Method and device for reconstructing logistics network, electronic equipment and storage medium

Abstract

The application relates to the technical field of logistics network reconstruction, and discloses a logistics network reconstruction method and device, an electronic device and a storage medium, wherein the method comprises the following steps: constructing a space-time heat map based on relevant geopolitical events; constructing a port layer penetration model, an airspace layer penetration model and a land layer penetration model, and performing cascading to generate a combined model and convert the combined model into a mixed integer linear programming model; and solving the model by using a preset cascading analysis solving algorithm to obtain a reconstruction scheme. The application has the beneficial effects that: by constructing the space-time heat map and the penetration model, the interconnection between the layers can quickly evaluate and adjust the transportation scheme when an event occurs, the stability and efficiency of the supply chain are ensured, the optimization capability of the mixed integer linear programming is utilized, the feasibility and efficiency of the reconstruction scheme are improved, a scientific and data-driven strategy selection is provided for decision makers, and the adaptability and pressure resistance of the global logistics network are enhanced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of logistics network reconstruction, and particularly relates to a logistics network reconstruction method and device, an electronic device and a storage medium. BACKGROUND

[0002] Traditional logistics management models usually rely on historical data and fixed statistical analysis, and cannot timely reflect the immediate impact of sudden geopolitical events. Unable to face unexpected situations, it leads to the collapse of the logistics network and the waste of resources. For example, when a conflict breaks out in a certain region, the relevant transportation routes may be blocked, and the uncertainty and real-time requirements of alternative paths make it difficult for traditional models to respond efficiently. This not only affects the efficiency of goods transportation, but also increases labor costs and operational risks. In addition, traditional methods cannot fully consider unstructured information such as political risks and market sentiment when dealing with complex international relations, leading to one-sided and lagging decisions. SUMMARY

[0003] Therefore, it is necessary to propose a logistics network reconstruction method, device, electronic device and storage medium for the existing logistics network reconstruction problem.

[0004] A logistics network reconstruction method, the method comprising:

[0005] Real-time detection of whether there is a related geopolitical event in the current logistics network, and real-time acquisition of data sets in three preset dimensions of sea, land and air;

[0006] If the related geopolitical event exists, a space-time heat map is constructed based on the related geopolitical event;

[0007] Based on the data sets of each of the preset dimensions and the space-time heat map, a port layer penetration model, an airspace layer penetration model and a land layer penetration model are constructed respectively;

[0008] Cascade the port layer penetration model, the airspace layer penetration model and the land layer penetration model to generate a combined model;

[0009] Convert the combined model into a mixed integer linear programming model;

[0010] Solve the mixed integer linear programming model by a preset cascade analysis solving algorithm to obtain a reconstruction scheme.

[0011] Further, if the related geopolitical event exists, the step of constructing a space-time heat map based on the related geopolitical event comprises:

[0012] Extracting key elements of the related geopolitical event through a named entity recognition model;

[0013] obtain a plurality of target dimension data based on the key elements, to obtain a target dimension data set;

[0014] score the target dimension data set by a preset multi-dimensional evaluation model, to obtain a heat value corresponding to the key elements;

[0015] construct the spatio-temporal heat map based on the key elements and the heat value.

[0016] Further, before the step of scoring the target dimension data set by a preset multi-dimensional evaluation model to obtain a heat value corresponding to the key elements, the method further comprises:

[0017] obtain an association value of the relevant geopolitical event and each target dimension in the preset multi-dimensional evaluation model;

[0018] set a scoring weight of each target dimension of the multi-dimensional evaluation model according to the association value.

[0019] Further, the step of solving the mixed integer linear programming model by a preset cascade analysis algorithm to obtain a reconstruction scheme comprises:

[0020] output a Pareto solution set based on the mixed integer linear programming model;

[0021] chromosome encode the schemes in the Pareto solution set, to obtain a first chromosome set;

[0022] perform a crossover mutation operation on the first chromosome set to obtain a second chromosome set;

[0023] combine the second chromosome set with the first chromosome set to generate a third chromosome set;

[0024] repeat the target step and the steps after the target step, taking the third chromosome set as the first chromosome set, until the number of chromosomes in the third chromosome set is greater than or equal to a preset number; the target step is the step of performing a crossover mutation operation on the first chromosome set to obtain a second chromosome set;

[0025] record the third chromosome set with a number of chromosomes greater than or equal to the preset number as a target third chromosome set;

[0026] calculate the fitness value of each chromosome in the target third chromosome set by a preset fitness calculation function;

[0027] select the chromosome with the highest fitness value as the reconstruction scheme.

[0028] Further, before the step of outputting a Pareto solution set based on the mixed integer linear programming model, the method further comprises:

[0029] acquiring constraints;

[0030] inputting the constraints into the mixed integer linear programming model to obtain a first target mixed integer linear programming model; wherein the first target mixed integer linear programming model is used to output a Pareto solution set.

[0031] Further, before the step of outputting the Pareto solution set based on the mixed integer linear programming model, the method further comprises:

[0032] setting a target function;

[0033] inputting the target function into the mixed integer linear programming model to obtain a second target mixed integer linear programming model; wherein the second target mixed integer linear programming model is used to output a Pareto solution set.

[0034] Further, before the steps of detecting in real time whether there is a relevant geopolitical event in the current logistics network and acquiring in real time a data set of three preset dimensions of sea, land and air, the method further comprises:

[0035] obtaining original data of each database through a distributed crawler cluster;

[0036] parsing the original data through a multilingual bill of lading parsing engine constructed by an XLM-RoBERTa model to obtain a geopolitical event set; wherein the geopolitical event set is used to detect whether there is the relevant geopolitical event.

[0037] A logistics network reconstruction device, the device comprising:

[0038] a detection module configured to detect in real time whether there is a relevant geopolitical event in the current logistics network and acquire in real time a data set of three preset dimensions of sea, land and air;

[0039] a first construction module configured to, if there is the relevant geopolitical event, construct a space-time heat map based on the relevant geopolitical event;

[0040] a second construction module configured to construct a port layer penetration model, an airspace layer penetration model and a land layer penetration model based on the data set of each of the preset dimensions and the space-time heat map respectively;

[0041] a cascading module configured to cascade the port layer penetration model, the airspace layer penetration model and the land layer penetration model to generate a combined model;

[0042] a conversion module configured to convert the combined model into a mixed integer linear programming model;

[0043] A calculation module is configured to solve the mixed integer linear programming model by a preset cascade analysis solution algorithm to obtain a reconstruction scheme.

[0044] An electronic device comprises a memory and a processor, the memory stores a computer program, and the computer program is executed by the processor to make the processor execute the following steps:

[0045] Real-time detection of whether there is a relevant geopolitical event in the current logistics network, and real-time acquisition of data sets in three preset dimensions of sea, land and air;

[0046] If the relevant geopolitical event exists, a space-time heat map is constructed based on the relevant geopolitical event;

[0047] Based on the data set of each preset dimension and the space-time heat map, a port layer penetration model, an airspace layer penetration model and a land layer penetration model are constructed respectively;

[0048] Cascade the port layer penetration model, the airspace layer penetration model and the land layer penetration model to generate a combined model;

[0049] Convert the combined model into a mixed integer linear programming model;

[0050] Solve the mixed integer linear programming model by a preset cascade analysis solution algorithm to obtain a reconstruction scheme.

[0051] A computer readable storage medium stores a computer program, and the computer program is executed by a processor to make the processor execute the following steps:

[0052] Real-time detection of whether there is a relevant geopolitical event in the current logistics network, and real-time acquisition of data sets in three preset dimensions of sea, land and air;

[0053] If the relevant geopolitical event exists, a space-time heat map is constructed based on the relevant geopolitical event;

[0054] Based on the data set of each preset dimension and the space-time heat map, a port layer penetration model, an airspace layer penetration model and a land layer penetration model are constructed respectively;

[0055] Cascade the port layer penetration model, the airspace layer penetration model and the land layer penetration model to generate a combined model;

[0056] Convert the combined model into a mixed integer linear programming model;

[0057] Solve the mixed integer linear programming model by a preset cascade analysis solution algorithm to obtain a reconstruction scheme.

[0058] The application has the advantages that by constructing the space-time thermal diagram and the penetration model, the interconnection between the levels can quickly evaluate and adjust the transportation scheme when the event occurs, ensure the stability and efficiency of the supply chain, improve the feasibility and efficiency of the reconstruction scheme by using the optimization ability of the mixed integer linear programming, provide the decision maker with scientific and data-driven strategy selection, and enhance the adaptability and pressure resistance of the global logistics network. BRIEF DESCRIPTION OF DRAWINGS

[0059] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description only represent some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0060] In the formula, the variables are as follows:

[0061] Figure 1 It is an application environment diagram of the logistics network reconstruction method in one embodiment.

[0062] Figure 2 It is a flowchart of the logistics network reconstruction method in one embodiment.

[0063] Figure 3 It is a structural block diagram of the logistics network reconstruction device in one embodiment.

[0064] Figure 4 It is a structural block diagram of the electronic device in one embodiment. DETAILED DESCRIPTION

[0065] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments only represent some embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0066] Figure 1 It is an application environment diagram of the logistics network reconstruction in one embodiment. Refer to Figure 1The logistics network reconstruction method is applied to a logistics network reconstruction system. The logistics network reconstruction system comprises a terminal 110 and a server 120. The terminal 110 and the server 120 are connected through a network. The terminal 110 can be a desktop terminal or a mobile terminal, and the mobile terminal can be at least one of a mobile phone, a tablet computer, a notebook computer, etc. The server 120 can be implemented by an independent server or a server cluster composed of multiple servers. The terminal 110 is used to obtain relevant geopolitical events, and the server 120 is used to generate a reconstruction scheme of a logistics network.

[0067] As shown in Figure 2 In one embodiment, a logistics network reconstruction method is provided. The method can be applied to a terminal or a server. In this embodiment, the method is exemplified by being applied to a terminal. The logistics network reconstruction method specifically comprises the following steps:

[0068] S1: Real-time detection of whether there is a relevant geopolitical event in the current logistics network, and real-time acquisition of data sets in three preset dimensions of sea, land and air;

[0069] S2: If the relevant geopolitical event exists, a space-time heat map is constructed based on the relevant geopolitical event;

[0070] S3: Based on the data sets of each of the preset dimensions and the space-time heat map, a port layer penetration model, an airspace layer penetration model and a land layer penetration model are constructed respectively;

[0071] S4: The port layer penetration model, the airspace layer penetration model and the land layer penetration model are cascaded to generate a combined model;

[0072] S5: The combined model is converted into a mixed integer linear programming model;

[0073] S6: The mixed integer linear programming model is solved by a preset cascade analysis solving algorithm to obtain a reconstruction scheme.

[0074] As described in step S1 above, it is detected in real time whether there is a relevant geopolitical event in the current logistics network, and data sets in three preset dimensions of sea, land and air are obtained in real time. Specifically, a multi-source data access system needs to be built to identify and confirm the occurrence of geopolitical events through various information channels (such as social media monitoring, news analysis, government reports, etc.), including monitoring of conflicts, sanctions, changes in trade policies, etc. At the same time, the system also needs to continuously obtain data sets in three preset dimensions of sea, land and air related to logistics. The data set in the preset dimension of sea includes shipping data (such as ship AIS signal), ship waiting time and crane operation efficiency, the data set in the preset dimension of land includes border crossing efficiency, average truck detention time at border port and real-time GPS data, etc., the data set in the preset dimension of air includes air traffic data, ADS-B signal and NOTAM flight notice, no-fly zone expansion path, etc., in addition, each data set can also include related climate, economic and political environment indicators.

[0075] As described in step S2 above, if the relevant geopolitical event exists, a space-time heat map is constructed based on the relevant geopolitical event. The purpose of the space-time heat map is to show the influence of the geopolitical event on the logistics network and its evolution process in a visual way. According to the data obtained, the logistics activity intensity, stress index and risk level of each region in a certain time period are calculated. In addition, these data can be converted into a visual heat map by kernel density estimation algorithm, etc., and the stress, risk and activity intensity of different regions are represented by different colors and graphics. The visual heat map can not only help decision makers quickly identify high-risk areas, but also show possible logistics bottlenecks and key nodes.

[0076] As described in step S3 above, based on the data set of each of the preset dimensions and the spatio-temporal heat map, a port layer penetration model, an airspace layer penetration model, and a land layer penetration model are respectively constructed. Based on the spatio-temporal heat map and the data set of each dimension that have been constructed, the penetration models of the port layer, the airspace layer, and the land layer are respectively constructed. The port layer penetration model focuses on evaluating the throughput capacity of the port and its carrying capacity under the influence of geopolitical events. The model needs to consider factors such as port congestion, availability of alternative ports, etc. The airspace layer penetration model mainly analyzes the situation of air transportation restrictions, such as the impact of flight restricted areas or changes in air routes on air transport efficiency, and identifies potential alternative routes. The land layer penetration model mainly focuses on the availability of ground transportation channels, evaluates border passage capacity and the risk of land transportation. Each model should integrate specific data sources and real-time information obtained through spatio-temporal heat map analysis to ensure the timeliness and accuracy of the model. Specifically, after obtaining the respective corresponding data sources, the port layer penetration model can be constructed by any one of the following modeling software: AnyLogic (discrete event simulation), FlexSim (3D port modeling), and PortOpt (specialized port optimization tool). The data sources of the port layer penetration model can include the following data: infrastructure dimension: number of berths / maximum draft / shore crane efficiency, operation dimension: TEU turnover rate (container volume berth hour), geopolitical risk coefficient: political stability index x port strategic value weight; the airspace layer penetration model can be constructed by any one of the following modeling software: AirTop (air traffic control professional simulation), SkyBreathe (fuel optimization), Python+PostGIS (custom development), and the data sources of the airspace layer penetration model can include the following data: spatial dimension: 3D air route corridor (including height layer), time dimension: peak flow period mapping, dynamic heat map superposition: use QGIS spatio-temporal cube to show the diffusion pattern of flight restricted areas; the land layer penetration model can be constructed by any one of the following modeling software: TransCAD (transportation planning dedicated), Vissim (micro-simulation), Arena (supply chain risk assessment), and the data sources of the land layer penetration model can include the following data: daily operation of China-Europe freight trains, alternative routes, geopolitics, natural disasters, social unrest.

[0077] The port layer penetration model, the airspace layer penetration model, and the land layer penetration model are cascaded to generate a combined model, as described in step S4 above, specifically according to the interdependence and interrelation between different layers. For example, congestion at the port layer can affect the logistics arrangement of the airspace and land, while changes in the airspace can affect the selection of land transportation, so the cascaded model needs to ensure information flow between the three layers when implemented, so that the state change of each layer can affect other layers. By establishing a multi-level interactive relationship, the system can more comprehensively evaluate the impact of geopolitical events on the entire logistics network, thereby forming a holistic and real-time response mechanism. Specifically, the specific generation steps of the combined model are as follows:

[0078] 1) Determine model parameters and variables;

[0079] Determine basic variables:

[0080] Transportation mode selection variables: for example, define as the transportation selection (sea, air, rail, etc.) from node i to node j.

[0081] Resource allocation variables: such as represent the amount of storage resources set at a specific geographic location.

[0082] Constraints:

[0083] Determine the constraints of each layer, such as the throughput of the port, the number of flights in the airspace, and the capacity of the land.

[0084] 2) Establish the output relationship of each layer model;

[0085] Port layer penetration model output:

[0086] Output the congestion rate, throughput of the port, and availability of alternative ports.

[0087] Airspace layer penetration model output:

[0088] Output the restricted air route and the feasibility of alternative routes, the number of flights that may be affected, and the time delay.

[0089] For example, if an area is marked as a no-fly zone, the additional transit time and cost need to be calculated.

[0090] Land layer penetration model output:

[0091] Output the capacity of land transportation, the volume of goods at the border, and the assessment of potential obstacles.

[0092] For example, according to historical data, the loading capacity saturation time of a certain border port is evaluated.

[0093] 3) Integrate Interactions;

[0094] Define Interactions:

[0095] Clarify the interactions between layers, such as whether port congestion affects flight adjustments or airspace restrictions change land transportation decisions.

[0096] For example, use matrix form to incorporate port layer output into airspace and land layer model construction.

[0097] 4) Establish Feedback Mechanisms:

[0098] Set up feedback relationships between layer models, such as how port congestion affects airspace and land optimization solutions in real time.

[0099] For example, if it is predicted that the port will reach its maximum capacity, the airspace and land layers should immediately take appropriate measures to change transportation strategies.

[0100] 5) Build Overall Combined Model;

[0101] Combined Model Design:

[0102] Integrate the results of the three-layer model into a unified model framework, which can include decision variables and constraints of each layer, forming a complete logical relationship network, allowing information to flow between layers.

[0103] 6) Verify and Adjust the Model;

[0104] Model Verification:

[0105] Use historical data and simulated events to verify the model to ensure that the combined model accurately reflects reality and can handle various possibilities.

[0106] Compare the model's predicted results with actual results to check for significant differences and adjust parameters or algorithms as needed.

[0107] Model Adjustment:

[0108] Make necessary adjustments based on verification results, such as resetting some constraints or optimizing model output based on feedback information.

[0109] Ensure that the entire combined model remains adaptable and robust in the face of geopolitical events.

[0110] As described in step S5 above, the combined model is converted into a mixed integer linear programming model. Mixed integer linear programming is an optimization method suitable for allocating resources and planning decisions in logistics networks. This stage requires the identification of various decision variables, such as transportation mode selection, resource allocation, cost control, etc., and the establishment of corresponding linear constraint conditions, which need to be set according to the output results of the penetration model and actual operation constraints (such as transportation capacity, time window, etc.). By formatting the complex cascade analysis into a mathematical model, the system will be able to provide clear optimization objectives for decision-makers, making the reconstruction scheme operable.

[0111] As described in step S6 above, the mixed integer linear programming model is solved by a preset cascade analysis solving algorithm to obtain the reconstruction scheme. Through the preset cascade analysis solving algorithm, the mixed integer linear programming model is solved, and the reconstruction scheme of the logistics network is obtained in this process. This process uses optimization algorithms (such as branch and bound algorithm, simplex method, etc.) to find the best solution of the model. The solving result will show the optimal resource allocation and transportation selection under different scenarios, which can be used to develop specific logistics adjustment measures. This provides support for subsequent implementation, so that the logistics network under the influence of geopolitical events can be quickly adjusted to ensure its continuity and efficiency.

[0112] In one embodiment, if the relevant geopolitical event exists, the step S2 of constructing a spatio-temporal heat map based on the relevant geopolitical event comprises:

[0113] S201: extracting key elements of the relevant geopolitical event through a named entity recognition model;

[0114] S202: obtaining a plurality of target dimension data based on the key elements to obtain a target dimension data set;

[0115] S203: scoring the target dimension data set through a preset multi-dimensional evaluation model to obtain a heat value corresponding to the key elements;

[0116] S204: constructing the spatio-temporal heat map based on the key elements and the heat value.

[0117] As described in steps S201-S204 above, the key elements of relevant geopolitical events are extracted through a Named Entity Recognition (NER) model. NER is a natural language processing technique aimed at identifying specific units of information, such as people, locations, organizations, and important events, from text. By monitoring various information sources in real-time, such as news reports, social media updates, policy statements, and more, the NER model is used to extract feature information related to geopolitical events. For example, when a country announces sanctions, the model can extract the name of the country, the affected countries, the type of sanctions, and the implementation time as key elements. These extracted key elements provide a foundation for subsequent data acquisition and analysis, helping to establish background knowledge of the current event and accurately define the scope of influence, thereby laying the foundation for the real-time and accuracy of the model. Based on these elements, data in multiple target dimensions is obtained to form a target dimension data set, including multiple dimensions such as economic indicators, transportation conditions, social security indexes, historical conflict records, and weather data. Through cross-analysis of multi-source data, the system can reflect the potential impact of geopolitical events on these dimensions. For example, if a region experiences logistics delays due to conflict, the system needs to collect information such as traffic flow data, port throughput, and air flight cancellations in that region.

[0118] After obtaining the target dimension data set, a pre-set multi-dimensional evaluation model is used to score these data to obtain a heat value related to the geopolitical event. The multi-dimensional evaluation model can be any of the following algorithms, such as weighted average method, analytic hierarchy process, fuzzy comprehensive evaluation, etc. These algorithms are based on the allocation of weights to each dimension data to calculate a comprehensive score. The heat value is a comprehensive indicator, usually used to represent the risk level or impact intensity of a specific region at a given time. In this way, the system can quantify the contribution of each dimension to the overall risk. For example, if the social security index of a region decreases significantly, its heat value will be correspondingly increased. By combining key elements and heat values, the system will construct a corresponding spatio-temporal heat map. The spatio-temporal heat map is a visualization tool that can show the distribution of data in time and space. In some embodiments, key elements can also be mapped to a geographic information system (GIS), with different color depths assigned to regions based on the intensity of the heat value. Regions with darker colors on the heat map represent areas with higher impact. The visualization effect of the heat map can be improved through rendering techniques and graphics processing algorithms, allowing users to easily identify the risk level of key regions. At the same time, such visualization also facilitates decision-makers to intuitively understand the impact of geopolitical events and adjust response strategies in a timely manner. This process not only improves the operability of the model, but also enhances the timeliness and accuracy of overall decision-making, providing intuitive and powerful support for subsequent logistics network reconstruction.

[0119] In one embodiment, before the step S203 of scoring the target dimension data set by the preset multi-dimensional evaluation model to obtain the heat value corresponding to the key elements, the method further comprises the following steps:

[0120] S2021: obtaining the correlation value between the relevant geopolitical event and each target dimension in the preset multi-dimensional evaluation model;

[0121] S2022: setting the scoring weight of each target dimension of the multi-dimensional evaluation model according to the correlation value.

[0122] As described in the steps S2021-S2022 above, before scoring the heat value, it is necessary to first analyze the correlation value between the relevant geopolitical event and each target dimension in the preset multi-dimensional evaluation model. Determine how different dimensions are affected by a particular geopolitical event. The calculation of the correlation value can be any one of correlation coefficient analysis, regression analysis, or pattern recognition based on historical data. Through the analysis of historical events, the system identifies past situations with similar patterns to the current geopolitical event, thereby assigning a corresponding correlation value to the target dimension. For example, if a country's supply chain disruption event caused by sanctions is analyzed, it may be found that multiple dimensions such as economic indicators, traffic delays, and social stability are significantly correlated with the event. On this basis, the system can generate a correlation value for each target dimension, indicating its importance and impact in the current event. The setting of this correlation value will directly affect the dynamic balance of subsequent scoring, ensuring that the model can fully consider the close relationship with the actual event when evaluating the heat value.

[0123] After obtaining the correlation value of the target dimension related to the geopolitical event, set the corresponding scoring weight for each target dimension of the multi-dimensional evaluation model according to the correlation value. To ensure fairness and scientificity, the system generally uses normalization method to convert the correlation value into weight, to prevent a dimension from dominating the overall score due to a large value range. The process of setting the weight can include setting the ratio of the maximum value and the minimum value to ensure the rationality of the weight distribution, and the weight calculation can be performed by weighted average method, analytic hierarchy process (AHP) and other methods. For example, the weight of each dimension is calculated by entropy weight method: The information entropy of the ith dimension is, and n is the total number of dimensions. Through these methods, the system can better reflect the importance of each dimension in the current geopolitical event context. For example, if the correlation value of a certain dimension is much higher than that of other dimensions, the corresponding weight will be higher, which means that in the calculation of the heat value, the influence of this dimension on the overall result is greater. At the same time, the weight setting also needs to consider the possible independence and interaction between different dimensions to avoid potential scoring bias. After this process, the final weight configuration enables the subsequent heat value calculation to reflect the actual influence of each dimension in the specific event background, helping to form a more accurate and efficient evaluation model.

[0124] In one embodiment, the step S6 of solving the mixed integer linear programming model by the preset cascade analysis solving algorithm to obtain a reconstruction scheme includes:

[0125] S601: output a Pareto solution set based on the mixed integer linear programming model;

[0126] S602: chromosome coding is performed on the schemes in the Pareto solution set, thereby obtaining a first chromosome set;

[0127] S603: cross mutation operation is performed on the first chromosome set to obtain a second chromosome set;

[0128] S604: the second chromosome set is combined with the first chromosome set to generate a third chromosome set;

[0129] S605: the third chromosome set is taken as the first chromosome set, and the target step and the steps after the target step are repeatedly executed until the number of chromosomes in the third chromosome set is greater than or equal to a preset number; the target step is the step of performing cross mutation operation on the first chromosome set to obtain a second chromosome set;

[0130] S606: the third chromosome set with the number of chromosomes greater than or equal to the preset number is recorded as a target third chromosome set;

[0131] S607: the fitness values of the chromosomes in the target third chromosome set are calculated by a preset fitness calculation function;

[0132] S608: the chromosome with the highest fitness value is selected as the reconstruction scheme.

[0133] As described in steps S601-S605 above, the system outputs a Pareto solution set based on the results of solving the mixed integer linear programming (MILP) model. The Pareto solution set, in the context of multi-objective optimization problems, represents solutions where no further improvement can be made in any one objective without compromising the others. To identify these solutions, the system calculates performance indicators for each possible scenario, such as transportation cost, timeliness, and risk value. By evaluating these indicators comprehensively, the system can identify optimal solutions that strike a balance between different objectives, forming a Pareto front in a multi-dimensional space. In one embodiment, a heuristic algorithm can be used to pre-screen feasible solutions, reducing the size of the MILP problem. Each solution corresponds to a practical logistics reconstruction scheme, with different characteristics and possible application scenarios. For example, the scheme with the lowest transportation cost may not necessarily be the one with the best timeliness; rather, it is a reasonable balance between cost and timeliness. This process provides multiple good initial solutions for the subsequent evolutionary algorithm, and through appropriate solving methods, the system will be able to improve the quality of the solutions through multiple iterations.

[0134] chromosome set. In this step, the purpose of chromosome encoding is to convert the optimization solution into a format suitable for genetic algorithm operation. Generally, chromosomes will be represented as binary strings, real number arrays, or other encoding methods. For example, the decision variables of each scheme (such as the selection of transportation mode, the allocation of resources, etc.) can be converted into a series of genes to form a chromosome. For example, the port selection, transportation price, and transportation plan of a certain scheme can be encoded as "110101", where each bit represents a different selection. In this way, the system can effectively handle these complex schemes, while facilitating subsequent crossover and mutation operations. Ensuring the quality and information integrity of the encoding is crucial for the success of subsequent evolutionary operations, and good encoding can preserve the diversity of information and the possibility of variation to achieve the optimization goal. Perform crossover and mutation operations on the first chromosome set to generate a second chromosome set. Crossover and mutation are core operations in genetic algorithms, aiming to explore better solutions by simulating the natural selection process. In the crossover operation, two chromosomes are randomly selected and crossed at a certain position to generate new offspring chromosomes. This process helps to combine the information of parent chromosomes and explore possible new solutions. For example, parent chromosomes "110101" and "011000" may generate "110000" and "011101" after crossing. The subsequent mutation operation randomly changes a gene of the chromosome to introduce new features or options, increasing the diversity of the search space. Through these operations, the generated second chromosome set not only maintains the excellent parent features, but also effectively increases the new search path, avoiding the risk of early convergence to local optimal solutions. It should be noted that the probability of mutation of each gene segment can be set, for example, set to 15% probability of mutation. Merge the second chromosome set with the first chromosome set to generate a third chromosome set. Through this merging operation, the system can retain the information of the original high-quality solutions while introducing newly generated solutions, thereby enhancing the diversity of the solution space. Ensure that excellent genetic features are not lost due to a single iteration. The third chromosome set is used as the new first chromosome set, and then the target step is repeated. The target step mainly refers to performing crossover and mutation operations on the chromosome set to obtain a new second chromosome set. This cycle process will continue until the number of chromosomes in the third chromosome set is greater than or equal to the set preset number. Through multiple generations of evolution and genetic operations, the system can continuously explore new solutions and optimize multiple times to ensure the diversity and excellence of the solutions. This process not only increases the breadth of solutions, but also enhances the effectiveness of the evolutionary algorithm. Such repeated iteration strategy allows the algorithm to conduct a comprehensive search in the solution space, helping to find the optimal solution or near-optimal solution, while ensuring that enough solutions are generated in practical applications for decision-makers to choose from.

[0135] As described in steps S606-S608 above, the third chromosome set with a chromosome number greater than or equal to the preset number is recorded as the target third chromosome set, and the fitness value of each chromosome in the target third chromosome set is calculated by the preset fitness calculation function. The fitness value is a quantitative indicator that measures the performance of each solution under the objective function. It is usually combined with multi-objective optimization problems, such as comprehensive evaluation of factors such as cost, time, risk, etc. The system will evaluate the performance of each chromosome solution in the given environment by analyzing its resource allocation, transportation efficiency, and related costs according to the preset fitness function. This process may involve multi-objective trade-offs to ensure balance between different indicators. For example, the fitness function may place a higher weight on transportation costs to reflect the importance of cost control in the current market environment. The chromosome with the highest fitness value is selected as the reconstruction scheme. The final goal of multi-objective optimization is achieved, ensuring that the selected scheme achieves the best results after comprehensive consideration of cost, time, risk, etc. This selection process will usually combine the target weight set in advance with the fitness function, ensuring that the selected scheme not only meets business needs but also has practicality and executability. The final reconstruction scheme will provide decision-makers with a clear action plan, ensuring that the logistics network can quickly and effectively respond to changes under the influence of geopolitical events, thereby reducing related risks.

[0136] In one embodiment, before the step S601 of outputting the Pareto solution set based on the mixed integer linear programming model, the method further comprises:

[0137] S6001: obtaining a constraint condition;

[0138] S6002: inputting the constraint condition into the mixed integer linear programming model to obtain a first target mixed integer linear programming model; wherein the first target mixed integer linear programming model is used to output a Pareto solution set.

[0139] As described in steps S6001-S6002 above, before solving the mixed integer linear programming (MILP) model, it is necessary to first collect and organize all the constraints related to the optimization problem. Constraints are key factors in defining the feasible solution set in the model, usually including resource limitations, operating conditions, time limitations, laws and regulations, etc. For example, capacity constraints: the maximum carrying capacity of each transportation node (such as ports, warehouses) cannot exceed its actual capacity. Time constraints: the transportation of goods must be completed within the specified time, with the shortest time limit between distribution points. Budget constraints: the total cost of the project must be less than or equal to the preset funding limit, including transportation costs, customs duties, etc. Regulatory constraints: comply with international and local trade laws and regulations, such as the use of logistics equipment and the corresponding document requirements. After obtaining the constraints, input these constraints into the mixed integer linear programming model to build a new model, called the first target mixed integer linear programming model. The core objective of this model is to solve a specific optimization problem and output the corresponding Pareto solution set. In the process of inputting constraints into the model, the system needs to convert each constraint into a mathematical expression, forming an operable form.

[0140] In one embodiment, the step S601 of outputting a Pareto solution set based on the mixed integer linear programming model further includes, before the step S601:

[0141] S6101: setting a target function;

[0142] S6102: inputting the target function into the mixed integer linear programming model to obtain a second target mixed integer linear programming model; wherein the second target mixed integer linear programming model is used to output a Pareto solution set.

[0143] As described in steps S6101-S6102 above, before solving the mixed integer linear programming (MILP) model, a clear objective function is set. It should be noted that the mixed integer linear programming (MILP) model can also be pre-set with an objective function, which can be updated here. The objective function is a key component of the optimization model, used to define the core indicators that the model wants to optimize. In logistics and supply chain management, the objective function often involves multiple aspects, such as: cost minimization: by choosing the most economical transportation mode and path to reduce overall transportation costs, including freight transportation, warehousing, distribution, and other expenses. Service level maximization: improve customer service quality, such as ensuring the proportion of on-time delivery or improving customer satisfaction. Risk minimization: consider potential risk factors in decision-making to reduce potential losses in response to uncertainties such as geopolitical events, market fluctuations, etc. When setting the objective function, multiple objectives often need to be considered, especially when multiple objective optimization is involved, involving the setting of the weight of the target, so as to reasonably balance multiple objectives in the solving process. Input this objective function into the mixed integer linear programming model, thereby constructing a second target mixed integer linear programming model.

[0144] In one embodiment, before the step S1 of detecting in real time whether there is a related geopolitical event in the current logistics network and acquiring a data set of three preset dimensions of sea, land and air in real time, the method comprises:

[0145] S001: Crawling raw data of each database through a distributed crawler cluster;

[0146] S002: Analyzing the raw data through a multilingual bill of lading parsing engine constructed by an XLM-RoBERTa model to obtain a geopolitical event set; wherein the geopolitical event set is used to detect whether there is the related geopolitical event.

[0147] As described in steps S001-S002 above, before implementing real-time detection of geopolitical events, the first step is to crawl raw data from various databases through a distributed crawler cluster. This process is the foundation of data collection, involving the use of web crawler technology to automatically extract information from various online data sources, including news websites, social media, government announcements, and reports from international organizations, etc. The distributed crawler cluster is composed of multiple crawler nodes, which can work in parallel, significantly improving the efficiency of data acquisition, and processing real-time data streams through a streaming computing framework such as Apache Storm, with a response delay of <1 minute. For example, a crawler node is responsible for accessing a specific news website, while another node focuses on social media platforms. Through distributed design, the system can efficiently handle a large number of requests and avoid restrictions encountered by frequently requesting a single website. At the same time, the crawling frequency and time limit can be set as needed to ensure the real-time and update of data. When crawling data, it is necessary to ensure that the extracted data is structured or semi-structured to facilitate subsequent natural language processing (NLP) and analysis. At the same time, the quality of raw data directly affects the results of subsequent analysis, so in this process, it is necessary to ensure that the collected data is reliable, relevant, and stored in a suitable manner for subsequent use. A multilingual bill of lading parsing engine built using the XLM-RoBERTa model is used to parse the collected raw data and identify and extract geopolitical events from it. XLM-RoBERTa is a pre-trained multilingual transformer that is trained through unsupervised learning and large-scale multilingual data sets, and can effectively process text in multiple languages. Using this model, the system can automatically identify key elements of geopolitical events in the text, such as conflicts, sanctions, negotiations, etc. This may involve extracting specific keywords, entities (such as countries, organizations), and event descriptions. The parsing engine converts raw data into a structured set of geopolitical events, which contains detailed information about each event, including the type, time, location, and participants of the event. Through automated bill of lading parsing, the system can timely capture global geopolitical dynamics and provide strong support for coping with uncertainty and optimizing decision-making.

[0148] Referring to Figure 3 The present application also provides a logistics network reconstruction device, which comprises:

[0149] A detection module 902 is configured to detect whether there is a relevant geopolitical event in the current logistics network in real time, and to obtain a data set in three preset dimensions of sea, land and air in real time;

[0150] A first construction module 904 is configured to construct a space-time heat map based on the relevant geopolitical event if the relevant geopolitical event exists;

[0151] The second construction module 906 is configured to construct a port layer penetration model, an airspace layer penetration model and a land layer penetration model based on the data set of each preset dimension and the spatio-temporal heat map respectively.

[0152] The cascade module 908 is configured to cascade the port layer penetration model, the airspace layer penetration model and the land layer penetration model to generate a combined model.

[0153] The conversion module 910 is configured to convert the combined model into a mixed integer linear programming model.

[0154] The calculation module 912 is configured to solve the mixed integer linear programming model by using a preset cascade analysis solving algorithm to obtain a reconstruction scheme.

[0155] In an embodiment, the first construction module 904 comprises:

[0156] The key element extraction submodule is configured to extract key elements of the relevant geopolitical event by using a named entity recognition model.

[0157] The target dimension data acquisition submodule is configured to acquire a plurality of target dimension data based on the key elements to obtain a target dimension data set.

[0158] The scoring submodule is configured to score the target dimension data set by using a preset multi-dimensional evaluation model to obtain a heat value corresponding to the key elements.

[0159] The spatio-temporal heat map construction submodule is configured to construct the spatio-temporal heat map based on the key elements and the heat value.

[0160] In an embodiment, the first construction module 904 further comprises:

[0161] The correlation value acquisition submodule is configured to acquire a correlation value of the relevant geopolitical event and each target dimension in the preset multi-dimensional evaluation model.

[0162] The scoring weight setting submodule is configured to set a scoring weight of each target dimension of the multi-dimensional evaluation model according to the correlation value.

[0163] In an embodiment, the calculation module 912 comprises:

[0164] The Pareto solution set output submodule is configured to output a Pareto solution set based on the mixed integer linear programming model.

[0165] The chromosome coding submodule is configured to code schemes in the Pareto solution set as chromosomes to obtain a first chromosome set.

[0166] a variation submodule configured to perform a crossover variation operation on the first chromosome set to obtain a second chromosome set;

[0167] a combination submodule configured to combine the second chromosome set with the first chromosome set to obtain a third chromosome set;

[0168] an iteration submodule configured to repeat the target step and the steps after the target step, taking the third chromosome set as the first chromosome set, until the number of chromosomes in the third chromosome set is greater than or equal to a preset number; the target step is a step of performing a crossover variation operation on the first chromosome set to obtain a second chromosome set;

[0169] a marking submodule configured to mark the third chromosome set with the number of chromosomes greater than or equal to the preset number as a target third chromosome set;

[0170] a fitness value calculation submodule configured to calculate the fitness values of the chromosomes in the target third chromosome set by using a preset fitness calculation function;

[0171] a selection submodule configured to select a chromosome with the highest fitness value as a reconstruction scheme.

[0172] In an embodiment, the computing module 912 further includes:

[0173] a constraint condition acquisition submodule configured to acquire a constraint condition;

[0174] a constraint condition input submodule configured to input the constraint condition into the mixed integer linear programming model to obtain a first target mixed integer linear programming model; the first target mixed integer linear programming model is configured to output a Pareto solution set.

[0175] In an embodiment, the computing module 912 further includes:

[0176] a target function setting submodule configured to set a target function;

[0177] a target function input submodule configured to input the target function into the mixed integer linear programming model to obtain a second target mixed integer linear programming model; the second target mixed integer linear programming model is configured to output a Pareto solution set.

[0178] In an embodiment, the logistics network reconstruction device includes:

[0179] an original data crawling module configured to crawl original data of each database by using a distributed crawler cluster;

[0180] The original data analysis module is configured to analyze the original data by using a multilingual bill of lading analysis engine constructed by an XLM-RoBERTa model to obtain a geopolitical event set; wherein the geopolitical event set is used to detect whether there is the relevant geopolitical event.

[0181] Figure 4 An internal structure diagram of an electronic device in an embodiment is shown. The electronic device can be a terminal, a server, or a computer device. As shown in the figure, Figure 4 The electronic device includes a processor, a memory, and a network interface connected by a system bus. The memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the electronic device stores an operating system and can also store a computer program. When the computer program is executed by the processor, the processor can implement the logistics network reconstruction method. The internal memory can also store a computer program. When the computer program is executed by the processor, the processor can execute the logistics network reconstruction method. Those skilled in the art can understand that Figure 4 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application and does not constitute a limitation on the electronic device to which the scheme of the present application is applied. The specific electronic device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0182] In one embodiment, an electronic device is provided, including a memory and a processor, the memory stores a computer program, the computer program is executed by the processor, so that the processor executes the following steps:

[0183] Real-time detection of whether there is a relevant geopolitical event in the current logistics network, and real-time acquisition of data sets in three preset dimensions of sea, land, and air;

[0184] If there is the relevant geopolitical event, a space-time heat map is constructed based on the relevant geopolitical event;

[0185] Based on the data sets of each of the preset dimensions and the space-time heat map, a port layer penetration model, an airspace layer penetration model, and a land layer penetration model are constructed respectively;

[0186] The port layer penetration model, the airspace layer penetration model, and the land layer penetration model are cascaded to generate a combined model;

[0187] The combined model is converted into a mixed integer linear programming model;

[0188] The mixed integer linear programming model is solved by a preset cascade analysis solving algorithm to obtain a reconstruction scheme.

[0189] By constructing the space-time thermal map and the penetration model, the interconnection between each level can quickly evaluate and adjust the transportation scheme when the event occurs, ensure the stability and efficiency of the supply chain, use the optimization ability of mixed integer linear programming, improve the feasibility and efficiency of the reconstruction scheme, provide scientific and data-driven strategy selection for decision makers, and enhance the adaptability and pressure resistance of the global logistics network.

[0190] In one embodiment, a computer readable storage medium is proposed, which stores a computer program, the computer program is executed by a processor to make the processor execute the following steps:

[0191] Real-time detection of whether there is a related geopolitical event in the current logistics network, and real-time acquisition of data sets in three preset dimensions of sea, land and air;

[0192] If there is the related geopolitical event, a space-time thermal map is constructed based on the related geopolitical event;

[0193] Based on the data set of each of the preset dimensions and the space-time thermal map, a port layer penetration model, an airspace layer penetration model and a land layer penetration model are constructed respectively;

[0194] Cascade the port layer penetration model, the airspace layer penetration model and the land layer penetration model to generate a combined model;

[0195] Convert the combined model into a mixed integer linear programming model;

[0196] Solve the mixed integer linear programming model by a preset cascade analysis solving algorithm to obtain a reconstruction scheme.

[0197] By constructing the space-time thermal map and the penetration model, the interconnection between each level can quickly evaluate and adjust the transportation scheme when the event occurs, ensure the stability and efficiency of the supply chain, use the optimization ability of mixed integer linear programming, improve the feasibility and efficiency of the reconstruction scheme, provide scientific and data-driven strategy selection for decision makers, and enhance the adaptability and pressure resistance of the global logistics network.

[0198] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The program can be stored in a non-volatile computer readable storage medium, and when the program is executed, the processes of the above-mentioned embodiment methods can be included. Any reference to memory, storage, database, or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0199] The technical features of the above embodiments can be combined in any way. In order to make the description simple, not all possible combinations of the technical features in the above embodiments are described, but as long as the combination of the technical features does not exist, it should be considered as the scope of the present application.

[0200] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A method for reconstructing a logistics network, characterized in that, The method includes: Real-time detection of relevant geopolitical events in the current logistics network, and real-time acquisition of datasets from three preset dimensions: sea, land, and air; If the aforementioned relevant geopolitical events exist, a spatiotemporal heat map is constructed based on these events. Based on the datasets of each of the preset dimensions and the spatiotemporal heatmap, port layer penetration models, airspace layer penetration models, and land layer penetration models are constructed respectively. The port layer penetration model is used to assess the throughput capacity of ports and their carrying capacity under the influence of geopolitical events, including port congestion and the availability of alternative ports. The airspace layer penetration model is used to analyze situations where air transport is restricted, including the impact of no-fly zones or route changes on air transport efficiency, and to identify potential alternative routes. The land layer penetration model focuses on the availability of ground transport channels, assesses border crossing capacity, and evaluates the risks of land transport. The port layer penetration model, the airspace layer penetration model, and the land route layer penetration model are cascaded to generate a combined model; The combined model is transformed into a mixed integer linear programming model; The mixed-integer linear programming model is solved using a pre-defined cascaded analysis algorithm to obtain a reconstruction scheme; The step of constructing a spatiotemporal heatmap based on the relevant geopolitical events, if such events exist, includes: Key elements of the relevant geopolitical events were extracted using a named entity recognition model. Based on the aforementioned key elements, multiple target dimension data are obtained to form a target dimension dataset. The target dimension dataset is scored by a preset multidimensional evaluation model to obtain the heat values ​​corresponding to the key elements; The spatiotemporal heat map is constructed based on the key elements and the thermal values; The step of solving the mixed-integer linear programming model using a preset cascaded analysis algorithm to obtain a reconstruction scheme includes: Output the Pareto solution set based on the aforementioned mixed-integer linear programming model; Chromosome encoding is performed on the schemes in the Pareto solution set to obtain the first chromosome set; Perform a crossover mutation operation on the first chromosome set to obtain the second chromosome set; The second chromosome set is combined with the first chromosome set to generate a third chromosome set; Using the third chromosome set as the first chromosome set, the target step and the steps following the target step are repeated until the number of chromosomes in the third chromosome set is greater than or equal to a preset number; the target step is to perform a crossover mutation operation on the first chromosome set to obtain the second chromosome set. The third chromosome set whose number of chromosomes is greater than or equal to the preset number is denoted as the target third chromosome set; The fitness value of each chromosome in the target third chromosome set is calculated using a preset fitness calculation function; The chromosome with the highest fitness value was selected as the reconstruction scheme.

2. The logistics network reconstruction method according to claim 1, characterized in that, Before the step of scoring the target dimension dataset using a preset multidimensional evaluation model to obtain the heat values ​​corresponding to the key elements, the method further includes: Obtain the correlation values ​​between the relevant geopolitical events and each target dimension in the preset multidimensional assessment model; The scoring weights of each target dimension of the multidimensional evaluation model are set based on the correlation values.

3. The logistics network reconstruction method according to claim 1, characterized in that, Before the step of outputting the Pareto solution set based on the mixed-integer linear programming model, the method further includes: Obtain the constraints; The constraints are input into the mixed-integer linear programming model to obtain a first objective mixed-integer linear programming model; wherein the first objective mixed-integer linear programming model is used to output the Pareto solution set.

4. The logistics network reconstruction method according to claim 1, characterized in that, Before the step of outputting the Pareto solution set based on the mixed-integer linear programming model, the method further includes: Define the objective function; The objective function is input into the mixed-integer linear programming model to obtain a second-objective mixed-integer linear programming model; wherein the second-objective mixed-integer linear programming model is used to output the Pareto solution set.

5. The logistics network reconstruction method according to claim 1, characterized in that, Before the steps of real-time detection of relevant geopolitical events in the current logistics network and real-time acquisition of datasets from three preset dimensions (sea, land, and air), the following are included: Raw data from various databases is crawled using a distributed crawler cluster; A multilingual bill of lading parsing engine built using the XLM-RoBERTa model is used to parse the original data to obtain a geopolitical event set; wherein, the geopolitical event set is used to detect whether the relevant geopolitical events exist.

6. A logistics network reconfiguration device, characterized in that, The device includes: The detection module is used to detect in real time whether there are relevant geopolitical events in the current logistics network, and to acquire datasets in three preset dimensions: sea, land, and air. The first construction module is used to construct a spatiotemporal heat map based on the relevant geopolitical events if such events exist. The second construction module is used to construct port layer penetration models, airspace layer penetration models, and land layer penetration models based on the datasets of each preset dimension and the spatiotemporal heatmap, respectively. The port layer penetration model is used to evaluate the throughput capacity of ports and their carrying capacity under the influence of geopolitical events, including port congestion and the availability of alternative ports. The airspace layer penetration model is used to analyze situations where air transport is restricted, including the impact of no-fly zones or route changes on air transport efficiency, and to identify potential alternative routes. The land layer penetration model focuses on the availability of ground transport channels and assesses border crossing capacity and the risks of land transport. The cascading module is used to cascade the port layer penetration model, the airspace layer penetration model, and the land route layer penetration model to generate a combined model. The conversion module is used to convert the combined model into a mixed integer linear programming model; The calculation module is used to solve the mixed integer linear programming model through a preset cascaded analysis solution algorithm to obtain a reconstruction scheme; The first building module includes: The key element extraction submodule is used to extract key elements of the relevant geopolitical events through a named entity recognition model. The target dimension data acquisition submodule is used to acquire multiple target dimension data based on the key elements to obtain a target dimension dataset. The scoring submodule is used to score the target dimension dataset using a preset multidimensional evaluation model to obtain the heat values ​​corresponding to the key elements. A spatiotemporal heat map construction submodule is used to construct the spatiotemporal heat map based on the key elements and the heat values; The computing module includes: The Pareto solution set output submodule is used to output a Pareto solution set based on the mixed-integer linear programming model. The chromosome encoding submodule is used to encode the schemes in the Pareto solution set into chromosomes, thereby obtaining the first chromosome set; The mutation submodule is used to perform a crossover mutation operation on the first chromosome set to obtain a second chromosome set; The combination submodule is used to combine the second chromosome set with the first chromosome set to generate a third chromosome set; An iterative submodule is used to repeatedly execute the target step and the steps following the target step, using the third chromosome set as the first chromosome set, until the number of chromosomes in the third chromosome set is greater than or equal to a preset number; the target step is to perform a crossover mutation operation on the first chromosome set to obtain the second chromosome set. The tagging submodule is used to mark the third chromosome set whose number of chromosomes is greater than or equal to a preset number as the target third chromosome set; The fitness value calculation submodule is used to calculate the fitness value of each chromosome in the target third chromosome set through a preset fitness calculation function; The selection submodule is used to select the chromosome with the highest fitness value as the reconstruction scheme.

7. A computer-readable storage medium, characterized in that, The system contains a computer program that, when executed by a processor, causes the processor to perform the steps of the logistics network reconfiguration method as described in any one of claims 1 to 5.

8. An electronic device, characterized in that, The device includes a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of the logistics network reconfiguration method as described in any one of claims 1 to 5.

Images