An agricultural product circulation project site selection decision method, device and electronic equipment

Abstract

This invention provides a method, apparatus, and electronic device for site selection decision-making in agricultural product distribution projects, relating to the field of agricultural product distribution technology. The method includes collecting multi-source heterogeneous data within a target area and preprocessing it to obtain a basic distribution database; constructing a complex agricultural product distribution network using agricultural product producers, distributors, and consumer markets as nodes, and logistics flow direction and volume as edges; processing geographic information data using spatial analysis methods to quantify the strength of logistics connections and spatial constraints between nodes in the complex agricultural product distribution network; applying the DBSCAN clustering algorithm to perform cluster analysis on each node, identifying core node clusters with highly dense logistics connections and significant spatial agglomeration characteristics; and comprehensively evaluating the identified core node clusters based on spatial attributes, land planning compliance, and traffic accessibility to determine the optimal site location. This invention can effectively improve the scientific rigor and accuracy of site selection for agricultural product distribution projects.

Description

Technical Field

[0001] This invention relates to the field of agricultural product distribution technology, and in particular to a method, apparatus, and electronic device for site selection decision-making of agricultural product distribution projects based on complex network clustering. Background Technology

[0002] Agricultural product distribution parks are key hubs connecting agricultural production and consumer markets, playing a vital role in reducing distribution links, minimizing logistics losses, and ensuring a stable supply and quality safety of agricultural products. With the upgrading of consumption patterns and the rapid development of the agricultural product supply chain, higher demands are being placed on the scientific layout, operational efficiency, and reach of the distribution system. This is especially true for fresh agricultural products such as eggs, where distribution efficiency directly impacts product freshness and market competitiveness.

[0003] However, in the current planning of agricultural product circulation projects, site selection decisions often rely on industry experience, qualitative analysis, or single geographical factors. They often fail to fully integrate multi-dimensional data such as production, circulation, consumption, transportation, and land use, and lack systematic and quantitative scientific evaluation methods. This leads to problems such as low matching degree between project site selection and actual logistics pattern and unreasonable service coverage.

[0004] Therefore, how to construct a data-driven, model-supported, and refined site selection method has become an urgent need to improve the planning level of agricultural product circulation facilities and optimize the supply chain layout. Summary of the Invention

[0005] This invention provides a method, apparatus, and electronic device for site selection decision-making in agricultural product distribution projects. It addresses technical problems such as unreasonable site selection and high logistics costs resulting from reliance on industry experience in current agricultural product distribution project planning. This invention significantly improves the scientific rigor and accuracy of site selection decisions. The technical solution is as follows:

[0006] In a first aspect, embodiments of the present invention provide a method for site selection decision-making for agricultural product distribution projects, including:

[0007] Collect multi-source heterogeneous data within the target area and preprocess the collected multi-source heterogeneous data to obtain a circulation basic database. The multi-source heterogeneous data includes at least the geographical location and production capacity data of agricultural product producers, the location and operation data of circulation entities, the geographical location and demand data of consumer markets, and regional transportation network data.

[0008] Based on the data in the aforementioned circulation database, a complex agricultural product circulation network is constructed, with agricultural product producers, circulation entities, and consumer markets as nodes and logistics flow direction and volume as edges.

[0009] Spatial analysis methods are used to process geographic information data to quantify the strength of logistics connections and spatial constraints among nodes in the complex agricultural product circulation network.

[0010] The DBSCAN clustering algorithm is applied to perform cluster analysis on each node in the complex agricultural product circulation network. Based on the spatial distance between nodes and the strength of logistics connections, the core node clusters with highly dense logistics connections and significant spatial agglomeration characteristics are identified.

[0011] Based on the identified core node clusters, a comprehensive evaluation is conducted, taking into account their spatial attributes, land planning compliance, and traffic accessibility, to determine the optimal site location.

[0012] Optionally, the construction of a complex agricultural product distribution network, using agricultural product producers, distributors, and consumer markets as nodes and logistics flow direction and volume as edges, includes:

[0013] Each agricultural product producer, distributor, and consumer market is abstracted into a network node;

[0014] If there is a stable agricultural product circulation relationship between node i and node j, then a directed edge e_ij is established between node i and node j, where i and j are positive integers, and the weight w_ij of the directed edge is represented by the circulation volume or transportation frequency.

[0015] Based on each node, directed edge, and the weight of the directed edge, a weighted directed complex network G for agricultural product circulation is constructed, G = (V, E, W), where V represents the set of nodes, E represents the set of edges, and W represents the set of weights.

[0016] Optionally, the step of using spatial analysis methods to process geographic information data and quantify the strength of logistics connections and spatial constraints between nodes in the complex agricultural product distribution network includes:

[0017] The optimal path and logistics cost between nodes in the complex agricultural product distribution network are calculated using network analysis.

[0018] The service coverage of each node in the complex agricultural product distribution network is determined using buffer analysis.

[0019] Optionally, the DBSCAN clustering algorithm is applied to perform cluster analysis on each node in the complex agricultural product circulation network. Based on the spatial distance and logistics connection strength between nodes, core node clusters with highly dense logistics connections and significant spatial agglomeration characteristics are identified, including:

[0020] Define a comprehensive feature vector for each node i in the complex agricultural product distribution network. , ;in This represents the geographical Euclidean distance between node i and node j. This represents the strength of the logistics connection from node i to node j, where Norm() is the normalization function. and It is a weighting coefficient, and + =1;

[0021] Let the set of nodes be V, Preset any node v i Let the neighborhood radius be Eps, and determine the node v i The set of nodes whose distance does not exceed the neighborhood radius Eps , Where 1 ≤ i ≤ n, and i and n are both positive integers;

[0022] If node v i If the number of nodes contained within the neighborhood radius Eps is not less than the preset minimum number of samples MinPts, then node v will be... i It has been identified as a core node;

[0023] For an unvisited core node v i Create a new cluster , and All nodes join ;for For each new core node, recursively add nodes within its neighborhood radius Eps that have not yet been assigned to any cluster. ;when When it can no longer expand, the cluster is complete.

[0024] Optionally, =0.4, =0.6.

[0025] Optionally, the optimal site location is determined by comprehensively evaluating each identified core node cluster in conjunction with its spatial attributes, land planning compliance, and traffic accessibility, including:

[0026] For each core node cluster, calculate the average coordinates of all nodes within the cluster, or calculate the cluster centroid coordinates based on the node traffic weights, and use the average coordinates or the cluster centroid coordinates as representative points of the core node cluster.

[0027] A comprehensive evaluation of each representative location was conducted based on its spatial attributes, compliance with land planning, and accessibility.

[0028] The representative point with the highest score is determined as the optimal site.

[0029] Optionally, after determining the representative point with the highest score as the optimal location, the method further includes:

[0030] Based on the logistics coverage of the optimal location, mark the total number of agricultural production entities within the logistics coverage area.

[0031] Optionally, the method further includes:

[0032] The site selection results are visualized and output as a thematic map containing recommended site locations and logistics coverage areas.

[0033] Optionally, the agricultural products are fresh agricultural products, including at least one of the following: eggs, fresh milk and dairy products, aquatic products, grains, vegetables, fruits, and livestock and poultry meat products.

[0034] Secondly, embodiments of the present invention provide a site selection decision-making device for agricultural product circulation projects, comprising:

[0035] The multi-source heterogeneous data processing module is used to collect multi-source heterogeneous data within the target area and preprocess the collected multi-source heterogeneous data to obtain a circulation basic database. The multi-source heterogeneous data includes at least the geographical location and production capacity data of agricultural product producers, the location and operation data of circulation entities, the geographical location and demand data of consumer markets, and regional transportation network data.

[0036] The network construction module is used to construct a complex agricultural product circulation network based on the data in the circulation basic database, with agricultural product producers, circulation entities, and consumer markets as nodes and logistics flow direction and volume as edges.

[0037] The spatial analysis module is used to process geographic information data using spatial analysis methods to quantify the strength of logistics connections and spatial constraints between nodes in the complex agricultural product circulation network.

[0038] The clustering analysis module is used to apply the DBSCAN clustering algorithm to perform clustering analysis on each node in the complex agricultural product circulation network. Based on the spatial distance between nodes and the strength of logistics connections, it identifies core node clusters with highly dense logistics connections and significant spatial agglomeration characteristics.

[0039] The site determination module is used to comprehensively evaluate the identified core node clusters based on their spatial attributes, land planning compliance, and traffic accessibility to determine the optimal site location.

[0040] Thirdly, embodiments of the present invention provide an electronic device, including: a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the agricultural product circulation project site selection decision method as described in the first aspect.

[0041] Fourthly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the site selection decision method for agricultural product circulation projects as described in the first aspect.

[0042] Fifthly, embodiments of the present invention provide a computer program product including computer instructions that, when executed by a processor, implement the steps of the agricultural product distribution project site selection decision method as described in the first aspect.

[0043] The beneficial effects of the above-mentioned technical solution of the present invention are:

[0044] The site selection decision-making method for agricultural product circulation projects provided in this invention includes: collecting multi-source heterogeneous data within a target area and preprocessing the collected multi-source heterogeneous data to obtain a circulation basic database. The multi-source heterogeneous data includes at least the geographical location and production capacity data of agricultural product producers, the location and operation data of circulation entities, the geographical location and demand data of consumer markets, and regional transportation network data. Based on the data in the circulation basic database, a complex agricultural product circulation network is constructed with agricultural product producers, circulation entities, and consumer markets as nodes and logistics flow direction and volume as edges. Spatial analysis methods are used to process the geographic information data to quantify the logistics connection strength and spatial constraints between nodes in the complex agricultural product circulation network. The DBSCAN clustering algorithm is applied to perform cluster analysis on each node in the complex agricultural product circulation network. Based on the spatial distance and logistics connection strength between nodes, core node clusters with highly dense logistics connections and significant spatial agglomeration characteristics are identified. Based on the identified core node clusters, a comprehensive evaluation is conducted combining their spatial attributes, land planning compliance, and traffic accessibility to determine the optimal site location. This invention constructs a complex agricultural product circulation network by integrating multi-source heterogeneous data, and applies the DBSCAN algorithm to identify logistics cluster cores from both network and spatial dimensions. Finally, it combines multiple constraints to perform refined site selection calculations, realizing the transformation from experience-based decision-making to data model-driven decision-making, which can effectively improve the scientificity and accuracy of site selection for agricultural product circulation projects.

[0045] The site selection decision-making method for agricultural product circulation projects provided in this embodiment of the invention is applicable to the planning, construction, and operation management of agricultural product circulation projects, circulation parks, and other entities such as county-level agricultural departments and agricultural enterprises. Attached Figure Description

[0046] Figure 1 This is a flowchart of a site selection decision-making method for agricultural product circulation projects disclosed in an embodiment of the present invention;

[0047] Figure 2 This is a flowchart illustrating the method for constructing a complex egg distribution network in an embodiment of the present invention.

[0048] Figure 3 This is a schematic diagram of the structure of a site selection decision-making device for agricultural product circulation projects disclosed in an embodiment of the present invention;

[0049] Figure 4 This is a schematic diagram of the structure of an electronic device disclosed in an embodiment of the present invention. Detailed Implementation

[0050] To make the technical problems, technical solutions, and advantages of this invention clearer, a detailed description will be provided below in conjunction with the accompanying drawings and specific embodiments. In the following description, specific details such as particular configurations and components are provided merely to aid in a comprehensive understanding of the embodiments of this invention. Therefore, those skilled in the art should understand that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this invention. Furthermore, for clarity and brevity, descriptions of known functions and structures have been omitted.

[0051] It should be understood that the phrase "one embodiment" or "an embodiment" throughout the specification means that a specific feature, structure, or characteristic related to the embodiment is included in at least one embodiment of the invention. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification do not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments.

[0052] In various embodiments of the present invention, it should be understood that the sequence number of each process described below does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0053] Scientific planning of agricultural product distribution projects is key to optimizing the supply chain and reducing costs while increasing efficiency. Traditional site selection methods often rely on expert experience or single-factor analysis, making it difficult to systematically integrate heterogeneous data from multiple sources such as production, distribution, consumption, transportation, and land, resulting in insufficient accuracy in site selection. Therefore, this invention provides a site selection decision-making method for agricultural product distribution projects based on complex network clustering. By constructing a technical framework of "data-network-model-decision," it achieves quantitative and refined decision-making for the site selection of agricultural product distribution projects.

[0054] like Figure 1 As shown, the site selection decision-making method for agricultural product circulation projects provided in this embodiment of the invention includes:

[0055] Step 101: Collect multi-source heterogeneous data within the target area and preprocess the collected multi-source heterogeneous data to obtain a circulation basic database. The multi-source heterogeneous data includes at least the geographical location and production capacity data of agricultural product producers, the location and operation data of circulation entities, the geographical location and demand data of consumer markets, and regional transportation network data.

[0056] Specifically, this step is crucial for building a unified spatial data foundation. In practical applications, this may involve collecting data on the geographical location and annual inventory (or annual egg production) of all egg-laying chicken farms (households) within the target county, the geographical location and annual operating scale of major egg traders, the geographical location and annual demand data of major consumer markets (such as wholesale markets and large supermarkets), and vector road network data of roads at all levels within the county (railways, expressways, national highways, provincial highways, county roads, and township roads). This data can come from agricultural and rural affairs department statistical reports, enterprise surveys, transportation geographic information platforms, and remote sensing image interpretation.

[0057] All collected data undergoes preprocessing, which may include cleaning, standardization, and spatialization. Cleaning removes duplicate data and corrects or removes or corrects obviously erroneous or anomaly data. Standardization normalizes all data or standardizes it to the same scale using Z-score. Spatialization converts all entities with geographic attributes into a geographic point layer with a unified coordinate system (CGCS2000), and attaches attribute data as attribute fields for each point, thereby constructing a comprehensive, layered basic database of agricultural product circulation suitable for GIS analysis.

[0058] The agricultural products used in these embodiments of the invention are preferably fresh agricultural products, including at least one of the following: eggs, fresh milk and dairy products, aquatic products, grains, vegetables, fruits, and livestock and poultry meat. To facilitate a clearer description of these embodiments, the applicant will use eggs as an example in the following description.

[0059] Step 102: Based on the data in the circulation basic database, construct a complex agricultural product circulation network with agricultural product producers, circulation entities, and consumer markets as nodes and logistics flow direction and volume as edges.

[0060] This invention constructs a complex agricultural product distribution network based on the data in the distribution database obtained in step 101. The specific implementation method is as follows: Figure 2 As shown, it includes:

[0061] Step 1021: Abstract each agricultural product producer, distributor, and consumer market into a network node.

[0062] Step 1022: If there is a stable agricultural product circulation relationship between node i and node j, then establish a directed edge e_ij between node i and node j, where i and j are positive integers, and the weight w_ij of the directed edge is represented by the circulation volume or transportation frequency.

[0063] Step 1023: Based on each node, directed edge, and the weight of the directed edge, construct a weighted directed complex network G for agricultural product circulation, G = (V, E, W), where V represents the set of nodes, E represents the set of edges, and W represents the set of weights.

[0064] In constructing a complex agricultural product circulation network, this invention abstracts each agricultural product producer (e.g., a farm), distributor (i.e., a distribution enterprise), and consumer market as a network node i. Based on actual logistics surveys or transportation trajectory data, if a stable agricultural product circulation relationship exists between node i and node j, a directed edge e_ij is established between them. The weight w_ij of the edge can be represented by the circulation volume (tons / year) or transportation frequency. Thus, based on each node, the directed edge, and the weight of the directed edge, a weighted directed complex agricultural product circulation network G is constructed, G = (V, E, W), where V is the set of nodes, E is the set of edges, and W is the set of weights.

[0065] Step 103: Use spatial analysis methods to process geographic information data and quantify the strength of logistics connections and spatial constraints between nodes in the complex agricultural product circulation network.

[0066] The complex agricultural product distribution network constructed in step 102 needs to be spatially analyzed. Specifically, a geographic information system (GIS) is used to conduct spatial analysis of the logistics network and consumption points, quantifying the logistics costs, spatiotemporal distances, and spatial constraints between nodes. Specifically:

[0067] Network analysis is used to calculate the optimal path and logistics cost (such as the shortest transportation time or distance) between nodes (i.e., between any two nodes) in the complex agricultural product distribution network.

[0068] The service coverage of each node in the complex agricultural product distribution network was determined using buffer analysis.

[0069] Step 103 assigns spatial attributes and relational weights to each node in the complex agricultural product circulation network.

[0070] Step 104: Apply the DBSCAN clustering algorithm to perform cluster analysis on each node in the complex agricultural product circulation network. Based on the spatial distance between nodes and the strength of logistics connections, identify the core node clusters with highly dense logistics connections and significant spatial agglomeration characteristics.

[0071] This invention applies the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) clustering algorithm to perform cluster analysis on the nodes in a constructed complex agricultural product distribution network. This algorithm maps network nodes to geographic space, using geographical distance and / or logistics connection strength between nodes as distance metrics. By setting a neighborhood radius and a minimum sample size, it performs clustering to automatically identify node clusters with high-density connections and marks nodes in low-density areas as noise points, thereby identifying core node clusters with highly dense logistics connections and significant spatial agglomeration characteristics.

[0072] Specifically, step 104 in this embodiment of the invention may include:

[0073] Step 1041: Define a comprehensive feature vector for each node i in the complex agricultural product circulation network. , .

[0074] in This represents the geographical Euclidean distance between node i and node j. This represents the strength of the logistics connection from node i to node j, where Norm() is the normalization function. and It is a weighting coefficient, and + =1.

[0075] It should be noted that the Norm() function is used to map values ​​of different dimensions to the same dimension, such as mapping to the interval [0,1]. If there is no flow from node i to node j, then... Set to 0; this case is considered during calculation. No calculations are performed. and To balance the importance of geographical distance and logistical connections in clustering, it can be set as follows in specific applications: =0.4, =0.6, which places greater emphasis on logistics connections.

[0076] This step is crucial for achieving automatic identification of core nodes. First, in this embodiment of the invention, a comprehensive feature vector is defined for each node i. This is used to measure its "proximity" to other nodes. Specifically, This represents the combined distance between node i and node j.

[0077] Step 1042, let the set of nodes be V, Preset any node v iLet the neighborhood radius be Eps, and determine the node v i The set of nodes whose distance does not exceed the neighborhood radius Eps , , where 1≤i≤n, and i and n are both positive integers.

[0078] Step 1043, if node v i If the number of nodes within a neighborhood radius Eps is not less than the preset minimum number of samples MinPts, then node v will be... i It has been identified as a core node.

[0079] Nodes that do not belong to any cluster are marked as noise points.

[0080] Step 1044, for an unvisited core node v i Create a new cluster , and All nodes join ;for For each new core node, recursively add nodes within its neighborhood radius Eps that have not yet been assigned to any cluster. ;when When it can no longer expand, the cluster is complete.

[0081] This can be expressed by the formula:

[0082]

[0083] In this embodiment of the invention, the neighborhood radius Eps and the minimum number of samples MinPts can be initially set according to the actual situation and adjusted and optimized through multiple experiments. This embodiment of the invention ultimately outputs a series of core node clusters {C1, C2, ...} representing the core region and a set of noise points representing the non-core region.

[0084] Step 105: Based on the identified core node clusters, a comprehensive evaluation is conducted, taking into account their spatial attributes, land planning compliance, and traffic accessibility, to determine the optimal site location.

[0085] Based on the core node clusters identified in step 104, this embodiment of the invention performs a comprehensive evaluation of each core node cluster, specifically:

[0086] Step 1051: For each core node cluster, calculate the average coordinates of all nodes within the cluster, or calculate the cluster centroid coordinates based on the node traffic weights, and use the average coordinates or the cluster centroid coordinates as representative points of the core node cluster.

[0087] Step 1052: Conduct a comprehensive evaluation of each representative location based on its spatial attributes, land planning compliance, and traffic accessibility.

[0088] Step 1053: Determine the representative point with the highest score as the optimal location point.

[0089] In this embodiment of the invention, each core node cluster identifies a representative location, and each representative location is evaluated based on multiple criteria: 1) Spatial attributes: whether the terrain is flat and the geological conditions are favorable; 2) Land planning compliance: through GIS overlay analysis, verifying whether it is located within logistics and warehousing land or permitted agricultural facility land, and whether it avoids the red lines for arable land protection and ecological protection; 3) Transportation accessibility: calculating the distance from the representative location to highway entrances, national and provincial highways, or using network analysis to calculate the average time cost to major consumer markets, etc. Each representative location receives a score after comprehensive evaluation. In this embodiment of the invention, representative locations can be ranked according to their scores, and the location with the highest score is selected as the optimal project site.

[0090] More preferably, in this embodiment of the invention, after selecting the location with the highest score as the optimal project site, the total number of agricultural production entities within the logistics radiation range of the optimal site can be marked according to the logistics radiation range of the optimal site.

[0091] Based on the foregoing embodiments, the site selection decision-making method for agricultural product circulation projects provided by the embodiments of the present invention may further include:

[0092] The site selection results are visualized and output as a thematic map containing recommended site locations and logistics coverage areas.

[0093] The present invention provides a site selection decision method for agricultural product circulation projects based on complex network clustering. By integrating multi-source heterogeneous data to construct a complex agricultural product circulation network, and applying the DBSCAN algorithm to identify the core of logistics agglomeration from both network and spatial dimensions, the method combines multiple constraints to perform refined site selection calculations. This realizes the transformation from experience-based decision-making to data model-driven decision-making, effectively improving the scientificity, accuracy, and practicality of project planning.

[0094] Based on the site selection decision-making method for agricultural product circulation projects provided in the foregoing embodiments of the present invention, the present invention also provides a site selection decision-making device for agricultural product circulation projects, such as... Figure 3 As shown, it includes:

[0095] The multi-source heterogeneous data processing module 10 is used to collect multi-source heterogeneous data within the target area and preprocess the collected multi-source heterogeneous data to obtain a circulation basic database. The multi-source heterogeneous data includes at least the geographical location and production capacity data of agricultural product production entities, the location and operation data of circulation entities, the geographical location and demand data of consumer markets, and regional transportation network data.

[0096] Network construction module 20 is used to construct a complex agricultural product circulation network based on the data in the circulation basic database, with agricultural product producers, circulation entities, and consumer markets as nodes and logistics flow direction and volume as edges;

[0097] Spatial analysis module 30 is used to process geographic information data using spatial analysis methods to quantify the strength of logistics connections and spatial constraints between nodes in the complex agricultural product circulation network.

[0098] The clustering analysis module 40 is used to apply the DBSCAN clustering algorithm to perform clustering analysis on each node in the complex agricultural product circulation network. Based on the spatial distance between nodes and the strength of logistics connections, it identifies core node clusters with highly dense logistics connections and significant spatial agglomeration characteristics.

[0099] The site determination module 50 is used to comprehensively evaluate each identified core node cluster based on its spatial attributes, land planning compliance, and traffic accessibility to determine the optimal site location.

[0100] Optionally, the network construction module 20 is specifically used for:

[0101] Each agricultural product producer, distributor, and consumer market is abstracted into a network node;

[0102] If there is a stable agricultural product circulation relationship between node i and node j, then a directed edge e_ij is established between node i and node j, where i and j are positive integers, and the weight w_ij of the directed edge is represented by the circulation volume or transportation frequency.

[0103] Based on each node, directed edge, and the weight of the directed edge, a weighted directed complex network G for agricultural product circulation is constructed, G = (V, E, W), where V represents the set of nodes, E represents the set of edges, and W represents the set of weights.

[0104] Optionally, the spatial analysis module 30 is specifically used for:

[0105] The optimal path and logistics cost between nodes in the complex agricultural product distribution network are calculated using network analysis.

[0106] The service coverage of each node in the complex agricultural product distribution network is determined using buffer analysis.

[0107] Optionally, the clustering analysis module 40 is specifically used for:

[0108] Define a comprehensive feature vector for each node i in the complex agricultural product distribution network. , ;in This represents the geographical Euclidean distance between node i and node j. This represents the strength of the logistics connection from node i to node j, where Norm() is the normalization function. and It is a weighting coefficient, and + =1;

[0109] Let the set of nodes be V, Preset any node v i Let the neighborhood radius be Eps, and determine the node v i The set of nodes whose distance does not exceed the neighborhood radius Eps , Where 1 ≤ i ≤ n, and i and n are both positive integers;

[0110] If node v i If the number of nodes within a neighborhood radius Eps is not less than the preset minimum number of samples MinPts, then node v will be... i It has been identified as a core node;

[0111] For an unvisited core node v i Create a new cluster , and All nodes join ;for For each new core node, recursively add nodes within its neighborhood radius Eps that have not yet been assigned to any cluster. ;when When it can no longer expand, the cluster is complete.

[0112] Preferably, =0.4, =0.6.

[0113] Optionally, the location determination module 50 is specifically used for:

[0114] For each core node cluster, calculate the average coordinates of all nodes within the cluster, or calculate the cluster centroid coordinates based on the node traffic weights, and use the average coordinates or the cluster centroid coordinates as representative points of the core node cluster.

[0115] A comprehensive evaluation of each representative location was conducted based on its spatial attributes, compliance with land planning, and accessibility.

[0116] The representative point with the highest score is determined as the optimal site.

[0117] Preferably, the agricultural product circulation project site selection decision device provided in this embodiment of the invention may further include a labeling module, used to label the total number of agricultural product production entities within the logistics radiation range based on the logistics radiation range of the optimal site location.

[0118] Preferably, the agricultural product circulation project site selection decision device provided in this embodiment of the invention may further include a visualization module, which is used to visualize the site selection result and generate a thematic map containing recommended site locations and logistics coverage.

[0119] The agricultural products in the foregoing embodiments of the present invention are preferably fresh agricultural products, including at least one of the following: eggs, fresh milk and dairy products, aquatic products, grains, vegetables, fruits, and livestock and poultry meat products.

[0120] It should be noted that the agricultural product circulation project site selection decision device is the same as the agricultural product circulation project site selection decision method in the aforementioned embodiments. All the implementation means in the above method embodiments are applicable to the embodiments of the agricultural product circulation project site selection decision device and can achieve the same technical effect.

[0121] like Figure 4 As shown, embodiments of the present invention also provide an electronic device, including:

[0122] The processor 1000; and the memory 1020 connected to the processor 1000 via a bus interface, the memory 1020 being used to store programs and data used by the processor 1000 during operation, and the processor 1000 calling and executing the programs and data stored in the memory 1020.

[0123] The transceiver 1010 is connected to a bus interface and is used to receive and send data under the control of the processor 1000; the processor 1000 is used to read the program in the memory 1020 to implement the steps of the agricultural product circulation project site selection decision method described in the foregoing embodiments.

[0124] Among them, Figure 4In this context, the bus architecture can include any number of interconnected buses and bridges, specifically linking various circuits together, represented by one or more processors (processor 1000) and memory (memory 1020). The bus architecture can also link various other circuits, such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. The bus interface provides an interface. The transceiver 1010 can be multiple components, including transmitters and transceivers, providing a unit for communicating with various other devices over a transmission medium. For different terminals, the user interface 1030 can also be an interface capable of connecting external or internal devices, including but not limited to keypads, displays, speakers, microphones, joysticks, etc. The processor 1000 is responsible for managing the bus architecture and general processing, and the memory 1020 can store data used by the processor 1000 during operation.

[0125] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a computer program instructing the relevant hardware to implement them. The computer program includes instructions to perform some or all of the steps of the above methods; and the computer program can be stored in a readable storage medium, which can be any form of storage medium.

[0126] In addition, this embodiment of the invention also provides a computer-readable storage medium storing a computer program thereon. When the program is executed by a processor, it implements the steps of the site selection decision method for agricultural product circulation projects in the foregoing embodiments and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0127] This application also provides a computer program product, including computer instructions. When executed by a processor, the computer instructions implement the various processes of the above-mentioned embodiment of the agricultural product circulation project site selection decision method, and can achieve the same technical effect. To avoid repetition, they will not be described again here.

[0128] Furthermore, it should be noted that in the apparatus and method of the present invention, it is obvious that the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered equivalent solutions of the present invention. Moreover, the steps performing the above series of processes can naturally be executed in the order described, but are not necessarily required to be executed in chronological order; some steps can be executed in parallel or independently of each other. Those skilled in the art will understand that all or any step or component of the method and apparatus of the present invention can be implemented in any computing device (including processors, storage media, etc.) or network of computing devices, in hardware, firmware, software, or a combination thereof. This is something that those skilled in the art can achieve by using their basic programming skills after reading the description of the present invention.

[0129] Therefore, the object of the present invention can also be achieved by running a program or a set of programs on any computing device. The computing device can be a known general-purpose device. Therefore, the object of the present invention can also be achieved simply by providing a program product containing program code implementing the method or apparatus. That is, such a program product also constitutes the present invention, and the storage medium storing such a program product also constitutes the present invention. Obviously, the storage medium can be any known storage medium or any storage medium developed in the future. It should also be noted that in the apparatus and method of the present invention, it is obvious that the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered equivalent to the present invention. Furthermore, the steps performing the above series of processes can naturally be performed in the order described, but are not necessarily required to be performed in chronological order. Some steps can be performed in parallel or independently of each other.

[0130] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A site selection decision-making method for agricultural product distribution projects, characterized in that, include: Collect multi-source heterogeneous data within the target area and preprocess the collected multi-source heterogeneous data to obtain a circulation basic database. The multi-source heterogeneous data includes at least the geographical location and production capacity data of agricultural product producers, the location and operation data of circulation entities, the geographical location and demand data of consumer markets, and regional transportation network data. Based on the data in the aforementioned circulation database, a complex agricultural product circulation network is constructed, with agricultural product producers, circulation entities, and consumer markets as nodes and logistics flow direction and volume as edges. Spatial analysis methods are used to process geographic information data to quantify the strength of logistics connections and spatial constraints among nodes in the complex agricultural product circulation network. The DBSCAN clustering algorithm is applied to perform cluster analysis on each node in the complex agricultural product circulation network. Based on the spatial distance between nodes and the strength of logistics connections, the core node clusters with highly dense logistics connections and significant spatial agglomeration characteristics are identified. Based on the identified core node clusters, a comprehensive evaluation is conducted, taking into account their spatial attributes, land planning compliance, and traffic accessibility, to determine the optimal site location.

2. The site selection decision-making method for agricultural product circulation projects according to claim 1, characterized in that, The aforementioned complex agricultural product distribution network is constructed using agricultural product producers, distributors, and consumer markets as nodes, and logistics flow direction and volume as edges, including: Each agricultural product producer, distributor, and consumer market is abstracted into a network node; If there is a stable agricultural product circulation relationship between node i and node j, then a directed edge e_ij is established between node i and node j, where i and j are positive integers, and the weight w_ij of the directed edge is represented by the circulation volume or transportation frequency. Based on each node, directed edge, and the weight of the directed edge, a weighted directed complex network G for agricultural product circulation is constructed, G = (V, E, W), where V represents the set of nodes, E represents the set of edges, and W represents the set of weights.

3. The site selection decision-making method for agricultural product circulation projects according to claim 1, characterized in that, The process of using spatial analysis methods to process geographic information data and quantify the strength of logistical connections and spatial constraints among nodes in the complex agricultural product distribution network includes: The optimal path and logistics cost between nodes in the complex agricultural product distribution network are calculated using network analysis. The service coverage of each node in the complex agricultural product distribution network is determined using buffer analysis.

4. The site selection decision-making method for agricultural product circulation projects according to claim 1, characterized in that, The DBSCAN clustering algorithm is applied to perform cluster analysis on the nodes in the complex agricultural product circulation network. Based on the spatial distance and logistics connection strength between nodes, core node clusters with highly dense logistics connections and significant spatial agglomeration characteristics are identified, including: Define a comprehensive feature vector for each node i in the complex agricultural product distribution network. , ;in This represents the geographical Euclidean distance between node i and node j. This represents the strength of the logistics connection from node i to node j, where Norm() is the normalization function. and It is a weighting coefficient, and + =1; Let the set of nodes be V, Preset any node v i Let the neighborhood radius be Eps, and determine the node v i The set of nodes whose distance does not exceed the neighborhood radius Eps , Where 1 ≤ i ≤ n, and i and n are both positive integers; If node v i If the number of nodes within a neighborhood radius Eps is not less than the preset minimum number of samples MinPts, then node v will be... i It has been identified as a core node; For an unvisited core node v i Create a new cluster , and All nodes join ;for For each new core node, recursively add nodes within its neighborhood radius Eps that have not yet been assigned to any cluster. ;when When it can no longer expand, the cluster is complete.

5. The site selection decision-making method for agricultural product circulation projects according to claim 4, characterized in that, =0.4， =0.6。 6. The site selection decision-making method for agricultural product circulation projects according to claim 1, characterized in that, The optimal site location is determined by comprehensively evaluating each identified core node cluster in conjunction with its spatial attributes, land planning compliance, and traffic accessibility, including: For each core node cluster, calculate the average coordinates of all nodes within the cluster, or calculate the cluster centroid coordinates based on the node traffic weights, and use the average coordinates or the cluster centroid coordinates as representative points of the core node cluster. A comprehensive evaluation of each representative location was conducted based on its spatial attributes, compliance with land planning, and accessibility. The representative point with the highest score is determined as the optimal site.

7. The site selection decision-making method for agricultural product circulation projects according to claim 6, characterized in that, After determining the representative point with the highest score as the optimal location, the method further includes: Based on the logistics coverage of the optimal location, mark the total number of agricultural production entities within the logistics coverage area.

8. The site selection decision-making method for agricultural product circulation projects according to claim 1, characterized in that, The method further includes: The site selection results are visualized and output as a thematic map that includes recommended site locations and logistics coverage areas.

9. The method for site selection decision-making for agricultural product circulation projects according to any one of claims 1-8, characterized in that, The agricultural products mentioned are fresh agricultural products, including at least one of the following: eggs, fresh milk and dairy products, aquatic products, grains, vegetables, fruits, and livestock and poultry meat products.

10. A site selection decision-making device for agricultural product distribution projects, characterized in that, include: The multi-source heterogeneous data processing module is used to collect multi-source heterogeneous data within the target area and preprocess the collected multi-source heterogeneous data to obtain a circulation basic database. The multi-source heterogeneous data includes at least the geographical location and production capacity data of agricultural product producers, the location and operation data of circulation entities, the geographical location and demand data of consumer markets, and regional transportation network data. The network construction module is used to construct a complex agricultural product circulation network based on the data in the circulation basic database, with agricultural product producers, circulation entities, and consumer markets as nodes and logistics flow direction and volume as edges. The spatial analysis module is used to process geographic information data using spatial analysis methods, and to quantify the strength of logistics connections and spatial constraints between nodes in the complex agricultural product circulation network. The clustering analysis module is used to apply the DBSCAN clustering algorithm to perform clustering analysis on each node in the complex agricultural product circulation network. Based on the spatial distance between nodes and the strength of logistics connections, it identifies core node clusters with highly dense logistics connections and significant spatial agglomeration characteristics. The site selection module is used to determine the optimal site location by comprehensively evaluating each identified core node cluster in combination with its spatial attributes, land planning compliance, and traffic accessibility.

Images