sequence to obtain the scheduling energy consumption objective function.

[0024] Set matrix generation constraints based on the vehicle supply matrix.

[0025] Optionally, the step of calculating vehicle scheduling energy consumption using the coded demand sequence and the coded location sequence to obtain the current vehicle energy consumption value includes:

[0026] Calculate the current vehicle carrying capacity based on the coded demand sequence;

[0027] Vehicle routes are constructed based on preset distribution center locations and coded location sequences to obtain a vehicle dispatch route set. The vehicle dispatch route set includes multiple vehicle dispatch routes, and each vehicle dispatch route corresponds to a dispatched store terminal.

[0028] Extract vehicle dispatch paths sequentially from the vehicle dispatch path set and obtain the dispatch path distance of the extracted vehicle dispatch paths.

[0029] Calculate the energy consumption and scheduling duration of the current route based on the scheduling path distance and the current vehicle load.

[0030] The dispatched demand is determined based on the dispatched store terminals in the extracted vehicle dispatch route.

[0031] The vehicle capacity is calculated and updated based on the current vehicle capacity and the already scheduled demand.

[0032] The updated vehicle capacity is used as the current vehicle capacity, and the step of sequentially extracting vehicle scheduling paths from the vehicle scheduling path set is returned until all vehicle scheduling paths in the vehicle scheduling path set have been extracted.

[0033] By summing the current path energy consumption and the current scheduling duration, we obtain the current path energy consumption sequence and the current scheduling duration sequence.

[0034] The current vehicle energy consumption value is obtained by weighted summation of the current path energy consumption sequence and the current scheduling duration sequence.

[0035] Optionally, the step of setting matrix generation constraints based on the vehicle supply matrix includes:

[0036] Multiple supply column vectors are generated based on the vehicle supply matrix, where each supply column vector corresponds to a store terminal to be delivered;

[0037] Set store demand constraints based on multiple supply column vectors, wherein each supply column vector has one and only one supply code with a value of 1.

[0038] Multiple supply row vectors in the vehicle supply matrix are denoted as multiple vehicle constraint vectors;

[0039] For each of the multiple vehicle constraint vectors, perform the following operation:

[0040] The vehicle dispatch store set is obtained based on the vehicle constraint vector, and the target demand set corresponding to the vehicle dispatch store set is determined from the dispatch demand set.

[0041] Summing the target demand set yields the total target demand.

[0042] Sum the total target demand corresponding to each vehicle constraint vector to obtain multiple total target demands;

[0043] Vehicle constraints are set based on the preset maximum vehicle capacity and multiple total target demand, wherein each total target demand is not greater than the maximum vehicle capacity.

[0044] By summarizing the store demand constraints and vehicle constraints, the matrix generation constraints are obtained.

[0045] Optionally, the step of using the scheduling energy consumption objective function to perform genetic iteration on the current genetic population to obtain the optimal vehicle scheduling scheme includes:

[0046] Extract the current chromosome sequentially from the current genetic population, and obtain the current supply matrix corresponding to the extracted current chromosome;

[0047] Input the current supply matrix into the scheduling energy consumption objective function to obtain the current scheduling energy consumption value;

[0048] Summarize the current scheduling energy consumption values ​​for each current chromosome to obtain the current scheduling energy consumption value set;

[0049] Based on a preset high-quality population ratio, identify low scheduling energy consumption sets within the current scheduling energy consumption value set;

[0050] Identify the set of low-scheduled chromosomes corresponding to the set of low-scheduled energy consumption values ​​in the current genetic population;

[0051] The sum of the current energy consumption values ​​is calculated to obtain the total energy consumption of the current scheduling.

[0052] By using the sum of current scheduled energy consumption, the ratio of each current scheduled energy consumption value in the current scheduled energy consumption value set is calculated to obtain the current scheduled energy consumption ratio set.

[0053] The remaining population size is calculated based on the proportion of high-quality populations.

[0054] Based on the remaining population size and the current scheduling energy consumption ratio set, multiple current chromosomes are randomly and probabilistically extracted to obtain the updated scheduling chromosome set;

[0055] The low-scheduled chromosome set and the updated-scheduled chromosome set are merged to obtain the parental genetic population.

[0056] Genetic iteration is performed based on the parental genetic population to obtain an iterative genetic population;

[0057] The iterative genetic population is used as the current genetic population, and the step of sequentially extracting the current chromosome in the current genetic population is returned until a preset stop iteration command is received.

[0058] The optimal genetic population is determined based on the stop iteration instruction, the optimal chromosome in the optimal genetic population is identified, and the optimal vehicle scheduling scheme is generated based on the current supply matrix in the optimal chromosome.

[0059] Optionally, the step of performing genetic iteration based on the parental genetic population to obtain an iterative genetic population includes:

[0060] Crossover and mutation operations are performed sequentially on the parent genetic population to obtain the offspring genetic population, which includes multiple offspring chromosomes;

[0061] Obtain the average scheduling energy consumption of the parent genetic population;

[0062] Chromosomes are selected from the offspring genetic population based on the average scheduling energy consumption value to obtain an effective chromosome set;

[0063] Obtain the number of valid chromosomes in the valid chromosome set;

[0064] If the number of effective chromosomes is less than the preset standard number of chromosomes, then the number of chromosomes to be supplemented between the number of effective chromosomes and the standard number of chromosomes is calculated.

[0065] Select a supplementary chromosome set from the parent genetic population based on the number of chromosomes to be supplemented;

[0066] The supplementary chromosome set is added to the effective chromosome set to obtain the iterative genetic population.

[0067] Optionally, the step of selecting chromosomes from the offspring genetic population based on the average scheduling energy consumption value to obtain an effective chromosome set includes:

[0068] Perform the following operation on each offspring chromosome in the offspring genetic population:

[0069] Calculate the offspring scheduling energy consumption value of offspring chromosomes;

[0070] If the offspring scheduling energy consumption value is less than the average scheduling energy consumption value, then the offspring chromosome is recorded as a valid chromosome;

[0071] If the energy consumption of the offspring scheduling is not less than the average energy consumption, then the retention probability is calculated based on the energy consumption of the offspring scheduling and the average energy consumption to obtain the offspring retention probability value.

[0072] Chromosomes of offspring are selected for retention based on the offspring retention probability value, and the retention selection result is: retain or not retain.

[0073] If the selection result is "retain", then the offspring chromosomes will be recorded as valid chromosomes;

[0074] By summing up the valid chromosomes, we obtain the effective chromosome set.

[0075] Optionally, the calculation of the retention probability based on the offspring scheduling energy consumption value and the average scheduling energy consumption value to obtain the offspring retention probability value includes:

[0076] The offspring retention probability value is calculated using the following formula:

[0077]

[0078] in, This represents the probability of offspring retention. This represents an exponential function with the natural constant as its base. This represents the average dispatch energy consumption value. This represents the energy consumption value of offspring scheduling.

[0079] To achieve the above objectives, the present invention also provides a catering supply chain scheduling system based on intelligent optimization algorithms, comprising:

[0080] The scheduling request receiving module is used to receive catering scheduling requests based on pre-built distribution center terminals, and determine the set of store terminals to be delivered based on the catering scheduling requests, wherein the set of store terminals to be delivered includes multiple store terminals to be delivered.

[0081] The delivery vehicle identification module is used to query the set of locations to be delivered and the set of scheduling requirements corresponding to the set of stores to be delivered based on the catering scheduling request, and to identify the set of deliverable vehicle terminals based on the distribution center terminal. The set of deliverable vehicle terminals includes multiple deliverable vehicle terminals.

[0082] The scheduling scheme generation module is used to construct a vehicle supply matrix based on the set of deliverable vehicle terminals and the set of store terminals to be delivered. It uses the set of locations to be delivered, the set of scheduling demand, and the vehicle supply matrix to set the scheduling energy consumption objective function and matrix generation constraints. Based on the matrix generation constraints, it generates the current genetic population, which consists of multiple current chromosomes, and each current chromosome corresponds to a vehicle scheduling scheme.

[0083] The scheduling scheme execution module is used to perform genetic iteration on the current genetic population using the scheduling energy consumption objective function to obtain the optimal vehicle scheduling scheme. Based on the optimal vehicle scheduling scheme, the module performs terminal control on the set of deliverable vehicle terminals to obtain the controlled vehicle terminal set.

[0084] To address the above problems, the present invention also provides an electronic device, the electronic device comprising:

[0085] Memory, storing at least one instruction;

[0086] The processor executes the instructions stored in the memory to implement the above-described catering supply chain scheduling method based on intelligent optimization algorithms.

[0087] To address the aforementioned problems, the present invention also provides a computer-readable storage medium storing at least one instruction, which is executed by a processor in an electronic device to implement the aforementioned catering supply chain scheduling method based on intelligent optimization algorithms.

[0088] To address the problems described in the background, this invention first receives standardized digital instructions for catering scheduling through distribution center terminals. This step automates and accurately collects scheduling demands, replacing traditional methods that rely on manual aggregation or inefficient communication. Furthermore, this solution constructs a vehicle supply matrix based on the set of deliverable vehicle terminals and the set of stores to be delivered. It then uses the set of locations to be delivered, the set of scheduling demands, and the vehicle supply matrix to set a scheduling energy consumption objective function and matrix generation constraints. This step, by constructing the vehicle supply matrix, transforms the complex many-to-many vehicle-to-store allocation relationship into a clear binary mathematical expression, thus encoding the scheduling scheme. Based on this matrix, store locations, and demand, a scheduling energy consumption objective function integrating path energy consumption and delivery time is set, and corresponding matrix generation constraints are constructed. This provides a foundation for subsequent intelligent optimization algorithms. This invention provides a clear mathematical framework for solving the problem, overcoming the limitations of traditional methods that rely on empirical rules or simple greedy strategies. Finally, it uses a scheduling energy consumption objective function to perform genetic iteration on the current genetic population to obtain the optimal vehicle scheduling scheme. Based on this optimal scheme, it performs terminal control on the set of deliverable vehicle terminals to obtain the controlled vehicle terminal set. This step iteratively optimizes the scheduling scheme using a genetic algorithm. Through selection, crossover, and mutation operations, the genetic algorithm can extensively search the solution space, avoiding getting trapped in local optima, thus having a higher probability of finding a vehicle allocation and route planning scheme with lower overall scheduling energy consumption. Compared to traditional fixed routes or simple heuristic rules, this method can dynamically generate comprehensive optimal scheduling instructions that adapt to specific delivery needs and real-time traffic conditions, and ultimately achieve automatic execution of the scheme through terminal control, completing a closed loop from intelligent decision-making to automated scheduling. Therefore, this invention can improve the scheduling efficiency and intelligence level of the catering supply chain, and reduce the overall energy consumption during the scheduling process. Attached Figure Description

[0089] Figure 1 A flowchart illustrating a catering supply chain scheduling method based on intelligent optimization algorithms provided in an embodiment of the present invention;

[0090] Figure 2 A functional module diagram of a catering supply chain scheduling system based on intelligent optimization algorithms provided in an embodiment of the present invention;

[0091] Figure 3 This is a schematic diagram of the structure of an electronic device that implements the catering supply chain scheduling method based on intelligent optimization algorithm according to an embodiment of the present invention.

[0092] Explanation of reference numerals in the attached figures:

[0093] 10. Electronic device; 11. Processor; 12. Memory; 13. Bus.

[0094] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0095] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0096] This application provides a catering supply chain scheduling method based on an intelligent optimization algorithm. The executing entity of the catering supply chain scheduling method based on the intelligent optimization algorithm includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application embodiment: a server, a terminal, etc. In other words, the catering supply chain scheduling method based on the intelligent optimization algorithm can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0097] Reference Figure 1 The diagram shown is a flowchart illustrating a catering supply chain scheduling method based on an intelligent optimization algorithm according to an embodiment of the present invention. In this embodiment, the catering supply chain scheduling method based on the intelligent optimization algorithm includes:

[0098] S1. Receive catering dispatch requests based on pre-built distribution center terminals, and determine the set of store terminals to be delivered based on catering dispatch requests, wherein the set of store terminals to be delivered includes multiple store terminals to be delivered.

[0099] It is clear that the distribution center terminal refers to the central dispatch and control system in the catering supply chain, such as a server or cloud platform. The catering dispatch request refers to a digital instruction initiated by each catering store terminal, containing store information (such as store identification, required weight of goods, etc.) that needs to be delivered within a specific time period. The set of stores to be delivered refers to a collection of multiple stores to be delivered, wherein the stores to be delivered refer to the catering store terminals included in the catering dispatch request. For example, at 10:00 AM, the central distribution center of a catering chain receives a catering dispatch request automatically generated by the system. This catering dispatch request indicates that fresh ingredients need to be delivered to three stores A, B, and C located in the eastern part of the city before the lunch peak (such as before 11:00 AM). After parsing the request, the distribution center terminal determines that the objects to be dispatched this time are the stores to be delivered to stores A, B, and C.

[0100] S2. Based on the catering dispatch request, query the set of locations to be delivered and the set of dispatch demand corresponding to the set of stores to be delivered.

[0101] Understandably, the set of locations to be delivered refers to a collection of multiple locations to be delivered, where a location to be delivered refers to the actual store location corresponding to a certain store terminal in the set of stores to be delivered. The set of scheduling demand refers to a collection of multiple scheduling demand quantities, where the scheduling demand quantity refers to the weight of goods required by a certain store terminal in the set of stores to be delivered.

[0102] S3. Identify the set of deliverable vehicle terminals based on the distribution center terminal, wherein the set of deliverable vehicle terminals includes multiple deliverable vehicle terminals.

[0103] It is clear that the set of deliverable vehicle terminals refers to a collection of multiple deliverable vehicle terminals, wherein a deliverable vehicle terminal refers to a refrigerated truck that is currently idle and has no dispatching task at the distribution center terminal.

[0104] S4. Construct a vehicle supply matrix based on the set of deliverable vehicle terminals and the set of store terminals to be delivered. Use the set of locations to be delivered, the set of scheduling demand, and the vehicle supply matrix to set the scheduling energy consumption objective function and matrix generation constraints.

[0105] It should be explained that the vehicle supply matrix refers to a binary matrix composed of values ​​0 and 1, which represents the scheduling and allocation relationship between deliverable vehicle terminals and store terminals to be delivered. The scheduling energy consumption objective function refers to the fitness function in the subsequent genetic optimization algorithm. The matrix generation constraints refer to the conditions that constrain the generation of the vehicle supply matrix in the genetic optimization algorithm. These constraints include store demand constraints and vehicle constraints. The store demand constraints ensure that each store terminal to be delivered has exactly one deliverable vehicle terminal responsible for delivery (i.e., each column of the vehicle supply matrix has exactly one element of 1), and the vehicle constraints ensure that the total delivery demand allocated to each deliverable vehicle terminal does not exceed the maximum carrying capacity of that deliverable vehicle terminal.

[0106] Specifically, the construction of the vehicle supply matrix based on the set of deliverable vehicle terminals and the set of store terminals to be delivered includes:

[0107] Sequentially extract deliverable vehicle terminals from the deliverable vehicle terminal set and record the extracted deliverable vehicle terminals as vehicle terminals to be dispatched.

[0108] Obtain the number of stores to be delivered in the set of stores to be delivered, and generate a vehicle supply vector based on the number of stores to be delivered. The vehicle supply vector contains multiple supply codes, and each supply code corresponds one-to-one with a store terminal to be delivered. The supply code is either the value 1 or the value 0.

[0109] Summarize the vehicle supply vectors corresponding to each vehicle terminal to be dispatched to obtain a vehicle supply vector set;

[0110] The vehicle supply matrix is ​​obtained by concatenating the vehicle supply vector set. The vehicle supply matrix contains multiple supply row vectors, and each supply row vector corresponds one-to-one with a vehicle supply vector.

[0111] It should be explained that the number of stores to be delivered refers to the number of store terminals in the set of store terminals to be delivered. The vehicle supply vector refers to a binary vector composed of multiple supply codes with values ​​of 1 or 0. This vehicle supply vector represents a delivery plan for a deliverable vehicle terminal; that is, each supply code in the vehicle supply vector corresponds to a specific store terminal in the set of store terminals to be delivered. If the supply code is 0, it means that the deliverable vehicle terminal corresponding to the vehicle supply vector does not pass through the store terminal corresponding to that supply code during the goods transportation process. If the deliverable vehicle terminal passes through a store terminal, then the deliverable vehicle terminal needs to allocate goods to that store terminal. If the supply code is 1, it means that the deliverable vehicle terminal passes through the store terminal corresponding to that supply code during the goods transportation process. The vehicle supply matrix refers to a matrix composed of the various vehicle supply vectors in the vehicle supply vector set. Each row vector of the vehicle supply matrix represents the transportation path of a deliverable vehicle terminal, and each column vector represents a store terminal to be delivered.

[0112] For example, there are two delivery vehicle terminals, denoted as C1 and C2, and three store terminals to be delivered, denoted as D1, D2, and D3. The vehicle supply vectors corresponding to C1 and C2 are [1, 0, 0] and [0, 1, 1], respectively. The vehicle supply matrix formed by these vehicle supply vectors is: The meaning of this vehicle supply matrix is ​​as follows: Deliverable vehicle terminal C1 is assigned to store terminal D1 (that is, delivery vehicle terminal C1 needs to pass through store terminal D1), and deliverable vehicle terminal C2 is assigned to store terminals D2 and D3.

[0113] In detail, the step of setting the scheduling energy consumption objective function and matrix generation constraints using the set of locations to be delivered, the set of scheduling demand, and the vehicle supply matrix includes:

[0114] Perform the following operation on each supply row vector in the vehicle supply matrix:

[0115] Obtain the non-zero encoded sequence from the supply row vector, where the non-zero encoded sequence includes multiple non-zero codes;

[0116] Identify the coded store terminal corresponding to each non-zero code in the non-zero coded sequence to obtain the coded store terminal sequence;

[0117] Based on the scheduling demand set and the delivery location set, the coding demand and coding location of each coded store terminal in the coded store terminal sequence are obtained, resulting in the coding demand sequence and the coding location sequence.

[0118] Vehicle scheduling energy consumption is calculated using the coded demand sequence and coded location sequence to obtain the current vehicle energy consumption value;

[0119] Summarize the current vehicle energy consumption values ​​corresponding to each supply row vector to obtain the current vehicle energy consumption value sequence. Perform a summation operation based on the current vehicle energy consumption value sequence to obtain the scheduling energy consumption objective function.

[0120] Set matrix generation constraints based on the vehicle supply matrix.

[0121] It should be explained that the non-zero encoding sequence refers to the set of supply codes with a value of 1 (i.e., non-zero codes) in the supply row vector. For example, if the supply row vector is (0, 1, 0, 0, 1), and the supply codes in this supply row vector correspond to the delivery terminals K1, K2, K3, K4, and K5 respectively, then the non-zero encoding sequence is supply code 1 corresponding to K2 and supply code 1 corresponding to K5. The encoded store terminal sequence refers to a set of multiple encoded store terminals, where an encoded store terminal refers to the delivery terminal corresponding to a certain non-zero code in the non-zero encoding sequence. The encoded demand sequence refers to a set of multiple encoded demand quantities, where an encoded demand quantity refers to the scheduling demand quantity corresponding to a certain encoded store terminal. The encoded location sequence refers to a set of multiple encoded locations, where an encoded location refers to the delivery location corresponding to a certain encoded store terminal. The current vehicle energy consumption value refers to the energy consumption required for the delivery vehicle terminal to perform delivery according to the corresponding supply row vector. The above summation operation based on the current vehicle energy consumption value sequence yields the scheduling energy consumption objective function. This means summing the energy consumption values ​​of each current vehicle in the current energy consumption value sequence; the result is the scheduling energy consumption objective function. Since each element in the vehicle supply matrix is ​​a variable in the subsequent genetic optimization algorithm, and each current vehicle energy consumption value in the current energy consumption value sequence is calculated from the vehicle supply matrix, the sum of these values ​​can be considered a mapping function of the vehicle supply matrix as the variable in the subsequent genetic optimization algorithm. That is, the scheduling energy consumption objective function. The smaller the output value of this scheduling energy consumption objective function, the better the scheduling scheme represented by the vehicle supply matrix corresponding to this scheduling energy consumption objective function.

[0122] In detail, the step of calculating vehicle scheduling energy consumption using the coded demand sequence and the coded location sequence to obtain the current vehicle energy consumption value includes:

[0123] Calculate the current vehicle carrying capacity based on the coded demand sequence;

[0124] Vehicle routes are constructed based on preset distribution center locations and coded location sequences to obtain a vehicle dispatch route set. The vehicle dispatch route set includes multiple vehicle dispatch routes, and each vehicle dispatch route corresponds to a dispatched store terminal.

[0125] Extract vehicle dispatch paths sequentially from the vehicle dispatch path set and obtain the dispatch path distance of the extracted vehicle dispatch paths.

[0126] Calculate the energy consumption and scheduling duration of the current route based on the scheduling path distance and the current vehicle load.

[0127] The dispatched demand is determined based on the dispatched store terminals in the extracted vehicle dispatch route.

[0128] The vehicle capacity is calculated and updated based on the current vehicle capacity and the already scheduled demand.

[0129] The updated vehicle capacity is used as the current vehicle capacity, and the step of sequentially extracting vehicle scheduling paths from the vehicle scheduling path set is returned until all vehicle scheduling paths in the vehicle scheduling path set have been extracted.

[0130] By summing the current path energy consumption and the current scheduling duration, we obtain the current path energy consumption sequence and the current scheduling duration sequence.

[0131] The current vehicle energy consumption value is obtained by weighted summation of the current path energy consumption sequence and the current scheduling duration sequence.

[0132] It should be explained that the current vehicle capacity refers to the sum of all coded demands in the coded demand sequence. The distribution center location refers to the location of the distribution center terminal. The vehicle scheduling path set refers to a collection of multiple vehicle scheduling paths, where a vehicle scheduling path refers to the travel path between two adjacent coded locations. If the deliverable vehicle terminal has not yet departed, then the vehicle scheduling path refers to the travel path between the distribution center location and the first coded location in the coded location sequence. For example, if the distribution center location is Q1 and the coded location sequence is (Q2, Q3, Q4), then the vehicle scheduling path set is: (the path between Q1 and Q2, the path between Q2 and Q3, and the path between Q3 and Q4). The scheduled store terminal refers to the store terminal to be delivered that needs to be passed on the vehicle scheduling path. The scheduling path distance refers to the distance traveled by the deliverable vehicle terminal to complete the vehicle scheduling path. The scheduling path distance is obtained by calling the route planning API of the electronic map service and calculating the actual road travel distance based on the coordinates of two location points (i.e., the start and end points of the vehicle scheduling path). The current route energy consumption refers to the energy consumed by a delivery vehicle terminal when traveling a segment of a vehicle dispatch route under a specific load (such as the current vehicle load capacity). This current route energy consumption can be converted into fuel or electricity consumption, and the calculation formula for the current route energy consumption is as follows: ,in, Indicates the energy consumption of the current path. Indicates the distance of the scheduling path. Indicates the current vehicle load capacity. This represents the basic energy consumption coefficient of the delivery vehicle terminal per unit distance and unit load. This basic energy consumption coefficient can be obtained by querying the relevant performance data of the delivery vehicle terminal. The current scheduling time refers to the time taken for the delivery vehicle terminal to complete a vehicle scheduling route. This current scheduling time can be estimated using relevant map software.

[0133] Furthermore, the scheduled demand refers to the scheduled demand corresponding to the scheduled store terminal. When a delivery vehicle terminal completes a certain vehicle scheduling route, it means that the delivery of goods to the scheduled store terminal on that vehicle scheduling route has been completed. At this time, the weight of the goods of the delivery vehicle terminal will decrease. That is, at this time, the current vehicle carrying capacity needs to be subtracted from the scheduled demand, and the difference obtained (which is the updated vehicle carrying capacity mentioned above) is the weight of the goods of the delivery vehicle terminal on the next vehicle scheduling route. In the catering industry, timely delivery of goods to relevant stores is crucial. Therefore, ensuring the scheduling efficiency of the entire supply chain is essential. This requires incorporating scheduling time into the fitness function of the subsequent genetic optimization algorithm. Consequently, the aforementioned step of weighted summation based on the current path energy consumption sequence and the current scheduling time sequence is necessary. Specifically, this step involves summing the current path energy consumption sequence and the current scheduling time sequence to obtain the total path energy consumption and total scheduling time. Then, energy consumption weights and time weights are set, with a sum of 1. These weights are set by the relevant scheduling personnel. For example, if the current scheduling task is urgent, the time weight can be set to a larger value, such as an energy consumption weight of 0.3 and a time weight of 0.7. If the current scheduling task has ample time to complete, the focus can be on energy conservation, i.e., setting the energy consumption weight to a larger value. Finally, the current vehicle energy consumption value is calculated using the following formula: ,in, This indicates the current energy consumption value of the vehicle. and These represent energy consumption weight and duration weight, respectively. Represents the normalization function. and These represent the total energy consumption of the path and the total scheduling time, respectively.

[0134] Specifically, the matrix generation constraints based on the vehicle supply matrix include:

[0135] Multiple supply column vectors are generated based on the vehicle supply matrix, where each supply column vector corresponds to a store terminal to be delivered;

[0136] Set store demand constraints based on multiple supply column vectors, wherein each supply column vector has one and only one supply code with a value of 1.

[0137] Multiple supply row vectors in the vehicle supply matrix are denoted as multiple vehicle constraint vectors;

[0138] For each of the multiple vehicle constraint vectors, perform the following operation:

[0139] The vehicle dispatch store set is obtained based on the vehicle constraint vector, and the target demand set corresponding to the vehicle dispatch store set is determined from the dispatch demand set.

[0140] Summing the target demand set yields the total target demand.

[0141] Sum the total target demand corresponding to each vehicle constraint vector to obtain multiple total target demands;

[0142] Vehicle constraints are set based on the preset maximum vehicle capacity and multiple total target demand, wherein each total target demand is not greater than the maximum vehicle capacity.

[0143] By summarizing the store demand constraints and vehicle constraints, the matrix generation constraints are obtained.

[0144] It is clear that the supply column vector refers to a column vector in the vehicle supply matrix. The meaning of the above store demand constraint is: to ensure that in the delivery plan, each store terminal to be delivered has one and only one deliverable vehicle terminal responsible for its goods delivery, that is, each supply column vector has one and only one supply code with a value of 1. The vehicle dispatch store set refers to the set of store terminals to be delivered corresponding to all non-zero values ​​in the vehicle constraint vector. The target demand set refers to the set of dispatch demand (i.e., target demand) corresponding to each vehicle dispatch store in the vehicle dispatch store set. The total target demand refers to the sum of all target demand values ​​in the target demand set. The maximum vehicle carrying capacity refers to the maximum carrying capacity of the deliverable vehicle terminal. The meaning of the above vehicle constraint condition is: to ensure that the total delivery tasks allocated to each deliverable vehicle terminal do not exceed the maximum load capacity of that deliverable vehicle terminal itself.

[0145] S5. Generate the current genetic population based on matrix generation constraints. The current genetic population consists of multiple current chromosomes, and each current chromosome corresponds to a vehicle scheduling scheme.

[0146] It is clear that the current genetic population refers to a set of multiple current chromosomes, where a current chromosome refers to the encoded individual representing a candidate solution in the genetic algorithm. Each current chromosome corresponds to a vehicle scheduling scheme, which is mathematically represented as a supply matrix (i.e., the subsequent current supply matrix), and the generation of the supply matrix needs to satisfy the matrix generation constraint condition.

[0147] S6. Use the scheduling energy consumption objective function to perform genetic iteration on the current genetic population to obtain the optimal vehicle scheduling scheme. Based on the optimal vehicle scheduling scheme, perform terminal control on the set of deliverable vehicle terminals to obtain the control vehicle terminal set, and complete the catering supply chain scheduling based on intelligent optimization algorithm.

[0148] It should be explained that the optimal vehicle scheduling scheme refers to the vehicle scheduling scheme corresponding to the chromosome with the smallest fitness value obtained after genetic iteration. Mathematically, the optimal vehicle scheduling scheme represents an optimal supply matrix. According to the optimal supply matrix, each deliverable vehicle terminal participating in the scheduling task is assigned the store terminal to be delivered to, and the goods are loaded according to the specific types of goods required by the store terminal to be delivered. The deliverable vehicle terminal that completes the loading and has a clear vehicle scheduling path is the control vehicle terminal. All control vehicle terminals form the control vehicle terminal set.

[0149] For example, a delivery vehicle terminal needs to pass through two store terminals, E1 and E2. The types of goods and scheduling requirements for delivery to store terminal E1 are 50 kg of fresh vegetables, and the types of goods and scheduling requirements for delivery to store terminal E2 are 30 kg of frozen meat. Then, the delivery vehicle terminal is loaded with the corresponding types of goods (i.e., 50 kg of fresh vegetables and 30 kg of frozen meat) to control the vehicle terminal.

[0150] In detail, the step of using the scheduling energy consumption objective function to perform genetic iteration on the current genetic population to obtain the optimal vehicle scheduling scheme includes:

[0151] Extract the current chromosome sequentially from the current genetic population, and obtain the current supply matrix corresponding to the extracted current chromosome;

[0152] Input the current supply matrix into the scheduling energy consumption objective function to obtain the current scheduling energy consumption value;

[0153] Summarize the current scheduling energy consumption values ​​for each current chromosome to obtain the current scheduling energy consumption value set;

[0154] Based on a preset high-quality population ratio, identify low scheduling energy consumption sets within the current scheduling energy consumption value set;

[0155] Identify the set of low-scheduled chromosomes corresponding to the set of low-scheduled energy consumption values ​​in the current genetic population;

[0156] The sum of the current energy consumption values ​​is calculated to obtain the total energy consumption of the current scheduling.

[0157] By using the sum of current scheduled energy consumption, the ratio of each current scheduled energy consumption value in the current scheduled energy consumption value set is calculated to obtain the current scheduled energy consumption ratio set.

[0158] The remaining population size is calculated based on the proportion of high-quality populations.

[0159] Based on the remaining population size and the current scheduling energy consumption ratio set, multiple current chromosomes are randomly and probabilistically extracted to obtain the updated scheduling chromosome set;

[0160] The low-scheduled chromosome set and the updated-scheduled chromosome set are merged to obtain the parental genetic population.

[0161] Genetic iteration is performed based on the parental genetic population to obtain an iterative genetic population;

[0162] The iterative genetic population is used as the current genetic population, and the step of sequentially extracting the current chromosome in the current genetic population is returned until a preset stop iteration command is received.

[0163] The optimal genetic population is determined based on the stop iteration instruction, the optimal chromosome in the optimal genetic population is identified, and the optimal vehicle scheduling scheme is generated based on the current supply matrix in the optimal chromosome.

[0164] It is clear that the current supply matrix refers to the supply matrix corresponding to the current chromosome. The current scheduling energy consumption value refers to the energy consumption value output by the scheduling energy consumption objective function after the current supply matrix is ​​input into it. The high-quality population ratio refers to the proportion of chromosomes in the current genetic population that are directly selected and enter the parent genetic population. This high-quality population ratio can be set manually according to the size of the current genetic population, for example, 20%. The low scheduling energy consumption value set refers to a set of multiple low scheduling energy consumption values, where a low scheduling energy consumption value is the one that appears first in the current scheduling energy consumption value set. Small set of current scheduling energy consumption values, among which, This indicates the proportion of high-quality population. Introducing the proportion of high-quality population in this step can prevent chromosomes that have been found during the iteration process (i.e., chromosomes with low scheduling energy consumption values) from being eliminated due to randomness. In other words, the scheduling scheme represented by the low-schedule chromosomes in the low-schedule chromosome set is better and can participate in an iteration process.

[0165] It should be explained that the total current scheduling energy consumption refers to the sum of all current scheduling energy consumption values ​​in the current scheduling energy consumption value set. The current scheduling energy consumption ratio set refers to a set of multiple current scheduling energy consumption ratios, where each current scheduling energy consumption ratio is the ratio of a current scheduling energy consumption value to the total current scheduling energy consumption. The smaller the current scheduling energy consumption ratio, the better the scheduling scheme represented by the corresponding current chromosome, meaning that the probability of this current chromosome being extracted as the update scheduling chromosome in subsequent random probability extraction is higher. The remaining population size refers to the number of chromosomes that need to be added after the number of chromosomes corresponding to the proportion of high-quality populations. The calculation method for the remaining population size is as follows: ,in, Indicates the remaining population size. This represents the total number of chromosomes in the current genetic population. The updated scheduling chromosome set refers to a collection of multiple updated scheduling chromosomes, where an updated scheduling chromosome is a current chromosome extracted in a random probability extraction. The above-mentioned random probability extraction of multiple current chromosomes based on the remaining population size and the current scheduling energy consumption ratio set refers to: calculating an extraction probability value set based on the current scheduling energy consumption ratio set, where the extraction probability value is the value 1 minus the corresponding current scheduling energy consumption ratio, and the extraction probability value corresponds one-to-one with the current chromosome, that is, the extraction probability value represents the probability of the corresponding current chromosome being extracted. Then, m current chromosomes are extracted from multiple current chromosomes according to this extraction probability value set, and these m current chromosomes constitute the updated scheduling chromosome set, where m represents the remaining population size. The parent genetic population refers to the set composed of the low-schedule chromosome set and the updated scheduling chromosome set. The iterative genetic population refers to the new genetic population obtained after genetic iteration. The stop iteration command refers to a preset signal used to terminate the genetic algorithm iteration process. When the iteration reaches the maximum number, such as 1000 times, this stop iteration command is generated. The optimal genetic population refers to the iterative genetic population at the time the stop iteration command is received. The optimal chromosome refers to the chromosome with the lowest scheduling energy consumption in the optimal genetic population.

[0166] In detail, the genetic iteration based on the parental genetic population to obtain the iterative genetic population includes:

[0167] Crossover and mutation operations are performed sequentially on the parent genetic population to obtain the offspring genetic population, which includes multiple offspring chromosomes;

[0168] Obtain the average scheduling energy consumption of the parent genetic population;

[0169] Chromosomes are selected from the offspring genetic population based on the average scheduling energy consumption value to obtain an effective chromosome set;

[0170] Obtain the number of valid chromosomes in the valid chromosome set;

[0171] If the number of effective chromosomes is less than the preset standard number of chromosomes, then the number of chromosomes to be supplemented between the number of effective chromosomes and the standard number of chromosomes is calculated.

[0172] Select a supplementary chromosome set from the parent genetic population based on the number of chromosomes to be supplemented;

[0173] The supplementary chromosome set is added to the effective chromosome set to obtain the iterative genetic population.

[0174] It should be explained that the crossover and mutation operations are existing techniques in genetic algorithms and will not be elaborated further here. The offspring genetic population refers to the new genetic population obtained by sequentially performing crossover and mutation operations on the parent genetic population. The offspring chromosomes refer to the chromosomes in the offspring genetic population. The average scheduling energy consumption value refers to the average scheduling energy consumption value corresponding to all chromosomes in the parent genetic population. The effective chromosome set refers to the set of offspring chromosomes selected from the offspring genetic population; the method of chromosome selection will be described in subsequent embodiments. The effective chromosome number refers to the number of effective chromosomes in the effective chromosome set. The standard chromosome number refers to the total number of chromosomes in the parent genetic population, i.e., the number of chromosomes required to maintain normal genetic iteration. The number to be supplemented refers to the difference between the effective chromosome number and the standard chromosome number. The supplementary chromosome set refers to the set of x chromosomes selected from the parent genetic population, where x represents the number to be supplemented. The supplementary chromosome set is selected by ranking the chromosomes with the smallest scheduling energy consumption values ​​in the parent genetic population as the supplementary chromosome set.

[0175] In detail, the step of selecting chromosomes from the offspring genetic population based on the average scheduling energy consumption value to obtain an effective chromosome set includes:

[0176] Perform the following operation on each offspring chromosome in the offspring genetic population:

[0177] Calculate the offspring scheduling energy consumption value of offspring chromosomes;

[0178] If the offspring scheduling energy consumption value is less than the average scheduling energy consumption value, then the offspring chromosome is recorded as a valid chromosome;

[0179] If the energy consumption of the offspring scheduling is not less than the average energy consumption, then the retention probability is calculated based on the energy consumption of the offspring scheduling and the average energy consumption to obtain the offspring retention probability value.

[0180] Chromosomes of offspring are selected for retention based on the offspring retention probability value, and the retention selection result is: retain or not retain.

[0181] If the selection result is "retain", then the offspring chromosomes will be recorded as valid chromosomes;

[0182] By summing up the valid chromosomes, we obtain the effective chromosome set.

[0183] It should be explained that the offspring scheduling energy consumption value refers to the scheduling energy consumption value (i.e., fitness value) corresponding to the offspring chromosome. When the offspring scheduling energy consumption value is less than the average scheduling energy consumption value, it indicates that the scheduling scheme corresponding to the offspring chromosome is better, and the offspring chromosome can be retained, i.e., the offspring chromosome is recorded as a valid chromosome. When the offspring scheduling energy consumption value is not less than the average scheduling energy consumption value, it indicates that the scheduling scheme corresponding to the offspring chromosome is worse than or only equal to the average level of the parent population. However, to avoid the genetic algorithm getting trapped in local optima, it is necessary to retain the offspring chromosome with a certain probability to maintain the diversity of the genetic population and provide the possibility for the algorithm to explore a better solution space, i.e., to introduce the subsequent retention selection operation. The offspring retention probability value refers to a probability value between 0 and 1. The larger the offspring retention probability value, the greater the probability that the offspring chromosome will be retained in the subsequent retention selection process. The retention selection result refers to the result obtained after retention selection, where retention means recording the offspring chromosome as a valid chromosome, and non-retention means not including the offspring chromosome in the set of valid chromosomes.

[0184] In detail, the calculation of the retention probability based on the offspring scheduling energy consumption value and the average scheduling energy consumption value to obtain the offspring retention probability value includes:

[0185] The offspring retention probability value is calculated using the following formula:

[0186]

[0187] in, This represents the probability of offspring retention. This represents an exponential function with the natural constant as its base. This represents the average dispatch energy consumption value. This represents the energy consumption value of offspring scheduling.

[0188] It needs to be explained that in the above formula for calculating the offspring retention probability, The term represents the relative advantage or disadvantage of the scheduling energy consumption value of the offspring chromosome compared to the average scheduling energy consumption value of the parent population. The larger the term, the more obvious the advantage of the scheduling energy consumption value of the offspring chromosome compared to the average scheduling energy consumption value of the parent population, that is, the greater the offspring retention probability value.

[0189] To address the problems described in the background, this invention first receives standardized digital instructions for catering scheduling through distribution center terminals. This step automates and accurately collects scheduling demands, replacing traditional methods that rely on manual aggregation or inefficient communication. Furthermore, this solution constructs a vehicle supply matrix based on the set of deliverable vehicle terminals and the set of stores to be delivered. It then uses the set of locations to be delivered, the set of scheduling demands, and the vehicle supply matrix to set a scheduling energy consumption objective function and matrix generation constraints. This step, by constructing the vehicle supply matrix, transforms the complex many-to-many vehicle-to-store allocation relationship into a clear binary mathematical expression, thus encoding the scheduling scheme. Based on this matrix, store locations, and demand, a scheduling energy consumption objective function integrating path energy consumption and delivery time is set, and corresponding matrix generation constraints are constructed. This provides a foundation for subsequent intelligent optimization algorithms. This invention provides a clear mathematical framework for solving the problem, overcoming the limitations of traditional methods that rely on empirical rules or simple greedy strategies. Finally, it uses a scheduling energy consumption objective function to perform genetic iteration on the current genetic population to obtain the optimal vehicle scheduling scheme. Based on this optimal scheme, it performs terminal control on the set of deliverable vehicle terminals to obtain the controlled vehicle terminal set. This step iteratively optimizes the scheduling scheme using a genetic algorithm. Through selection, crossover, and mutation operations, the genetic algorithm can extensively search the solution space, avoiding getting trapped in local optima, thus having a higher probability of finding a vehicle allocation and route planning scheme with lower overall scheduling energy consumption. Compared to traditional fixed routes or simple heuristic rules, this method can dynamically generate comprehensive optimal scheduling instructions that adapt to specific delivery needs and real-time traffic conditions, and ultimately achieve automatic execution of the scheme through terminal control, completing a closed loop from intelligent decision-making to automated scheduling. Therefore, this invention can improve the scheduling efficiency and intelligence level of the catering supply chain, and reduce the overall energy consumption during the scheduling process.

[0190] like Figure 2 The diagram shown is a functional block diagram of a catering supply chain scheduling system based on intelligent optimization algorithms provided in an embodiment of the present invention.

[0191] The catering supply chain scheduling system 100 based on intelligent optimization algorithms described in this invention can be installed in an electronic device. Depending on the functions implemented, the catering supply chain scheduling system 100 based on intelligent optimization algorithms may include a scheduling request receiving module 101, a delivery vehicle identification module 102, a scheduling scheme generation module 103, and a scheduling scheme execution module 104. The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and which are stored in the memory of the electronic device.

[0192] The scheduling request receiving module 101 is used to receive catering scheduling requests based on pre-built distribution center terminals, and determine a set of store terminals to be delivered based on the catering scheduling requests, wherein the set of store terminals to be delivered includes multiple store terminals to be delivered.

[0193] The delivery vehicle identification module 102 is used to query the set of locations to be delivered and the set of scheduling requirements corresponding to the set of stores to be delivered according to the catering scheduling request, and to identify the set of deliverable vehicle terminals based on the distribution center terminal, wherein the set of deliverable vehicle terminals includes multiple deliverable vehicle terminals.

[0194] The scheduling scheme generation module 103 is used to construct a vehicle supply matrix based on the set of deliverable vehicle terminals and the set of store terminals to be delivered, and to set a scheduling energy consumption objective function and matrix generation constraints using the set of locations to be delivered, the set of scheduling demand, and the vehicle supply matrix. Based on the matrix generation constraints, a current genetic population is generated, wherein the current genetic population consists of multiple current chromosomes, and each current chromosome corresponds to a vehicle scheduling scheme.

[0195] The scheduling scheme execution module 104 is used to perform genetic iteration on the current genetic population using the scheduling energy consumption objective function to obtain the optimal vehicle scheduling scheme, and to perform terminal control on the set of deliverable vehicle terminals based on the optimal vehicle scheduling scheme to obtain the controlled vehicle terminal set.

[0196] In detail, the modules in the catering supply chain scheduling system 100 based on intelligent optimization algorithms described in this embodiment of the invention employ the same methods as described above. Figure 1 The method uses the same technical means as the intelligent optimization algorithm-based catering supply chain scheduling method described in the article, and can produce the same technical effect, so it will not be repeated here.

[0197] like Figure 3 The diagram shown is a structural schematic of an electronic device for implementing a catering supply chain scheduling method based on an intelligent optimization algorithm, according to an embodiment of the present invention.

[0198] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and capable of running on the processor 10, such as a catering supply chain scheduling method program based on intelligent optimization algorithms.

[0199] The memory 11 includes at least one type of readable storage medium, such as flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as the portable hard drive of the electronic device 1. In other embodiments, the memory 11 can be an external storage device of the electronic device 1, such as a plug-in portable hard drive, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device 1. Furthermore, the memory 11 includes both internal storage units and external storage devices of the electronic device 1. The memory 11 can be used not only to store application software and various types of data installed on the electronic device 1, such as the code of a catering supply chain scheduling method program based on intelligent optimization algorithms, but also to temporarily store data that has been output or will be output.

[0200] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., a catering supply chain scheduling method program based on intelligent optimization algorithms) and calls data stored in the memory 11 to perform various functions of the electronic device 1 and process data.

[0201] The bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 can be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize the connection and communication between the memory 11 and at least one processor 10, etc.

[0202] Figure 3 Only electronic devices with components are shown; it will be understood by those skilled in the art that... Figure 3The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0203] For example, although not shown, the electronic device 1 may also include a power supply (such as a battery) to power the various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management device, thereby enabling functions such as charging management, discharging management, and power consumption management. The power supply may also include one or more DC or AC power supplies, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0204] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, a Bluetooth interface, etc.), which is typically used to establish communication connections between the electronic device 1 and other electronic devices.

[0205] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), and optionally, a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device 1 and to display a visual user interface.

[0206] The catering supply chain scheduling method program based on intelligent optimization algorithms stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When run in the processor 10, it can achieve the following:

[0207] Based on the pre-built distribution center terminal, the catering dispatch request is received, and based on the catering dispatch request, the set of store terminals to be delivered is determined, wherein the set of store terminals to be delivered includes multiple store terminals to be delivered.

[0208] Based on the catering dispatch request, query the set of locations to be delivered and the set of dispatch demand corresponding to the set of stores to be delivered;

[0209] Based on the distribution center terminal identification of the deliverable vehicle terminal set, the deliverable vehicle terminal set includes multiple deliverable vehicle terminals;

[0210] A vehicle supply matrix is ​​constructed based on the set of deliverable vehicle terminals and the set of store terminals to be delivered. The objective function of scheduling energy consumption and the matrix generation constraints are set using the set of locations to be delivered, the set of scheduling demand, and the vehicle supply matrix.

[0211] The current genetic population is generated based on matrix generation constraints. The current genetic population consists of multiple current chromosomes, and each current chromosome corresponds to a vehicle scheduling scheme.

[0212] By using the scheduling energy consumption objective function to perform genetic iteration on the current genetic population, the optimal vehicle scheduling scheme is obtained. Based on the optimal vehicle scheduling scheme, the set of deliverable vehicle terminals is controlled to obtain the set of controlled vehicle terminals, thus completing the catering supply chain scheduling based on intelligent optimization algorithms.

[0213] Specifically, the processor 10's implementation method for the above instructions can be found in [reference needed]. Figures 1 to 3 The descriptions of the relevant steps in the corresponding embodiments are not repeated here.

[0214] Furthermore, if the modules / units integrated in the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0215] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor of an electronic device, can perform the following:

[0216] Based on the pre-built distribution center terminal, the catering dispatch request is received, and based on the catering dispatch request, the set of store terminals to be delivered is determined, wherein the set of store terminals to be delivered includes multiple store terminals to be delivered.

[0217] Based on the catering dispatch request, query the set of locations to be delivered and the set of dispatch demand corresponding to the set of stores to be delivered;

[0218] Based on the distribution center terminal identification of the deliverable vehicle terminal set, the deliverable vehicle terminal set includes multiple deliverable vehicle terminals;

[0219] A vehicle supply matrix is ​​constructed based on the set of deliverable vehicle terminals and the set of store terminals to be delivered. The objective function of scheduling energy consumption and the matrix generation constraints are set using the set of locations to be delivered, the set of scheduling demand, and the vehicle supply matrix.

[0220] The current genetic population is generated based on matrix generation constraints. The current genetic population consists of multiple current chromosomes, and each current chromosome corresponds to a vehicle scheduling scheme.

[0221] By using the scheduling energy consumption objective function to perform genetic iteration on the current genetic population, the optimal vehicle scheduling scheme is obtained. Based on the optimal vehicle scheduling scheme, the set of deliverable vehicle terminals is controlled to obtain the set of controlled vehicle terminals, thus completing the catering supply chain scheduling based on intelligent optimization algorithms.

[0222] In the embodiments provided by this invention, it should be understood that the disclosed devices, systems, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative, and actual implementations may have other classification methods.

[0223] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0224] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0225] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0226] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A catering supply chain scheduling method based on intelligent optimization algorithms, characterized in that, The method includes: Based on the pre-built distribution center terminal, the catering dispatch request is received, and based on the catering dispatch request, the set of store terminals to be delivered is determined, wherein the set of store terminals to be delivered includes multiple store terminals to be delivered. Based on the catering dispatch request, query the set of locations to be delivered and the set of dispatch demand corresponding to the set of stores to be delivered; Based on the distribution center terminal identification of the deliverable vehicle terminal set, the deliverable vehicle terminal set includes multiple deliverable vehicle terminals; A vehicle supply matrix is ​​constructed based on the set of deliverable vehicle terminals and the set of store terminals to be delivered. The objective function of scheduling energy consumption and the matrix generation constraints are set using the set of locations to be delivered, the set of scheduling demand, and the vehicle supply matrix. The current genetic population is generated based on matrix generation constraints. The current genetic population consists of multiple current chromosomes, and each current chromosome corresponds to a vehicle scheduling scheme. By using the scheduling energy consumption objective function to perform genetic iteration on the current genetic population, the optimal vehicle scheduling scheme is obtained. Based on the optimal vehicle scheduling scheme, the set of deliverable vehicle terminals is controlled to obtain the set of controlled vehicle terminals, thus completing the catering supply chain scheduling based on intelligent optimization algorithms.

2. The catering supply chain scheduling method based on intelligent optimization algorithm as described in claim 1, characterized in that, The construction of the vehicle supply matrix based on the set of deliverable vehicle terminals and the set of store terminals to be delivered includes: Sequentially extract deliverable vehicle terminals from the deliverable vehicle terminal set and record the extracted deliverable vehicle terminals as vehicle terminals to be dispatched. Obtain the number of stores to be delivered in the set of stores to be delivered, and generate a vehicle supply vector based on the number of stores to be delivered. The vehicle supply vector contains multiple supply codes, and each supply code corresponds one-to-one with a store terminal to be delivered. The supply code is either the value 1 or the value 0. Summarize the vehicle supply vectors corresponding to each vehicle terminal to be dispatched to obtain a vehicle supply vector set; The vehicle supply matrix is ​​obtained by concatenating the vehicle supply vector set. The vehicle supply matrix contains multiple supply row vectors, and each supply row vector corresponds one-to-one with a vehicle supply vector.

3. The catering supply chain scheduling method based on intelligent optimization algorithm as described in claim 2, characterized in that, The process of setting the scheduling energy consumption objective function and matrix generation constraints using the set of locations to be delivered, the set of scheduling demand, and the vehicle supply matrix includes: Perform the following operation on each supply row vector in the vehicle supply matrix: Obtain the non-zero encoded sequence from the supply row vector, where the non-zero encoded sequence includes multiple non-zero codes; Identify the coded store terminal corresponding to each non-zero code in the non-zero coded sequence to obtain the coded store terminal sequence; Based on the scheduling demand set and the delivery location set, the coding demand and coding location of each coded store terminal in the coded store terminal sequence are obtained, resulting in the coding demand sequence and the coding location sequence. Vehicle scheduling energy consumption is calculated using the coded demand sequence and coded location sequence to obtain the current vehicle energy consumption value; Summarize the current vehicle energy consumption values ​​corresponding to each supply row vector to obtain the current vehicle energy consumption value sequence. Perform a summation operation based on the current vehicle energy consumption value sequence to obtain the scheduling energy consumption objective function. Set matrix generation constraints based on the vehicle supply matrix.

4. The catering supply chain scheduling method based on intelligent optimization algorithm as described in claim 3, characterized in that, The calculation of vehicle scheduling energy consumption using the coded demand sequence and coded location sequence to obtain the current vehicle energy consumption value includes: Calculate the current vehicle carrying capacity based on the coded demand sequence; Vehicle routes are constructed based on preset distribution center locations and coded location sequences to obtain a vehicle dispatch route set. The vehicle dispatch route set includes multiple vehicle dispatch routes, and each vehicle dispatch route corresponds to a dispatched store terminal. Extract vehicle dispatch paths sequentially from the vehicle dispatch path set and obtain the dispatch path distance of the extracted vehicle dispatch paths. Calculate the energy consumption and scheduling duration of the current route based on the scheduling path distance and the current vehicle load. The dispatched demand is determined based on the dispatched store terminals in the extracted vehicle dispatch route. The vehicle capacity is calculated and updated based on the current vehicle capacity and the already scheduled demand. The updated vehicle capacity is used as the current vehicle capacity, and the step of sequentially extracting vehicle scheduling paths from the vehicle scheduling path set is returned until all vehicle scheduling paths in the vehicle scheduling path set have been extracted. By summing the current path energy consumption and the current scheduling duration, we obtain the current path energy consumption sequence and the current scheduling duration sequence. The current vehicle energy consumption value is obtained by weighted summation of the current path energy consumption sequence and the current scheduling duration sequence.

5. The catering supply chain scheduling method based on intelligent optimization algorithm as described in claim 4, characterized in that, The matrix generation constraints based on the vehicle supply matrix include: Multiple supply column vectors are generated based on the vehicle supply matrix, where each supply column vector corresponds to a store terminal to be delivered; Set store demand constraints based on multiple supply column vectors, wherein each supply column vector has one and only one supply code with a value of 1. Multiple supply row vectors in the vehicle supply matrix are denoted as multiple vehicle constraint vectors; For each of the multiple vehicle constraint vectors, perform the following operation: The vehicle dispatch store set is obtained based on the vehicle constraint vector, and the target demand set corresponding to the vehicle dispatch store set is determined from the dispatch demand set. Summing the target demand set yields the total target demand. Sum the total target demand corresponding to each vehicle constraint vector to obtain multiple total target demands; Vehicle constraints are set based on the preset maximum vehicle capacity and multiple total target demand, wherein each total target demand is not greater than the maximum vehicle capacity. By summarizing the store demand constraints and vehicle constraints, the matrix generation constraints are obtained.

6. The catering supply chain scheduling method based on intelligent optimization algorithm as described in claim 5, characterized in that, The step of using a scheduling energy consumption objective function to perform genetic iteration on the current genetic population to obtain the optimal vehicle scheduling scheme includes: Extract the current chromosome sequentially from the current genetic population, and obtain the current supply matrix corresponding to the extracted current chromosome; Input the current supply matrix into the scheduling energy consumption objective function to obtain the current scheduling energy consumption value; Summarize the current scheduling energy consumption values ​​for each current chromosome to obtain the current scheduling energy consumption value set; Based on a preset high-quality population ratio, identify low scheduling energy consumption sets within the current scheduling energy consumption value set; Identify the set of low-scheduled chromosomes corresponding to the set of low-scheduled energy consumption values ​​in the current genetic population; The sum of the current energy consumption values ​​is calculated to obtain the total energy consumption of the current scheduling. By using the sum of current scheduled energy consumption, the ratio of each current scheduled energy consumption value in the current scheduled energy consumption value set is calculated to obtain the current scheduled energy consumption ratio set. The remaining population size is calculated based on the proportion of high-quality populations. Based on the remaining population size and the current scheduling energy consumption ratio set, multiple current chromosomes are randomly and probabilistically extracted to obtain the updated scheduling chromosome set; The low-scheduled chromosome set and the updated-scheduled chromosome set are merged to obtain the parental genetic population. Genetic iteration is performed based on the parental genetic population to obtain an iterative genetic population; The iterative genetic population is used as the current genetic population, and the step of sequentially extracting the current chromosome in the current genetic population is returned until a preset stop iteration command is received. The optimal genetic population is determined based on the stop iteration instruction, the optimal chromosome in the optimal genetic population is identified, and the optimal vehicle scheduling scheme is generated based on the current supply matrix in the optimal chromosome.

7. The catering supply chain scheduling method based on intelligent optimization algorithm as described in claim 6, characterized in that, The genetic iteration based on the parental genetic population to obtain the iterative genetic population includes: Crossover and mutation operations are performed sequentially on the parent genetic population to obtain the offspring genetic population, which includes multiple offspring chromosomes; Obtain the average scheduling energy consumption of the parent genetic population; Chromosomes are selected from the offspring genetic population based on the average scheduling energy consumption value to obtain an effective chromosome set; Obtain the number of valid chromosomes in the valid chromosome set; If the number of effective chromosomes is less than the preset standard number of chromosomes, then the number of chromosomes to be supplemented between the number of effective chromosomes and the standard number of chromosomes is calculated. Select a supplementary chromosome set from the parent genetic population based on the number of chromosomes to be supplemented; The supplementary chromosome set is added to the effective chromosome set to obtain the iterative genetic population.

8. The catering supply chain scheduling method based on intelligent optimization algorithm as described in claim 7, characterized in that, The step of selecting chromosomes from the offspring genetic population based on the average scheduling energy consumption value to obtain an effective chromosome set includes: Perform the following operation on each offspring chromosome in the offspring genetic population: Calculate the offspring scheduling energy consumption value of offspring chromosomes; If the offspring scheduling energy consumption value is less than the average scheduling energy consumption value, then the offspring chromosome is recorded as a valid chromosome; If the energy consumption of the offspring scheduling is not less than the average energy consumption, then the retention probability is calculated based on the energy consumption of the offspring scheduling and the average energy consumption to obtain the offspring retention probability value. Chromosomes of offspring are selected for retention based on the offspring retention probability value, and the retention selection result is: retain or not retain. If the selection result is "retain", then the offspring chromosomes will be recorded as valid chromosomes; By summing up the valid chromosomes, we obtain the effective chromosome set.

9. The catering supply chain scheduling method based on intelligent optimization algorithm as described in claim 8, characterized in that, The calculation of the retention probability based on the child scheduling energy consumption value and the average scheduling energy consumption value yields the child retention probability value, including: The offspring retention probability value is calculated using the following formula: in, This represents the probability of offspring retention. This represents an exponential function with the natural constant as its base. This represents the average dispatch energy consumption value. This represents the energy consumption value of offspring scheduling.

10. A catering supply chain scheduling system based on intelligent optimization algorithms, characterized in that, The system includes: The scheduling request receiving module is used to receive catering scheduling requests based on pre-built distribution center terminals, and determine the set of store terminals to be delivered based on the catering scheduling requests, wherein the set of store terminals to be delivered includes multiple store terminals to be delivered. The delivery vehicle identification module is used to query the set of locations to be delivered and the set of scheduling requirements corresponding to the set of stores to be delivered based on the catering scheduling request, and to identify the set of deliverable vehicle terminals based on the distribution center terminal. The set of deliverable vehicle terminals includes multiple deliverable vehicle terminals. The scheduling scheme generation module is used to construct a vehicle supply matrix based on the set of deliverable vehicle terminals and the set of store terminals to be delivered. It uses the set of locations to be delivered, the set of scheduling demand, and the vehicle supply matrix to set the scheduling energy consumption objective function and matrix generation constraints. Based on the matrix generation constraints, it generates the current genetic population, which consists of multiple current chromosomes, and each current chromosome corresponds to a vehicle scheduling scheme. The scheduling scheme execution module is used to perform genetic iteration on the current genetic population using the scheduling energy consumption objective function to obtain the optimal vehicle scheduling scheme. Based on the optimal vehicle scheduling scheme, the module performs terminal control on the set of deliverable vehicle terminals to obtain the controlled vehicle terminal set.

Images