Logistics hub planning method and device, computer equipment and storage medium

Abstract

The invention relates to a logistics hub planning method and device, computer equipment and a storage medium. The method comprises the following steps: obtaining distribution vehicle positioning data and a total production value of a target area; predicting a first number of distribution vehicles in the target year based on the distribution vehicle positioning data and the total production value; establishing a clustering number convergence model based on the first number; wherein the clustering number convergence model is used for determining the number of target logistics hubs; and clustering the distribution vehicle positioning data based on the target logistics hub number in combination with the optimized target function to obtain target logistics hub positioning. Through the method, the planning and decision-making process of the logistics hub is more scientific and objective, the actual logistics demand and the industrial development trend can be reflected more accurately, and the limitation of experience judgment and static indexes is reduced; moreover, the number of logistics hubs and positioning of the logistics hubs can be reasonably planned, and the logistics efficiency and the service quality are improved.

Description

Technical Field

[0001] This application relates to the field of logistics management technology, and in particular to a logistics hub planning method, apparatus, computer equipment, and storage medium. Background Technology

[0002] As core nodes of the integrated transportation system and comprehensive three-dimensional transportation network, logistics hubs play a vital role in the national strategy of building a strong transportation nation, optimizing the layout of the comprehensive three-dimensional transportation network, and promoting the construction of a modern integrated transportation service system. The rationality of their planning and layout is directly related to the efficiency of logistics transportation and the level of regional industrial synergy.

[0003] Traditional logistics hub planning methods mainly revolve around dimensions such as distribution cost optimization, node importance assessment, and transportation hub layout. Although these methods have played a positive role in a certain historical period, they rely too much on experience and static indicators, lack accurate capture of dynamic logistics needs, and have a single data collection dimension, making it difficult to support cross-regional, multi-modal networked decision-making.

[0004] Therefore, how to accurately and rationally plan and layout logistics hubs is an urgent problem to be solved. Summary of the Invention

[0005] Therefore, it is necessary to provide a logistics hub planning method, apparatus, computer equipment, and storage medium to address the aforementioned technical problems.

[0006] In a first aspect, this application provides a logistics hub planning method, the method comprising: Obtain delivery vehicle location data and gross production value for the target area; Based on the delivery vehicle location data and the gross domestic product, predict the first number of delivery vehicles for the target year; A cluster number convergence model is established based on the first quantity; wherein, the cluster number convergence model is used to determine the number of target logistics hubs in the target area; Based on the number of target logistics hubs, the location data of the delivery vehicles is clustered using an optimized objective function to obtain the location of the target logistics hubs.

[0007] In one embodiment, predicting the first number of delivery vehicles for a target year based on the delivery vehicle location data and the gross domestic product includes: A target prediction model is determined based on the difference between the target year and the current year; wherein, the target prediction model includes at least one of a linear regression model, a dynamic adjustment model, an error correction model, and a phased prediction model; Based on the delivery vehicle location data and the total production value, the first quantity is determined using the target prediction model adapted to the difference.

[0008] In one embodiment, establishing a clustering number convergence model based on the first quantity includes: Initialize the coverage radius of each logistics hub; Based on the first quantity, a second quantity of target data points in each cluster that are at a distance less than or equal to the coverage radius from the cluster center is determined; wherein, each target data point corresponds one-to-one with the delivery vehicle; Based on the second quantity and the relationship between the number of cluster centers and the coverage of delivery vehicles, a cluster number convergence model is established.

[0009] In one embodiment, the step of clustering the delivery vehicle location data based on the number of target logistics hubs and combining it with an optimization objective function to obtain the target logistics hub location includes: The number of target logistics hubs is determined as the number of target clusters; Randomly select data points from the delivery vehicle location data that match the target cluster number as cluster centers; calculate the distance between the i-th data point and each cluster center to obtain the distance set corresponding to the i-th data point; where i is a positive integer; Based on the minimum distance in the distance set, the i-th data point is reclassified to obtain the i-th data point after the updated classification; Based on the first to mth data points after the update classification, the cluster centers are updated to obtain the updated cluster centers; wherein, m is a positive integer and m is greater than or equal to i; Repeat the process of calculating the distance between the i-th data point and each cluster center to updating the cluster centers to obtain the updated cluster centers, until each cluster center remains unchanged; The location of the target logistics hub is obtained based on the unchanged cluster centers.

[0010] In one embodiment, the method further includes: The delivery vehicle location data is divided into a training set and a test set; wherein the number / location of logistics hubs is labeled in both the training set and the test set. The test set is input into the cluster number convergence model to obtain the quantity evaluation results; Based on the clustering algorithm and the quantity evaluation results, the test set is clustered to obtain the location evaluation results; If the quantity assessment result is inconsistent with the number of logistics hubs and / or the location assessment result is inconsistent with the location of the logistics hubs, a prompt message will be output; wherein, the prompt message is used to remind that the accuracy of the logistics hub planning is insufficient.

[0011] In one embodiment, the expression for the cluster number convergence model is as follows: x′ k ∈D,D={x i |dist(x i Center k )≤R}; Where, x′ k Indicates the target data point in the k-th cluster; |x′ k | Indicates the number of target data points in the k-th cluster; n indicates the number of cluster centers; C k Indicates the cluster center in the k-th cluster; T n Indicates the coverage of the delivery vehicles.

[0012] In one embodiment, the expression for the optimization objective function is as follows: Where k indicates the number of target clusters; C i x indicates the cluster center in each cluster; x indicates the data point within each cluster.

[0013] Secondly, this application also provides a logistics hub planning device, the device comprising: The acquisition module is used to acquire the location data of delivery vehicles and the total production value of the target area; The prediction module is used to predict the first number of delivery vehicles in a target year based on the delivery vehicle location data and the gross domestic product. A modeling module is used to establish a cluster number convergence model based on the first quantity; wherein, the cluster number convergence model is used to determine the number of target logistics hubs in the target area; The clustering module is used to cluster the delivery vehicle location data based on the number of target logistics hubs and in conjunction with an optimization objective function to obtain the location of the target logistics hubs.

[0014] Thirdly, this application also provides a computer device, including a processor and a memory for storing a computer program of the processor; wherein the processor is configured to, when executing the computer program, implement the steps of the method described in any embodiment of this application.

[0015] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps of the methods described in any embodiment of this application.

[0016] The aforementioned logistics hub planning method, on the one hand, utilizes multi-dimensional big data resources such as delivery vehicle location data (e.g., Global Positioning System, GPS) and GDP to make the planning and decision-making process for logistics hubs more scientific and objective. Compared to traditional methods, data-driven decision-making can more accurately reflect actual logistics needs and industry development trends, reducing the limitations of experience-based judgments and static indicators. On the other hand, it can more accurately predict the initial number of delivery vehicles in a target year, helping to rationally plan the number of logistics hubs, reducing resource waste and ensuring sufficient logistics services. Furthermore, by clustering delivery vehicle location data using an optimization objective function, the positioning of logistics hubs can be made more precise, contributing to the optimal layout of the logistics network and improving logistics efficiency and service quality. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating a logistics hub planning method according to an exemplary embodiment; Figure 2 This is a schematic diagram illustrating delivery vehicle coverage under different numbers of clusters according to an exemplary embodiment; Figure 3 This is a schematic diagram illustrating the logistics hub planning of city A according to an exemplary embodiment; Figure 4 This is a flowchart illustrating a logistics hub planning method according to another exemplary embodiment; Figure 5 This is a structural block diagram of a logistics hub planning device according to an exemplary embodiment; Figure 6 This is an internal structural diagram of a computer device according to an exemplary embodiment. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0019] The terms "first," "second," and "third" used in the embodiments of this application are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first," "second," or "third" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0020] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0021] In some embodiments, the logistics hub planning method provided in this application can be applied to computer equipment. The computer equipment can be any mobile terminal or fixed terminal. The terminal can be a device that provides voice and / or data connectivity to a user. For example, the terminal can be an Internet of Things (IoT) terminal, such as a sensor device, a mobile phone or so-called "cellular" phone, and a computer with an IoT terminal, for example, a fixed, portable, pocket-sized, handheld, or computer-embedded device.

[0022] In some embodiments, such as Figure 1 As shown, a logistics hub planning method is provided, the method comprising the following steps: S101, Obtain the location data of delivery vehicles and the total production value of the target area.

[0023] In this embodiment, the target area can be divided according to different dimensions (administrative level / geographical features / functional positioning); for example, the target area can be divided into provincial / prefectural level areas, district / county level areas, township / street level areas, etc., according to administrative level. Alternatively, the target area can be a custom range; for example, the target area can be a radiation area with a radius of 5 kilometers centered on the First Shopping Mall.

[0024] In this embodiment of the application, the delivery vehicle positioning data may include, but is not limited to, at least one of the following: vehicle identification, timestamp, longitude / latitude, driving speed, driving direction, and load status; wherein, the timestamp indicates the data collection time; longitude / latitude can be obtained through GPS or other positioning technologies.

[0025] In this embodiment of the application, Gross Domestic Product (GDP) indicates the total market value of all goods and services produced in the target region within a certain period.

[0026] S102, based on the delivery vehicle location data and the gross production value, predict the first number of delivery vehicles for the target year.

[0027] In one embodiment, the computer device can determine the number of trucks in a target year based on a linear relationship between GDP and a first number of delivery vehicles. For example, it can determine the number of trucks in a target year based on the number of trucks in the current year, GDP and historical GDP growth trends, combined with random error terms (such as seasonal fluctuations, unforeseen events, etc.).

[0028] In one embodiment, the computer device can determine the GDP forecast for the target year based on the current year's GDP and historical GDP growth trends; based on the GDP forecast, it can use time series models (such as Autoregressive Integrated Moving Average (ARIMA)) or machine learning models (such as Long Short-Term Memory (LSTM) networks), and take into account external factors such as seasonal fluctuations and policy changes, to predict the first number of delivery vehicles in the target year.

[0029] S103, establish a cluster number convergence model based on the first quantity; wherein, the cluster number convergence model is used to determine the number of target logistics hubs in the target area.

[0030] In this embodiment of the application, the delivery vehicle may include, but is not limited to, at least one of micro-vehicles (such as tricycles and vans), light trucks, medium trucks, and large trucks / trailers.

[0031] In some embodiments, establishing a clustering number convergence model based on the first quantity includes: Initialize the coverage radius of each logistics hub; Based on the first quantity, a second quantity of target data points in each cluster that are at a distance less than or equal to the coverage radius from the cluster center is determined; wherein, each target data point corresponds one-to-one with the delivery vehicle; Based on the second quantity and the relationship between the number of cluster centers and the coverage of delivery vehicles, a cluster number convergence model is established.

[0032] In one embodiment, the computer equipment can pre-set the coverage radius of a single logistics hub based on historical experience values; or, it can determine the coverage radius of the logistics hub based on the total area of ​​the target area, the construction cost of the logistics hub, and the unit distance transportation cost.

[0033] In this embodiment of the application, the delivery vehicle coverage rate indicates the coverage rate of the delivery vehicle within the coverage radius.

[0034] In one embodiment, a computer device can establish a data point set P based on a predicted first number of delivery vehicles for a target year and the location data of each delivery vehicle; wherein each data point in the data point set corresponds one-to-one with a delivery vehicle; initialize the number of clusters k and the coverage radius R; use the K-means algorithm to cluster the data point set into k clusters, obtaining a cluster center set C; calculate the distance between each data point and the cluster center in its cluster based on algorithms such as Euclidean distance or Manhattan distance, and determine the target data points in each cluster whose distance from the cluster center is less than or equal to the coverage radius; establish a cluster number convergence model based on the second number of target data points, the number of cluster centers, and the delivery vehicle coverage rate; determine the delivery vehicle coverage rate based on the cluster number convergence model; and determine the target number of logistics hubs based on the delivery vehicle coverage rate.

[0035] In some embodiments, the expression for the cluster number convergence model is as follows: x′ k ∈D,D={x i |dist(x i Center k )≤R}; Where, x′ k Indicates the target data point in the k-th cluster; |x′ k | Indicates the number of target data points in the k-th cluster; n indicates the number of cluster centers; C k Indicates the cluster center in the k-th cluster; T n Indicates the coverage of the delivery vehicles.

[0036] For example, such as Figure 2 As shown, Figure 2 This is a schematic diagram illustrating delivery vehicle coverage under different numbers of clusters. From Figure 2As can be seen, when the number of clusters is less than 10, the coverage rate of delivery vehicles increases with the increase of the number of clusters; when the number of clusters is greater than or equal to 10, the coverage rate of delivery vehicles tends to be stable and remains basically unchanged; based on the basic principle of the highest coverage rate of delivery vehicles (i.e. the most delivery vehicle data points covered within the coverage radius) and the fewest number of clusters (number of cluster centers), the number of clusters of 10 can be determined as the target number of logistics hubs.

[0037] S104, Based on the number of target logistics hubs, cluster the delivery vehicle positioning data using an optimized objective function to obtain the target logistics hub positioning.

[0038] In one embodiment, the computer device uses the K-means++ algorithm to optimize the initial cluster centers; iteratively calculates the distance from each data point to each cluster center using the optimization objective function; repeatedly assigns the data points to the clusters based on the distance until the cluster centers are stable; and determines the latitude and longitude coordinates of the stable cluster centers as the location of the target logistics hub, and displays it spatially using a map visualization tool (such as ArcGIS).

[0039] The aforementioned logistics hub planning method, on the one hand, utilizes multi-dimensional big data resources such as delivery vehicle location data (e.g., Global Positioning System, GPS) and GDP to make the planning and decision-making process for logistics hubs more scientific and objective. Compared to traditional methods, data-driven decision-making can more accurately reflect actual logistics needs and industry development trends, reducing the limitations of experience-based judgments and static indicators. On the other hand, it can more accurately predict the initial number of delivery vehicles in a target year, helping to rationally plan the number of logistics hubs, reducing resource waste and ensuring sufficient logistics services. Furthermore, by clustering delivery vehicle location data using an optimization objective function, the positioning of logistics hubs can be made more precise, contributing to the optimal layout of the logistics network and improving logistics efficiency and service quality.

[0040] In some embodiments, predicting a first number of delivery vehicles for a target year based on the delivery vehicle location data and the gross domestic product includes: A target prediction model is determined based on the difference between the target year and the current year; wherein, the target prediction model includes at least one of a linear regression model, a dynamic adjustment model, an error correction model, and a phased prediction model; Based on the delivery vehicle location data and the total production value, the first quantity is determined using the target prediction model adapted to the difference.

[0041] In one embodiment, when the difference is less than or equal to a first threshold (e.g., 3 years, 4 years, etc.) and / or delivery vehicle location data is scarce, the computer device can determine the target prediction model as a linear regression model, an error correction model, or a phased prediction model.

[0042] Alternatively, the expression for the linear regression model can be as follows: N t =α·GDP t +β·T+ε; Where, N t Indicates the first number of delivery vehicles for the target year; GDP t The GDP forecast for the target year is indicated by: T (e.g., T = t - t0, where t0 is the base year); α (e.g., the GDP elasticity coefficient, such as the increase in the number of vehicles corresponding to each unit of GDP growth); β (e.g., the time trend coefficient); and ε (e.g., the random error term, such as seasonal fluctuations or sudden events).

[0043] Alternatively, the expression for the error correction model is as follows: Where, ΔN t Indicates the increase in the number of delivery vehicles; ΔGDP t Indicates GDP increment; φ indicates forecast error; φ indicates short-term elasticity coefficient; ψ indicates error correction coefficient; ε indicates random error term (such as seasonal fluctuations, sudden events).

[0044] Optionally, the expression for the staged prediction model is as follows: Where, N t Indicates the first number of delivery vehicles for the target year; T p The indicators are: α1 and α2, which indicate the year in which special factors (such as policy changes, infrastructure investment, and upgrades to investment standards) occur; β1 and β2, which indicate the GDP elasticity coefficients before and after the occurrence of special factors; β1 and β2, which indicate the time trend coefficients before and after the occurrence of special factors; T, which indicates the time trend term (e.g., T = t - t0, where t0 is the base year); and ε, which indicates the random error term (e.g., seasonal fluctuations and sudden events).

[0045] In one embodiment, when the difference is greater than a first threshold and / or there is a large amount of delivery vehicle location data, the computer device can determine that the target prediction model is a dynamically adjusted model.

[0046] Optionally, the expression for dynamically adjusting the model is as follows: N t =γ·In(GDP) t )+δ·e -θT+ε Where γ indicates the logarithmic elasticity coefficient; δ·e -θT Indicator of time decay term; GDP t The value indicates the GDP forecast for the target year; T indicates the time trend term (e.g., T = t - t0, where t0 is the base year); ε indicates the random error term (e.g., seasonal fluctuations, sudden events).

[0047] In this embodiment, by selecting a suitable target prediction model based on matching time span characteristics, the one-sidedness of a single model can be reduced, and the prediction needs of delivery vehicles in different scenarios can be met. By using a linear regression model suitable for short-term prediction, the linear trend of historical data (delivery vehicle location data) can be quickly fitted, resulting in high computational efficiency. By using a dynamic adjustment model suitable for long-term prediction, nonlinear changes, periodic fluctuations, or policy influences in historical data can be captured, reducing interference.

[0048] In some embodiments, the step of clustering the delivery vehicle location data based on the number of target logistics hubs and combining it with an optimization objective function to obtain the target logistics hub location includes: The number of target logistics hubs is determined as the number of target clusters; Randomly select data points from the delivery vehicle location data that match the target cluster number as cluster centers; Calculate the distance between the i-th data point and each cluster center to obtain the distance set corresponding to the i-th data point; where i is a positive integer; Based on the minimum distance in the distance set, the i-th data point is reclassified to obtain the i-th data point after the updated classification; Based on the first to mth data points after the update classification, the cluster centers are updated to obtain the updated cluster centers; wherein, m is a positive integer and m is greater than or equal to i; Repeat the process of calculating the distance between the i-th data point and each cluster center to updating the cluster centers to obtain the updated cluster centers, until each cluster center remains unchanged; The location of the target logistics hub is obtained based on the unchanged cluster centers.

[0049] In some embodiments, the computer device may determine the number of target logistics hubs as the number of target clusters k; randomly select k data points from the delivery vehicle positioning data as cluster centers; calculate the distance between the i-th data point and the k cluster centers according to a distance algorithm (such as Euclidean distance algorithm) to obtain a distance set; update the i-th data point to the data point of the cluster corresponding to the minimum distance in the distance set; update the cluster center of each cluster based on the mean of each data point in each cluster after the update; repeat the process steps of calculating the distance between the i-th data point and the k cluster centers to updating the cluster center of each cluster until the k cluster centers remain unchanged (their positions no longer move), and determine the final unchanged cluster centers as the target logistics hub locations.

[0050] In some embodiments, the expression for the Euclidean distance algorithm is as follows: Where, x i Indicates the n-dimensional vector corresponding to x; u i The pointer indicates the n-dimensional vector corresponding to u; d(x,u) indicates the distance between x and u.

[0051] In some embodiments, the expression for the optimization objective function is as follows: Where k indicates the number of target clusters; C i x indicates the cluster center in each cluster; x indicates the data point within each cluster.

[0052] In this embodiment, clustering is performed based on delivery vehicle location data (reflecting historical order distribution and high-frequency delivery areas) to ensure that hub location closely matches actual logistics demand hotspots and reduce subjective biases of traditional empirical methods (such as manually delineating areas). The minimum intra-class distance is the optimization objective (each data point belongs to the nearest hub), and the final converged cluster center is the geometric centroid of the corresponding area, which minimizes the average driving distance from all delivery points in the area to the hub and reduces transportation costs.

[0053] In some embodiments, the method further includes: The delivery vehicle location data is divided into a training set and a test set; wherein the number / location of logistics hubs is labeled in both the training set and the test set. The test set is input into the cluster number convergence model to obtain the quantity evaluation results; Based on the clustering algorithm and the quantity evaluation results, the test set is clustered to obtain the location evaluation results; If the quantity assessment result is inconsistent with the number of logistics hubs and / or the location assessment result is inconsistent with the location of the logistics hubs, a prompt message will be output; wherein, the prompt message is used to remind that the accuracy of the logistics hub planning is insufficient.

[0054] For example, the target area is city A. The computer device can obtain the current year's delivery vehicle location data and GDP of city A from the test set; predict the first number of delivery vehicles in the target year based on the current year's delivery vehicle location data and GDP; based on the first number, use a clustering number convergence model to determine the quantity assessment result; wherein, the quantity assessment result includes the number of target logistics hubs corresponding to city A; based on the quantity assessment result, use the optimization objective function in the clustering algorithm to perform clustering to obtain the location assessment result; wherein, the location assessment result includes the location of the target logistics hubs corresponding to city A; match the quantity assessment result with the number of logistics hubs already marked in city A, and match the location assessment result with the location of logistics hubs already marked in city A, and evaluate each model algorithm based on the two matching results; when any matching result is inconsistent, a prompt message can be output to inform the user; subsequently, the user can expand the training set to retrain and iteratively fine-tune each model until the matching result is consistent.

[0055] For example, such as Figure 3 As shown, Figure 3 This is a schematic diagram of the logistics hub planning for city A.

[0056] In this embodiment of the application, the logistics hub planning method is verified and evaluated through a test set. This can quantitatively evaluate the reliability and stability of the algorithm, accurately locate planning errors, and reduce the risk of logistics hub planning decisions. Furthermore, it can also trigger early warnings in a timely manner, optimize the various model algorithms used in the logistics hub planning method, and ensure the accuracy of the final planning results (the number of target logistics hubs and the location of target logistics hubs).

[0057] In this application embodiment, specific examples are provided below in conjunction with any of the above embodiments: Specific example 1: Figure 4 This is an exemplary flowchart illustrating the implementation of any embodiment of the logistics hub planning method provided in this application, such as... Figure 4 As shown, the execution steps of this logistics hub planning method in a computer device are as follows: S401, obtain the location data of delivery vehicles and the total production value of the target area.

[0058] In one alternative embodiment, the delivery vehicle location data can be obtained through a GPS positioning device installed on the delivery vehicle.

[0059] S402, based on delivery vehicle location data and gross domestic product, predicts the first number of delivery vehicles for a target year.

[0060] In an optional embodiment, the current year can be year j, and the target year can be year j+2; where j is a positive integer.

[0061] S403 sets the coverage radius for each logistics hub.

[0062] In one optional embodiment, the coverage radius of each logistics hub can be the same or different; for example, logistics hubs in the urban area of ​​city C are identified as first-level hubs, and the coverage radius of the first-level hubs is set as the first radius; logistics hubs in rural areas of city C are identified as second-level hubs, and the coverage radius of the second-level hubs is set as the second radius; wherein, the first radius is greater than the second radius.

[0063] S404, based on the first quantity and coverage radius, establishes a cluster number convergence model.

[0064] S405, based on the cluster number convergence model, determines the number of target logistics hubs in the target area.

[0065] S406. Based on the number of target logistics hubs, cluster the delivery vehicle location data by combining the optimization objective function to obtain the target logistics hub location.

[0066] In one alternative embodiment, the computer device can plan and lay out the logistics hubs in the target area based on the number and location of the target logistics hubs.

[0067] In this embodiment, on the one hand, by utilizing multi-dimensional big data resources such as delivery vehicle location data and GDP, the planning and decision-making process for logistics hubs becomes more scientific and objective. Compared to traditional methods, data-driven decision-making can more accurately reflect actual logistics needs and industry development trends, reducing the limitations of experience-based judgments and static indicators. On the other hand, it can more accurately predict the initial number of delivery vehicles in a target year, helping to rationally plan the number of logistics hubs, reducing resource waste and ensuring sufficient logistics services. Furthermore, by clustering delivery vehicle location data using an optimization objective function, the location of logistics hubs can be made more precise, contributing to the optimal layout of the logistics network and improving logistics efficiency and service quality.

[0068] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0069] Based on the same inventive concept, this application also provides a logistics hub planning apparatus for implementing the logistics hub planning method described above. The solution provided by this apparatus is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more embodiments of the logistics hub planning apparatus provided below can be found in the limitations of the logistics hub planning method described above, and will not be repeated here.

[0070] In one embodiment, such as Figure 5 As shown, a logistics hub planning device is provided, the device including: an acquisition module 10, used to acquire delivery vehicle location data and gross production value of a target area; Prediction module 20 is used to predict the first number of delivery vehicles in a target year based on the delivery vehicle location data and the gross domestic product. Modeling module 30 is used to establish a cluster number convergence model based on the first quantity; wherein, the cluster number convergence model is used to determine the number of target logistics hubs in the target area; Clustering module 40 is used to cluster the delivery vehicle location data based on the number of target logistics hubs and in combination with an optimization objective function to obtain the location of the target logistics hubs.

[0071] In one embodiment, the prediction module 20 is configured to perform the following steps: A target prediction model is determined based on the difference between the target year and the current year; wherein, the target prediction model includes at least one of a linear regression model, a dynamic adjustment model, an error correction model, and a phased prediction model; Based on the delivery vehicle location data and the total production value, the first quantity is determined using the target prediction model adapted to the difference.

[0072] In one embodiment, the modeling module 30 is configured to perform the following steps: Initialize the coverage radius of each logistics hub; Based on the first quantity, a second quantity of target data points in each cluster that are at a distance less than or equal to the coverage radius from the cluster center is determined; wherein, each target data point corresponds one-to-one with the delivery vehicle; Based on the second quantity and the relationship between the number of cluster centers and the coverage of delivery vehicles, a cluster number convergence model is established.

[0073] In one embodiment, the clustering module 40 is configured to perform the following steps: The number of target logistics hubs is determined as the number of target clusters; Randomly select data points from the delivery vehicle location data that match the target cluster number as cluster centers; calculate the distance between the i-th data point and each cluster center to obtain the distance set corresponding to the i-th data point; where i is a positive integer; Based on the minimum distance in the distance set, the i-th data point is reclassified to obtain the i-th data point after the updated classification; Based on the first to mth data points after the update classification, the cluster centers are updated to obtain the updated cluster centers; wherein, m is a positive integer and m is greater than or equal to i; Repeat the process of calculating the distance between the i-th data point and each cluster center to updating the cluster centers to obtain the updated cluster centers, until each cluster center remains unchanged; The location of the target logistics hub is obtained based on the unchanged cluster centers.

[0074] In one embodiment, the apparatus further includes: A partitioning module is used to divide the delivery vehicle location data into a training set and a test set; wherein the number / location of logistics hubs is labeled in both the training set and the test set. The first evaluation module is used to input the test set into the cluster number convergence model to obtain the quantity evaluation result; The second evaluation module is used to cluster the test set based on the clustering algorithm and the quantity evaluation results to obtain the location evaluation results. The prompting module is used to output prompting information when the quantity assessment result is inconsistent with the number of logistics hubs and / or the location assessment result is inconsistent with the location of the logistics hubs; wherein, the prompting information is used to remind that the accuracy of the logistics hub planning is insufficient.

[0075] In one embodiment, the expression for the cluster number convergence model is as follows: x′k ∈D,D={x i |dist(x i Center k )≤R}; Where, x′ k Indicates the target data point in the k-th cluster; |x′ k | Indicates the number of target data points in the k-th cluster; n indicates the number of cluster centers; C k Indicates the cluster center in the k-th cluster; T n Indicates the coverage of the delivery vehicles.

[0076] In one embodiment, the expression for the optimization objective function is as follows: Where k indicates the number of target clusters; C i x indicates the cluster center in each cluster; x indicates the data point within each cluster.

[0077] Each module in the aforementioned logistics hub planning device can be implemented entirely or partially through software, hardware, or a combination thereof. Each module can be embedded in the processor of the computer device in hardware form or independent of the processor, or stored in the memory of the computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0078] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 6 As shown, the computer device includes a processor, memory, communication interface, display unit, and input device connected via a method bus. The processor provides computational and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores operating methods and computer programs. The internal memory provides an environment for the operation of the operating methods and computer programs stored in the non-volatile storage medium. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements an image processing method. The display screen can be an LCD screen or an e-ink display screen. The input device can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0079] Those skilled in the art will understand that Figure 6The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0080] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0081] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps performed by the processor of the computer device of any of the above.

[0082] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0083] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, compilable logic units, quantum computing-based data processing logic units, etc., and are not limited to these.

[0084] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0085] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A logistics hub planning method, characterized in that, The method includes: Obtain delivery vehicle location data and gross production value for the target area; Based on the delivery vehicle location data and the gross domestic product, predict the first number of delivery vehicles for the target year; A cluster number convergence model is established based on the first quantity; wherein, the cluster number convergence model is used to determine the number of target logistics hubs in the target area; Based on the number of target logistics hubs, the location data of the delivery vehicles is clustered using an optimized objective function to obtain the location of the target logistics hubs.

2. The method according to claim 1, characterized in that, The prediction of the first number of delivery vehicles for a target year based on the delivery vehicle location data and the gross domestic product includes: A target prediction model is determined based on the difference between the target year and the current year; wherein, the target prediction model includes at least one of a linear regression model, a dynamic adjustment model, an error correction model, and a phased prediction model; Based on the delivery vehicle location data and the total production value, the first quantity is determined using the target prediction model adapted to the difference.

3. The method according to claim 1, characterized in that, The step of establishing a clustering number convergence model based on the first quantity includes: Initialize the coverage radius of each logistics hub; Based on the first quantity, a second quantity of target data points in each cluster that are at a distance less than or equal to the coverage radius from the cluster center is determined; wherein, each target data point corresponds one-to-one with the delivery vehicle; Based on the second quantity and the relationship between the number of cluster centers and the coverage of delivery vehicles, a cluster number convergence model is established.

4. The method according to claim 1, characterized in that, The step of clustering the delivery vehicle location data based on the number of target logistics hubs and combining it with an optimization objective function to obtain the target logistics hub location includes: The number of target logistics hubs is determined as the number of target clusters; Randomly select data points from the delivery vehicle location data that match the target cluster number as cluster centers; Calculate the distance between the i-th data point and each cluster center to obtain the distance set corresponding to the i-th data point; where i is a positive integer; Based on the minimum distance in the distance set, the i-th data point is reclassified to obtain the i-th data point after the updated classification; Based on the first to mth data points after the update classification, the cluster centers are updated to obtain the updated cluster centers; wherein, m is a positive integer and m is greater than or equal to i; Repeat the process of calculating the distance between the i-th data point and each cluster center to updating the cluster centers to obtain the updated cluster centers, until each cluster center remains unchanged; The location of the target logistics hub is obtained based on the unchanged cluster centers.

5. The method according to claim 1, characterized in that, The method further includes: The delivery vehicle location data is divided into a training set and a test set; wherein the number / location of logistics hubs is labeled in both the training set and the test set. The test set is input into the cluster number convergence model to obtain the quantity evaluation results; Based on the clustering algorithm and the quantity evaluation results, the test set is clustered to obtain the location evaluation results; If the quantity assessment result is inconsistent with the number of logistics hubs and / or the location assessment result is inconsistent with the location of the logistics hubs, a prompt message will be output; wherein, the prompt message is used to remind that the accuracy of the logistics hub planning is insufficient.

6. The method according to claim 3, characterized in that, The expression for the cluster number convergence model is shown below: Where, x ′ k Indicates the target data point in the k-th cluster; |x ′ k | Indicates the number of target data points in the k-th cluster; n indicates the number of cluster centers; C k Indicates the cluster center in the k-th cluster; T n Indicates the coverage of the delivery vehicles.

7. The method according to claim 4, characterized in that, The expression for the optimization objective function is as follows: Where k indicates the number of target clusters; C i x indicates the cluster center in each cluster; x indicates the data point within each cluster.

8. A logistics hub planning device, characterized in that, The device includes: The acquisition module is used to acquire the location data of delivery vehicles and the total production value of the target area; The prediction module is used to predict the first number of delivery vehicles in a target year based on the delivery vehicle location data and the gross domestic product. A modeling module is used to establish a cluster number convergence model based on the first quantity; wherein, the cluster number convergence model is used to determine the number of target logistics hubs in the target area; The clustering module is used to cluster the delivery vehicle location data based on the number of target logistics hubs and in conjunction with an optimization objective function to obtain the location of the target logistics hubs.

9. A computer device, characterized in that, The system includes a processor and a memory for storing a computer program of the processor; wherein the processor is configured to, when executing the computer program, implement the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it performs the steps of the method according to any one of claims 1 to 7.

Images