Air freight network hub site selection method, device and equipment and readable storage medium

Abstract

The invention provides an air freight network hub site selection method, device and equipment and a readable storage medium, and relates to the technical field of logistics transportation, and the method comprises the steps: obtaining first information which comprises the basic data of all city nodes in a freight network; performing prediction processing according to the historical mail throughput data to obtain future mail throughput of each city node; calculating an attraction intensity result among cities according to the future mail throughput, and obtaining a freight volume distribution result; carrying out transportation cost analysis processing according to the freight volume distribution result and the transportation distance data to obtain a transportation mode analysis result; establishing a hub site selection model according to the transportation mode analysis result; and performing optimization processing according to the hub site selection model to obtain an optimal hub configuration scheme. According to the method, the future cargo handling capacity is accurately predicted by constructing the grey prediction model, and more accurate demand prediction is provided in combination with the attraction intensity and the freight volume distribution.

Description

Technical Field

[0001] The present invention relates to the field of logistics and transportation technology, and in particular to a method, device, equipment and readable storage medium for selecting a hub site for an air cargo network. Background Art

[0002] In modern logistics systems, road transport and air transport each have their own unique advantages. Road transport has obvious advantages in short-distance transportation within a certain distance (usually 500 kilometers), and can achieve flexible door-to-door service, but its speed is slow and timeliness is insufficient in long-distance transportation. Air transport is suitable for long-distance transportation with its high timeliness and safety, but it is costly and has limited coverage. With the continuous growth and complexity of logistics demand, how to find the best connection point between road and air transport has become the key to optimizing the transportation network. The selection and layout of freight hubs are of great significance to improving transportation efficiency and reducing transportation costs. Hub site selection not only involves how to efficiently allocate road and air resources, but also involves the prediction of transportation demand, the comprehensive evaluation of transportation costs, and the economic analysis of hub construction and operation. However, existing hub site selection technologies mainly focus on the optimization of a single mode of transportation and the topological structure design of the hub network. These methods often only optimize a certain mode of transportation, fail to consider the joint benefits of road and air transportation, and fail to fully utilize the complementary advantages of the two.

[0003] Based on the above-mentioned defects of the prior art, there is an urgent need for an air cargo network hub site selection method, device, equipment and readable storage medium. Summary of the invention

[0004] The purpose of the present invention is to provide a method, device, equipment and readable storage medium for selecting a hub for an air cargo network to improve the above-mentioned problems. In order to achieve the above-mentioned purpose, the technical solution adopted by the present invention is as follows: In a first aspect, the present application provides a method for selecting a hub site for an air cargo network, comprising: Acquire first information, wherein the first information includes basic data of all city nodes in the freight network, wherein the basic data includes transportation distance data between city nodes and historical freight and mail throughput data of each city node; Performing forecasting processing based on the historical cargo and mail throughput data, by constructing a grey forecasting model based on the original data and solving the model, obtaining the future cargo and mail throughput of each city node; Calculating the attraction intensity result between cities according to the future cargo and mail throughput, and allocating the freight volume between the city nodes based on the attraction intensity result to obtain the freight volume allocation result; Performing a transportation cost analysis process based on the freight volume allocation result and the transportation distance data, and obtaining a transportation mode analysis result by determining the optimal road-air transportation combination mode between nodes; Model building is performed based on the analysis results of the transportation mode, and a hub location model with the minimum total cost as the goal is established by combining hub construction cost, loading and unloading cost and transportation cost; The hub location selection model is optimized by using an immune genetic algorithm to iteratively optimize the location and number of hubs to obtain the optimal hub configuration solution that minimizes the total network cost.

[0005] In a second aspect, the present application also provides an air cargo network hub site selection device, comprising: An acquisition module, acquiring first information, wherein the first information includes basic data of all city nodes in the freight network, wherein the basic data includes transportation distance data between city nodes and historical freight and mail throughput data of each city node; A prediction module is used to perform prediction processing based on the historical cargo and mail throughput data, and obtain the future cargo and mail throughput of each city node by constructing a grey prediction model based on the original data and solving the model; An allocation module, used to calculate the attraction intensity result between cities according to the future cargo and mail throughput, and allocate the freight volume between the city nodes based on the attraction intensity result to obtain the freight volume allocation result; An analysis module, used to perform transportation cost analysis based on the freight volume allocation result and the transportation distance data, and obtain a transportation mode analysis result by determining the optimal road-air transportation combination mode between nodes; A modeling module, used for constructing a model according to the analysis results of the transportation mode, and establishing a hub location model with the minimum total cost as the goal by combining hub construction cost, loading and unloading cost and transportation cost; The optimization module is used to perform optimization processing according to the hub site selection model, and iteratively optimize the location and number of hub points by using an immune genetic algorithm to obtain the optimal hub configuration plan that minimizes the total network cost.

[0006] In a third aspect, the present application also provides an air cargo network hub site selection device, including: Memory for storing computer programs; A processor is used to implement the steps of the air cargo network hub site selection method when executing the computer program.

[0007] In a fourth aspect, the present application further provides a readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above-mentioned air cargo network hub site selection method are implemented.

[0008] The beneficial effects of the present invention are: The present invention accurately predicts future cargo and mail throughput by constructing a grey prediction model, and provides a more accurate demand forecast by combining attraction intensity and freight volume distribution; by comprehensively considering hub construction costs, loading and unloading costs, and transportation costs, a hub site selection model is constructed, making hub site selection more scientific and economical.

[0009] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or be understood by implementing the embodiments of the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0011] Figure 1 A schematic diagram of the process flow of the air cargo network hub site selection method described in an embodiment of the present invention; Figure 2 It is a schematic diagram of the structure of the air cargo network hub site selection device described in an embodiment of the present invention; Figure 3 It is a schematic diagram of the structure of the air cargo network hub site selection equipment described in an embodiment of the present invention.

[0012] Markings in the figure: 1. Acquisition module; 2. Prediction module; 21. First processing unit; 22. First construction unit; 23. Second processing unit; 24. First prediction unit; 3. Allocation module; 31. First integration unit; 32. First analysis unit; 33. Second construction unit; 34. Third construction unit; 4. Analysis module; 41. First fusion unit; 42. Third processing unit; 43. First optimization unit; 5. Modeling module; 51. Second analysis unit; 52. First evaluation unit; 53. First calculation unit; 54. Fourth construction unit; 6. Optimization module; 61. First screening unit; 62. Second calculation unit; 63. Fourth processing unit; 64. Fifth processing unit; 800. Air cargo network hub site selection equipment; 801. Processor; 802. Memory; 803. Multimedia component; 804. I / O interface; 805. Communication component. DETAILED DESCRIPTION

[0013] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0014] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0015] Embodiment 1: See also Figure 1 , the figure shows that the method includes step S100, step S200, step S300, step S400, step S500 and step S600.

[0016] Step S100, obtaining first information, the first information including basic data of all city nodes in the freight network, the basic data including transportation distance data between city nodes and historical freight and mail throughput data of each city node; It is understandable that, firstly, the transportation distance data between city nodes is the basis for evaluating the cost and timeliness of goods circulation between each node in the logistics network. Accurate transportation distance data can help determine the optimal transportation route and method, thereby effectively reducing transportation costs. Secondly, historical cargo and mail throughput data reflects the freight demand and scale of logistics activities at each city node, and these data play an important role in predicting future demand.

[0017] Step S200: Perform forecasting based on historical cargo and mail throughput data, construct a grey forecasting model based on the original data and solve the model to obtain the future cargo and mail throughput of each city node; It is understandable that the grey forecasting model is a forecasting tool for processing incomplete information, and is particularly suitable for situations where the amount of data is small or the law of data change is unclear. In freight network planning, accurate forecasts of future cargo and mail throughput are essential for optimizing transportation routes and hub locations. The use of the grey forecasting model enables forecasting future demand even when historical data is limited, thereby providing data support for optimizing the layout of the transportation network.

[0018] Further, step S200 includes step S210 to step S240.

[0019] Step S210, performing accumulation processing according to the historical cargo and mail throughput data, and obtaining a cargo and mail throughput data sequence by accumulating the annual data year by year; It is understandable that through this accumulation process, long-term trends and overall changes can be better captured, which helps to accurately predict future cargo and mail volume. Specifically, first, the historical cargo and mail throughput data is used as the original data, which contains There are discrete data points representing the cargo and mail throughput at different points in time, as shown below: ; Next, these original data points are accumulated to generate a new accumulated data sequence: ; The calculation method of the accumulation processing is: ; in, Represents the original data; An index representing a time point; It represents the cargo and mail throughput in the first year; represents the cargo and mail throughput in the second year; represents the cargo and mail throughput in the third year; Represents a new data sequence obtained by accumulating the original data; represents the cumulative throughput of the first year; It represents the cumulative total throughput from the starting point to the second year; From the starting point to the Total annual throughput; Represents the total throughput from the starting point to the previous time point; Indicates Actual throughput data for the year.

[0020] Step S220: construct a model based on the cargo and mail throughput data sequence, and obtain a grey prediction model that expresses the data change trend by setting a differential equation of the model to describe the data generation law; Specifically, the basic form of the grey prediction model is: ; in, Indicates time; Indicates time The cumulative sequence value of ; It is the development coefficient in the grey model, indicating the growth trend of the data; Represents the gray contribution.

[0021] Step S230, performing a solution process according to the grey prediction model, obtaining model related parameters by analyzing and calculating related statistics of the data sequence, wherein the model related parameters include development coefficient and grey action amount; Preferably, the solution is performed by the least squares method: ; ; ; Then , Substituting into the differential equation yields the prediction model: ; in, Represents the grey prediction model for the future moment The predicted value of It is the development coefficient in the grey model, indicating the growth trend of the data; represents the gray action amount; An index representing a time point; represents the matrix of linear equations; represents the target vector; represents the cargo and mail throughput in the second year; represents the cargo and mail throughput in the third year; Indicates Annual cargo and mail throughput; represents the cumulative throughput of the first year; It represents the cumulative total throughput from the starting point to the second year; From the starting point to the Total annual throughput; From the starting point to the The total throughput for the year.

[0022] Step S240: perform prediction processing according to model-related parameters, calculate the cumulative prediction value of the future preset time period, and reduce the cumulative prediction value to obtain the future cargo and mail throughput.

[0023] Step S300: Calculate the attraction intensity result between cities according to the future cargo and mail throughput data, and allocate the freight volume between the city nodes based on the attraction intensity result to obtain the freight volume allocation result; Further, step S300 includes step S310 to step S340.

[0024] Step S310, obtaining the take-off and landing data of the city airport, the GDP data of the city where the airport is located, the permanent population data and the total retail sales data of social consumer goods, and combining them with the future cargo and mail throughput data to construct a scoring set; Step S320: Perform data correlation analysis and factor extraction processing based on the score set, confirm the data applicability by using KMO statistics and Bartlett's sphericity test, and obtain the main components; Step S330: construct a matrix based on the main components to obtain a component score coefficient matrix, and calculate the comprehensive service capability score of each airport based on the component score coefficient matrix; Step S340: Based on the comprehensive service capability scores of the airports in each city, a gravity model is constructed to calculate the intensity of freight attraction between cities. By combining the flight time and service capability scores between cities, the gravity formula is used to calculate the freight attraction between cities, and the freight volume between the nodes of each city is allocated based on the freight attraction to obtain the freight volume allocation result.

[0025] In a specific case, first, five indicators are selected as the comprehensive service level scoring indicators of the city airport, which are GDP, permanent population, future cargo and mail throughput data, take-off and landing flights, and total retail sales of consumer goods. Then, the premise of using the principal component analysis method for analysis is that the variables must be correlated, and the KMO statistic and Bartlett's sphericity test are used for judgment. Among them, the KMO statistic is 0.80711<0.9, and the Bartlett value is 210.013, which proves that the variables are correlated and factor analysis can be used for the evaluation of each city.

[0026] Furthermore, the variance explanation rate is used to evaluate the contribution of a factor to the explanation of the variable. Generally, the higher the variance explanation rate, the more important the principal component is and the larger its weight should be. According to the principle that the eigenvalue is greater than 1, two principal components can be extracted, namely component 1 and component 2, with corresponding eigenvalues ​​of 2.44 and 2.36. At the same time, the component score coefficient matrix can also be obtained, as shown in the following table: Table 1 Component score coefficient matrix

[0027] According to the component score coefficient matrix, the comprehensive service level score of each city airport node can be calculated. ; ; ; in, , Represent the score values ​​of the two components respectively; Represents the comprehensive service capability score of each city airport; , , , , It represents five evaluation indicators, namely GDP, permanent population, freight volume, take-off and landing times, and total retail sales of consumer goods.

[0028] Finally, the comprehensive service capability score of each city airport is obtained.

[0029] Furthermore, a gravity model is constructed based on the comprehensive service capability evaluation of each city airport, and the formula is: ; ; in, and Indicates the serial number of the airport node; express Node and The degree of connection between nodes; express The airport’s comprehensive service capability score; express The airport’s comprehensive service capability score; Indicates the total number of airports; express Node and the strength of attraction between nodes; Representation Node With Node The transportation time between Representation Node The degree of connection, that is When fixed, each node The connection degree value of the point.

[0030] Therefore, through the gravity model, the attraction intensity between cities is calculated to determine the trend of freight volume and allocate the freight volume.

[0031] Step S400: Performing transportation cost analysis based on the freight volume allocation result and the transportation distance data, and obtaining the transportation mode analysis result by determining the optimal road-air transportation combination mode between nodes; Further, step S400 includes step S410 to step S430.

[0032] Step S410, perform data fusion processing according to the freight distribution results and the transportation distance data, by constructing a data matrix, in which each row represents a freight connection, and the columns include the starting point, the end point, the expected freight volume and the corresponding transportation distance, to a fused data set; Understandably, such a data matrix helps to systematically analyze the cost-effectiveness of each transportation route, evaluate the costs of different modes of transportation, and conduct more accurate cost and resource optimization.

[0033] Step S420: cost calculation is performed based on the fused data set. By applying a linear cost model and combining the unit costs of road transport and air transport, the basic transport cost of each freight connection is calculated to obtain a preliminary transport cost. The preliminary transport cost includes a preliminary freight connection mode and a corresponding economic evaluation result. It should be noted that this step can comprehensively evaluate the economic feasibility of each freight connection by considering different transport modes and unit costs, thereby supporting more reasonable transportation network design and resource allocation.

[0034] Step S430: Optimize and analyze the preliminary transportation cost, and use a linear programming algorithm to process the cost efficiency, transportation time, and load limit of each freight connection to obtain a transportation mode analysis result for each freight connection.

[0035] It should be noted that linear programming is an optimization technique used to optimize a linear objective function under certain constraints. In this step, the linear programming algorithm is used to find the optimal combination of transportation modes to minimize transportation costs and other related indicators.

[0036] Step S500: construct a model based on the analysis results of the transportation mode, and establish a hub location model with the minimum total cost as the goal by combining hub construction cost, loading and unloading cost and transportation cost; Further, step S500 includes step S510 to step S540.

[0037] Step S510: According to the analysis result of the transportation mode, the distance between nodes and the future cargo and mail throughput data are integrated and processed to obtain a basic data set; Step S520: Perform direct transportation cost evaluation processing according to the transportation mode and inter-node distance data in the basic data set, and calculate the basic cost from any node to another node under the selected transportation mode by combining the cost characteristics of different transportation modes to obtain the direct transportation cost evaluation result; Step S530: Calculate transshipment and hub-related costs based on the transport mode and direct transport cost evaluation results in the basic data, and obtain transshipment and hub-related costs by analyzing the standard cost of hub operations and the scale effect generated by hub aggregation; Step S540: construct a model based on the direct transportation cost evaluation results and the transshipment and hub-related costs, and obtain a hub location model by setting the objective function and constraint conditions.

[0038] First, the air-highway freight network is a directed network including hubs and non-hub points. In this freight network, when transporting goods from a supply node to another demand node, they will be transferred through hub nodes during transportation. There are two modes of transportation, road and air, between the transportation paths between nodes. Different transportation costs are generated when different modes of transportation are used for transportation. Since road transportation has a cost advantage over short distances, when the transportation distance between any two node cities is within a certain numerical range, road transportation is used. Long-distance transportation beyond this range and between hubs use air transportation. Therefore, the road transportation part can be regarded as branch line transportation, and the air freight part can be regarded as "trunk line transportation". This value is usually 500 kilometers and can be set in the system as needed. During the transportation process, the goods may have to transit through the hub. The site selection research of the air-highway freight network hub is extremely critical to reducing the logistics costs of the transportation network. Selecting a suitable node as the hub in the logistics network is an important issue that needs to be studied. In order to better construct the model, the following assumptions are made: In the entire freight network, each city is regarded as a node in the network, and all city nodes are divided into hub nodes and non-hub nodes; When goods are transported in a hub network, considering the timeliness of the transportation process, the transfer between nodes can only be carried out through the hub point, and the entire network undergoes at most two transfers. Therefore, there are three ways to connect between nodes: direct transportation between two nodes, one transfer through a hub point, and two transfers through a hub point; When goods are transferred through hub nodes, the cost will be reduced to a certain extent due to the scale effect of the hub network, and a discount coefficient will be introduced. To express the cost discount between hubs due to scale effects, and assume that the discount coefficient is a constant and is not affected by other factors; Taking into account that the airport's cargo and mail throughput will not reach the airport's saturation capacity in a short period of time, there are no capacity restrictions on the nodes and transportation routes in the entire transportation network, and the freight capacity can meet the transportation needs.

[0039] Based on the above assumptions and data processing, the hub location model is constructed as follows: The objective function is: ; ; ; ; The constraints are: ； ; ; ; ; ; in, Represents the set of all nodes in the network; represents the hub node set, ; , , , Indicates the node's sequence number; represents the total cost; represents the transportation cost; represents the hub construction cost; represents the cost of transshipment; It represents the unit economic cost of road transport (yuan / ton × 100 kilometers); It represents the unit economic cost of air transport (yuan / ton × 100 kilometers); represents the unit loading and unloading cost of transshipment at the hub point; Representation Node To Node road transport costs; Representation Node To Node road transport costs; Representation Node To Node road transport costs; Representation Node To Node Air transport costs; Representation Node To Node Air transport costs; Representation Node To Node The cost of air transportation; Representation Node To Node Air transport costs; Representation Node To Node Freight volume (tons); Representation Node To Node Distance (km); Representation Node To Node The road transport cost, ; Representation Node To Node Air transport costs; ; Representation Node To Node The cost of loading and unloading for transshipment at hubs; The discount factor that represents the reduction in transportation costs due to economies of scale in transportation between hubs; Represents a hub node construction costs; is a binary variable, when the node To Node It is equal to 1 when road transport is adopted, otherwise it is equal to 0; is a binary variable, when the node To Node It is equal to 1 when road transport is adopted, otherwise it is equal to 0; is a binary variable, when the node To Node It is equal to 1 when road transport is adopted, otherwise it is equal to 0; is a binary variable, when the node To Node It is equal to 1 when road transport is adopted, otherwise it is equal to 0; is a binary variable, when the node To Node It is equal to 1 when air transport is adopted, otherwise it is equal to 0; is a binary variable, when the node To Node It is equal to 1 when air transport is adopted, otherwise it is equal to 0; is a binary variable, when the node To Node It is equal to 1 when air transport is adopted, otherwise it is equal to 0; is a binary variable, when the node To Node It is equal to 1 when air transport is adopted, otherwise it is equal to 0; is a binary variable, when the node To Node It is equal to 1 when air transport is adopted, otherwise it is equal to 0; is a binary variable, when the node To Node The demand is at the hub node It is equal to 1 when the transfer is in progress, otherwise it is equal to 0; is a binary variable, when the node To Node The demand is at the hub node , It is equal to 1 when the transfer is in progress, otherwise it is equal to 0; It is at the node shared costs of building the hub; is a binary variable, at the node It is 1 when it is a construction hub, otherwise it is 0; Indicates the total number of hub nodes built in the entire network.

[0040] Step S600: Optimize the hub site selection model by iteratively optimizing the location and number of hub points using an immune genetic algorithm to obtain an optimal hub configuration solution that minimizes the total network cost.

[0041] It can be understood that this step solves the hub location model by using the immune genetic algorithm, which is an evolutionary algorithm that combines the genetic algorithm with the immune system theory. It uses concepts in immunology, such as antibodies, antigens, immunity, etc., combined with selection, inheritance, mutation, etc. in the genetic algorithm to enhance the diversity and global search capabilities of the algorithm. The immune genetic algorithm is used to optimize the hub location. The algorithm combines the global search capability of the genetic algorithm and the diversity maintenance mechanism of the immune algorithm, which can better avoid local optimal solutions and improve the global optimality and stability of the hub location scheme.

[0042] Further, step S600 includes step S610 to step S640.

[0043] Step S610: Based on the hub site selection model, initial candidate nodes are screened from the candidate hub node set, and the selection of each initial candidate node is integer-encoded to obtain an initial population. The gene position of each chromosome in the initial population indicates whether a node is selected as a hub; It should be noted that this step selects candidate nodes that may serve as hub nodes from a larger set of nodes, and represents the selection of each initial candidate node by integer coding. By encoding and forming the initial population, different hub configuration schemes are fully explored, providing a variety of initial solutions for the subsequent optimization process.

[0044] Step S620: construct a fitness function according to the objective function of the hub location model, calculate the direct transportation cost, hub transfer cost and hub construction cost under the hub configuration represented by the chromosome in each initial population, and evaluate the diversity of the antibody population to obtain the fitness value; It is understandable that direct transportation costs and hub transit costs reflect the actual costs in the transportation and transit process, while hub construction costs involve the costs of establishing and maintaining hubs. The fitness function combines these costs to evaluate the economic benefits of each configuration scheme. Next, the diversity evaluation of the antibody population is carried out, including calculating the fitness value of each individual and determining the reproduction probability based on the fitness value and antibody concentration. In this way, individuals with high fitness values ​​can be retained and the diversity of the population can be ensured, thereby avoiding the algorithm from falling into a local optimal solution and increasing the possibility of finding a global optimal solution. This step not only optimizes the accuracy of fitness calculation, but also improves the diversity and optimization efficiency of the population in the genetic process.

[0045] Step S630: Based on the roulette wheel selection method, chromosomes are selected for genetic operation according to the fitness value, and a new generation of population is obtained by continuously approaching the global optimal solution while maintaining the elite solution; It should be noted that roulette wheel selection is a probabilistic selection mechanism in which the selection probability of each chromosome is proportional to its fitness value, aiming to increase the probability of selection of chromosomes with high fitness values ​​(i.e., configurations with lower costs). In this way, chromosomes with better fitness are retained and a new generation of population is generated. This process ensures that the elite solution, that is, the individuals with the best fitness, is retained and their excellent characteristics are passed on to the next generation. At the same time, the roulette wheel selection method continuously introduces individuals with better fitness and further explores the solution space through genetic operations (such as crossover and mutation), thereby gradually approaching the global optimal solution. The method in this step not only retains the current optimal solution, but also promotes the global search ability of the population and increases the possibility of finding the optimal solution.

[0046] Step S640: save the individuals in the new generation population whose fitness is higher than the preset threshold into the memory bank, generate a new population based on the current population and the individuals in the memory bank, and gradually optimize the solution through continuous iteration until the preset number of iterations is reached to obtain the optimal solution, and obtain the optimal hub configuration solution based on the optimal solution.

[0047] Embodiment 2: like Figure 2 As shown, this embodiment provides an air cargo network hub site selection device, the device comprising: Acquisition module 1, acquiring first information, the first information including basic data of all city nodes in the freight network, the basic data including transportation distance data between city nodes and historical cargo and mail throughput data of each city node; Prediction module 2 is used to perform prediction processing based on historical cargo and mail throughput data, and obtain the future cargo and mail throughput of each city node by constructing a grey prediction model based on the original data and solving the model; Allocation module 3, used to calculate the attraction intensity result between cities according to the future cargo and mail throughput, and allocate the freight volume between the city nodes based on the attraction intensity result to obtain the freight volume allocation result; Analysis module 4, used to perform transportation cost analysis based on the freight volume allocation results and transportation distance data, and obtain transportation mode analysis results by determining the optimal road-air transportation combination mode between nodes; Modeling module 5, used for model building processing according to the results of transportation mode analysis, and establishing a hub location model with the minimum total cost as the goal by combining hub construction cost, loading and unloading cost and transportation cost; The optimization module 6 is used to perform optimization processing according to the hub location selection model, and iteratively optimize the location and number of hub points by using the immune genetic algorithm to obtain the optimal hub configuration plan that minimizes the total network cost.

[0048] In a specific embodiment disclosed in the present invention, the prediction module 2 includes: The first processing unit 21 is used to perform accumulation processing according to the historical cargo and mail throughput data, and obtain a cargo and mail throughput data sequence by accumulating the annual data year by year; The first construction unit 22 is used to perform model construction processing according to the cargo and mail throughput data sequence, and to obtain a grey prediction model that expresses the data change trend by setting a differential equation of the model to describe the data generation law; The second processing unit 23 is used to perform solution processing according to the grey prediction model, and obtain model related parameters by analyzing and calculating relevant statistics of the data sequence, and the model related parameters include development coefficient and grey action amount; The first prediction unit 24 is used to perform prediction processing according to model related parameters, calculate the cumulative prediction value of the future preset time period, and reduce the cumulative prediction value to obtain the future cargo and mail throughput.

[0049] In a specific embodiment disclosed in the present invention, the allocation module 3 includes: The first integration unit 31 is used to obtain the take-off and landing data of the city airport, the GDP data of the city where the airport is located, the permanent population data and the total retail sales data of social consumer goods, and construct a scoring set in combination with the future cargo and mail throughput data; A first analysis unit 32 is used to perform data correlation analysis and factor extraction processing according to the score set, and obtain the main components by confirming the data suitability by using KMO statistics and Bartlett's sphericity test; A second construction unit 33 is used to construct a matrix according to the main components to obtain a component score coefficient matrix, and calculate the comprehensive service capability score of each airport based on the component score coefficient matrix; The third construction unit 34 is used to construct a gravity model to calculate the freight attraction intensity between cities based on the comprehensive service capability score of each city airport, and to calculate the freight attraction between cities using the gravity formula by combining the flight time and service capability score between cities, and to allocate the freight volume between each city node based on the freight attraction to obtain the freight volume allocation result.

[0050] In a specific embodiment disclosed in the present invention, the analysis module 4 includes: A first fusion unit 41 is used to perform data fusion processing according to the freight distribution results and the transportation distance data, by constructing a data matrix, in which each row represents a freight connection, and the columns include the starting point, the end point, the expected freight volume and the corresponding transportation distance, to a fused data set; The third processing unit 42 is used to perform cost calculation processing according to the fused data set, by applying a linear cost model, combining the unit costs of road transportation and air transportation, and calculating the basic transportation cost of each freight connection to obtain a preliminary transportation cost, wherein the preliminary transportation cost includes a preliminary freight connection mode and a corresponding economic evaluation result; The first optimization unit 43 is used to perform optimization analysis based on the preliminary transportation cost, and obtain the transportation mode analysis result of each freight connection by processing the cost efficiency, transportation time and load limit of each freight connection using a linear programming algorithm.

[0051] In a specific embodiment disclosed in the present invention, the modeling module 5 includes: The second analysis unit 51 is used to integrate and process the analysis results of the transportation mode, the distance between nodes and the future cargo and mail throughput data to obtain a basic data set; The first evaluation unit 52 is used to perform direct transportation cost evaluation processing according to the transportation mode and inter-node distance data in the basic data set, and calculate the basic cost from any node to another node under the selected transportation mode by combining the cost characteristics of different transportation modes to obtain the direct transportation cost evaluation result; The first calculation unit 53 is used to calculate the transshipment and hub-related costs according to the transport mode and direct transport cost evaluation results in the basic data, and obtain the transshipment and hub-related costs by analyzing the standard cost of hub operation and the scale effect generated by hub aggregation; The fourth construction unit 54 is used to construct a model based on the direct transportation cost evaluation results and the transshipment and hub-related costs, and obtain the hub location model by setting the objective function and constraint conditions.

[0052] In a specific embodiment disclosed in the present invention, the optimization module 6 includes: The first screening unit 61 screens initial candidate nodes from the candidate hub node set based on the hub site selection model, and integer encodes the selection of each initial candidate node to obtain an initial population, wherein the gene position of each chromosome in the initial population indicates whether a node is selected as a hub; The second calculation unit 62 is used to construct a fitness function according to the objective function of the hub location model, calculate the direct transportation cost, hub transfer cost and hub construction cost under the hub configuration represented by the chromosome in each initial population, and evaluate the diversity of the antibody population to obtain the fitness value; The fourth processing unit 63 selects chromosomes for genetic operation based on the fitness value based on the roulette wheel selection method, and obtains a new generation of population by continuously approaching the global optimal solution while maintaining the elite solution; The fifth processing unit 64 is used to save the individuals in the new generation population whose fitness is higher than a preset threshold into the memory bank, generate a new population based on the current population and the individuals in the memory bank, and gradually optimize the solution through continuous iteration until the preset number of iterations is reached to obtain the optimal solution, and obtain the optimal hub configuration solution based on the optimal solution.

[0053] Embodiment 3: Figure 3 FIG. 8 is a block diagram of an air cargo network hub site selection device 800 according to an exemplary embodiment. Figure 3 As shown, the air cargo network hub site selection device 800 may include: a processor 801 and a memory 802. The air cargo network hub site selection device 800 may also include one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0054] The processor 801 is used to control the overall operation of the air cargo network hub site selection device 800 to complete all or part of the steps in the above-mentioned air cargo network hub site selection method. The memory 802 is used to store various types of data to support the operation of the air cargo network hub site selection device 800, and these data may include, for example, instructions for any application or method operated on the air cargo network hub site selection device 800, and application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, disk or optical disk. The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 802 or sent via the communication component 805. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 804 provides an interface between the processor 801 and other interface modules, and the above-mentioned other interface modules can be keyboards, mice, buttons, etc. These buttons can be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the air cargo network hub site selection device 800 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 805 can include: Wi-Fi module, Bluetooth module, NFC module.

[0055] In an exemplary embodiment, the air cargo network hub site selection device 800 can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned air cargo network hub site selection method.

[0056] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned air cargo network hub site selection method are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 802 including program instructions, and the above-mentioned program instructions can be executed by the processor 801 of the air cargo network hub site selection device 800 to complete the above-mentioned air cargo network hub site selection method.

[0057] Embodiment 4: Corresponding to the above method embodiment, a readable storage medium is also provided in this embodiment. The readable storage medium described below and the air cargo network hub site selection method described above can refer to each other.

[0058] A readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the air cargo network hub site selection method of the above method embodiment.

[0059] The readable storage medium may specifically be a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or other readable storage medium that can store program codes.

[0060] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0061] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for selecting a hub site for an air cargo network, characterized in that: include: Acquire first information, wherein the first information includes basic data of all city nodes in the freight network, wherein the basic data includes transportation distance data between city nodes and historical freight and mail throughput data of each city node; Performing forecasting processing based on the historical cargo and mail throughput data, by constructing a grey forecasting model based on the original data and solving the model, obtaining the future cargo and mail throughput of each city node; Calculating the attraction intensity result between cities according to the future cargo and mail throughput, and allocating the freight volume between the city nodes based on the attraction intensity result to obtain the freight volume allocation result; Performing a transportation cost analysis process based on the freight volume allocation result and the transportation distance data, and obtaining a transportation mode analysis result by determining the optimal road-air transportation combination mode between nodes; Model building is performed based on the analysis results of the transportation mode, and a hub location model with minimum total cost as the goal is established by combining hub construction cost, loading and unloading cost and transportation cost; The hub location selection model is optimized by using an immune genetic algorithm to iteratively optimize the location and number of hubs to obtain the optimal hub configuration solution that minimizes the total network cost.

2. The method for selecting a hub for an air cargo network according to claim 1, characterized in that: According to the historical cargo and mail throughput data, forecasting is performed, by constructing a grey forecasting model based on the original data and solving the model, the future cargo and mail throughput of each city node is obtained, including: Performing accumulation processing according to the historical cargo and mail throughput data, and obtaining a cargo and mail throughput data sequence by accumulating the annual data year by year; A model is constructed based on the cargo and mail throughput data sequence, and a grey prediction model expressing the data change trend is obtained by setting a differential equation of the model to describe the data generation law; Solving the grey prediction model, obtaining model-related parameters by analyzing and calculating relevant statistics of the data sequence, wherein the model-related parameters include development coefficient and grey action amount; Prediction processing is performed according to the relevant parameters of the model, by calculating the cumulative prediction value of the future preset time period, and reducing the cumulative prediction value to obtain the future cargo and mail throughput.

3. The method for selecting a hub for an air cargo network according to claim 1, characterized in that: The model is constructed based on the analysis results of the transportation mode, and a hub location model with the minimum total cost as the goal is established by combining the hub construction cost, loading and unloading cost and transportation cost, including: According to the analysis results of the transportation mode, the distance between nodes and the future cargo and mail throughput data are integrated and processed to obtain a basic data set; Performing direct transportation cost evaluation processing according to the transportation mode and node distance data in the basic data set, and calculating the basic cost from any node to another node under the selected transportation mode by combining the cost characteristics of different transportation modes to obtain a direct transportation cost evaluation result; Calculate transshipment and hub-related costs based on the transportation modes in the basic data and the direct transportation cost assessment results, and obtain transshipment and hub-related costs by analyzing the standard costs of hub operations and the scale effect generated by hub aggregation; A model is constructed based on the direct transportation cost evaluation results and the transshipment and hub-related costs, and a hub location model is obtained by setting an objective function and constraint conditions.

4. The method for selecting a hub for an air cargo network according to claim 1, characterized in that: According to the hub location model, optimization processing is performed, and the location and number of hub points are iteratively optimized using an immune genetic algorithm to obtain the optimal hub configuration solution that minimizes the total network cost, including: Based on the hub site selection model, initial candidate nodes are screened from the candidate hub node set, and the selection of each of the initial candidate nodes is integer-encoded to obtain an initial population, wherein the gene position of each chromosome in the initial population indicates whether a node is selected as a hub; Constructing a fitness function according to the objective function of the hub location model, calculating the direct transportation cost, hub transfer cost and hub construction cost under the hub configuration represented by the chromosome in each of the initial populations, and evaluating the diversity of the antibody population to obtain a fitness value; Based on the roulette wheel selection method, chromosomes are selected for genetic operation according to the fitness value, and a new generation of population is obtained by continuously approaching the global optimal solution while maintaining the elite solution; The individuals in the new generation population whose fitness is higher than a preset threshold are saved in the memory bank, and a new population is generated based on the current population and the individuals in the memory bank. Through continuous iteration, the solution is gradually optimized until the preset number of iterations is reached to obtain the optimal solution, and the optimal hub configuration solution is obtained based on the optimal solution.

5. An air cargo network hub site selection device, characterized in that: include: An acquisition module, acquiring first information, wherein the first information includes basic data of all city nodes in the freight network, wherein the basic data includes transportation distance data between city nodes and historical freight and mail throughput data of each city node; A prediction module is used to perform prediction processing based on the historical cargo and mail throughput data, and obtain the future cargo and mail throughput of each city node by constructing a grey prediction model based on the original data and solving the model; An allocation module, used to calculate the attraction intensity result between cities according to the future cargo and mail throughput, and allocate the freight volume between the city nodes based on the attraction intensity result to obtain the freight volume allocation result; An analysis module, used to perform transportation cost analysis based on the freight volume allocation result and the transportation distance data, and obtain a transportation mode analysis result by determining the optimal road-air transportation combination mode between nodes; A modeling module, used for constructing a model according to the analysis results of the transportation mode, and establishing a hub location model with the minimum total cost as the goal by combining hub construction cost, loading and unloading cost and transportation cost; The optimization module is used to perform optimization processing according to the hub site selection model, and iteratively optimize the location and number of hub points by using an immune genetic algorithm to obtain the optimal hub configuration plan that minimizes the total network cost.

6. The air cargo network hub site selection device according to claim 5, characterized in that: The prediction module comprises: A first processing unit is used to perform accumulation processing according to the historical cargo and mail throughput data, and obtain a cargo and mail throughput data sequence by accumulating the annual data year by year; A first construction unit is used to perform model construction processing according to the cargo and mail throughput data sequence, and to obtain a grey prediction model expressing the data change trend by setting a differential equation of the model to describe the data generation law; A second processing unit is used to perform a solution process according to the grey prediction model, and obtain model related parameters by analyzing and calculating relevant statistics of the data sequence, wherein the model related parameters include a development coefficient and a grey action amount; The first prediction unit is used to perform prediction processing according to the relevant parameters of the model, calculate the cumulative prediction value of the future preset time period, and reduce the cumulative prediction value to obtain the future cargo and mail throughput.

7. The air cargo network hub site selection device according to claim 5, characterized in that: The modeling module includes: A second analysis unit is used to integrate and process the analysis results of the transportation mode, the distance between nodes and the future cargo and mail throughput data to obtain a basic data set; A first evaluation unit is used to perform direct transportation cost evaluation processing according to the transportation mode and inter-node distance data in the basic data set, and calculate the basic cost from any node to another node under the selected transportation mode by combining the cost characteristics of different transportation modes to obtain a direct transportation cost evaluation result; A first calculation unit is used to calculate transshipment and hub-related costs according to the transportation mode in the basic data and the direct transportation cost evaluation result, and obtain transshipment and hub-related costs by analyzing the standard cost of hub operation and the scale effect generated by hub aggregation; The fourth construction unit is used to perform model construction processing according to the direct transportation cost evaluation result and the transshipment and hub-related costs, and obtain the hub location model by setting the objective function and constraint conditions.

8. The air cargo network hub site selection device according to claim 5, characterized in that: The optimization module includes: A first screening unit, based on the hub site selection model, screens initial candidate nodes from the candidate hub node set, integer encodes the selection of each of the initial candidate nodes to obtain an initial population, wherein the gene position of each chromosome in the initial population indicates whether a node is selected as a hub; The second calculation unit is used to construct a fitness function according to the objective function of the hub location model, calculate the direct transportation cost, hub transfer cost and hub construction cost under the hub configuration represented by the chromosome in each of the initial populations, and evaluate the diversity of the antibody population to obtain a fitness value; A fourth processing unit, based on a roulette wheel selection method, selects chromosomes for genetic operation according to the fitness value, and obtains a new generation of population by continuously approaching the global optimal solution while maintaining the elite solution; The fifth processing unit is used to save the individuals in the new generation population whose fitness is higher than a preset threshold into a memory bank, generate a new population based on the current population and the individuals in the memory bank, and gradually optimize the solution through continuous iteration until the preset number of iterations is reached to obtain the optimal solution, and obtain the optimal hub configuration solution based on the optimal solution.

9. An air cargo network hub site selection device, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the steps of the method for selecting a location for an air cargo network hub as claimed in any one of claims 1 to 4 when executing the computer program.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the method for selecting a site for an air cargo network hub as claimed in any one of claims 1 to 4.

Images