A method and system for optimizing the handling of transport lines based on intelligent scheduling

Abstract

This invention proposes a method and system for optimizing the handling of dedicated transportation lines based on intelligent scheduling. The method includes: constructing a dynamic timeliness graph model and collecting real-time data; performing path planning and task allocation based on the dynamic timeliness graph model; designing a microservice architecture based on a distributed architecture; and designing a self-learning mechanism to automatically adjust based on historical tasks and real-time feedback to optimize the handling tasks of dedicated transportation lines. By introducing graph theory optimization, microservice architecture, and intelligent self-learning algorithms, this invention effectively overcomes the problems of low efficiency, low flexibility, poor scalability, and insufficient real-time scheduling capabilities in traditional dedicated transportation line scheduling methods.

Description

Technical Field

[0001] This invention belongs to the field of intelligent scheduling, and in particular relates to a method and system for optimizing the handling of dedicated transportation lines based on intelligent scheduling. Background Technology

[0002] With the booming development of the modern logistics industry, dedicated transportation lines have become a crucial link. Dedicated transportation systems play a vital role in the transportation of various materials and goods, especially in large-scale, time-bound, and fixed-point freight transport, where they hold a central position. Traditional dedicated transportation line scheduling methods typically rely on manual scheduling, empiricism, or scheduling algorithms based on fixed rules. While these methods ensure the completion of transportation tasks to a certain extent, they face numerous limitations and challenges. Especially when dealing with increasingly complex transportation networks, frequently changing transportation tasks, ever-increasing scheduling demands, and the diversity of transportation resources, traditional solutions often struggle to meet these challenges.

[0003] First, the inefficiency and lack of flexibility of traditional scheduling methods are among the biggest problems. Existing dedicated transportation line scheduling systems are often centralized, and most employ static scheduling methods based on rules or heuristic algorithms, lacking flexibility and real-time capabilities. This results in the scheduling system being unable to respond quickly and dynamically adjust when traffic congestion, sudden weather events, or vehicle breakdowns occur in the transportation network, thus increasing the risk of transportation delays. Furthermore, most current systems fail to fully utilize advanced technologies such as big data, cloud computing, and artificial intelligence; scheduling decisions mainly rely on historical data and qualitative analysis, failing to provide comprehensive optimization and dynamic prediction of transportation tasks.

[0004] Secondly, the scalability and modularity issues of traditional dedicated transportation line dispatching systems also limit their further development. With the continuous expansion of transportation networks and the diversification of transportation tasks and resource types, traditional dispatching systems typically employ a single, large-scale, centralized architecture. This architecture struggles to flexibly scale when faced with complex and dynamically changing task requirements. For example, during peak freight transport periods, adding new dispatching resources or adjusting task allocation often requires modifying the entire system, which is not only inefficient but also increases system maintenance costs. Furthermore, the problem of information silos in transportation dispatching is also significant. Information from different transportation links and data sources is difficult to coordinate efficiently, resulting in dispatching decisions that cannot reflect the current transportation situation in a real-time and comprehensive manner.

[0005] Third, the limitations of scheduling task optimization. Currently, most transportation scheduling systems rely solely on static route selection and resource allocation rules, lacking dynamic optimization for complex spatiotemporal constraints. For example, in certain special cases, route selection must consider not only factors such as time and distance, but also real-time information such as weather, road conditions, and traffic flow. If the system cannot make timely adjustments, it may lead to resource waste or transportation delays, severely impacting transportation efficiency and service quality.

[0006] To address the aforementioned issues, existing technologies generally face the challenge of improving the efficiency, flexibility, and scalability of dedicated transportation line scheduling through innovative algorithms, advanced architectures, and the synergy of real-time data streams. Although transportation scheduling systems based on technologies such as artificial intelligence, the Internet of Things, and cloud computing have gradually emerged in recent years, these systems still have significant room for improvement in terms of overall architectural flexibility, intelligent real-time scheduling, and the ability to optimize large-scale transportation networks. Summary of the Invention

[0007] The purpose of this invention is to propose a transportation line handling optimization method and system based on intelligent scheduling. By introducing graph theory optimization, microservice architecture and intelligent self-learning algorithm, it effectively overcomes the problems of low efficiency, low flexibility, poor scalability and insufficient real-time scheduling capability in traditional transportation line scheduling methods.

[0008] To achieve the above objectives, a first aspect of the present invention provides a method for optimizing the handling of transport lines based on intelligent scheduling, the method comprising:

[0009] S1. Construct a dynamic timeliness graph model and collect data in real time; wherein, the structure of the dynamic timeliness graph model is as follows: each node represents a key location, including the starting point, the ending point or the transfer point, and contains location information and key attributes of the task; each edge represents a transportation path, and the weight of the edge reflects the timeliness of the path; the update mechanism of the dynamic timeliness graph model adopts a sliding window mechanism to update the weight of the edge.

[0010] S2. Route planning and task allocation based on a dynamic timeliness graph model; wherein, the objective function of the route planning and task allocation is to minimize the total transportation cost while satisfying the task time window and resource constraints, wherein the total transportation cost includes time cost and resource allocation cost, and the objective function of the total transportation cost is:

[0011]

[0012] Where C is the total transportation cost, w ij For edge (v) i ,v j The weight of x represents the path cost. ij∈{0,1} is the decision variable, representing the edge (v i ,v j Is it selected? φ r Costs are allocated to resources, taking into account the empty load rate and allocation efficiency of each transportation resource;

[0013] S3. Design a microservice architecture based on a distributed architecture, dividing functions into different modules. Different microservices are responsible for independent functions. Each microservice will dynamically adjust its execution strategy based on the output of the dynamic timeliness graph model and real-time monitoring data. If a delay or resource idleness occurs during task execution, the scheduling service of the microservice architecture needs to dynamically adjust the task allocation strategy according to the task deviation time. The division of functions into different modules includes: path planning service, task scheduling service, real-time monitoring service, and adaptive scheduling adjustment service.

[0014] The path planning service is used to calculate and dynamically adjust the path selection for the task.

[0015] The task scheduling service is used to schedule tasks based on path planning results and real-time data.

[0016] The real-time monitoring service is used to monitor the status changes during task execution in real time and provide feedback.

[0017] The adaptive scheduling adjustment service is used to automatically adjust resource allocation strategies based on real-time feedback and task status.

[0018] S4. Design a self-learning mechanism to automatically adjust based on historical tasks and real-time feedback to optimize the handling tasks on the transportation line.

[0019] Furthermore, the edge weights of the dynamic timeliness graph model are calculated as follows:

[0020] w ij =α·D ij +β·T ij +γ·C ij +δ·W ij +λ·f ij

[0021] Among them, D ij T is the distance between nodes i and j. ij C represents the estimated time for the transportation route. ij To understand the impact of traffic flow on routes, W ij To account for the impact of weather on the path, f ij For additional path constraints, α, β, γ, δ, and λ are adjustment parameters that adjust the influence of different factors on the weights, respectively.

[0022] The method of updating edge weights using a sliding window mechanism is expressed as follows:

[0023] Updatedw ij (t)=w ij (t-Δt)+Δw ij (t)

[0024] Among them, w ij (t) represents the edge weight at time t, Δt is the time interval, and Δw ij (t) represents the change in edge weights caused by the real-time data stream.

[0025] Furthermore, S1 also includes optimizing the sensor data using Kalman filtering, expressed as:

[0026]

[0027] in, z represents the estimate of the state (such as position, velocity, etc.) at time k. k Let K be the measured value at time k. k For Kalman gain, H k This is the measurement matrix, which represents the relationship between measurements and states.

[0028] Furthermore, the total transportation cost is subject to constraints, including:

[0029] Each task node must be accessed exactly once:

[0030]

[0031] Where V is the set of nodes in the graph;

[0032] All tasks must meet the time window constraint:

[0033]

[0034] Where T i T is the task start time. start,i and T end,i The earliest and latest times for the task;

[0035] The load on transport resources must not exceed their capacity:

[0036]

[0037] Where d i For the task requirements, C r This represents the maximum load capacity of resource r.

[0038] Furthermore, S2 also includes joint optimization of path planning and task allocation, specifically:

[0039] Based on the task priority and time window constraints, an initial access sequence is generated, in which the node with the highest priority and tightest time window is accessed first.

[0040] Path planning is performed using a dynamic time-sensitive graph model for each task node v. i Choose weight w ij Minimum edge (v) i ,v j );

[0041] Each transportation resource r is preferentially allocated to the task node v that best matches its current state. i ;

[0042] An adjustment mechanism is introduced to recalculate w using a sliding window. ij and x ij Dynamically update paths and task assignments.

[0043] Furthermore, the sorting strategy for the access sequence is as follows:

[0044]

[0045] Where S is the access sequence, argsort is the sorting function, V is the total number of nodes, and T is the total number of nodes. end,i To close the window, T start,i This is the start window;

[0046] The dynamic path selection rules for path planning in the dynamic timeliness graph model are as follows:

[0047]

[0048] Among them, f ij For additional path constraints, λ is the regularization coefficient used to adjust the importance of the additional constraints, and x i t j This is the initial path;

[0049] The process involves preferentially allocating each transportation resource r to the task node v that best matches its current state. i Specifically:

[0050] Based on the distance D between the current location of the resource and the location of the task r , No load rate η r and task requirements d i The resource suitability is calculated and expressed as:

[0051]

[0052] Select φ r Perform the task with minimal resources;

[0053] The recalculation of w via a sliding window ij and x ij Dynamically update paths and task assignments, specifically:

[0054] Within each sliding window period, the updated path selection rule is as follows:

[0055]

[0056] in, For the updated path, For the initial path, Δx ij This refers to path changes caused by real-time data streams.

[0057] Furthermore, S3 specifically includes:

[0058] The path weights are adjusted based on real-time traffic information, and the actual weights of each path are calculated in real time. The adjusted path planning formula is:

[0059]

[0060] Among them, w ij It is the initial path weight, traffic ij For path (v i ,v j Real-time traffic information, weather ij For path (v i ,v j The weather affects the time of day ij For real-time time factors on the path, λ1, λ2, and λ3 are weighting coefficients that adjust the impact of real-time information on path selection.

[0061] If a delay or resource idleness occurs during task execution, the scheduling service of the microservice architecture needs to dynamically adjust the task allocation strategy based on the task's deviation time, specifically including:

[0062] First, define the task deviation time ΔT. i :

[0063] ΔT i =T actual,i -T planned,i

[0064] Among them, T actual,i T represents the actual execution time of task i. planned,i ΔT represents the planned execution time of task i.i This represents the execution deviation time of task i.

[0065] When the task deviation is too large, the scheduling algorithm will automatically adjust the resource allocation of the task, selecting the nearest and more suitable resource r for task rescheduling. The adjustment strategy is as follows:

[0066]

[0067] in, For the updated strategy, dist r The distance between resource r and task i, avail r For the current availability of resource r, priority r Let r be the priority of resource r, reflecting its applicable priority requirements. β1 and β2 are adjustment weights that determine the impact of distance and resource priority on scheduling decisions.

[0068] Furthermore, S3 also includes a real-time monitoring service that detects state changes during task execution in real time. If a deviation or anomaly is detected, the real-time monitoring service will transmit the real-time monitoring data to the task scheduling service, triggering the task scheduling service to make dynamic adjustments, specifically as follows:

[0069] ΔT i =T actual,i -T planned,i

[0070] Where, ΔT i The deviation time for each task, T actual,i For actual time, T planned,i For the planned time, if ΔT i >δ i Then, task rescheduling will be triggered through the scheduling system;

[0071] The usage status of each resource is monitored, as shown below:

[0072]

[0073] Among them, T assigned,r T represents the allocated working time of resource r. total,r For resource r, the total working time (maximum available time) is defined. When the resource load exceeds a set threshold, L... r >τ r This triggers resource reallocation to avoid overuse of a particular resource;

[0074] Simultaneously, in the microservice architecture, dynamic adjustments are made through load balancing strategies to ensure that the response time of each service does not exceed a predetermined threshold. When service overload is detected, automatic switching to a backup service ensures that the entire scheduling process is uninterrupted. The load balancing strategy is expressed as follows:

[0075]

[0076] Among them, response time s τ is the response time of service s. s As a threshold for response time, Status s The current state of the service.

[0077] Furthermore, S4 specifically includes:

[0078] Based on the skew time and resource load changes for each task, the deviation of the scheduling model is calculated. This is then used to learn from historical feedback data, and the original path planning and task scheduling strategies are adjusted according to the deviation to optimize the scheduling results. This is expressed as:

[0079]

[0080] Where, ΔT i L represents the execution time deviation of task i. r Let T be the current load of resource r, α, β, and γ be the influence coefficients of scheduling error on path selection and task allocation strategies, and T be the current load of resource r. actual,i and T planned,i w represents the actual execution time and the planned execution time of task i, respectively. ij The original path weights are η1 and ΔM is the sensitivity factor for path adjustment. i The scheduling error is the output of the error model, and α is a hyperparameter that controls the degree of influence of the error.

[0081] Design a dynamic task adjustment strategy, combining the optimization results of path planning, to reallocate resources, including:

[0082] If the actual execution time of the task exceeds the expected deviation range ΔT i Then, through the rescheduling mechanism, the most suitable resources are selected to reallocate tasks. During reallocation, task priority is determined. i Adjustments will be made based on the urgency and importance of the task. The formula for task rescheduling is:

[0083]

[0084] Among them, dist r The distance between resource r and task i, avail rPriority is the availability of resource r. r Let γ represent the priority of the resource, and let γ be the coefficient of influence of feedback error on resource scheduling.

[0085] Collect user feedback data and update the scheduling error output by the error model through incremental learning, thereby dynamically updating path planning and task scheduling.

[0086] In a second aspect, the present invention provides a transportation line handling optimization system based on intelligent scheduling, the system comprising:

[0087] A dynamic timeliness graph model unit is used to construct a dynamic timeliness graph model and perform real-time data acquisition. The structure of the dynamic timeliness graph model is as follows: each node represents a key location, including a start point, end point, or transit point, containing location information and key attributes of the task; each edge represents a transportation path, and the edge weight reflects the timeliness of the path; the update mechanism of the dynamic timeliness graph model uses a sliding window mechanism to update the edge weights.

[0088] A route planning and task allocation unit is used for route planning and task allocation based on a dynamic timeliness graph model. The objective function of the route planning and task allocation is to minimize the total transportation cost while satisfying task time windows and resource constraints. The total transportation cost includes time cost and resource allocation cost. The objective function for the total transportation cost is:

[0089]

[0090] Where C is the total transportation cost, w ij For edge (v) i ,v j The weight of x represents the path cost. ij ∈{0,1} is the decision variable, representing the edge (v i ,v j Is it selected? φ r Costs are allocated to resources, taking into account the empty load rate and allocation efficiency of each transportation resource;

[0091] The microservice architecture building unit is used to design a microservice architecture based on a distributed architecture. It breaks down functionality into different modules, with each microservice responsible for an independent function. Each microservice dynamically adjusts its execution strategy based on the output of the dynamic timeliness graph model and real-time monitoring data. If a delay or resource idleness occurs during task execution, the microservice architecture's scheduling service needs to dynamically adjust the task allocation strategy according to the task's deviation time. The breakdown of functionality into different modules includes: path planning service, task scheduling service, real-time monitoring service, and adaptive scheduling adjustment service.

[0092] The path planning service is used to calculate and dynamically adjust the path selection for the task.

[0093] The task scheduling service is used to schedule tasks based on path planning results and real-time data.

[0094] The real-time monitoring service is used to monitor the status changes during task execution in real time and provide feedback.

[0095] The adaptive scheduling adjustment service is used to automatically adjust resource allocation strategies based on real-time feedback and task status.

[0096] The self-learning optimization unit is used to design a self-learning mechanism that automatically adjusts based on historical tasks and real-time feedback to optimize the handling tasks on the transportation line.

[0097] The beneficial technical effects of the present invention are at least as follows:

[0098] First, this invention employs graph theory optimization algorithms. By modeling the dedicated transportation line as a weighted directed graph, it comprehensively considers various spatiotemporal constraints, resource allocation, and path selection factors in the transportation network. Furthermore, it utilizes dynamic timeliness graph algorithms to adjust transportation routes and task allocation in real time. This method not only solves the problem of static path selection in existing scheduling systems but also enables real-time response to emergencies such as traffic congestion and weather changes, achieving dynamic optimization of transportation tasks and significantly improving transportation efficiency and reliability.

[0099] To address the scalability and flexibility issues of existing centralized system architectures, this invention employs a microservice architecture. Each transportation scheduling task is handled by an independent microservice module, including multiple core modules such as route planning, resource management, scheduling execution, and real-time monitoring. These modules collaborate through message queues, enabling the system to quickly adjust and expand as needed, responding in real-time to changes in transportation tasks. For example, when transportation demand surges, the system can rapidly add new scheduling modules to share the workload, thereby maintaining scheduling efficiency. Furthermore, the microservice architecture effectively solves the information silo problem, enabling efficient flow and collaboration of information between different modules through API interfaces, ensuring the real-time and comprehensive nature of decision-making.

[0100] Finally, this invention introduces self-learning algorithms such as reinforcement learning, enabling the scheduling system to continuously learn from historical data and real-time execution results, gradually optimizing scheduling decisions and resource allocation strategies. Feedback data after each transportation task is completed serves as training data, continuously adjusting the scheduling strategy to adapt to the diverse needs of transportation tasks. Through this self-learning mechanism, the system can achieve dynamic self-optimization, gradually improving scheduling efficiency and avoiding inefficient scheduling problems caused by human rules or insufficient experience.

[0101] In summary, this invention, by introducing graph theory optimization, microservice architecture, and intelligent self-learning algorithms, effectively overcomes the problems of low efficiency, low flexibility, poor scalability, and insufficient real-time scheduling capabilities in traditional dedicated transportation line scheduling methods. This system not only provides efficient, dynamic, and intelligent transportation path and task scheduling schemes, but also ensures efficient operation and flexible expansion within large-scale transportation networks, significantly improving the overall efficiency and responsiveness of dedicated transportation line handling. Therefore, the dedicated transportation handling optimization system of this invention is not only technically innovative but also significantly improves the practical application effects of existing systems. Attached Figure Description

[0102] The present invention will be further described with reference to the accompanying drawings, but the embodiments in the drawings do not constitute any limitation on the present invention. For those skilled in the art, other drawings can be obtained based on the following drawings without creative effort.

[0103] Figure 1 This is a flowchart of a transportation line handling optimization method based on intelligent scheduling according to the present invention.

[0104] Figure 2 This is a framework diagram of a transportation line handling optimization system based on intelligent scheduling according to the present invention. Detailed Implementation

[0105] Embodiments of the present invention are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0106] like Figure 1 As shown in the figure, an embodiment of the present invention provides a method for optimizing the handling of dedicated transportation lines based on intelligent scheduling. The method includes the following:

[0107] S1. Construct a dynamic timeliness graph model and collect data in real time.

[0108] Specifically, graph data is collected to represent the network structure of transportation tasks. Nodes in the graph represent key locations of the transportation task (such as the origin, destination, and transfer points), and edges represent the transportation paths connecting these locations. Each edge contains weight information, reflecting timeliness factors such as estimated transportation time and traffic conditions.

[0109] Among them, real-time data stream (D t This includes real-time data from IoT sensors, GPS devices, traffic monitoring systems, and more. This data primarily includes traffic flow, weather conditions, and equipment status. The input of real-time data streams is crucial for continuously updating the graphical model.

[0110] Furthermore, the dynamic timeliness graph model is constructed as follows:

[0111] Each node represents a key location, such as a start point, end point, or transit point, and contains location information and other key attributes of the task, such as priority and time window.

[0112] Node attributes can be represented as: v i =(x i ,y i ,P i ,T window U i )

[0113] Among them, v i Represents the location information of node i (x) i ,y i ), P i For task priority, T window For the task's time window (earliest start and latest end time), U i The availability of a node indicates whether the device is available or whether the path is unobstructed.

[0114] Each node represents a key location, such as a start point, end point, or transit point, and contains location information and other key attributes of the task, such as priority and time window.

[0115] Node attributes can be represented as: v i =(x i ,y i ,P i ,T window U i ), where v i Represents the location information of node i (x) i ,y i ), P i For task priority, T window For the task's time window (earliest start and latest end time), U i The availability of a node indicates whether the device is available or whether the path is unobstructed.

[0116] Furthermore, each edge represents a transportation path, and the weight of the edge reflects the timeliness of the path. In addition to distance and time, the weight also considers real-time data such as traffic flow and weather.

[0117] edge weight w ij The calculation formula is as follows:

[0118] w ij =α·D ij +β·T ij +γ·Cij +δ·W ij +λ·f ij

[0119] Among them, D ij T is the distance between nodes i and j. ij C represents the estimated time for the transportation route. ij W represents the impact of traffic flow on routes (e.g., traffic congestion). ij For the impact of weather on the route (such as delays caused by severe weather), f ij For additional path constraints, such as equipment availability and traffic restrictions on special road sections, α, β, γ, δ, and λ are adjustment parameters that adjust the influence of different factors on the weights.

[0120] Understandably, an additional constraint term f was added to the edge weight calculation. ij This allows the model to flexibly respond to special needs in transportation tasks, such as equipment availability or safety factors.

[0121] Furthermore, the weights of the time-sensitive graph are dynamically updated as real-time data streams are input. To ensure the real-time performance and accuracy of the graph, a sliding window mechanism is used to update the edge weights.

[0122] The formula for updating the sliding window is:

[0123] Updatedw ij (t)=w ij (t-Δt)+Δw ij (t)

[0124] Among them, w ij (t) represents the edge weight at time t, Δt is the time interval, and Δw ij 9t) represents the edge weight changes caused by the real-time data stream. The sliding window mechanism ensures that the system responds to environmental changes in real time within each time window, guaranteeing the timeliness of the data.

[0125] Furthermore, to ensure the accuracy of real-time data, Kalman filtering is used to optimize the sensor data. Kalman filtering helps reduce noise and improve data accuracy, especially in complex transportation scheduling scenarios.

[0126] The core formula of Kalman filtering is:

[0127]

[0128] in, z represents the estimate of the state (such as position, velocity, etc.) at time k. k Let K be the measured value at time k (data from the sensor). kFor Kalman gain, H k The measurement matrix represents the relationship between measurements and states. The Kalman filter algorithm not only processes basic sensor data but also integrates various external environmental data (such as traffic and weather), providing more accurate real-time data for timeliness maps.

[0129] Finally, the output dynamic timeliness diagram (G) t This graph includes the latest state of all nodes and edges, with edge weights reflecting real-time factors such as traffic, weather, and equipment status. This graph can be directly used for subsequent route planning and task scheduling. The key to updating the dynamic timeliness graph is adjusting the edge weights to ensure that each transportation task makes the optimal decision based on the latest real-time data.

[0130] Through these steps, the present invention not only realizes a timeliness graph model that can respond to changes in transportation tasks in real time, but also enables efficient and accurate route planning and task scheduling based on this model, solving the bottleneck problem of the inability to adjust in real time in traditional methods.

[0131] S2. Path planning and task allocation based on dynamic timeliness graph model.

[0132] Specifically, based on the dynamic timeliness graph G t Simultaneously, path planning and task allocation are performed to minimize the total transportation cost C (including time cost and resource allocation cost) while satisfying task time windows and resource constraints. Objective function:

[0133]

[0134] Among them, w ij For edge (v) i ,v j The weight of x represents the path cost. ij ∈{0,1} is the decision variable, representing the edge (v i ,v j Whether it is selected, φ r When allocating costs for resources, consider the empty load rate and allocation efficiency of each transportation resource.

[0135] Furthermore, the constraints are as follows:

[0136] Each task node must be accessed exactly once:

[0137]

[0138] Where V is the set of nodes in the graph.

[0139] All tasks must meet the time window constraint:

[0140]

[0141] Among them, T i T is the task start time. start,i and T end,i The earliest and latest times for the task.

[0142] The load on transport resources must not exceed their capacity:

[0143]

[0144] Where, d i For the task requirements, C r This represents the maximum load capacity of resource r.

[0145] Furthermore, node priority sorting:

[0146] Based on task priority P i and time window constraint T window,i Generate an initial access sequence. Prioritize accessing nodes with high priority and tight time windows.

[0147] Sorting strategy:

[0148]

[0149] Furthermore, path selection and allocation optimization:

[0150] Path planning is performed using a dynamic time-sensitive graph model. For each task node v... i Choose weight w ij Minimum edge (v) i ,v j ).

[0151] Define dynamic path selection rules:

[0152]

[0153] Among them, f ij For additional path constraints (such as changes in road conditions or equipment limitations), λ is a regularization coefficient used to adjust the importance of the additional constraints.

[0154] Furthermore, resource allocation rules:

[0155] Each transportation resource r is preferentially allocated to the task node v that best matches its current state. i Based on the distance D between the current location of the resource and the location of the task. r , No load rate η r and task requirements d i Computational resource suitability:

[0156]

[0157] Select φ r The minimum resources required to perform the task.

[0158] Furthermore, to address real-time data changes (such as traffic congestion, new tasks, etc.), an adjustment mechanism is introduced after the initial planning. w is recalculated using a sliding window. ij and x ij Dynamically update paths and task assignments.

[0159] Within each sliding window period, the updated path selection rule is as follows:

[0160]

[0161] Where, Δx ij This refers to path changes caused by real-time data streams.

[0162] Furthermore, the optimized path planning scheme and task allocation results are output, including the selection decision x for each path. ij and the task allocation strategy for each resource φ r The results are directly used as input for subsequent steps (scheduling execution and monitoring) to ensure the efficiency of resource scheduling and the optimality of path selection.

[0163] This step achieves joint optimization of route planning and task allocation, making full use of the weight information of the dynamic timeliness graph and the real-time status of transportation resources. By introducing priority ranking, dynamic route selection rules, and resource suitability optimization methods, it solves the problem of separating task allocation and route planning in traditional methods, providing optimal decision-making basis for subsequent task execution.

[0164] S3. Design a microservice architecture based on a distributed architecture, splitting functions into different modules. Different microservices are responsible for independent functions. Each microservice will dynamically adjust its execution strategy based on the output of the dynamic timeliness graph model and real-time monitoring data. If a delay or resource idleness occurs during task execution, the scheduling service of the microservice architecture needs to dynamically adjust the task allocation strategy according to the task deviation time.

[0165] Specifically, the core of this step is managing path planning and task scheduling execution within a microservice architecture. By splitting the system into different modules, we ensure high flexibility, scalability, and dynamic responsiveness. Different microservices are responsible for independent functional modules, including path planning, task allocation, execution monitoring, and adjustment. Each microservice dynamically adjusts its execution strategy based on the output of the previous step and real-time monitoring data.

[0166] Path planning service (S path ): Responsible for calculating and dynamically adjusting the path selection for tasks.

[0167] Task scheduling service (S task ): Responsible for scheduling tasks based on path planning results and real-time data.

[0168] Real-time monitoring service (S monitor ): Monitors the status changes during task execution in real time and provides feedback.

[0169] Adaptive scheduling adjustment service (S adaptive ): Automatically adjust resource allocation strategies based on real-time feedback and task status.

[0170] Microservices communicate with each other through message queues (such as Kafka) or asynchronous message passing mechanisms to ensure data flow and execution coordination between modules.

[0171] Furthermore, the scheduling decision is based on the path planning result x. ij Task allocation strategy φ r and real-time monitoring data D t The execution strategy is dynamically adjusted. The main factors considered in scheduling decisions include real-time traffic conditions, resource availability, and task execution deviations, to ensure that tasks can be completed efficiently and accurately.

[0172] Furthermore, the path weights are adjusted based on real-time traffic information, and the actual weights of each path are calculated in real time. The adjusted path planning formula is:

[0173]

[0174] Among them, w ij It is the initial path weight, traffic ij For path (v i ,v j Real-time traffic information (such as traffic delays, road congestion, etc.), weather ij For path (v i ,v j Weather effects (such as traffic slowdown due to rain or snow), timeofday ij For real-time time-dependent factors along the route (such as traffic changes during peak hours), λ1, λ2, and λ3 are weighting coefficients that adjust the impact of real-time information on route selection. This adjustment formula ensures the dynamic adaptability of the route, promptly reflecting changes in traffic, weather, and time-related factors, and avoiding delays in route selection.

[0175] Furthermore, if delays or resource idleness occur during task execution, the scheduling service needs to dynamically adjust the task allocation strategy based on the task skew time. To achieve this, the task skew time ΔT is first defined.i :

[0176] ΔT i =T actual,i -T planned,i

[0177] Among them, T actual,i T represents the actual execution time of task i. planned,i ΔT represents the planned execution time of task i. i This represents the execution skew time of task i. When the task skew is too large, the scheduling algorithm will automatically adjust the resource allocation of the task, selecting the nearest and more suitable resource r for task rescheduling. The adjustment strategy is as follows:

[0178]

[0179] Among them, dist r The distance between resource r and task i, avail r For the current availability (e.g., idle time, load status) of resource r, priority r Let β1 and β2 be the priority of resource r, reflecting its applicable priority requirements. β1 and β2 are adjustment weights that determine the impact of distance and resource priority on scheduling decisions. This adjustment formula ensures timely task execution and can automatically adjust resource allocation in cases of task delays or resource scarcity, guaranteeing successful task completion.

[0180] Furthermore, the core function of the real-time monitoring module is to detect changes in the status of tasks during execution, especially task deviations, resource status, and system load. If a deviation or anomaly is detected, the monitoring module will transmit the monitoring data to the scheduling system, triggering the scheduling service to make dynamic adjustments.

[0181] Furthermore, to effectively monitor the real-time performance of task execution, this invention introduces a real-time feedback mechanism. The real-time monitoring formula for task execution is:

[0182] ΔT i =T actual,i -T planned,i

[0183] If ΔT i >δ i If the set tolerance range is reached, the task will be rescheduled through the scheduling system.

[0184] Furthermore, for each resource's usage state, this invention defines the resource's workload L. r :

[0185]

[0186] Among them, T assigned,r T represents the allocated working time of resource r. total,r The total working time (maximum available time) of resource r. When the resource load exceeds the set threshold (L... r >τ r This will trigger resource reallocation to avoid overuse of a particular resource.

[0187] Furthermore, in addition to basic path adjustment and task rescheduling, the scheduling service also needs to have dynamic load balancing capabilities to ensure that resources can be allocated reasonably when the system load is high, and to avoid overloading of individual nodes.

[0188] In a microservice architecture, the system dynamically adjusts load balancing strategies (such as load monitoring based on request volume or service response time) to ensure that the response time of each service does not exceed a predetermined threshold τ. max .

[0189] Load balancing adjustment formula:

[0190]

[0191] Among them, response time s τ is the response time of service s. s As a threshold for response time, Status s This indicates the current state of the service (normal or standby). When service overload is detected, the system will automatically switch to a standby service to ensure that the entire scheduling process is uninterrupted.

[0192] The final output includes task execution status, path selection, resource usage, and real-time monitoring data. By analyzing these results, the system can further optimize the scheduling algorithm and improve path planning and task allocation strategies.

[0193] This step achieves real-time scheduling and optimization of path planning and task allocation through a microservice architecture and dynamic scheduling mechanism. By innovatively combining path planning, task scheduling, and real-time monitoring, it solves the complex problems of path selection and resource scheduling in dynamic environments. The use of microservice architecture ensures the system's efficiency, scalability, and stability, while the real-time monitoring and feedback mechanism enables the system to adaptively adjust the task execution process, ensuring the smooth completion of tasks in any complex environment.

[0194] S4. Design a self-learning mechanism to automatically adjust based on historical tasks and real-time feedback to optimize the handling tasks on the transportation line.

[0195] Specifically, the goal of the self-learning feedback mechanism is to dynamically adjust the path planning and task scheduling models based on real-time feedback data from the system to cope with complex real-world scenarios. This mechanism optimizes path selection, task allocation, and resource scheduling strategies by continuously accumulating actual performance data on task execution and scheduling.

[0196] The key to self-learning lies in utilizing feedback data to establish a scheduling decision-making mechanism capable of dynamically learning and adjusting. Its main process includes the following parts:

[0197] Error analysis and adjustment model:

[0198] Based on the deviation time ΔT for each task i and resource load changes L r The deviation ΔM of the scheduling model is calculated. i It also incorporates historical feedback data for learning. The update formula for the scheduling error model is as follows:

[0199]

[0200] Where, ΔT i L represents the execution time deviation of task i. r Let T be the current load of resource r, α, β, and γ be the influence coefficients of scheduling error on path selection and task allocation strategies, and T be the current load of resource r. actual,i and T planned,i These represent the actual execution time and the planned execution time of task i, respectively. The purpose of this formula is to combine the deviation in the execution of each task with the resource load, forming a feedback error model ΔM. i This will provide a basis for the next round of scheduling decisions.

[0201] Model optimization and tuning:

[0202] Using the error model ΔM i Adjust the existing path planning and task scheduling strategies. Based on the task execution performance, resource load, and skew time, adjust the path planning model and resource allocation strategy to optimize the scheduling results. The specific path planning optimization formula is as follows:

[0203]

[0204] Among them, w ij The original path weights are η1 and ΔM is the sensitivity factor for path adjustment. i The scheduling error is the output of the error model, and α is a hyperparameter controlling the degree of influence of the error. This formula combines the error model ΔM... i The path planning is dynamically adjusted to achieve path optimization based on feedback data.

[0205] Furthermore, under the self-learning feedback mechanism, the task scheduling and execution process will be dynamically adjusted based on real-time feedback. The core objective is to improve the accuracy and efficiency of task execution and ensure that the system can adaptively handle various complex situations. To this end, this invention proposes a dynamic task adjustment strategy and, in conjunction with the optimization results of path planning, reallocates resources.

[0206] Furthermore, during task execution, if the actual execution time of the task exceeds the expected deviation range ΔT... i If the task is not assigned, a rescheduling mechanism will be used to select the most suitable resources for task reallocation. During reallocation, task priority will be prioritized. i Adjustments will be made based on the urgency and importance of the task. The formula for task rescheduling is:

[0207]

[0208] Among them, dist r The distance between resource r and task i, avail r Priority is the availability (such as idle time, current load, etc.) of resource r. r Let γ represent the resource priority, and γ be the impact coefficient of feedback error on resource scheduling. During task execution, the system optimizes resource allocation to ensure that each task receives optimal resource support, thereby improving the success rate and efficiency of task completion.

[0209] Furthermore, the system continuously collects execution feedback data and updates the scheduling model through incremental learning. To achieve the system's adaptability, this invention introduces an incremental learning update mechanism to dynamically update the path planning and task scheduling models based on historical feedback data. Incremental learning update formula.

[0210] After each feedback step, the system updates the path planning model based on the new data. The update formula is as follows:

[0211] θ new =θ old +η2·ΔM i

[0212] Where, θ old The parameters before the update (such as weights for path planning, priorities for resource allocation, etc.), η² is the learning rate, and ΔM is the model parameters before the update. i This is the feedback error generated by the error model. The updated model θ new This information will be used in the next path planning and task scheduling decision. Through this incremental learning and update mechanism, the system can gradually optimize its scheduling strategy and form a more efficient path planning and task allocation scheme as it continuously accumulates feedback data.

[0213] Furthermore, in the output of this step, the system adjusts its path planning strategy, task allocation strategy, and resource scheduling strategy based on the results of the self-learning feedback mechanism. The final scheduling results include:

[0214] Optimized path planning decision,

[0215] New task allocation scheme,

[0216] Adjusted resource scheduling strategy

[0217] Feedback error data during the adaptive scheduling process.

[0218] The core of this step is to dynamically optimize path planning and task scheduling strategies through a self-learning feedback mechanism and incremental learning methods. By analyzing feedback and scheduling errors in real time, the system can continuously update the model and adaptively adjust path planning, task allocation, and resource scheduling. The self-learning feedback mechanism ensures that the system maintains high efficiency and accuracy when facing constantly changing task execution environments, thereby improving overall scheduling efficiency, optimizing resource utilization, and ensuring that tasks are completed on time and accurately.

[0219] like Figure 2 As shown in the figure, this embodiment of the invention also provides a transportation line handling optimization system based on intelligent scheduling, the system comprising:

[0220] The dynamic timeliness graph model unit 601 is used to construct a dynamic timeliness graph model and perform real-time data acquisition. The structure of the dynamic timeliness graph model is as follows: each node represents a key location, including a start point, end point, or transit point, containing location information and key attributes of the task; each edge represents a transportation path, and the edge weight reflects the timeliness of the path; the update mechanism of the dynamic timeliness graph model uses a sliding window mechanism to update the edge weights.

[0221] The route planning and task allocation unit 602 is used for route planning and task allocation based on a dynamic timeliness graph model; wherein, the objective function of the route planning and task allocation is to minimize the total transportation cost while satisfying the task time window and resource constraints, wherein the total transportation cost includes time cost and resource allocation cost, and the objective function of the total transportation cost is:

[0222]

[0223] Where C is the total transportation cost, w ij For edge (v) i ,v j The weight of x represents the path cost. ij ∈{0,1} is the decision variable, representing the edge (v i ,vj Is it selected? φ r Costs are allocated to resources, taking into account the empty load rate and allocation efficiency of each transportation resource;

[0224] The microservice architecture building unit 603 is used to design a microservice architecture based on a distributed architecture. It breaks down functionality into different modules, with each microservice responsible for an independent function. Each microservice dynamically adjusts its execution strategy based on the output of the dynamic timeliness graph model and real-time monitoring data. If a delay or resource idleness occurs during task execution, the microservice architecture's scheduling service needs to dynamically adjust the task allocation strategy according to the task's deviation time. The breakdown of functionality into different modules includes: path planning service, task scheduling service, real-time monitoring service, and adaptive scheduling adjustment service.

[0225] The path planning service is used to calculate and dynamically adjust the path selection for the task.

[0226] The task scheduling service is used to schedule tasks based on path planning results and real-time data.

[0227] The real-time monitoring service is used to monitor the status changes during task execution in real time and provide feedback.

[0228] The adaptive scheduling adjustment service is used to automatically adjust resource allocation strategies based on real-time feedback and task status.

[0229] The self-learning optimization unit 604 is used to design a self-learning mechanism to automatically adjust based on historical tasks and real-time feedback to optimize the handling tasks of the transportation line.

[0230] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0231] In the embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection of apparatuses or units may be electrical, mechanical, or other forms.

[0232] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0233] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

Claims

1. A method for optimizing the handling of transport lines based on intelligent scheduling, characterized in that, The method includes: S1. Construct a dynamic timeliness graph model and collect data in real time; wherein, the structure of the dynamic timeliness graph model is as follows: each node represents a key location, including the starting point, the ending point or the transfer point, and contains location information and key attributes of the task; each edge represents a transportation path, and the weight of the edge reflects the timeliness of the path; the update mechanism of the dynamic timeliness graph model adopts a sliding window mechanism to update the weight of the edge. S2. Route planning and task allocation based on a dynamic timeliness graph model; wherein, the objective function of the route planning and task allocation is to minimize the total transportation cost while satisfying the task time window and resource constraints, wherein the total transportation cost includes time cost and resource allocation cost, and the objective function of the total transportation cost is: ； in, For total transportation costs, For the edge The weight represents the path cost. Let be the decision variable, representing the edge. Is it selected? Costs are allocated to resources, taking into account the empty load rate and allocation efficiency of each transportation resource; S3. Design a microservice architecture based on a distributed architecture, dividing functions into different modules. Different microservices are responsible for independent functions. Each microservice will dynamically adjust its execution strategy based on the output of the dynamic timeliness graph model and real-time monitoring data. If a delay or resource idleness occurs during task execution, the scheduling service of the microservice architecture needs to dynamically adjust the task allocation strategy according to the task deviation time. The division of functions into different modules includes: path planning service, task scheduling service, real-time monitoring service, and adaptive scheduling adjustment service. The path planning service is used to calculate and dynamically adjust the path selection for the task. The task scheduling service is used to schedule tasks based on path planning results and real-time data. The real-time monitoring service is used to monitor the status changes during task execution in real time and provide feedback. The adaptive scheduling adjustment service is used to automatically adjust resource allocation strategies based on real-time feedback and task status. S4. Design a self-learning mechanism to automatically adjust based on historical tasks and real-time feedback to optimize the handling tasks of the transportation line. The edge weights of the dynamic time-sensitive graph model are calculated as follows: ； in, For nodes and The distance between them This represents the estimated time for the transportation route. The impact of traffic flow on routes, The impact of weather on the path, For additional path constraints, To adjust the parameters, the influence of different factors on the weights is adjusted separately; Among them, based on the distance between the current location of the resource and the location of the task. Empty load rate and task requirements The cost of resource allocation is calculated and expressed as: ； S3 specifically includes: The path weights are adjusted based on real-time traffic information, and the actual weights of each path are calculated in real time. The adjusted path planning formula is: ； in, It is the edge The weight, For path Real-time traffic information For path Due to weather conditions, For real-time time factors along the path, It is a weighting coefficient that adjusts the impact of real-time information on path selection; If a delay or resource idleness occurs during task execution, the scheduling service of the microservice architecture needs to dynamically adjust the task allocation strategy based on the task's deviation time, specifically including: First, define the task deviation time. : ； in, Indicates task The actual execution time Indicates task The planned execution time, Indicates task Execution deviation time; When the task deviation is too large, the scheduling algorithm will automatically adjust the resource allocation of the task, selecting resources that are closer and in a more suitable state. Perform task rescheduling and adjust the strategy as follows: ； in, For the updated strategy, For resources With the task The distance between them For resources Current availability, For resources The priority reflects the priority requirements to which it applies. It involves adjusting weights to determine the impact of distance and resource priority on scheduling decisions; S3 further includes a real-time monitoring service that detects state changes during task execution in real time. If a deviation or anomaly is detected, the real-time monitoring service will transmit the real-time monitoring data to the task scheduling service, triggering the task scheduling service to make dynamic adjustments, specifically as follows: ； in, For the task Execution deviation time, For the task The actual execution time For the task The planned execution time, if Then, task rescheduling will be triggered through the scheduling system; Monitoring the load on each resource is represented as follows: ； in, For resources The allocated work time, For resources The total working time, when the resource load exceeds the set threshold. This triggers resource reallocation to avoid overuse of a particular resource; Simultaneously, in the microservice architecture, dynamic adjustments are made through load balancing strategies to ensure that the response time of each service does not exceed a predetermined threshold. When service overload is detected, automatic switching to a backup service ensures that the entire scheduling process is uninterrupted. The load balancing strategy is expressed as follows: ； in, For service Response time The threshold for response time, The current state of the service.

2. The method for optimizing the handling of transport lines based on intelligent scheduling according to claim 1, characterized in that, The method of updating edge weights using a sliding window mechanism is expressed as follows: ； in, Indicates time Edge weights at time step For time intervals, This refers to the edge weight changes caused by the real-time data stream.

3. The method for optimizing the handling of transport lines based on intelligent scheduling according to claim 2, characterized in that, S1 further includes optimizing the sensor data using Kalman filtering, expressed as: ； in, Indicates at time The estimated value of the state, For a moment The measured value, For Kalman gain, This is the measurement matrix, which represents the relationship between measurements and states.

4. The method for optimizing the handling of transport lines based on intelligent scheduling according to claim 1, characterized in that, The total transportation cost is also subject to constraints, including: Each task node must be accessed exactly once: ； in Let be the set of nodes in the graph; All tasks must meet the time window constraint: ； in The task start time. and The earliest and latest times for the task; The load on transport resources must not exceed their capacity: ； in For the required quantity of the task, For resources Maximum load capacity.

5. The method for optimizing the handling of transport lines based on intelligent scheduling according to claim 4, characterized in that, S2 further includes joint optimization of path planning and task allocation, specifically: Based on the task priority and time window constraints, an initial access sequence is generated, in which the node with the highest priority and tightest time window is accessed first. Path planning is performed using a dynamic time-sensitive graph model for each task node. Select weights Minimum edge ; Each transportation resource Prioritize assigning tasks to the task nodes that best match their current state. ; An adjustment mechanism is introduced to recalculate using a sliding window. and Dynamically update paths and task assignments.

6. The method for optimizing the handling of transport lines based on intelligent scheduling according to claim 5, characterized in that, The sorting strategy for the access sequence is as follows: ； in, For the access sequence, For sorting functions, Let be the set of nodes in the graph. and The earliest and latest times for the task; Prioritize tasks; The decision variables for the dynamic path selection rules in the dynamic timeliness graph model for path planning are calculated as follows: ； in, For additional path constraints, This is the regularization coefficient, used to adjust the importance of additional constraints; The term will be each transportation resource Prioritize assigning tasks to the task nodes that best match their current state. Specifically: choose Perform the task with minimal resources; The recalculation via sliding window and Dynamically update paths and task assignments, specifically: Within each sliding window period, the updated path is calculated as follows: ； in, For the updated path, This is the initial path. This refers to path changes caused by real-time data streams.

7. The method for optimizing the handling of transport lines based on intelligent scheduling according to claim 1, characterized in that, S4 specifically includes: Based on the skew time and resource load changes for each task, the deviation of the scheduling model is calculated. This is then used to learn from historical feedback data, and the original path planning and task scheduling strategies are adjusted according to the deviation to optimize the scheduling results. This is expressed as: ； ； in, For the task Execution time deviation, For resources The current load, This represents the impact coefficient of scheduling error on path selection and task allocation strategies. and Tasks The actual execution time and the planned execution time The sensitivity factor for path adjustment. The scheduling error is the output of the error model. Hyperparameters used to control the degree of influence of errors; Design a dynamic task adjustment strategy, combining the optimization results of path planning, to reallocate resources, including: If the actual execution time of the task exceeds the expected deviation range Then, through the rescheduling mechanism, the most suitable resources are selected for task reallocation. During reallocation, task priority is determined. Adjustments will be made based on the urgency and importance of the task. The formula for task rescheduling is: ； in, For resources With the task The distance between them For resources Current availability, For resources The priority reflects the priority requirements to which it applies. The coefficient representing the impact of feedback error on resource scheduling; Collect user feedback data and update the scheduling error output by the error model through incremental learning, thereby dynamically updating path planning and task scheduling.

8. A system for implementing the intelligent scheduling-based transportation line handling optimization method as described in claim 1, characterized in that, The system includes: A dynamic timeliness graph model unit is used to construct a dynamic timeliness graph model and perform real-time data acquisition. The structure of the dynamic timeliness graph model is as follows: each node represents a key location, including a start point, end point, or transit point, containing location information and key attributes of the task; each edge represents a transportation path, and the edge weight reflects the timeliness of the path; the update mechanism of the dynamic timeliness graph model uses a sliding window mechanism to update the edge weights. A route planning and task allocation unit is used for route planning and task allocation based on a dynamic timeliness graph model. The objective function of the route planning and task allocation is to minimize the total transportation cost while satisfying task time windows and resource constraints. The total transportation cost includes time cost and resource allocation cost. The objective function for the total transportation cost is: ； in, For total transportation costs, For the edge The weight represents the path cost. Let be the decision variable, representing the edge. Is it selected? Costs are allocated to resources, taking into account the empty load rate and allocation efficiency of each transportation resource; The microservice architecture building unit is used to design a microservice architecture based on a distributed architecture. It breaks down functionality into different modules, with each microservice responsible for an independent function. Each microservice dynamically adjusts its execution strategy based on the output of the dynamic timeliness graph model and real-time monitoring data. If a delay or resource idleness occurs during task execution, the microservice architecture's scheduling service needs to dynamically adjust the task allocation strategy according to the task's deviation time. The breakdown of functionality into different modules includes: path planning service, task scheduling service, real-time monitoring service, and adaptive scheduling adjustment service. The path planning service is used to calculate and dynamically adjust the path selection for the task. The task scheduling service is used to schedule tasks based on path planning results and real-time data. The real-time monitoring service is used to monitor the status changes during task execution in real time and provide feedback. The adaptive scheduling adjustment service is used to automatically adjust resource allocation strategies based on real-time feedback and task status. The self-learning optimization unit is used to design a self-learning mechanism that automatically adjusts based on historical tasks and real-time feedback to optimize the handling tasks on the transportation line.

Images