Intelligent logistics scheduling method and device for optimizing agricultural product distribution

Abstract

The invention discloses an intelligent logistics scheduling method and device for optimizing agricultural product distribution, and relates to the technical field of logistics scheduling, and the method comprises the steps: obtaining an alternative delivery position set of a target agricultural product and a corresponding basic information flow set, and carrying out the multi-dimensional attribute marking, and determining an alternative agricultural product attribute parameter set; analyzing the target order task to obtain an agricultural product distribution demand quantity and a transportation task destination, carrying out transportation line optimization, and determining an alternative transportation logistics line set; constructing a logistics scheduling fitness function, performing distribution analysis on the alternative agricultural product attribute parameter set, generating an agricultural product scheduling parameter solution space, performing global optimization, determining target agricultural product scheduling parameters, and performing logistics distribution scheduling on target agricultural products. The technical problems of low agricultural product logistics scheduling efficiency, high cost and unreasonable resource allocation in the prior art are solved, and the technical effects of improving the logistics scheduling efficiency, reducing the transportation cost and realizing reasonable resource allocation are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of logistics scheduling, and particularly relates to an intelligent logistics scheduling method and device for optimizing the distribution of agricultural products. Background Art

[0002] With the rapid development of agricultural modernization and the logistics transportation industry, the distribution of agricultural products and logistics scheduling play a crucial role in ensuring the efficient operation of the agricultural product supply chain. However, with the continuous expansion of the circulation scale of agricultural products and the increasing complexity of the logistics network, traditional agricultural product logistics scheduling methods have been difficult to meet the needs of modern logistics management. The existing logistics scheduling methods mainly rely on manual experience or static scheduling models based on fixed rules, often having problems such as low scheduling efficiency, unreasonable resource allocation, and high transportation costs, and are difficult to adapt to the changing market demands and complex transportation environments. Summary of the Invention

[0003] This application provides an intelligent logistics scheduling method and device for optimizing the distribution of agricultural products, aiming to solve the technical problems of low efficiency, high cost, and unreasonable resource allocation in the existing agricultural product logistics scheduling.

[0004] In view of the above problems, this application provides an intelligent logistics scheduling method and device for optimizing the distribution of agricultural products.

[0005] In the first aspect of this application, an intelligent logistics scheduling method for optimizing the distribution of agricultural products is provided. The method includes: Collect and obtain a set of alternative shipping locations for the target agricultural product, interactively obtain a set of basic information flows for the set of alternative shipping locations, and respectively perform multi-dimensional attribute marking on the set of basic information flows to obtain a set of alternative agricultural product attribute parameters; analyze the target order task to obtain the agricultural product distribution demand quantity and the destination of the transportation task, respectively perform optimization of the transportation route based on the set of alternative shipping locations and the destination of the transportation task, and determine a set of alternative transportation logistics routes; define an agricultural product distribution optimization goal, perform index decomposition and fitting on the agricultural product distribution optimization goal, and construct a logistics scheduling fitness function; use the agricultural product distribution demand quantity and the set of alternative transportation logistics routes as constraint parameters, and use the logistics scheduling fitness function to perform distribution analysis on the set of alternative agricultural product attribute parameters to generate an agricultural product scheduling parameter solution space; perform global optimization within the agricultural product scheduling parameter solution space to determine the target agricultural product scheduling parameters, and perform logistics distribution scheduling on the target agricultural product through the target agricultural product scheduling parameters.

[0006] In the second aspect of this application, an intelligent logistics scheduling device for optimizing the distribution of agricultural products is provided. The device includes: An information collection and marking module is used to collect and obtain an alternative shipping location set of target agricultural products, interactively obtain a basic information flow set of the alternative shipping location set, and perform multi-dimensional attribute marking on the basic information flow set respectively to obtain an alternative agricultural product attribute parameter set; A route optimization module is used to analyze the target order task to obtain the agricultural product allocation demand and the destination of the transportation task, and perform transportation route optimization respectively based on the alternative shipping location set and the destination of the transportation task to determine an alternative transportation logistics route set; A disassembly and fitting module is used to define the agricultural product allocation optimization target, perform index disassembly and fitting on the agricultural product allocation optimization target, and construct a logistics scheduling fitness function; An allocation analysis module is used to use the agricultural product allocation demand and the alternative transportation logistics route set as constraint parameters, and use the logistics scheduling fitness function to perform allocation analysis on the alternative agricultural product attribute parameter set to generate an agricultural product scheduling parameter solution space; An allocation and scheduling module is used to perform global optimization within the agricultural product scheduling parameter solution space to determine the target agricultural product scheduling parameters, and perform logistics allocation and scheduling on the target agricultural products through the target agricultural product scheduling parameters.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: This application collects and obtains an alternative shipping location set of target agricultural products, interactively obtains a basic information flow set of the alternative shipping location set, and performs multi-dimensional attribute marking on the basic information flow set respectively to obtain an alternative agricultural product attribute parameter set; Analyze the target order task to obtain the agricultural product allocation demand and the destination of the transportation task, and perform transportation route optimization respectively based on the alternative shipping location set and the destination of the transportation task to determine an alternative transportation logistics route set; Define the agricultural product allocation optimization target, perform index disassembly and fitting on the agricultural product allocation optimization target, and construct a logistics scheduling fitness function; Use the agricultural product allocation demand and the alternative transportation logistics route set as constraint parameters, and use the logistics scheduling fitness function to perform allocation analysis on the alternative agricultural product attribute parameter set to generate an agricultural product scheduling parameter solution space; Perform global optimization within the agricultural product scheduling parameter solution space to determine the target agricultural product scheduling parameters, and perform logistics allocation and scheduling on the target agricultural products through the target agricultural product scheduling parameters. This invention solves the technical problems of low efficiency, high cost and unreasonable resource allocation in the existing agricultural product logistics scheduling. By optimizing the scheduling parameters through data processing based on multi-dimensional attribute marking, transportation route optimization, fitness function construction and global optimization algorithm, the technical effects of improving the logistics scheduling efficiency, reducing the transportation cost and realizing the reasonable allocation of resources are achieved. Description of the Drawings

[0008] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for description in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0009] Figure 1 Schematic flow diagram of an intelligent logistics scheduling method for optimizing agricultural product distribution provided by an embodiment of the present application; Figure 2 Schematic structural diagram of an intelligent logistics scheduling device for optimizing agricultural product distribution provided by an embodiment of the present application.

[0010] Explanation of reference numerals: Information collection and marking module 11, route optimization module 12, disassembly and fitting module 13, distribution analysis module 14, distribution scheduling module 15. Detailed implementation manners

[0011] The present application provides an intelligent logistics scheduling method and device for optimizing agricultural product distribution. To solve the technical problems of low efficiency, high cost, and unreasonable resource allocation in the existing agricultural product logistics scheduling, by processing data based on multi-dimensional attribute marking, optimizing transportation routes, constructing a fitness function, and optimizing scheduling parameters using a global optimization algorithm, the technical effects of improving logistics scheduling efficiency, reducing transportation costs, and achieving reasonable resource allocation are achieved.

[0012] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0013] It should be noted that any variations of the terms "comprising" and "having" are intended to cover non-exclusive inclusions. For example, a process, method, device, product, or server that includes a series of steps or units does not necessarily have to be limited to those clearly listed steps or units, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products, or devices.

[0014] Embodiment 1, as Figure 1 shown, the present application provides an intelligent logistics scheduling method for optimizing agricultural product distribution, and the method includes: Step S100: Collect and obtain the set of alternative shipping locations for the target agricultural product, interactively obtain the basic information flow set of the set of alternative shipping locations, and perform multi-dimensional attribute labeling on the basic information flow set respectively to obtain the set of alternative agricultural product attribute parameters.

[0015] In the embodiment of the present application, first collect and obtain the set of alternative shipping locations for the target agricultural product from the preset database. The preset database stores information on each alternative shipping location, including agricultural product production bases, warehousing centers, distribution outlets, etc. By collecting the information in the preset database, the set of alternative shipping locations is obtained.

[0016] Next, based on the obtained set of alternative shipping locations, interactively obtain the basic information flow set of the set of alternative shipping locations. This process establishes a connection through the real-time data interaction interfaces (such as ERP systems, Internet of Things sensing devices, etc.) with each shipping node to dynamically collect detailed data including real-time inventory levels, batch information of agricultural products in stock, product shelf life, temperature and humidity monitoring data, shipping capacity, current order processing status, etc. These data together form the basic information flow set.

[0017] After the data collection is completed, perform multi-dimensional attribute labeling on the obtained basic information flow data to extract key feature parameters to support subsequent scheduling optimization. This process uses the principal component analysis (PCA) technique, aiming to extract the most representative core features from a large amount of data. Specifically, first define the key attribute dimensions, such as geographical attributes (location, transportation convenience), inventory attributes (quantity, turnover rate), logistics capabilities (transportation equipment, delivery timeliness), etc., and then perform feature extraction and dimensionality reduction processing on the original data based on the PCA algorithm, converting the high-dimensional data into key features in a low-dimensional space, retaining the most explanatory information in the data, and reducing redundancy and noise. After the principal component analysis processing, label the data with different attributes, such as labeling tags like "high-priority shipping point" and "cold chain required" to ensure that the data has good interpretability and comparability in the scheduling algorithm. Finally, the data set formed after the multi-dimensional attribute labeling process forms the set of alternative agricultural product attribute parameters. Among them, the data set formed after the multi-dimensional attribute labeling process refers to the structured data set formed through feature extraction and attribute labeling on the basis of the basic information flow set.

[0018] Step S200: Analyze the target order task to obtain the agricultural product distribution demand quantity and the destination of the transportation task, and respectively optimize the transportation routes based on the set of alternative shipping locations and the destination of the transportation task to determine the set of alternative transportation and logistics routes.

[0019] In the embodiments of the present application, first, the target order task is parsed by reading the structured data of the order, including information such as the order number, product type, quantity requirement, delivery address, delivery time, etc. Using a data parsing algorithm (such as rule-based parsing technology), the core information is extracted from the target order to obtain the agricultural product allocation demand quantity and the destination of the transportation task.

[0020] Next, route optimization is performed based on the set of alternative shipping locations and the destination of the transportation task respectively. Specifically, map area mapping is performed based on the alternative shipping locations and the destination of the transportation task to obtain a set of transportation route area map information, which includes basic data such as road networks, traffic conditions, and geographical distributions. Then, the obtained map information set is converted into a graph model to generate a set of alternative agricultural product transportation path graph models. After constructing the graph model, a transportation cost target is set, which covers key indicators such as transportation distance, time, cost, and traffic conditions, and a transportation cost function is constructed accordingly to quantify the comprehensive cost of each transportation path. Finally, the transportation cost function is used to perform iterative evaluation and optimization in the set of path graph models. Through multiple rounds of calculation and optimization, paths with cost advantages and transportation efficiency are selected, and finally a set of alternative transportation logistics routes is determined.

[0021] Furthermore, in the method provided by the application embodiments, the determination of the set of alternative transportation logistics routes further includes: Map area mapping is performed based on the set of alternative shipping locations and the destination of the transportation task respectively to obtain a set of transportation route area map information; the set of transportation route area map information is sequentially converted into a graph model to generate a set of alternative agricultural product transportation path graph models; a transportation cost target is set, and a transportation cost function is constructed according to the transportation cost target; the transportation cost function is used to perform iterative evaluation and optimization respectively within the set of alternative agricultural product transportation path graph models to determine the set of alternative transportation logistics routes.

[0022] In the embodiments of the present application, first, map area mapping is performed based on the set of alternative shipping locations and the destination of the transportation task. This step relies on geographic information system (GIS) technology. By calling the map service API or the internal map database, the shipping points and destinations are accurately located on the digital map. This process not only shows their geographical distributions but also includes road networks, traffic conditions, terrain information, etc. Through mapping, a set of transportation route area map information is formed.

[0023] Subsequently, the obtained set of transportation route area map information is converted into a graph model to generate a set of alternative agricultural product transportation path graph models. This process uses graph theory methods to abstract the actual road network into a graph structure composed of nodes and edges. Nodes represent the shipping points, destinations, and key intersections along the way, and edges represent the roads connecting these nodes. Each edge is assigned corresponding attributes to reflect information such as the physical distance, estimated travel time, and traffic conditions of the road. Through this process, a set of alternative agricultural product transportation path graph models is generated.

[0024] After the graph model is constructed, set the transportation cost target according to the actual requirements of logistics scheduling, and construct a transportation cost function accordingly. The transportation cost target usually considers various factors, such as transportation distance, time, fuel consumption, tolls, etc. To achieve quantitative evaluation, a linear weighted model is used to combine different cost factors into a unified cost function, in the form of: where C represents the total transportation cost, D is the path distance, T is the transportation time, F is the fuel consumption cost, R is the road risk coefficient, and are the corresponding weight coefficients, reflecting the priorities of each factor in different scenarios. and R are all preset by technical experts in advance.

[0025] Finally, use the constructed transportation cost function to perform iterative evaluation and optimization in the set of alternative agricultural product transportation path graph models. This process uses a heuristic search algorithm (such as the A* algorithm) to optimize the path. First, generate an initial path based on the graph model and calculate the transportation cost value of each path. Subsequently, through multiple rounds of iterative optimization, explore different path combinations in the path graph model, continuously adjust the path structure, optimize the path selection strategy, and gradually converge to the optimal or near-optimal solution in terms of cost. Each round of iteration will screen and improve the path based on the evaluation results of the cost function to ensure that the optimization process has a global perspective and avoids falling into local optimal solutions. After completing multiple rounds of iterative optimization, sort the cost values of all paths and select the top 30% of the paths with the lowest cost values as the final set of alternative transportation logistics routes.

[0026] Furthermore, in the method provided by the application embodiment, the generation of the set of alternative agricultural product transportation path graph models further includes: Construct a transport route entity tag library, and use the transport route entity tag library to perform entity recognition on the transport route area map information set to obtain a set of alternative transport route entities; define graph node attributes and graph edge attributes according to the transport route entity tag library; respectively perform graph node extraction and graph edge attribute marking on the set of alternative transport route entities based on the graph node attributes and graph edge attributes to determine a set of graph model node sets and node edge connection attribute sets; perform graph model topological transformation on the set of graph model nodes according to the node edge connection attribute sets to generate the set of alternative agricultural product transport path graph models.

[0027] In the embodiment of the present application, first start constructing a transport route entity tag library. This tag library is based on geographic information system technology and database management methods, and integrates common transportation and logistics-related entities in map data, such as roads, toll stations, rivers, warehouses, etc. Each type of entity is defined with standardized attributes in the tag library, including entity type (such as main road, bridge, warehouse, etc.), functional characteristics (such as whether restricted, whether tolled), and geometric characteristics (such as area, length, location coordinates, etc.). Through this step, a transport route entity tag library is obtained.

[0028] Next, perform entity recognition on the transport route area map information set based on the constructed transport route entity tag library. This step combines geographic data processing algorithms and spatial analysis techniques to automatically extract physical entities matching the tag library from the map data to form a set of alternative transport route entities. This set contains all key entities related to logistics path planning, such as warehouse nodes, toll stations, road network structures, bridges spanning rivers, etc. distributed in different regions.

[0029] Then, based on the entity tag library, define graph node attributes and graph edge attributes respectively. In this process, entities with independent functions and fixed positions (such as warehouses, toll stations, transportation hubs) are defined as graph nodes and corresponding attributes are assigned to them, such as node type, area, service capacity, and access restrictions. At the same time, roads, bridges, rivers, etc. representing actual transport routes are defined as graph edges, and attributes including type (such as highway, urban road, bridge), length, access cost, road grade, etc. are added to them. Through this process, the definition of graph node attributes and graph edge attributes is completed.

[0030] After defining the node and edge attributes, graph node extraction and graph edge attribute marking are performed on the set of alternative transportation route entities based on these attributes. Specifically, using graph data processing techniques, eligible logistics entities are extracted as nodes in the graph model, and edge attributes are assigned to the paths between these nodes according to the actual road connection relationships. During the node extraction process, ensure that all entities with logistics value (such as main warehouses, transportation hubs) are included in the model. In the edge attribute marking, combined with the actual road data, information such as the passing capacity, transportation distance, and traffic conditions of the paths are marked. Through this step, the graph model node set and the node edge connection attribute set are obtained.

[0031] Finally, the graph model node set is topologically transformed according to the node edge connection attribute set to generate a set of alternative agricultural product transportation path graph models. The topological transformation is based on graph theory algorithms (such as the preprocessing model of the Dijkstra algorithm or the adjacency matrix representation method), abstracting the complex real-world transportation network into a graph model with a topological structure.

[0032] Step S300: Define the optimization objective for agricultural product distribution, decompose and fit the indicators of the optimization objective for agricultural product distribution, and construct a logistics scheduling fitness function.

[0033] In the embodiment of the present application, first, the optimization objective for agricultural product distribution is defined, including reducing transportation costs, improving distribution timeliness, optimizing resource utilization rate, reducing the loss rate of agricultural products, etc.

[0034] Next, the optimization objective for agricultural product distribution is decomposed into indicators, refining the abstract optimization objective into quantifiable sub-indicators, forming a set of evaluation indicators for agricultural product distribution effects covering aspects such as transportation costs, distribution timeliness, resource utilization rate, and product loss rate. Based on this indicator set, further historical data mining and evaluation function fitting are carried out. By analyzing historical logistics data, a set of sub-optimization indicator scheduling fitness functions reflecting the relationship between each sub-indicator and the scheduling effect is constructed. Subsequently, a criticality evaluation is performed on the evaluation indicator set to determine the importance of each sub-indicator in the overall optimization objective, generating corresponding sub-optimization indicator criticality factor information to quantify the weight of each indicator in the decision-making. Finally, based on the criticality factor information, the set of sub-optimization indicator scheduling fitness functions is weighted and fused to construct a comprehensive logistics scheduling fitness function.

[0035] Furthermore, in the method provided by the embodiment of the application, the construction of the logistics scheduling fitness function further includes: Decompose the optimization objectives of the agricultural product distribution to obtain a set of evaluation indicators for the agricultural product distribution effect; conduct historical data mining and evaluation function fitting based on the set of evaluation indicators for the agricultural product distribution effect to obtain a set of sub-optimization index scheduling fitness functions; conduct a criticality evaluation on the set of evaluation indicators for the agricultural product distribution effect to determine the criticality factor information of the sub-optimization indicators; and perform weighted fusion on the set of sub-optimization index scheduling fitness functions based on the criticality factor information of the sub-optimization indicators to construct the logistics scheduling fitness function.

[0036] In the embodiment of the present application, first, decompose the optimization objectives of the agricultural product distribution to transform the abstract optimization requirements into specific and quantifiable evaluation indicators. To achieve this goal, the analytic hierarchy process is adopted, and through the construction of a multi-level structure of the decision-making layer, the criterion layer, and the index layer, the overall distribution optimization objective is refined into multiple sub-objectives and evaluation indicators. For example, "improving the efficiency of agricultural product distribution" can be decomposed into first-level indicators such as reducing transportation costs, improving distribution timeliness, optimizing resource utilization rate, and reducing product loss rate, and then further refined into second-level sub-indicators such as fuel consumption, on-time rate, vehicle load rate, cold-chain product loss rate, etc. Through this process, a set of evaluation indicators for the agricultural product distribution effect is obtained.

[0037] Next, conduct historical data mining and evaluation function fitting based on the set of evaluation indicators for the agricultural product distribution effect. Using linear regression analysis, model the historical logistics data to explore the relationship between each evaluation indicator and the actual scheduling effect. Specifically, first, perform data preprocessing, including data cleaning, standardization, and outlier removal, to ensure reliable data quality. Subsequently, extract the feature variables highly correlated with each sub-indicator, construct a linear regression model, and fit the linear relationship between each sub-indicator and the scheduling performance (such as cost, time, loss, etc.). After the model is trained and verified, it can accurately reflect the impact of the changes in each sub-indicator on the scheduling effect, forming multiple sub-optimization index scheduling fitness functions, and obtaining a set of sub-optimization index scheduling fitness functions.

[0038] Subsequently, conduct a criticality evaluation on the set of evaluation indicators for the agricultural product distribution effect. Using the entropy weight method, calculate the information entropy based on the distribution difference of the data of each sub-indicator to quantify the difference in the contribution of each indicator to the decision-making. The smaller the entropy value, the greater the amount of information of the indicator, and the more important its impact on the decision-making. Through standardization processing and entropy value calculation, determine the criticality factor of each sub-indicator to obtain the criticality factor information of the sub-optimization indicators.

[0039] Finally, based on the sub-optimization index criticality factor information, a logistics scheduling fitness function is constructed. During the construction process, a weighted summation model is adopted, and the sub-optimization index scheduling fitness functions are weighted and fused according to the proportion of their criticality factors in the total sum of all factors. Specifically, first, the proportion of each sub-optimization index criticality factor in the total factors is calculated as the weight of the corresponding fitness function. Then, each fitness function is multiplied by its weight, and finally, all the weighted results are added together to form the final logistics scheduling fitness function.

[0040] Step S400: Using the agricultural product distribution demand quantity and the set of alternative transportation logistics routes as constraint parameters, the alternative agricultural product attribute parameter set is analyzed and allocated by using the logistics scheduling fitness function to generate an agricultural product scheduling parameter solution space.

[0041] In the embodiment of the present application, first, the agricultural product distribution demand quantity and the set of alternative transportation logistics routes are used as constraint parameters to ensure the feasibility and efficiency of the scheduling plan. On this basis, the priority allocation factor information is further obtained, including storage cost, the shelf life of agricultural products, and the carrying capacity of logistics equipment, to determine the key factors affecting the scheduling decision. Then, the priority allocation factor information is used to evaluate and sort the alternative agricultural product attribute parameter set to determine the alternative agricultural product shipping priority sequence, so as to reflect the priority processing order of different agricultural products in the scheduling.

[0042] Subsequently, the alternative agricultural product shipping priority sequence is used as an additional constraint condition, combined with the previous constraint parameters (such as transportation limit, time limit, etc.), to perform scheduling search and solution on the alternative agricultural product attribute parameter set, so as to obtain a set of feasible agricultural product scheduling parameters that meet all the constraint conditions. To further improve the optimization effect of the scheduling plan, the logistics scheduling fitness function is used to optimize and update the set of feasible parameters, and the optimal plan in terms of cost, timeliness, resource utilization, etc. is selected. Finally, an agricultural product scheduling parameter solution space is generated, which contains multiple feasible allocation plans, and each plan corresponds to a specific shipping location and shipping allocation quantity, meeting the intelligent logistics scheduling requirements in different scenarios.

[0043] Furthermore, in the method provided by the embodiment of the application, the generation of the agricultural product scheduling parameter solution space further includes: Obtain priority allocation factor information, where the priority allocation factor information includes warehousing costs, the shelf life of agricultural products, and the carrying capacity of logistics equipment; use the priority allocation factor information to perform a priority evaluation and sorting on the set of alternative agricultural product attribute parameters to determine the alternative agricultural product shipping priority sequence; use the alternative agricultural product shipping priority sequence as an additional constraint condition, and based on the additional constraint condition and the constraint parameters, perform a scheduling search and solution on the set of alternative agricultural product attribute parameters to obtain a feasible parameter solution set for agricultural product scheduling; use the logistics scheduling fitness function to optimize and update the feasible parameter solution set for agricultural product scheduling to generate an agricultural product scheduling parameter solution space.

[0044] In the embodiment of the present application, first, obtain priority allocation factor information to provide a key reference basis for scheduling decisions. The priority allocation factors mainly include warehousing costs, the shelf life of agricultural products, and the carrying capacity of logistics equipment. By extracting data from the warehousing management system, the supply chain database, and the logistics equipment monitoring system, the warehousing costs at each shipping location, the remaining shelf life of agricultural products, and the maximum carrying capacity of logistics equipment can be obtained.

[0045] Next, use the priority allocation factor information to perform a priority evaluation and sorting on the set of alternative agricultural product attribute parameters based on the weighted scoring method. This method first assigns weights to each priority factor. For example, the weights of warehousing costs, shelf life, and the carrying capacity of logistics equipment are set to 40%, 35%, and 25% respectively. Then, standardize the data, normalizing data with different dimensions (such as costs, days, tons, etc.) to the same evaluation scale. Finally, calculate the comprehensive score for each alternative shipping location. The higher the score, the higher the shipping priority. In particular, shipping locations with higher warehousing costs, shorter shelf lives of agricultural products, and stronger carrying capacities of logistics equipment will be given priority to achieve cost control and resource optimization. Eventually, generate an alternative agricultural product shipping priority sequence through this process.

[0046] Subsequently, use the alternative agricultural product shipping priority sequence as an additional constraint condition, and combine the previously determined constraint parameters (such as transportation limits, time windows, distribution demand, etc.) to perform a scheduling search and solution on the set of alternative agricultural product attribute parameters. This step is to find all scheduling plans that can meet the constraint conditions. By using a heuristic search algorithm, systematically explore all possible combination plans and verify whether they meet the established hard constraint conditions. During this process, any scheduling plan that meets the constraint conditions is regarded as a valid solution, regardless of its advantages and disadvantages in dimensions such as cost and timeliness. Finally, screen out all qualified plans to form a feasible parameter solution set for agricultural product scheduling.

[0047] Finally, the logistics scheduling fitness function is used to optimize and update the solution set of feasible parameters for the agricultural product scheduling. Specifically, first, the logistics scheduling fitness function is used to evaluate the fitness of the solution set of feasible parameters for the agricultural product scheduling, generating a fitness set of feasible parameter solutions that reflects the advantages and disadvantages of each solution. Based on this fitness set, excellent solutions are selected to form a parental scheduling parameter set, and a new offspring scheduling parameter set is generated through crossover and mutation operations. Subsequently, the fitness of the offspring solutions is evaluated again to obtain the offspring parameter fitness set, and it is iteratively optimized and updated with the parental fitness set to continuously improve the solution quality. This process is repeated until a preset termination condition is met, such as reaching the maximum number of iterations, and finally, an agricultural product scheduling parameter solution space containing multiple high-quality scheduling solutions is formed.

[0048] Further, in the method provided by the application embodiment, generating the agricultural product scheduling parameter solution space further includes: Using the logistics scheduling fitness function to evaluate the fitness of the solution set of feasible parameters for the agricultural product scheduling, obtaining a fitness set of feasible parameter solutions; based on the fitness set of feasible parameter solutions, optimizing the solution set of feasible parameters for the agricultural product scheduling to determine a parental scheduling parameter set; performing iterative crossover and mutation operations on the parental scheduling parameter set to obtain an offspring scheduling parameter set, and evaluating through the logistics scheduling fitness function to obtain an offspring parameter fitness set of the offspring scheduling parameter set; based on the offspring parameter fitness set, iteratively optimizing and updating the fitness set of feasible parameter solutions until a preset termination condition is met, obtaining the agricultural product scheduling parameter solution space.

[0049] In the embodiment of the present application, first, the logistics scheduling fitness function is used to evaluate the fitness of the solution set of feasible parameters for the agricultural product scheduling to quantify the advantages and disadvantages of each scheduling solution. This step adopts a batch calculation method, and for each solution in the solution set of feasible parameters, its fitness score is quickly calculated to form a fitness set of feasible parameter solutions.

[0050] Next, based on the fitness set of feasible parameter solutions, the solution set of feasible parameters for the agricultural product scheduling is optimized. In this process, the tournament selection method is adopted, randomly selecting multiple solutions from the solution set of feasible parameters for the agricultural product scheduling for fitness comparison, and selecting the solution with the highest fitness as the parent in each round to ensure the retention of excellent genes and determine the parental scheduling parameter set.

[0051] Subsequently, iterative crossover and mutation operations are performed on the parental scheduling parameter set. The crossover operation uses the single-point crossover method to exchange genes of two parental solutions at a random position to generate new offspring solutions, promoting the diversification of the solution space. The mutation operation adopts the random-bit mutation method to randomly adjust some scheduling parameters in the offspring solutions (such as adjusting the shipping order, changing the allocation quantity, etc.), increasing the randomness of the solution and avoiding the algorithm falling into a local optimum. Through this process, an offspring scheduling parameter set is obtained.

[0052] After obtaining the offspring scheduling parameter set, use the logistics scheduling fitness function to evaluate the offspring scheduling parameter set, evaluate the performance of the new solution in terms of cost, timeliness, resource utilization, etc., and obtain the offspring parameter fitness set.

[0053] Finally, based on the offspring parameter fitness set, iteratively optimize and update the feasible parameter solution fitness set, and adopt the elitist retention strategy to ensure that the solution with the highest fitness in each generation is retained to maintain the overall quality of the solution set. By continuously performing crossover, mutation, and evaluation operations until the preset termination conditions are met, such as reaching the maximum number of iterations or the fitness improvement amplitude is lower than the threshold. Finally, form an agricultural product scheduling parameter solution space containing multiple high-quality scheduling solutions.

[0054] Step S500: Perform global optimization within the agricultural product scheduling parameter solution space, determine the target agricultural product scheduling parameters, and perform logistics distribution scheduling on the target agricultural product through the target agricultural product scheduling parameters.

[0055] In the embodiment of the present application, the particle swarm optimization algorithm is used for global optimization within the agricultural product scheduling parameter solution space. Specifically, the particle swarm optimization algorithm is used to perform a global search on all feasible scheduling solutions in the agricultural product scheduling parameter solution space. Each scheduling solution is regarded as a particle, and its comprehensive performance in terms of transportation cost, distribution timeliness, resource utilization rate, and product freshness preservation is evaluated through the fitness function. In multiple rounds of iteration, the particles continuously adjust their positions and velocities according to their own historical optimal solutions and the global optimal solution of the group, and gradually approach the global optimal solution. When the preset termination conditions are met, such as reaching the maximum number of iterations, finally determine the scheduling solution with the highest fitness score as the target agricultural product scheduling parameters.

[0056] Based on the determined target agricultural product scheduling parameters, generate detailed logistics distribution instructions, clarify key scheduling information such as the shipping location, distribution quantity, transportation route, and delivery time, and perform logistics distribution scheduling on the target agricultural product to ensure the reasonable allocation of logistics resources and the efficient execution of tasks.

[0057] Furthermore, the method provided by the application embodiment further includes: Perform logistics distribution monitoring on the target agricultural product through the target agricultural product scheduling parameters to obtain agricultural product scheduling feedback parameters; perform optimization analysis on the agricultural product scheduling feedback parameters to determine parameter optimization rules; perform mutation optimization on the target agricultural product scheduling parameters based on the parameter optimization rules to obtain optimized agricultural product scheduling parameters, and perform agricultural product distribution scheduling through the optimized agricultural product scheduling parameters.

[0058] In the embodiment of the present application, during the process of performing logistics allocation and scheduling based on the target agricultural product scheduling parameters, real-time monitoring is synchronously started to obtain the dynamic data of logistics execution, and agricultural product scheduling feedback parameters are formed. This monitoring link is based on GPS positioning technology and sensor monitoring methods. The transportation route and location are tracked in real time through vehicle GPS devices, the cold chain transportation environment is monitored by combining temperature and humidity sensors, and the warehouse management system is coordinated to record key data such as loading and unloading time, inventory status, and transportation progress. These data together constitute the real-time feedback information of agricultural products during the logistics scheduling process, that is, agricultural product scheduling feedback parameters.

[0059] After obtaining the scheduling feedback parameters, they are optimized and analyzed to identify bottlenecks or potential problems in the scheduling process, aiming to improve scheduling efficiency and resource utilization. This step adopts the difference analysis method. By comparing the actual scheduling data with the expected values of the target scheduling parameters, abnormal situations such as transportation delays, high costs, and uneven resource allocation are found. For example, when it is detected that the actual delivery duration significantly exceeds the expectation, the influencing factors such as traffic congestion and waiting time at distribution nodes are analyzed, and then specific parameter optimization rules are determined, such as adjusting the transportation route, optimizing the delivery time window, or improving the loading strategy. Finally, a set of parameter optimization rules for scheduling deviations is obtained, providing a basis for adjusting the scheduling parameters.

[0060] Based on the determined parameter optimization rules, mutation optimization is performed on the target agricultural product scheduling parameters being executed. This step adopts the local adjustment method, that is, without changing the overall scheduling strategy, fine-tuning is performed on the key parameters with deviations. For example, the priority of a certain route can be adjusted, the time allocation of specific distribution nodes can be optimized, or some transportation resources can be reallocated to quickly respond to the dynamic changes in scheduling. These adjustments are based on real-time data for rapid decision-making, ensuring that the scheduling plan has higher flexibility and adaptability. Finally, the adjusted optimized scheduling parameters of agricultural products are obtained through this step, making the scheduling plan more efficient and accurate in the real-time environment.

[0061] Subsequently, based on the optimized scheduling parameters of agricultural products, the agricultural product allocation and scheduling are continued, and the adjustment results are applied to the actual logistics process. Updated logistics instructions are generated according to the new optimized scheduling parameters of agricultural products, including adjusted shipping locations, transportation routes, allocation quantities, and delivery times, and are quickly sent to each logistics node to ensure the immediate implementation of the scheduling strategy. At the same time, real-time monitoring is continuously carried out to form a closed-loop feedback mechanism, continuously collecting new scheduling feedback parameters, and continuously optimizing the scheduling plan. Through this step, the flexibility, efficiency, and reliability of logistics scheduling are improved.

[0062] In the embodiment of the present application, in summary, the embodiment of the present application has at least the following technical effects: This application collects and obtains a set of alternative shipping locations for target agricultural products, interactively obtains a basic information flow set of the set of alternative shipping locations, and performs multi-dimensional attribute marking on the basic information flow set respectively to obtain a set of alternative agricultural product attribute parameters; parses the target order task to obtain the agricultural product allocation demand quantity and the destination of the transportation task, and respectively performs transportation route optimization based on the set of alternative shipping locations and the destination of the transportation task to determine a set of alternative transportation logistics routes; defines an agricultural product allocation optimization target, performs index decomposition and fitting on the agricultural product allocation optimization target, and constructs a logistics scheduling fitness function; uses the agricultural product allocation demand quantity and the set of alternative transportation logistics routes as constraint parameters, and uses the logistics scheduling fitness function to perform allocation analysis on the set of alternative agricultural product attribute parameters to generate an agricultural product scheduling parameter solution space; performs global optimization within the agricultural product scheduling parameter solution space to determine the target agricultural product scheduling parameters, and performs logistics allocation scheduling on the target agricultural product through the target agricultural product scheduling parameters. The present invention solves the technical problems of low efficiency, high cost and unreasonable resource allocation in the existing agricultural product logistics scheduling. By optimizing the scheduling parameters through data processing based on multi-dimensional attribute marking, transportation route optimization, fitness function construction and global optimization algorithm, the technical effects of improving the logistics scheduling efficiency, reducing the transportation cost and realizing the reasonable allocation of resources are achieved.

[0063] Embodiment 2, based on the same inventive concept as the intelligent logistics scheduling method for optimizing agricultural product allocation in the foregoing embodiment, as Figure 2 shown, this application provides an intelligent logistics scheduling device for optimizing agricultural product allocation. The device in the embodiments of this application and the method embodiments are based on the same inventive concept. Among them, the device includes: An information collection and marking module 11, configured to collect and obtain a set of alternative shipping locations for target agricultural products, interactively obtain a basic information flow set of the set of alternative shipping locations, and perform multi-dimensional attribute marking on the basic information flow set respectively to obtain a set of alternative agricultural product attribute parameters; a route optimization module 12, configured to parse the target order task to obtain the agricultural product allocation demand quantity and the destination of the transportation task, and respectively perform transportation route optimization based on the set of alternative shipping locations and the destination of the transportation task to determine a set of alternative transportation logistics routes; a decomposition and fitting module 13, configured to define an agricultural product allocation optimization target, perform index decomposition and fitting on the agricultural product allocation optimization target, and construct a logistics scheduling fitness function; an allocation analysis module 14, configured to use the agricultural product allocation demand quantity and the set of alternative transportation logistics routes as constraint parameters, and use the logistics scheduling fitness function to perform allocation analysis on the set of alternative agricultural product attribute parameters to generate an agricultural product scheduling parameter solution space; an allocation scheduling module 15, configured to perform global optimization within the agricultural product scheduling parameter solution space to determine the target agricultural product scheduling parameters, and perform logistics allocation scheduling on the target agricultural product through the target agricultural product scheduling parameters.

[0064] Further, the device is also used to implement the following functions: Based on the alternative shipping location set and the destination of the transportation task, map regions are respectively mapped to obtain a set of transportation route region map information; the set of transportation route region map information is sequentially converted into graph models to generate a set of alternative agricultural product transportation path graph models; a transportation cost target is set, and a transportation cost function is constructed according to the transportation cost target; the transportation cost function is used to perform iterative evaluation and optimization respectively within the set of alternative agricultural product transportation path graph models to determine the set of alternative transportation logistics routes.

[0065] Further, the device is also used to implement the following functions: Construct a transportation route entity tag library, use the transportation route entity tag library to perform entity recognition on the set of transportation route region map information to obtain a set of alternative transportation route entities; according to the transportation route entity tag library, define graph node attributes and graph edge attributes; based on the graph node attributes and graph edge attributes, perform graph node extraction and graph edge attribute marking on the set of alternative transportation route entities respectively to determine a set of graph model nodes and a set of node edge connection attributes; the set of graph model nodes is topologically transformed according to the set of node edge connection attributes to generate the set of alternative agricultural product transportation path graph models.

[0066] Further, the device is also used to implement the following functions: Obtain priority allocation factor information, where the priority allocation factor information includes warehousing cost, agricultural product shelf life, and logistics equipment carrying capacity; use the priority allocation factor information to perform priority evaluation and sorting on the set of alternative agricultural product attribute parameters to determine an alternative agricultural product shipping priority sequence; use the alternative agricultural product shipping priority sequence as an additional constraint condition, and based on the additional constraint condition and the constraint parameters, perform scheduling search and solution on the set of alternative agricultural product attribute parameters to obtain a set of feasible agricultural product scheduling parameter solutions; use the logistics scheduling fitness function to optimize and update the set of feasible agricultural product scheduling parameter solutions to generate an agricultural product scheduling parameter solution space.

[0067] Further, the device is also used to implement the following functions: Use the logistics scheduling fitness function to evaluate the fitness of the solution set of feasible parameters for the agricultural product scheduling, and obtain the fitness set of feasible parameter solutions; based on the fitness set of feasible parameter solutions, optimize and select the solution set of feasible parameters for the agricultural product scheduling to determine the parent generation scheduling parameter set; perform iterative crossover and mutation operations on the parent generation scheduling parameter set to obtain the offspring generation scheduling parameter set, and evaluate through the logistics scheduling fitness function to obtain the offspring parameter fitness set of the offspring generation scheduling parameter set; based on the offspring parameter fitness set, perform iterative optimization and update on the fitness set of feasible parameter solutions until the preset termination condition is reached to obtain the solution space of the agricultural product scheduling parameters.

[0068] Further, the device is also used to implement the following functions: Decompose the index of the optimization target for the agricultural product allocation to obtain a set of evaluation indexes for the agricultural product allocation effect; based on the set of evaluation indexes for the agricultural product allocation effect, perform historical data mining and evaluation function fitting to obtain a set of sub-optimization index scheduling fitness functions; perform criticality evaluation on the set of evaluation indexes for the agricultural product allocation effect to determine the criticality factor information of the sub-optimization indexes; based on the criticality factor information of the sub-optimization indexes, perform weighted fusion on the set of sub-optimization index scheduling fitness functions to construct the logistics scheduling fitness function.

[0069] Further, the device is also used to implement the following functions: Monitor the logistics allocation of the target agricultural product through the target agricultural product scheduling parameters to obtain the agricultural product scheduling feedback parameters; perform optimization analysis on the agricultural product scheduling feedback parameters to determine the parameter optimization rules; based on the parameter optimization rules, perform mutation optimization on the target agricultural product scheduling parameters to obtain the optimized agricultural product scheduling parameters, and perform agricultural product allocation scheduling through the optimized agricultural product scheduling parameters.

[0070] It should be noted that the above sequence of embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. And the above describes specific embodiments of this specification. The processes depicted in the drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0071] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0072] This specification and the drawings are merely exemplary illustrations of the present application and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. An intelligent logistics scheduling method for optimizing the distribution of agricultural products, characterized in that: The method comprises: Collect and obtain a set of candidate delivery locations for target agricultural products, interactively obtain a set of basic information flows for the set of candidate delivery locations, and respectively perform multi-dimensional attribute marking on the basic information flows to obtain a set of attribute parameters for the candidate agricultural products; Analyze the target order task to obtain the agricultural product distribution demand and the transportation task destination, optimize the transportation route based on the alternative delivery location set and the transportation task destination, and determine the alternative transportation logistics route set; Define the optimization target of agricultural product distribution, perform index decomposition and fitting on the optimization target of agricultural product distribution, and construct a logistics scheduling fitness function; Taking the agricultural product allocation demand and the alternative transportation logistics route set as constraint parameters, using the logistics scheduling fitness function to perform allocation analysis on the alternative agricultural product attribute parameter set to generate an agricultural product scheduling parameter solution space; A global optimization is performed in the agricultural product scheduling parameter solution space to determine the target agricultural product scheduling parameters, and logistics distribution scheduling is performed on the target agricultural product using the target agricultural product scheduling parameters.

2. The intelligent logistics scheduling method for optimizing the distribution of agricultural products according to claim 1, characterized in that: The step of determining a set of alternative transport logistics routes includes: Mapping of the regions of the transport routes is performed based on the candidate delivery location set and the transport task destination, respectively, to obtain a transport route region map information set; Convert the transport route area map information set into a graph model in sequence to generate a set of alternative agricultural product transport route graph models; Setting a transportation cost target and constructing a transportation cost function according to the transportation cost target; The transportation cost function is used to perform iterative evaluation and optimization in the set of candidate agricultural product transportation path graph models to determine the set of candidate transportation logistics routes.

3. The intelligent logistics scheduling method for optimizing the distribution of agricultural products as claimed in claim 2, characterized in that: The generating of the model set of alternative agricultural product transportation route diagrams includes: Constructing a transport route entity tag library, using the transport route entity tag library to perform entity recognition on the transport route area map information set, and obtaining a candidate transport route entity set; According to the transport route entity tag library, define graph node attributes and graph edge attributes; Based on the graph node attributes and graph edge attributes, the graph node extraction and graph edge attribute marking are respectively performed on the set of candidate transport route entities to determine a graph model node set and a node edge connection attribute set; The graph model node set is subjected to graph model topology transformation according to the node edge connection attribute set to generate the graph model set of alternative agricultural product transportation paths.

4. The intelligent logistics scheduling method for optimizing the distribution of agricultural products according to claim 1, characterized in that: The generating of agricultural product scheduling parameter solution space includes: Obtaining priority allocation factor information, wherein the priority allocation factor information includes storage cost, shelf life of agricultural products, and carrying capacity of logistics equipment; Using the priority allocation factor information to prioritize the attribute parameter sets of the candidate agricultural products, and determine a priority sequence for shipment of the candidate agricultural products; Taking the candidate agricultural product delivery priority sequence as an additional constraint condition, performing a scheduling search and solving the candidate agricultural product attribute parameter set based on the additional constraint condition and the constraint parameter, and obtaining a feasible parameter solution set for agricultural product scheduling; The logistics scheduling fitness function is used to optimize and update the feasible parameter solution set of agricultural product scheduling to generate the agricultural product scheduling parameter solution space.

5. The intelligent logistics scheduling method for optimizing the distribution of agricultural products according to claim 4, characterized in that: The generating of agricultural product scheduling parameter solution space includes: Using the logistics scheduling fitness function to perform fitness evaluation on the feasible parameter solution set of agricultural product scheduling to obtain a feasible parameter solution fitness set; Optimizing the feasible parameter solution set for agricultural product scheduling based on the feasible parameter solution fitness set to determine a parent scheduling parameter set; Performing an iterative crossover mutation operation on the parent scheduling parameter set to obtain a child scheduling parameter set, and obtaining a child parameter fitness set of the child scheduling parameter set through the logistics scheduling fitness function evaluation; The feasible parameter solution fitness set is iteratively optimized and updated based on the offspring parameter fitness set until a preset termination condition is reached to obtain the agricultural product scheduling parameter solution space.

6. The intelligent logistics scheduling method for optimizing the distribution of agricultural products according to claim 1, characterized in that: The construction of the logistics scheduling fitness function includes: Decomposing the agricultural product allocation optimization target into indicators to obtain an agricultural product allocation effect evaluation indicator set; Based on the agricultural product distribution effect evaluation index set, historical data mining and evaluation function fitting are performed to obtain a sub-optimization index scheduling fitness function set; Performing a criticality evaluation on the agricultural product distribution effect evaluation index set to determine criticality factor information of sub-optimization indicators; The sub-optimization indicator scheduling fitness function set is weighted and fused based on the sub-optimization indicator criticality factor information to construct the logistics scheduling fitness function.

7. The intelligent logistics scheduling method for optimizing the distribution of agricultural products according to claim 1, characterized in that: The method comprises: Performing logistics distribution monitoring on the target agricultural products through the target agricultural product scheduling parameters to obtain agricultural product scheduling feedback parameters; Optimizing and analyzing the agricultural product scheduling feedback parameters to determine parameter optimization rules; Based on the parameter optimization rules, the target agricultural product scheduling parameters are mutated and optimized to obtain agricultural product optimization scheduling parameters, and agricultural product distribution scheduling is performed using the agricultural product optimization scheduling parameters.

8. An intelligent logistics scheduling device for optimizing the distribution of agricultural products, characterized in that: The device comprises: An information collection and marking module is used to collect and obtain a set of candidate delivery locations for target agricultural products, interactively obtain a set of basic information flows of the set of candidate delivery locations, and respectively mark the basic information flows with multi-dimensional attributes to obtain a set of attribute parameters of candidate agricultural products; A route optimization module is used to analyze the target order task, obtain the agricultural product distribution demand and the transportation task destination, optimize the transportation route based on the alternative delivery location set and the transportation task destination, and determine the alternative transportation logistics route set; A disassembly and fitting module is used to define the optimization target of agricultural product distribution, perform index disassembly and fitting on the optimization target of agricultural product distribution, and construct a logistics scheduling fitness function; An allocation and analysis module is used to use the agricultural product allocation demand and the alternative transportation logistics route set as constraint parameters, and use the logistics scheduling fitness function to perform allocation and analysis on the alternative agricultural product attribute parameter set to generate an agricultural product scheduling parameter solution space; The allocation and scheduling module is used to perform global optimization in the agricultural product scheduling parameter solution space, determine the target agricultural product scheduling parameters, and perform logistics allocation and scheduling on the target agricultural product according to the target agricultural product scheduling parameters.

Images