Intelligent logistics scheduling system and method based on multi-source information fusion

Abstract

The invention provides an intelligent logistics scheduling system and method based on multi-source information fusion, and relates to the technical field of logistics scheduling, and the method comprises the steps: determining the cooperative adaptation degree of a scheduling resource to a logistics task through the execution state characteristics of the logistics task and a scheduling strategy; dividing the transportation resources into a plurality of resource allocation units, determining a resource cooperation relationship between the resource allocation units, and determining the scheduling cost of each resource allocation unit for the logistics task according to the resource cooperation relationship and the scheduling period constraint condition of the logistics network; performing fuzzy evaluation on a scheduling adaptation relationship between resource allocation and task requirements in the logistics network through all the scheduling costs and the collaborative adaptation degrees, and determining a scheduling optimization index based on fuzzy logic; and carrying out load balancing scheduling on the logistics tasks of the resource allocation units based on the scheduling optimization indexes. According to the method, the resource cooperation relationship and the scheduling adaptation degree in the complex logistics scheduling are comprehensively evaluated through the fuzzy logic, and the load balancing of the logistics scheduling can be realized.

Description

Technical Field

[0001] The present application relates to the technical field of logistics scheduling, and more specifically, to an intelligent logistics scheduling system and method based on multi-source information fusion. Background Art

[0002] In modern supply chain systems, multi-warehouse logistics scheduling, as a key link to ensure efficient circulation and timely delivery of materials, faces challenges such as multiple storage nodes, long transportation chains, and heterogeneous resource distribution. With the deepening collaboration between e-commerce business and manufacturing, logistics demand has become fragmented, time-sensitive, and dynamic. Traditional static, rule-driven scheduling methods can no longer meet the scheduling efficiency and response accuracy requirements under high-frequency, multi-node collaboration. Building an intelligent scheduling mechanism for multi-warehouse collaboration and improving resource coordination and task matching capabilities are important breakthroughs in improving operational efficiency and reducing scheduling costs in the current logistics field.

[0003] Existing technologies generally employ static mapping methods and single-metric driven mechanisms in resource scheduling and task matching. These methods fail to effectively integrate the dynamic relationships between multi-source logistics information and accurately reflect real-time changes in the system's operational status. This is particularly true in scenarios where transportation resources and task demands fluctuate frequently. Traditional scheduling strategies exhibit delayed response and insufficient flexibility. In real-world scenarios involving multiple nodes and concurrent tasks, the dynamic changes in the collaborative capabilities between resource allocation units are neglected. Furthermore, the coupling relationship between scheduling cycles and task timeliness is not effectively modeled. Existing technologies lack modeling methods based on multi-dimensional feature extraction and fusion analysis, resulting in scheduling decisions that fail to fully reflect the current resource load status and task execution constraints. Furthermore, scheduling cost assessment often relies on single-dimensional metrics, such as transportation distance, time, or cost, lacking comprehensive modeling of the coupling mechanism between resource collaborative efficiency and timeliness parameters. This can easily lead to problems such as low resource utilization and unbalanced task allocation. In complex logistics networks, these issues manifest as decreased scheduling accuracy, uneven system load, and increased task delays, severely restricting the overall system's scheduling responsiveness and operational stability. Therefore, how to use fuzzy logic to comprehensively evaluate the resource coordination relationship and scheduling adaptability in complex logistics scheduling and achieve load balancing in logistics scheduling has become a difficult problem faced by the industry. Summary of the Invention

[0004] The present application provides an intelligent logistics scheduling system and method based on multi-source information fusion, which comprehensively evaluates the resource coordination relationship and scheduling adaptability in complex logistics scheduling through fuzzy logic, and can achieve load balancing of logistics scheduling.

[0005] In a first aspect, the present application provides an intelligent logistics scheduling method based on multi-source information fusion, comprising the following steps: In the multi-warehouse logistics scheduling process, the logistics status information of multiple nodes in the logistics network is collected; Extracting execution status characteristics of the logistics task from the logistics status information, and then determining the collaborative adaptability of the scheduling resources to the logistics task based on the execution status characteristics and the scheduling strategy based on transportation resources in the logistics network; Based on the logistics knowledge graph, the transportation resources in the logistics network are divided into multiple resource allocation units, and the resource coordination relationship between each resource allocation unit is determined. The scheduling cost of each resource allocation unit for the logistics task is determined based on the resource coordination relationship and the scheduling cycle constraints of the logistics network; The scheduling adaptation relationship between resource allocation and task requirements in the logistics network is fuzzily evaluated by using all scheduling costs and the collaborative adaptation degree, thereby determining a scheduling optimization index based on fuzzy logic; The logistics tasks of each resource allocation unit are load balanced and scheduled based on the scheduling optimization index.

[0006] In this embodiment, extracting the execution status characteristics of the logistics task from the logistics status information specifically includes: For each logistics task, extracting the completion progress characteristics and transportation speed characteristics of the logistics task from the logistics status information; The execution status characteristics of the logistics tasks are determined by the completion progress characteristics and the transportation speed characteristics, and then the execution status characteristics of each logistics task are obtained.

[0007] In this embodiment, determining the collaborative adaptability of scheduling resources to logistics tasks based on the execution state characteristics and the scheduling strategy based on transportation resources in the logistics network specifically includes: Obtaining transportation resource-based scheduling strategies in logistics networks; For each logistics task, extracting execution status parameters of the logistics task from the execution status features; Performing adaptability evaluation on the execution state parameters through the scheduling strategy to obtain the collaborative value of the transportation resources in the logistics task, and then obtaining the collaborative value of the transportation resources in each logistics task; Determine the collaborative adaptability of scheduling resources to logistics tasks based on all collaborative values.

[0008] In this embodiment, dividing the transportation resources in the logistics network into multiple resource allocation units based on the logistics knowledge graph specifically includes: Obtain all transportation resource information of the logistics network and then determine the capacity characteristics of each transportation resource; Based on the logistics knowledge graph, all transport capacity characteristics are classified into multiple transport capacity levels; All transportation resources are divided into multiple resource allocation units according to various capacity levels.

[0009] In this embodiment, determining the resource coordination relationship between the resource allocation units specifically includes: For each resource allocation unit, obtaining the coordinated transportation data between the resource allocation unit and other resource allocation units; Determine the collaborative topology of the resource allocation unit through the collaborative transportation data, and then obtain the collaborative topology of each resource allocation unit; The resource coordination relationship between each resource allocation unit is determined based on all coordination topology diagrams.

[0010] In this embodiment, determining the scheduling cost of each resource allocation unit for the logistics task based on the resource coordination relationship and the scheduling cycle constraint of the logistics network specifically includes: For each resource allocation unit, extracting the resource coordination feature of the resource allocation unit from the resource coordination relationship; Extract the time constraint value of resource allocation unit to complete logistics task from the scheduling cycle constraint condition of logistics network; The time constraint value is associated and analyzed through the resource coordination feature to obtain the scheduling cost of the resource allocation unit for the logistics task, and then the scheduling cost of each resource allocation unit for the logistics task is obtained.

[0011] In this embodiment, the scheduling adaptation relationship between resource allocation and task requirements in the logistics network is fuzzily evaluated by all scheduling costs and the collaborative adaptation degree, and the scheduling optimization index based on fuzzy logic is determined to include: Establishing a fuzzy evaluation matrix, taking all scheduling costs and the collaborative fitness as matrix input parameters; The fuzzy evaluation matrix is ​​operated by a preset fuzzy logic rule to obtain a fuzzy value of the adaptability between resource allocation and task requirements; A scheduling optimization index based on fuzzy logic is determined according to the fuzzy value of the adaptability.

[0012] In this embodiment, performing load balancing scheduling on the logistics tasks of each resource allocation unit based on the scheduling optimization index specifically includes: Determine the current task load value of each resource allocation unit according to the scheduling optimization index; Compare the differences between the task load values ​​of each resource allocation unit and the system average load value, and then reallocate the logistics tasks of each resource allocation unit according to the differences to achieve load balancing scheduling.

[0013] In this embodiment, the node refers to a transportation control unit in the logistics network that has independent operating capabilities and participates in task execution.

[0014] In a second aspect, the present application provides an intelligent logistics scheduling system based on multi-source information fusion, which is used to execute an intelligent logistics scheduling method based on multi-source information fusion. The intelligent logistics scheduling system includes: The collection module is used to collect logistics status information of multiple nodes in the logistics network during the multi-warehouse logistics scheduling process; a feature processing module, configured to extract execution status features of the logistics task from the logistics status information, and then determine the collaborative adaptability of the scheduling resources to the logistics task based on the execution status features and the scheduling strategy based on transportation resources in the logistics network; The feature processing module is further configured to divide the transportation resources in the logistics network into multiple resource allocation units based on the logistics knowledge graph, thereby determining the resource coordination relationship between the resource allocation units, and determining the scheduling cost of each resource allocation unit for the logistics task based on the resource coordination relationship and the scheduling cycle constraints of the logistics network; The feature processing module is further used to perform a fuzzy evaluation on the scheduling adaptation relationship between resource allocation and task requirements in the logistics network through all scheduling costs and the collaborative adaptation degree, thereby determining a scheduling optimization index based on fuzzy logic; The scheduling module is used to perform load balancing scheduling on the logistics tasks of each resource allocation unit based on the scheduling optimization index.

[0015] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects: First, in the multi-warehouse logistics scheduling process, the logistics status information of multiple nodes in the logistics network is collected; the execution status characteristics of the logistics tasks are extracted from the logistics status information, and then the collaborative adaptability of the scheduling resources to the logistics tasks is determined through the execution status characteristics and the scheduling strategy based on transportation resources in the logistics network; the transportation resources in the logistics network are divided into multiple resource allocation units based on the logistics knowledge graph, and then the resource coordination relationship between each resource allocation unit is determined, and the scheduling cost of each resource allocation unit for the logistics task is determined according to the resource coordination relationship and the scheduling cycle constraints of the logistics network; the scheduling adaptation relationship between resource allocation and task requirements in the logistics network is fuzzy evaluated through all scheduling costs and the collaborative adaptability, and then the scheduling optimization index based on fuzzy logic is determined; the logistics tasks of each resource allocation unit are load-balanced based on the scheduling optimization index.

[0016] It can be seen that this application fuzzily evaluates the scheduling adaptation relationship between resource allocation and task requirements in the logistics network through all scheduling costs and collaborative adaptation degrees, determines the scheduling optimization index based on fuzzy logic, and then performs balanced scheduling of the logistics tasks of each resource allocation unit based on the scheduling optimization index; first, by dynamically collecting the status information of multiple nodes in the logistics network, it can comprehensively reflect the current operating load of the system, task execution progress and node resource status, and provide a high-efficiency and high-precision input basis for subsequent scheduling decisions; secondly, after extracting the execution status characteristics of the logistics task, through integration with the transportation resource scheduling strategy, the collaborative adaptation quantification of resources to tasks is realized, which effectively reflects the actual adaptation relationship between resources and tasks in terms of executability, timeliness and matching degree; thirdly, a hierarchical structure is used to divide the transportation resources into multiple resource allocation units, and through the nodes Historical collaborative transportation behaviors are used to construct a resource collaborative relationship network, and the time constraint information of resource scheduling is extracted in combination with the scheduling cycle constraints. Then, a scheduling cost model is established to realize a multi-dimensional evaluation of the scheduling consumption required for units to complete logistics tasks. Then, all scheduling costs and collaborative fitness are used to construct a fuzzy evaluation matrix, and a preset fuzzy rule system is introduced. The fuzzy value of the fitness between task requirements and resource allocation is obtained through membership calculation, realizing the fusion analysis of multi-source constraints and collaborative relationships, and solving the problems of low scheduling efficiency and evaluation distortion caused by strong coupling between parameters in traditional methods. Finally, scheduling optimization indicators are formed based on the fuzzy evaluation results, and load balancing scheduling is carried out accordingly. By analyzing the deviation between the task load value of the resource unit and the average load of the system, the task allocation strategy is dynamically adjusted to achieve a balanced configuration of resource load in the entire network, thereby improving the overall throughput capacity and scheduling stability of the system.

[0017] In summary, the present application scheme uses fuzzy logic to comprehensively evaluate the resource coordination relationship and scheduling adaptability in complex logistics scheduling, and can achieve load balancing of logistics scheduling. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0019] Figure 1 This is a flow chart of the intelligent logistics scheduling method based on multi-source information fusion provided by this application; Figure 2 is an exemplary flow chart for determining the degree of cooperative fitness provided in the present application; Figure 3is an exemplary flow chart for determining resource collaboration relationships provided in this application; Figure 4 This is a module structure diagram of the intelligent logistics scheduling system based on multi-source information fusion provided by this application. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0021] The embodiment of the present application provides an intelligent logistics scheduling system and method based on multi-source information fusion, the core of which is to determine the collaborative adaptability of scheduling resources to logistics tasks through the execution status characteristics and scheduling strategies of logistics tasks; divide transportation resources into multiple resource allocation units, determine the resource collaborative relationship between each resource allocation unit, and determine the scheduling cost of each resource allocation unit for logistics tasks based on the resource collaborative relationship and the scheduling cycle constraints of the logistics network; fuzzy evaluate the scheduling adaptation relationship between resource allocation and task requirements in the logistics network through all scheduling costs and collaborative adaptability, and determine the scheduling optimization index based on fuzzy logic; and perform load balancing scheduling on the logistics tasks of each resource allocation unit based on the scheduling optimization index. The present application uses fuzzy logic to comprehensively evaluate the resource collaborative relationship and scheduling adaptability in complex logistics scheduling, which can achieve load balancing of logistics scheduling.

[0022] Example 1: In order to better understand the above technical solution, the above technical solution will be described in detail below with reference to the accompanying drawings and specific implementation methods. Figure 1 As shown in FIG, this figure is an exemplary flow chart of an intelligent logistics scheduling method based on multi-source information fusion according to this embodiment of the present application. The intelligent logistics scheduling method based on multi-source information fusion includes the following steps: In step S1, during the multi-warehouse logistics scheduling process, logistics status information of multiple nodes in the logistics network is collected.

[0023] It should be noted that in the multi-warehouse logistics scheduling scenario, the logistics system presents complex characteristics of multiple nodes, high concurrency, heterogeneous tasks and dynamic changes in resources. When faced with parallel operations and asynchronous collaboration of multiple storage centers, traditional scheduling methods often lack a dynamic matching mechanism for real-time perception of node status and resource coordination capabilities, which can easily lead to local resource redundancy, scheduling delays and overall load imbalance. Therefore, multi-warehouse logistics scheduling requires the introduction of a multi-source information fusion mechanism at the scheduling strategy level. Through real-time collection and feature extraction of logistics status data of each warehouse node, a state perception model between resources and tasks is constructed, thereby realizing the linkage regulation of hierarchical management of transportation resources, dynamic evaluation of task status and resource collaborative adaptation analysis, providing technical support for achieving efficient multi-node collaboration and task load balancing.

[0024] In this embodiment, the node in this application refers to a transportation control unit in the logistics network that has independent operation capabilities and participates in task execution, including warehousing centers, transshipment hubs, and distribution terminals; the logistics status information in this application refers to the dynamic data generated by the logistics node during the execution of the task that reflects its operating status, including inventory levels, task progress, transportation location, speed and equipment availability.

[0025] In step S2, the execution status characteristics of the logistics task are extracted from the logistics status information, and then the collaborative adaptability of the scheduling resources to the logistics task is determined through the execution status characteristics and the scheduling strategy based on transportation resources in the logistics network.

[0026] In this embodiment, the following steps may be used to extract the execution status characteristics of the logistics task from the logistics status information: For each logistics task, extracting the completion progress characteristics and transportation speed characteristics of the logistics task from the logistics status information; The execution status characteristics of the logistics tasks are determined by the completion progress characteristics and the transportation speed characteristics, and then the execution status characteristics of each logistics task are obtained.

[0027] It should be noted that the completion progress feature in this application is a feature that measures the current degree of completion of the logistics task within a given scheduling cycle; the transportation speed feature in this application is a feature that measures the physical movement speed of the logistics task during the transportation process; the execution status feature in this application is a comprehensive feature that reflects the overall operating efficiency and progress of the logistics task, and reflects the coordinated performance of the task completion progress and transportation speed.

[0028] In specific implementation, first, based on the unique identifier of each logistics task, the system extracts the scheduling start time, expected completion time and task feedback data of the current node from the integrated transportation management system, calculates the task completion ratio by comparing the current time with the task progress node, and uses the task completion ratio as the completion progress feature. At the same time, the system relies on the vehicle's global positioning system and acceleration sensor to obtain continuous position data during the transportation process, combines the timestamp for piecewise linear fitting calculation, and uses the average speed per unit time as the transportation speed feature; then, the completion progress feature and the transportation speed feature are combined into a feature vector and input into a preset rule function or a weighted model based on weight settings, such as execution status feature = A*completion progress feature + B*transportation speed feature, where A and B are empirical weight coefficients. The execution status feature of the current logistics task can be quantified in the above manner.

[0029] In this embodiment, reference Figure 2 As shown in FIG, this figure is an exemplary flow chart for determining the collaborative adaptability in an embodiment of the present application. In this embodiment, the collaborative adaptability of the scheduling resources to the logistics tasks is determined by the execution state characteristics and the scheduling strategy based on transportation resources in the logistics network. The following steps can be used to implement it: In step S21, a scheduling strategy based on transportation resources in the logistics network is obtained; In step S22, for each logistics task, the execution status parameter of the logistics task is extracted from the execution status feature; In step S23, the execution state parameters are evaluated for adaptability using the scheduling strategy to obtain the coordination value of the transportation resources in the logistics task, and then the coordination value of the transportation resources in each logistics task is obtained; In step S24, the coordination adaptability of the scheduling resources to the logistics task is determined based on all the coordination values.

[0030] It should be noted that the coordination value in this application is an indicator for measuring the coordination between transportation resources and logistics tasks; the coordination adaptability in this application is a comprehensive indicator for measuring the coordination between overall scheduling resources and logistics tasks.

[0031] In specific implementation, first, the currently effective transportation resource scheduling strategy is obtained based on the logistics network scheduling system. The scheduling strategy usually exists in the form of a rule base, such as priority scheduling based on heuristic rules; secondly, for each logistics task, the system separates key execution state parameters from the aforementioned extracted execution state features, such as task progress and transportation speed, and constructs a task state vector; then, the task state vector is input into the adaptability evaluation module of the scheduling strategy. The adaptability evaluation module uses a rule matching algorithm to compare resource scheduling constraints with task requirements, and calculates the coordination value between transportation resources and logistics tasks. Specifically, a weighted scoring model can be used to quantify the degree of adaptability of resources to execute the task; finally, the coordination values ​​corresponding to all tasks can be summarized, and the average value of all coordination values ​​can be used as the coordination adaptability of scheduling resources to logistics tasks.

[0032] It should be noted that the present application scheme realizes the precise matching between scheduling resources and tasks by combining the execution status of logistics tasks and the scheduling strategy of transportation resources; firstly, the actual execution progress and transportation speed of the tasks are utilized to enable scheduling decisions to reflect the real-time status of the tasks, thus solving the problem that traditional scheduling methods cannot respond quickly to task changes and improving the accuracy and timeliness of scheduling; secondly, the execution status parameters are evaluated through the scheduling strategy to quantify the matching degree between transportation resources and tasks, thus realizing the effective combination of resource characteristics and task requirements, improving resource utilization efficiency, and reducing idle transportation resources and task conflicts; then, the matching results of all tasks are comprehensively calculated to obtain the overall collaborative adaptability index, which is convenient for evaluating and adjusting the resource allocation effect of the entire logistics network, supporting subsequent scheduling optimization and load balancing, and improving the overall efficiency and stability of multi-warehouse logistics scheduling.

[0033] In step S3, the transportation resources in the logistics network are divided into multiple resource allocation units based on the logistics knowledge graph, and then the resource coordination relationship between each resource allocation unit is determined. The scheduling cost of each resource allocation unit for the logistics task is determined according to the resource coordination relationship and the scheduling cycle constraints of the logistics network.

[0034] In this embodiment, the following steps can be used to divide the transportation resources in the logistics network into multiple resource allocation units based on the logistics knowledge graph: Obtain all transportation resource information of the logistics network and then determine the capacity characteristics of each transportation resource; Based on the logistics knowledge graph, all transport capacity characteristics are classified into multiple transport capacity levels; All transportation resources are divided into multiple resource allocation units according to various capacity levels.

[0035] It should be noted that the capacity characteristics in this application are characteristics that measure the carrying capacity of transportation resources in logistics operations; the capacity level in this application is an indicator that measures the classification level of the carrying capacity level of transportation resources; the resource allocation unit in this application refers to a collection of transportation resources that are divided according to capacity level, have similar transportation capabilities and serve as the basic unit of scheduling management.

[0036] In the specific implementation, first, detailed information of all transportation resources is collected through the logistics management system, including vehicle load, transportation capacity, operation frequency and status, to accurately describe the capacity characteristics of each transportation resource; then, based on the existing logistics knowledge graph construction method, all the above-mentioned capacity characteristics are mapped to the knowledge graph nodes through entity recognition and attribute normalization, and the relational reasoning module is used (this application adopts a similarity propagation algorithm based on graph structure to calculate the feature similarity between different transportation resources, divide the transportation resources into several capacity levels, and ensure that the difference in resource capacity within the same level is small; finally, according to the divided capacity levels, the resources are classified into corresponding resource allocation units to realize hierarchical management of transportation resources. This hierarchical structure not only makes the resource division more scientific and reasonable, but also provides a clear resource grouping basis for subsequent scheduling, thereby improving resource utilization efficiency and scheduling flexibility.

[0037] It should be noted that the logistics knowledge graph in this application refers to a semantic network that organizes entities and their relationships in the logistics field in a graph structure, which is used to describe the association logic and business rules between multiple types of elements such as transportation resources, operation nodes, paths, events, etc. Its technical principle is based on entity extraction, attribute labeling and relationship modeling, and constructs the original logistics data into a structured graph that can be used for semantic reasoning. In the process of transport resource division, the logistics knowledge graph supports the similarity calculation and classification reasoning of capacity level division by representing the association relationship between the capacity characteristics of each transport resource, and then realizes the intelligent clustering of transport resources based on semantic consistency, providing knowledge-driven support for the construction of resource allocation units.

[0038] In this embodiment, reference Figure 3 As shown in FIG, this figure is an exemplary flow chart of determining resource coordination relationships in an embodiment of the present application. In this embodiment, determining resource coordination relationships between various resource allocation units can be implemented using the following steps: In step S31, for each resource allocation unit, the coordinated transportation data between the resource allocation unit and other resource allocation units is obtained; In step S32, a collaborative topology graph of resource allocation units is determined by using the collaborative transportation data, thereby obtaining a collaborative topology graph of each resource allocation unit; In step S33, the resource coordination relationship between the resource allocation units is determined according to all coordination topology graphs.

[0039] It should be noted that the collaborative transportation data in this application refers to the operating records reflecting the transportation collaboration between different resource allocation units; the collaborative topology diagram in this application refers to a graphical model that uses nodes and edges to represent resource allocation units and their collaborative relationship structure; the resource collaborative relationship in this application is an indicator to measure the degree of collaboration between different resource allocation units.

[0040] In the specific implementation, first, the collaborative transportation data between each resource allocation unit is collected through the logistics information system, mainly including indicators such as cargo flow frequency, transportation route overlap, vehicle sharing and transshipment time. These data reflect the actual collaborative relationship between different resource allocation units; secondly, the adjacency matrix construction method in graph theory is used to convert the collaborative transportation data into a collaborative topology graph, in which the nodes represent resource allocation units and the edge weights represent the collaboration intensity between units. The edge weights can be obtained through weighted calculation; then, the topology graph is structurally analyzed through the shortest path algorithm to identify the collaborative groups and core connections between resource allocation units, and the overall collaborative structure characteristics can be extracted; finally, based on the topology graph analysis results, the resource collaborative relationship between each resource allocation unit is defined and quantified, providing a structured collaborative relationship basis for scheduling optimization, and realizing accurate characterization and scheduling support of the overall collaborative efficiency of logistics resources.

[0041] In this embodiment, the following steps can be used to determine the scheduling cost of each resource allocation unit for the logistics task based on the resource coordination relationship and the scheduling cycle constraint of the logistics network: For each resource allocation unit, extracting the resource coordination feature of the resource allocation unit from the resource coordination relationship; Extract the time constraint value of resource allocation unit to complete logistics task from the scheduling cycle constraint condition of logistics network; The time constraint value is associated and analyzed through the resource coordination feature to obtain the scheduling cost of the resource allocation unit for the logistics task, and then the scheduling cost of each resource allocation unit for the logistics task is obtained.

[0042] It should be noted that the scheduling cycle constraints in this application refer to the scheduling time requirements and time boundary parameters that limit the completion of logistics tasks within a specified time range; the resource collaboration characteristics in this application are characteristics that measure the ability of resource allocation units to collaborate with other resource allocation units during collaborative transportation; the time constraint value in this application is an indicator that measures the response and delivery capabilities of resource allocation units required to complete logistics tasks within a limited time; the scheduling cost in this application is an indicator that measures the comprehensive cost required for resource allocation units to complete logistics tasks under specific collaboration conditions and time constraints.

[0043] In the specific implementation, first, based on the established collaborative topology diagram, the resource collaborative characteristics of each resource allocation unit are extracted, including the connection strength, collaborative frequency and sharing efficiency with other resource allocation units; secondly, the scheduling cycle constraints can be obtained from the logistics management system, and the time constraint values ​​such as the latest completion time and maximum response time of each resource allocation unit in a specific task are extracted, and the extracted time constraint values ​​are converted into time window parameters that can be used for calculation; then, the resource collaborative characteristics and time constraint values ​​are modeled accordingly using association analysis methods (such as multivariate linear regression) to construct a scheduling cost function, wherein the scheduling cost function is used to evaluate the resource consumption, time cost and efficiency loss required for each resource allocation unit to participate in collaborative scheduling while meeting the task time requirements, and finally output the cost of each resource allocation unit for the logistics task. Scheduling cost; It needs to be further explained that the implementation of constructing the scheduling cost function in this application specifically includes: first converting the resource collaboration characteristics and the time requirements within the scheduling cycle into standardized numerical inputs, and then constructing a scheduling cost function, using these inputs as variables, setting the weights of various parameters to reflect the degree of their impact on the scheduling cost. For example, the higher the collaboration frequency, the lower the scheduling cost, the shorter the time remaining, and the higher the scheduling cost. Specifically, a weighted linear expression can be used, namely: Scheduling cost = a × resource collaboration characteristics + b × path sharing characteristics + c × time constraint characteristics, where a, b, and c can be obtained by fitting historical task data, or by training and determining through regression methods such as the least squares method. The scheduling cost function is used to actually evaluate the scheduling cost required for the resource unit to complete the task under current conditions, and the output result is the scheduling cost.

[0044] It should be noted that the present application scheme, by integrating resource collaboration characteristics with scheduling cycle constraints, constructs a joint scheduling cost function for task response timeliness and resource coordination capabilities, effectively solving the technical problems of insufficient modeling of dynamic collaboration capabilities and rough quantification of time constraints in existing scheduling methods. Traditional scheduling methods usually use static path optimization or allocate tasks based on static resource attributes, lacking modeling of the collaborative linkage history between different resource units, resulting in difficulty in reflecting resource availability and actual timeliness matching in a dynamic environment with multiple tasks and multiple nodes. The present application scheme extracts the collaborative topological relationship of resource allocation units and actual collaborative transportation data, quantitatively constructs their resource collaboration characteristics, and combines scheduling cycle constraints such as task time windows and node response delays, using weighted models or multivariate regression methods to construct a scheduling cost function, achieving two-way constraint matching of resource capabilities and time adaptability in the task scheduling process. In terms of technical effects, this method significantly improves the adaptive ability of resource scheduling schemes to changes in collaborative conditions, enhances the accuracy of scheduling path selection in complex networks, and effectively improves the overall timeliness and resource utilization efficiency of logistics network tasks.

[0045] In step S4, a fuzzy evaluation is performed on the scheduling adaptation relationship between resource allocation and task requirements in the logistics network through all scheduling costs and the collaborative adaptation degree, and then a scheduling optimization index based on fuzzy logic is determined.

[0046] In this embodiment, the scheduling adaptation relationship between resource allocation and task requirements in the logistics network is fuzzily evaluated using all scheduling costs and the collaborative adaptation degree, and the scheduling optimization index based on fuzzy logic is determined by the following steps: Establishing a fuzzy evaluation matrix, taking all scheduling costs and the collaborative fitness as matrix input parameters; The fuzzy evaluation matrix is ​​operated by a preset fuzzy logic rule to obtain a fuzzy value of the adaptability between resource allocation and task requirements; A scheduling optimization index based on fuzzy logic is determined according to the fuzzy value of the adaptability.

[0047] It should be noted that the fuzzy evaluation matrix in this application refers to a two-dimensional matrix used to represent the degree of scheduling matching between multiple resource allocation units and task requirements; the fuzzy value of adaptability in this application is a fuzzy indicator for measuring the degree of scheduling matching between resource allocation units and logistics tasks; the scheduling optimization index in this application refers to a quantitative evaluation parameter that comprehensively reflects the quality of matching between resource allocation and task requirements and scheduling efficiency in the logistics network.

[0048] In the specific implementation, first, a fuzzy evaluation matrix is ​​constructed based on the scheduling cost and collaborative adaptability of each resource allocation unit in the logistics network. Each row of the matrix corresponds to a resource allocation unit, and each column corresponds to a logistics task requirement. The matrix elements reflect the scheduling matching between resources and tasks; secondly, for the two indicators of scheduling cost and collaborative adaptability, appropriate membership functions are designed respectively, and the numerical values ​​are converted into fuzzy membership. Commonly used membership functions include triangular, trapezoidal or Gaussian functions, which respectively characterize the membership corresponding to different levels of scheduling cost (such as low, medium, high) and adaptability (such as weak, medium, strong). Then, based on expert experience or historical data, a fuzzy logic rule base is set, such as "when the scheduling cost is low and the collaborative fitness is high, the fitness output is excellent", "when the scheduling cost is high and the collaborative fitness is low, the fitness output is poor", and the fuzzy evaluation matrix is ​​inferred through a fuzzy inference system (this application uses Mamdani) to generate the fuzzy fitness output of each resource task pair, that is, the fitness fuzzy value; finally, the fuzzy aggregation method (this application uses the maximum membership) is used to process all the fitness fuzzy values, and the output result is used as the scheduling optimization indicator based on fuzzy logic.

[0049] It should be noted that the present application solution constructs a fuzzy evaluation matrix, takes scheduling cost and collaborative fitness as input parameters, and adopts fuzzy logic rules to realize comprehensive evaluation of multiple indicators, thereby solving the problem that single indicator evaluation in traditional logistics scheduling is difficult to take into account both resource efficiency and task matching. In the specific implementation, the fuzzy evaluation matrix uniformly expresses multi-source heterogeneous data, overcomes the influence of information uncertainty and complexity in the scheduling environment, and enables each indicator to be reasonably weighed under a unified framework, avoiding the distortion of scheduling decisions caused by the difficulty in accurately determining indicator weights. The fuzzy reasoning mechanism is used to calculate the fuzzy value of fitness, which can accurately reflect the degree of matching between resource allocation units and task requirements and their uncertainty, and enhance the responsiveness of the scheduling model to actual changes. The final scheduling optimization index provides a refined evaluation standard for the scheduling system, which helps to guide the load balancing and task scheduling adjustment of resource allocation units, reduce the overall scheduling cost, improve the utilization rate of transportation resources and the completion efficiency of logistics tasks, enhance the intelligence level and stability of the multi-warehouse logistics scheduling system, and meet the scheduling optimization needs in complex dynamic environments.

[0050] In step S5, load balancing scheduling is performed on the logistics tasks of each resource allocation unit based on the scheduling optimization index.

[0051] In this embodiment, load balancing scheduling of logistics tasks of each resource allocation unit based on the scheduling optimization index can be achieved by using the following steps: Determine the current task load value of each resource allocation unit according to the scheduling optimization index; Compare the differences between the task load values ​​of each resource allocation unit and the system average load value, and then reallocate the logistics tasks of each resource allocation unit according to the differences to achieve load balancing scheduling.

[0052] It should be noted that the task load value in this application is an indicator to measure the current workload and pressure borne by the resource allocation unit.

[0053] In the specific implementation, first, the task load value currently undertaken by each resource allocation unit is calculated based on the scheduling optimization index. The specific implementation can use weighted calculation to convert the scheduling optimization index into a quantitative load score to reflect the work intensity of the resource unit. It should be further explained that the use of weighted calculation to convert the scheduling optimization index into a quantitative load score in this application can be implemented in the following way: first determine the importance weights of each parameter in the scheduling optimization index. These weights can be obtained through expert experience or historical data analysis, and then the scheduling optimization index of each resource allocation unit is weightedly calculated according to the corresponding weight. Specifically, each parameter value is multiplied by its weight and then summed to obtain a comprehensive score. The comprehensive score is the load score of the resource unit, which can reflect its current work intensity and task Pressure, in the weighted summation process, in order to ensure the rationality of the calculation results, each parameter is usually normalized first, so that data of different dimensions are unified to the same level, so as to avoid a certain indicator from having too much influence on the result; then, by statistically analyzing the average level of the load values ​​of all resource allocation units, a difference analysis method (this application uses load deviation calculation) is used to measure the degree of deviation of the load of each unit from the average value. For resource units with large deviations, a load balancing algorithm is applied, such as a heuristic scheduling algorithm that adjusts part of the tasks of the overloaded unit to the unit with lower load to ensure more even task distribution. This process relies on real-time monitoring and feedback mechanisms, combined with the task queue management technology in the existing scheduling system, to dynamically update load data to ensure the timeliness and accuracy of scheduling adjustments.

[0054] It can be seen that this application fuzzily evaluates the scheduling adaptation relationship between resource allocation and task requirements in the logistics network through all scheduling costs and collaborative adaptation degrees, determines the scheduling optimization index based on fuzzy logic, and then performs balanced scheduling of the logistics tasks of each resource allocation unit based on the scheduling optimization index; first, by dynamically collecting the status information of multiple nodes in the logistics network, it can comprehensively reflect the current operating load of the system, task execution progress and node resource status, and provide a high-efficiency and high-precision input basis for subsequent scheduling decisions; secondly, after extracting the execution status characteristics of the logistics task, through integration with the transportation resource scheduling strategy, the collaborative adaptation quantification of resources to tasks is realized, which effectively reflects the actual adaptation relationship between resources and tasks in terms of executability, timeliness and matching degree; thirdly, a hierarchical structure is used to divide the transportation resources into multiple resource allocation units, and through the nodes Historical collaborative transportation behaviors are used to construct a resource collaborative relationship network, and the time constraint information of resource scheduling is extracted in combination with the scheduling cycle constraints. Then, a scheduling cost model is established to realize a multi-dimensional evaluation of the scheduling consumption required for units to complete logistics tasks. Then, all scheduling costs and collaborative fitness are used to construct a fuzzy evaluation matrix, and a preset fuzzy rule system is introduced. The fuzzy value of the fitness between task requirements and resource allocation is obtained through membership calculation, realizing the fusion analysis of multi-source constraints and collaborative relationships, and solving the problems of low scheduling efficiency and evaluation distortion caused by strong coupling between parameters in traditional methods. Finally, scheduling optimization indicators are formed based on the fuzzy evaluation results, and load balancing scheduling is carried out accordingly. By analyzing the deviation between the task load value of the resource unit and the average load of the system, the task allocation strategy is dynamically adjusted to achieve a balanced configuration of resource load in the entire network, thereby improving the overall throughput capacity and scheduling stability of the system.

[0055] In summary, the present application scheme uses fuzzy logic to comprehensively evaluate the resource coordination relationship and scheduling adaptability in complex logistics scheduling, and can achieve load balancing of logistics scheduling.

[0056] In the second embodiment, the present application provides an intelligent logistics scheduling system based on multi-source information fusion, referring to Figure 4 As shown in FIG, this figure is a schematic diagram of an intelligent logistics scheduling system based on multi-source information fusion according to this embodiment of the present application. The intelligent logistics scheduling system based on multi-source information fusion includes: The collection module 100 is used to collect logistics status information of multiple nodes in the logistics network during the multi-warehouse logistics scheduling process; A feature processing module 200 is configured to extract execution status features of the logistics task from the logistics status information, and further determine the collaborative adaptability of the scheduling resources to the logistics task based on the execution status features and the scheduling strategy based on transportation resources in the logistics network; The feature processing module 200 is further configured to divide the transportation resources in the logistics network into a plurality of resource allocation units based on the logistics knowledge graph, thereby determining the resource coordination relationship between the resource allocation units, and determining the scheduling cost of each resource allocation unit for the logistics task based on the resource coordination relationship and the scheduling cycle constraints of the logistics network; The feature processing module 200 is further configured to perform a fuzzy evaluation on the scheduling adaptation relationship between resource allocation and task requirements in the logistics network using all scheduling costs and the collaborative adaptation degree, thereby determining a scheduling optimization index based on fuzzy logic; The scheduling module 300 is used to perform load balancing scheduling on the logistics tasks of each resource allocation unit based on the scheduling optimization index.

[0057] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0058] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program. The program can be stored in a computer-readable storage medium, including a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM), or other optical disc storage, magnetic disk storage, or magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0059] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

Claims

1. An intelligent logistics scheduling method based on multi-source information fusion, characterized in that: The steps include: In the multi-warehouse logistics scheduling process, the logistics status information of multiple nodes in the logistics network is collected; Extracting execution status characteristics of the logistics task from the logistics status information, and then determining the collaborative adaptability of the scheduling resources to the logistics task based on the execution status characteristics and the scheduling strategy based on transportation resources in the logistics network; Based on the logistics knowledge graph, the transportation resources in the logistics network are divided into multiple resource allocation units, and the resource coordination relationship between each resource allocation unit is determined. The scheduling cost of each resource allocation unit for the logistics task is determined based on the resource coordination relationship and the scheduling cycle constraints of the logistics network; The scheduling adaptation relationship between resource allocation and task requirements in the logistics network is fuzzily evaluated by using all scheduling costs and the collaborative adaptation degree, thereby determining a scheduling optimization index based on fuzzy logic; The logistics tasks of each resource allocation unit are load balanced and scheduled based on the scheduling optimization index.

2. The method according to claim 1, wherein Extracting execution status features of logistics tasks from the logistics status information specifically includes: For each logistics task, extracting the completion progress characteristics and transportation speed characteristics of the logistics task from the logistics status information; The execution status characteristics of the logistics tasks are determined by the completion progress characteristics and the transportation speed characteristics, and then the execution status characteristics of each logistics task are obtained.

3. The method according to claim 1, wherein Determining the collaborative adaptability of scheduling resources to logistics tasks based on the execution state characteristics and the scheduling strategy based on transportation resources in the logistics network specifically includes: Obtaining transportation resource-based scheduling strategies in logistics networks; For each logistics task, extracting execution status parameters of the logistics task from the execution status features; Performing adaptability evaluation on the execution state parameters through the scheduling strategy to obtain the collaborative value of the transportation resources in the logistics task, and then obtaining the collaborative value of the transportation resources in each logistics task; Determine the collaborative adaptability of scheduling resources to logistics tasks based on all collaborative values.

4. The method according to claim 1, wherein Based on the logistics knowledge graph, the transportation resources in the logistics network are divided into multiple resource allocation units, including: Obtain all transportation resource information of the logistics network and then determine the capacity characteristics of each transportation resource; Based on the logistics knowledge graph, all transport capacity characteristics are classified into multiple transport capacity levels; All transportation resources are divided into multiple resource allocation units according to various capacity levels.

5. The method according to claim 1, wherein Determining the resource coordination relationship between each resource allocation unit specifically includes: For each resource allocation unit, obtaining the coordinated transportation data between the resource allocation unit and other resource allocation units; Determine the collaborative topology of the resource allocation unit through the collaborative transportation data, and then obtain the collaborative topology of each resource allocation unit; The resource coordination relationship between each resource allocation unit is determined based on all coordination topology diagrams.

6. The method according to claim 1, wherein The scheduling cost of each resource allocation unit for the logistics task is determined based on the resource coordination relationship and the scheduling cycle constraint of the logistics network, specifically including: For each resource allocation unit, extracting the resource coordination feature of the resource allocation unit from the resource coordination relationship; Extract the time constraint value of resource allocation unit to complete logistics task from the scheduling cycle constraint condition of logistics network; The time constraint value is associated and analyzed through the resource coordination feature to obtain the scheduling cost of the resource allocation unit for the logistics task, and then the scheduling cost of each resource allocation unit for the logistics task is obtained.

7. The method according to claim 1, wherein The scheduling adaptation relationship between resource allocation and task requirements in the logistics network is fuzzily evaluated through all scheduling costs and the collaborative adaptation degree, and then the scheduling optimization indicators based on fuzzy logic are determined, including: Establishing a fuzzy evaluation matrix, taking all scheduling costs and the collaborative fitness as matrix input parameters; The fuzzy evaluation matrix is ​​operated by a preset fuzzy logic rule to obtain a fuzzy value of the adaptability between resource allocation and task requirements; A scheduling optimization index based on fuzzy logic is determined according to the fuzzy value of the adaptability.

8. The method according to claim 1, wherein The load balancing scheduling of the logistics tasks of each resource allocation unit based on the scheduling optimization index specifically includes: Determine the current task load value of each resource allocation unit according to the scheduling optimization index; Compare the differences between the task load values ​​of each resource allocation unit and the system average load value, and then reallocate the logistics tasks of each resource allocation unit according to the differences to achieve load balancing scheduling.

9. The method according to claim 1, wherein The node refers to a transportation control unit in the logistics network that has the ability to operate independently and participate in task execution.

10. An intelligent logistics scheduling system based on multi-source information fusion, used to execute the intelligent logistics scheduling method based on multi-source information fusion according to any one of claims 1 to 9, characterized in that: The intelligent logistics scheduling system includes: The collection module is used to collect logistics status information of multiple nodes in the logistics network during the multi-warehouse logistics scheduling process; a feature processing module, configured to extract execution status features of the logistics task from the logistics status information, and then determine the collaborative adaptability of the scheduling resources to the logistics task based on the execution status features and the scheduling strategy based on transportation resources in the logistics network; The feature processing module is further configured to divide the transportation resources in the logistics network into multiple resource allocation units based on the logistics knowledge graph, thereby determining the resource coordination relationship between the resource allocation units, and determining the scheduling cost of each resource allocation unit for the logistics task based on the resource coordination relationship and the scheduling cycle constraints of the logistics network; The feature processing module is further used to perform a fuzzy evaluation on the scheduling adaptation relationship between resource allocation and task requirements in the logistics network through all scheduling costs and the collaborative adaptation degree, thereby determining a scheduling optimization index based on fuzzy logic; The scheduling module is used to perform load balancing scheduling on the logistics tasks of each resource allocation unit based on the scheduling optimization index.

Images