Warehouse scheduling method and device and terminal equipment

Abstract

The invention provides a warehouse scheduling method, a warehouse scheduling device and terminal equipment, and is suitable for the technical field of data processing. According to the multiple pieces of storage scheduling node position information, the multiple pieces of storage task priority information, the multiple pieces of transportation equipment speed information, the multiple pieces of warehouse obstacle position information and the transportation equipment driving direction angle range information, multiple pieces of initial storage scheduling track information are generated; and on the basis of a target storage scheduling trajectory generation model, according to the multiple pieces of warehouse obstacle position information and the transportation equipment driving direction angle range information, optimizing the multiple pieces of initial storage scheduling trajectory information, and generating multiple pieces of target storage scheduling trajectory information. According to the method, the transport equipment is ensured to avoid obstacles and run in compliance in a complex storage space, the actual operation capacity of the equipment is matched through the speed information of the transport equipment to reduce energy consumption, and the problems of task response lag, frequent equipment conflicts and over-high energy consumption in traditional storage scheduling are effectively solved.

Description

Technical Field

[0001] This application belongs to the field of data processing technology, and in particular relates to warehouse scheduling methods, devices and terminal equipment. Background Technology

[0002] With the deepening of the concepts of intelligent manufacturing and Industry 4.0, warehouse scheduling, as a core link in the logistics chain, has shifted from traditional manual scheduling to an intelligent scheduling mode centered on automated guided vehicles (AGVs).

[0003] In existing technologies, a warehouse space model is constructed using an undirected logistics graph. First, the risk index of the work area is calculated using event tree analysis, and the available work nodes are selected by combining the node carrying attributes and task data. Then, cellular automata are used to simulate the road segment travel time, and the shortest path to the task location is solved by combining ant colony algorithm. The parking area location and transportation route are optimized by genetic algorithm. Finally, an optimization model is constructed with the goal of minimizing the number of AGVs and maximizing the utilization rate. Task time window constraints are incorporated to generate a scheduling scheme, which is then verified by a digital twin model.

[0004] However, existing technologies cannot prioritize responding to the scheduling needs of high-priority tasks, nor can they optimize the driving trajectory for individual device performance, which can easily lead to device steering conflicts or energy waste. Summary of the Invention

[0005] In view of this, embodiments of this application provide a warehouse scheduling method, apparatus, and terminal device, aiming to solve the problems in the prior art that make it difficult to prioritize the scheduling needs of high-priority tasks, cannot optimize the driving trajectory for individual equipment performance, and have high energy consumption in warehouse scheduling.

[0006] The first aspect of this application provides a warehouse scheduling method, including:

[0007] Obtain location information of multiple warehouse scheduling nodes, priority information of multiple warehouse tasks, speed information of multiple transportation equipment, and location information of multiple warehouse obstacles;

[0008] Based on the preset initial warehouse scheduling trajectory generation model, multiple initial warehouse scheduling trajectory information is generated according to the multiple warehouse scheduling node location information, multiple warehouse task priority information, multiple transportation equipment speed information, multiple warehouse obstacle location information, and preset transportation equipment driving direction angle range information.

[0009] Based on the preset target warehouse scheduling trajectory generation model, the multiple initial warehouse scheduling trajectory information is optimized according to the location information of the multiple warehouse obstacles and the preset range of the driving direction angle of the transportation equipment, so as to generate multiple target warehouse scheduling trajectory information.

[0010] A second aspect of this application provides a warehouse scheduling device, comprising:

[0011] The information acquisition module is used to acquire location information of multiple warehouse scheduling nodes, priority information of multiple warehouse tasks, speed information of multiple transportation equipment, and location information of multiple warehouse obstacles.

[0012] The initial warehouse scheduling trajectory information generation module is used to generate multiple initial warehouse scheduling trajectory information based on a preset initial warehouse scheduling trajectory generation model, according to the multiple warehouse scheduling node location information, multiple warehouse task priority information, multiple transportation equipment speed information, multiple warehouse obstacle location information, and preset transportation equipment driving direction angle range information.

[0013] The target warehouse scheduling trajectory information generation module is used to optimize the multiple initial warehouse scheduling trajectory information based on the preset target warehouse scheduling trajectory generation model, the multiple warehouse obstacle location information and the preset transportation equipment driving direction angle range information, and generate multiple target warehouse scheduling trajectory information.

[0014] A third aspect of this application provides a terminal device, the terminal device including a memory and a processor, the memory storing a computer program executable on the processor, and the processor executing the computer program to implement the steps of the warehouse scheduling method described in the first aspect above.

[0015] A fourth aspect of this application provides a computer-readable storage medium, comprising: storing a computer program, which, when executed by a processor, implements the steps of the warehouse scheduling method described in the first aspect above.

[0016] Compared with the prior art, the beneficial effects of this application are as follows: This application is used to ensure that transportation equipment avoids obstacles and drives in compliance with regulations in complex warehouse spaces, prioritizes the timeliness of emergency tasks, matches the actual operating capacity of the equipment with the speed information of the transportation equipment to reduce energy consumption, improves scheduling flexibility, realizes efficient collaboration of transportation equipment throughout the entire warehousing process, accurate fulfillment of tasks, and rational utilization of space resources, and effectively solves the problems of delayed task response, frequent equipment conflicts, and excessive energy consumption in traditional warehouse scheduling. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a schematic diagram illustrating the implementation process of the warehouse scheduling method provided in Embodiment 1 of this application;

[0019] Figure 2 This is a schematic diagram illustrating the implementation process of the warehouse scheduling method provided in Embodiment 2 of this application;

[0020] Figure 3 This is a schematic diagram illustrating the implementation process of the warehouse scheduling method provided in Embodiment 3 of this application;

[0021] Figure 4 This is a schematic diagram illustrating the implementation process of the warehouse scheduling method provided in Embodiment 4 of this application;

[0022] Figure 5 This is a schematic diagram illustrating the implementation process of the warehouse scheduling method provided in Embodiment 5 of this application;

[0023] Figure 6 This is a schematic diagram illustrating the implementation process of the warehouse scheduling method provided in Embodiment Six of this application;

[0024] Figure 7 This is a schematic diagram illustrating the implementation process of the warehouse scheduling method provided in Embodiment 7 of this application;

[0025] Figure 8 This is a schematic diagram of the structure of the warehouse scheduling device provided in the embodiments of this application;

[0026] Figure 9 This is a schematic diagram of the terminal device provided in the embodiments of this application. Detailed Implementation

[0027] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0028] To illustrate the technical solution described in this application, specific embodiments are provided below.

[0029] Figure 1 A flowchart illustrating the implementation of the warehouse scheduling method provided in Embodiment 1 of this application is shown, and is described in detail below:

[0030] Step S101: Obtain location information of multiple warehouse scheduling nodes, priority information of multiple warehouse tasks, speed information of multiple transportation equipment, and location information of multiple warehouse obstacles.

[0031] In this embodiment, the warehouse scheduling node location information can refer to the coordinate information of various key locations related to transportation equipment scheduling within the warehouse space. This includes the starting point location information, ending point location information, and intermediate location information that the transportation equipment needs to pass through during the process of connecting the starting point and the ending point. This information can be obtained by marking and extracting the coordinate data of these key locations on a pre-drawn digital spatial map of the warehouse, combined with the requirements of the warehouse operation process. Warehouse task priority information can refer to different levels of information classified according to the urgency and importance of warehouse operation tasks. For example, priority information for urgent outbound tasks that need to be completed within a short time, priority information for regular goods replenishment tasks, and priority information for goods inventory tasks that can be delayed. This information can be obtained by extracting preset urgency tags and task deadlines for each operation task from the warehouse management system, thereby determining and generating the corresponding task priority information. Transportation equipment speed information refers to the speed data of various transportation equipment (such as AGVs and forklifts) participating in warehouse scheduling under different operating states. This includes the travel speed information of the transportation equipment when it is empty, when it is fully loaded with goods, and when it travels in different types of warehouse aisles. The operating speed data can be collected in real time by the speed sensors on the transportation equipment itself, and can also be obtained by combining the technical parameter manual of the transportation equipment. Warehouse obstacle location information refers to the location coordinate information of various obstacles in the warehouse space that may affect the normal operation of transportation equipment. This includes the location information of static obstacles, such as warehouse shelves, fixed columns, and operating platforms, as well as the location information of dynamic obstacles, such as personnel working, temporarily stacked goods, and other transportation equipment in motion. The location information of static obstacles can be directly extracted from the warehouse digital map, while the location information of dynamic obstacles can be collected in real time by LiDAR, vision sensors, etc. on the transportation equipment and transmitted to the scheduling system to generate corresponding location information.

[0032] Step S102: Based on the preset initial warehouse scheduling trajectory generation model, multiple initial warehouse scheduling trajectory information is generated according to the multiple warehouse scheduling node location information, multiple warehouse task priority information, multiple transportation equipment speed information, multiple warehouse obstacle location information, and preset transportation equipment driving direction angle range information.

[0033] In this embodiment, the preset initial warehouse scheduling trajectory generation model can be manually preset, set based on a genetic algorithm, set based on an ant colony algorithm, or a reinforcement learning model. The preset range of the driving direction angle of the transportation equipment can be manually set or set based on the user manual of the transportation equipment. Multiple warehouse scheduling node location information can be categorized and organized, identifying the starting node, ending node, and intermediate nodes. Then, combined with multiple warehouse task priority information, nodes corresponding to different priority tasks are assigned differentiated weights, prioritizing warehouse scheduling nodes related to high-priority tasks into the trajectory candidate range. Next, referring to multiple transportation equipment speed information, the time cost of different transportation equipment traveling between different nodes is analyzed. For example, based on the speed difference of transportation equipment in empty and fully loaded states, the travel time between each candidate node is calculated. Simultaneously, combined with multiple warehouse obstacle location information, node connection paths that pass through obstacle areas are eliminated to ensure the safety of candidate paths. Finally, the preset range of the driving direction angle of the transportation equipment is used to... Information limits the angle range of transportation equipment when turning between adjacent nodes to avoid equipment damage or driving conflicts caused by excessive turning angles. Multiple feasible paths are initially selected from candidate paths that meet the constraints. The initial warehouse scheduling trajectory generation model can be generated by using the location information of multiple warehouse scheduling nodes, the priority information of multiple warehouse tasks, the speed information of multiple transportation equipment, the location information of multiple warehouse obstacles, and the preset range of transportation equipment driving direction angles as input information. Through the iterative optimization mechanism of the initial warehouse scheduling trajectory generation model, the cost of the initially selected feasible paths is evaluated, and the connection order of nodes in the path is gradually adjusted. Finally, multiple sets of initial warehouse scheduling trajectory information that meet multi-dimensional constraints and have better cost are generated.

[0034] Step S103: Based on the preset target warehouse scheduling trajectory generation model, the multiple initial warehouse scheduling trajectory information is optimized according to the multiple warehouse obstacle location information and the preset transportation equipment driving direction angle range information to generate multiple target warehouse scheduling trajectory information.

[0035] In this embodiment, the preset target warehouse scheduling trajectory generation model can be manually set, based on a genetic algorithm, or based on the RRT algorithm. The preset range of the transportation equipment's driving direction angle can be manually set or set according to the transportation equipment's user manual. Each initial warehouse scheduling trajectory information can be divided into several continuous initial planning sub-path information segments, and the starting point of each initial planning sub-path information segment is extracted as the initial planning path starting node information. Then, using these initial planning path starting node information segments as the center and the length of the corresponding initial planning sub-path information segments as the radius, multiple path planning search areas are delineated to ensure that subsequent optimization is only performed within a reasonable range around the initial trajectory. Subsequently, multiple warehouse obstacle location information is used as input information for the target warehouse scheduling trajectory generation model. The target warehouse scheduling trajectory generation model checks one by one whether there are obstacles in each path planning search area. If it is found that a certain initial planning sub-path information segment passes through an obstacle area, then on that road... Within the path planning search area, alternative path segments that can bypass obstacles are re-explored. Simultaneously, based on pre-defined information on the driving direction angle range of transport equipment, the turning angle of the transport equipment in the alternative path segments is limited to prevent the turning angle from exceeding the equipment's physical limitations. Then, a feasibility assessment is performed on each alternative path segment within the path planning search area, selecting the optimal alternative path segment that meets the requirements of no collision, compliant driving direction angle, and minimal path length increment. Finally, all optimal alternative path segments within the path planning search areas are sequentially connected according to the node order of the original initial warehouse scheduling trajectory information, replacing problematic path segments in the original trajectory. This completes the optimization processing of multiple initial warehouse scheduling trajectory information, generating multiple target warehouse scheduling trajectory information.

[0036] The warehouse scheduling method provided in this application is used to ensure that transportation equipment avoids obstacles and drives in compliance with regulations in complex warehouse spaces, prioritizes the timeliness of urgent tasks, reduces energy consumption by matching the actual operating capacity of the equipment with the speed information of the transportation equipment, improves scheduling flexibility, realizes efficient coordination of transportation equipment throughout the warehouse process, accurate fulfillment of tasks, and rational utilization of space resources, and effectively solves the problems of delayed task response, frequent equipment conflicts, and excessive energy consumption in traditional warehouse scheduling.

[0037] Figure 2 The flowchart illustrating the implementation of the warehouse scheduling method provided in Embodiment 2 of this application is shown. Its difference from Embodiment 1 described above lies in:

[0038] The location information of the multiple warehouse scheduling nodes includes the initial node information of the warehouse scheduling trajectory, the target node information of the warehouse scheduling trajectory, and the intermediate node information of multiple warehouse scheduling trajectories;

[0039] The multiple initial warehouse scheduling trajectory information includes first initial warehouse scheduling trajectory information and second initial warehouse scheduling trajectory information;

[0040] Step S102 specifically includes:

[0041] Step S201: Based on the preset initial warehouse scheduling trajectory generation model, according to the priority information of multiple warehouse tasks, the speed information of multiple transportation equipment, the location information of multiple warehouse obstacles, and the preset range of transportation equipment driving direction angles, the intermediate node information of the multiple warehouse scheduling trajectories is selected and processed to obtain multiple warehouse scheduling node information.

[0042] In this embodiment, the preset initial warehouse scheduling trajectory generation model can be manually preset, set based on a genetic algorithm, set based on an ant colony algorithm, or a reinforcement learning model. The preset range of the transportation equipment's driving direction angle can be manually preset or set based on the transportation equipment's user manual. First, the information of multiple intermediate nodes of the warehouse scheduling trajectory is matched with the priority information of multiple warehouse tasks. The intermediate nodes of the warehouse scheduling trajectory associated with high-priority tasks are given higher selection weights. Then, combined with the speed information of multiple transportation equipment, the efficiency of the transportation equipment traveling between different intermediate nodes of the warehouse scheduling trajectory is analyzed. Nodes that allow the transportation equipment to travel at a better speed are prioritized and retained. Then, referring to the location information of multiple warehouse obstacles, intermediate nodes of the warehouse scheduling trajectory that are located in obstacle areas or will cause the transportation equipment to travel too far are eliminated. Finally, based on the preset range of the transportation equipment's driving direction angle, nodes that will cause the transportation equipment's turning angle to exceed the limit are excluded, thereby completing the selection process of multiple intermediate node information of the warehouse scheduling trajectory and obtaining multiple warehouse scheduling node information.

[0043] Step S202: Calculate the cost information of the first warehouse scheduling node based on the information of multiple warehouse scheduling nodes, the location information of multiple warehouse obstacles, the speed information of multiple transportation equipment, the preset range of transportation equipment driving direction angles, and the preset calibration speed information of transportation equipment.

[0044] In this embodiment, the preset calibration speed information of the transportation equipment can be preset manually, and the preset range of the transportation equipment's driving direction angle can also be preset manually. First, based on the information of each warehouse scheduling node, and combining the speed information of multiple transportation equipment with the preset calibration speed information, the speed deviation cost of the transportation equipment traveling between nodes can be calculated. The closer the speed is to the calibration speed, the lower the cost. Then, referring to the location information of multiple warehouse obstacles, the obstacle avoidance cost is increased for situations where there are obstacles around the node; the closer the obstacle and the longer the detour distance, the higher the cost. Next, based on the preset range of the transportation equipment's driving direction angle, the steering adjustment cost is increased for situations where the steering angle between nodes exceeds the limit; the larger the steering angle deviation, the higher the cost. Finally, by combining the speed deviation cost, obstacle avoidance cost, and steering adjustment cost, the cost information of the first warehouse scheduling node corresponding to each warehouse scheduling node is obtained through cumulative calculation, thus completing the calculation of the cost information of the first warehouse scheduling node.

[0045] Step S203: Generate first initial warehouse scheduling trajectory information based on the initial node information of the warehouse scheduling trajectory, the target node information of the warehouse scheduling trajectory, the cost information of the first warehouse scheduling node, and the information of multiple warehouse scheduling nodes.

[0046] In this embodiment, the initial node information of the warehouse scheduling trajectory can be used as the starting point of the trajectory, the target node information of the warehouse scheduling trajectory can be used as the ending point of the trajectory, and multiple warehouse scheduling node information can be used as intermediate candidate nodes connecting the starting point and the ending point. Then, based on the cost information of the first warehouse scheduling node, the warehouse scheduling node information with lower cost is selected first and included in the trajectory construction scope. Then, the nodes are connected in the order of "starting point → low-cost intermediate node → ending point". At the same time, it is checked whether the connection between nodes conforms to the basic driving logic of the transportation equipment to avoid invalid path segments. Then, the integrity of the initially constructed path is verified to ensure that a continuous trajectory can be formed from the starting point to the ending point through the selected nodes. Finally, the first initial warehouse scheduling trajectory information that meets the requirements of cost optimization and path continuity is generated, thereby completing the generation of the first initial warehouse scheduling trajectory information.

[0047] Step S204: Generate warehouse scheduling trajectory conflict information based on the first initial warehouse scheduling trajectory information.

[0048] In this embodiment, all nodes and path segments between nodes included in the initial warehouse scheduling trajectory information can be discretized first to clarify the spatial range and corresponding travel time of each path segment. Then, these discretized path information are compared with other planned or ongoing trajectory information within the warehouse to find whether there are spatially overlapping and temporally conflicting path segments. Subsequently, the specific location, conflict time period, and node information involved in these conflicting path segments are marked. Then, the marked conflict information is classified and organized to distinguish between node conflicts and path segment conflicts, forming a structured record. Finally, warehouse scheduling trajectory conflict information that can clearly reflect the conflict location, time period, and type is generated, thereby completing the generation of warehouse scheduling trajectory conflict information.

[0049] Step S205: Based on the preset initial warehouse scheduling trajectory generation model, calculate the cost information of the second warehouse scheduling node according to the information of multiple warehouse scheduling nodes, multiple warehouse task priority information, multiple transportation equipment speed information, multiple warehouse obstacle location information, warehouse scheduling trajectory conflict information, preset transportation equipment driving direction angle range information, and preset transportation equipment calibration speed information.

[0050] In this embodiment, the preset initial warehouse scheduling trajectory generation model can be preset manually, the preset range of the transportation equipment's driving direction angle can be preset manually, and the preset calibration speed information of the transportation equipment can be preset manually. The calculation logic for speed deviation cost, obstacle avoidance cost, and steering adjustment cost used when calculating the cost information of the first warehouse scheduling node can be followed to obtain basic cost data. Then, warehouse scheduling trajectory conflict information is incorporated into the cost calculation system, and conflict penalty costs are added to warehouse scheduling nodes involving conflict path segments; the more severe the conflict, the higher the penalty cost. Next, combining multiple warehouse task priority information, the weight of the basic cost of nodes associated with high-priority tasks is appropriately reduced to ensure that task priority still affects the cost assessment result. Finally, the basic cost, conflict penalty cost, and the cost after priority weight adjustment are combined, and a weighted calculation is performed to obtain the cost information of the second warehouse scheduling node corresponding to each warehouse scheduling node, thereby completing the calculation of the cost information of the second warehouse scheduling node.

[0051] Step S206: Generate second initial warehouse scheduling trajectory information based on the initial node information of the warehouse scheduling trajectory, the target node information of the warehouse scheduling trajectory, the cost information of the second warehouse scheduling node, and the information of multiple warehouse scheduling nodes.

[0052] In this embodiment, the initial node information of the warehouse scheduling trajectory can be used as the starting point and the target node information of the warehouse scheduling trajectory as the ending point. Multiple warehouse scheduling node information can be used as intermediate candidate nodes. Then, based on the cost information of the second warehouse scheduling node, warehouse scheduling node information with no conflict or low conflict penalty cost and good overall cost is selected first, avoiding the inclusion of nodes involving serious conflicts in the trajectory. Then, the nodes are connected in the order of "starting point → low conflict and low cost intermediate node → ending point". At the same time, the rationality of the connection between nodes and the continuity of the path are verified again. Then, the conflict is checked again on the initially formed trajectory to ensure that there are no unprocessed conflict path segments in the trajectory. Finally, the second initial warehouse scheduling trajectory information that avoids the main conflict and optimizes the cost is generated, thus completing the generation of the second initial warehouse scheduling trajectory information.

[0053] Step S207: Based on the preset initial warehouse scheduling trajectory generation model, the first initial warehouse scheduling trajectory information and the second initial warehouse scheduling trajectory information are iteratively optimized according to the cost information of the first warehouse scheduling node and the cost information of the second warehouse scheduling node to generate the first initial warehouse scheduling trajectory information and the second initial warehouse scheduling trajectory information.

[0054] In this embodiment, the preset initial warehouse scheduling trajectory generation model can be manually preset. First, the cost information of the first and second warehouse scheduling nodes can be compared to clarify the differences in cost composition between the two initial trajectories. Nodes or path segments with higher costs can be identified. Then, for the first initial warehouse scheduling trajectory information, attempts can be made to replace the high-cost nodes with lower-cost warehouse scheduling nodes that meet the constraints, while maintaining the overall trajectory continuity. Next, for the second initial warehouse scheduling trajectory information, the connection order of points can be fine-tuned to further reduce the overall cost, provided there are no conflicts. Then, the costs of the two adjusted trajectories are recalculated to check if the cost optimization objective is met. If not, the replacement and fine-tuning process is repeated. After multiple iterations, the first and second initial warehouse scheduling trajectory information with better costs and fewer conflicts are finally generated.

[0055] The warehouse scheduling method provided in this application improves the cost rationality and conflict avoidance capability of the initial trajectory. It ensures the priority scheduling of high-priority tasks and reduces transportation equipment driving conflicts through accurate cost calculation and conflict handling. At the same time, it adapts to the speed characteristics and steering constraints of transportation equipment, effectively reducing equipment energy consumption and wear. Thus, it realizes the refinement and efficiency of warehouse scheduling trajectory planning, so as to better meet the actual needs of multi-task and multi-equipment collaborative scheduling in complex warehouse environments.

[0056] Figure 3The flowchart illustrating the implementation of the warehouse scheduling method provided in Embodiment 3 of this application is shown. The difference between this method and Embodiment 2 is that step S207 specifically includes:

[0057] Step S301: Obtain key characterization information of multiple warehouse scheduling nodes.

[0058] In this embodiment, the key representation information of warehouse scheduling node information can be the key representation information of warehouse scheduling node information. First, warehouse scheduling node information associated with high-priority tasks can be assigned higher key representation scores, while nodes associated with medium- and low-priority tasks can be assigned relatively lower scores. Then, combined with the functional attributes of the warehouse scheduling node information, the key representation scores of core functional nodes, such as sorting area entrance nodes and high-frequency inbound / outbound nodes, can be further increased. Next, referring to the speed information of multiple transportation equipment, the scores of nodes that enable efficient transportation equipment passage, such as those approaching their rated speed, can be appropriately increased. Finally, considering the three factors of task priority, functional attributes, and passage efficiency, a weighted evaluation is used to generate key representation information corresponding to each warehouse scheduling node information, thereby achieving the acquisition of key representation information for multiple warehouse scheduling node information.

[0059] Step S302: Extract the warehouse scheduling node information corresponding to the first initial warehouse scheduling trajectory information and the warehouse scheduling node information corresponding to the second initial warehouse scheduling trajectory information to obtain multiple warehouse scheduling node information to be selected.

[0060] In this embodiment, the first initial warehouse scheduling trajectory information can be parsed first, and all warehouse scheduling node information contained in the trajectory can be extracted one by one, including the trajectory start point, end point and all intermediate connecting nodes. Then, the same parsing and extraction operation can be performed on the second initial warehouse scheduling trajectory information to obtain all the warehouse scheduling node information contained therein. Then, the warehouse scheduling node information extracted from the two initial trajectories can be summarized, and duplicate node information can be removed. Then, the summarized node information can be classified and sorted, and marked according to node function or task type. Finally, multiple warehouse scheduling node information to be selected can be obtained, thereby completing the extraction of multiple warehouse scheduling node information to be selected.

[0061] Step S303: Based on the cost information of the first warehouse scheduling node and the cost information of the second warehouse scheduling node, select the multiple warehouse scheduling node information to be selected, and obtain multiple selected warehouse scheduling node information.

[0062] In this embodiment, each candidate warehouse scheduling node information can be associated with the corresponding first warehouse scheduling node cost information and second warehouse scheduling node cost information to clarify the cost data of each node in different initial trajectories. Then, the two types of cost information of each candidate node are compared, and the node with the lower cost is selected as the candidate. If a node is at a low level in both types of cost information, it is directly included in the preliminary selection range. Then, for candidate nodes with similar cost levels, nodes in the high-priority task trajectory are selected first, based on the task priority of their respective trajectories. Then, the nodes selected in the preliminary selection are verified a second time to check whether the nodes meet the preset constraints of the transportation equipment driving direction angle range information and the location information of multiple warehouse obstacles. Nodes that do not meet the constraints are eliminated, and finally, multiple selected warehouse scheduling node information is obtained, thereby completing the selection process of multiple candidate warehouse scheduling node information.

[0063] Step S304: Based on the important characterization information of the multiple warehouse scheduling node information and the preset important characterization enhancement rules, update the important characterization information of the multiple selected warehouse scheduling node information to obtain multiple updated important characterization information; the updated important characterization information corresponds one-to-one with the selected warehouse scheduling node information.

[0064] In this embodiment, the preset important representation enhancement rules can be manually preset. These rules can involve increasing the initial important representation information of the selected warehouse scheduling nodes by a fixed percentage, or dynamically adjusting the enhancement rate based on the node's cost advantage. First, it can be determined which enhancement method is suitable for each selected node. If the node's cost is significantly lower than other nodes to be selected, its important representation information can be enhanced by a higher percentage. If the node's cost is only slightly lower than the average level, it can be enhanced by a basic percentage. Then, the enhancement value of the important representation information for each selected node is calculated according to the determined enhancement method. The initial important representation information is added to the enhancement value to obtain the updated important representation information. Finally, a one-to-one correspondence is established between the selected warehouse scheduling node information and the updated important representation information, ensuring that each node has a uniquely matched updated information, thereby completing the update processing of the important representation information of multiple selected warehouse scheduling nodes.

[0065] Step S305: Based on the preset initial warehouse scheduling trajectory generation model, the first initial warehouse scheduling trajectory information and the second initial warehouse scheduling trajectory information are iteratively optimized according to the cost information of the first warehouse scheduling node, the cost information of the second warehouse scheduling node, the important characterization information of multiple warehouse scheduling nodes, and multiple updated important characterization information, to generate the first initial warehouse scheduling trajectory information and the second initial warehouse scheduling trajectory information.

[0066] In this embodiment, the preset initial warehouse scheduling trajectory generation model can be preset by humans. The cost information of the first and second warehouse scheduling nodes can be used as the basic constraints for iterative optimization. At the same time, the important representation information of multiple warehouse scheduling nodes and multiple updated important representation information can be used as the optimization guide. It is clear that nodes with higher important representation information should have higher priority in the trajectory. Then, for the first initial warehouse scheduling trajectory information, the warehouse scheduling node information is checked. If there are nodes with low important representation information and high cost, try to replace them with nodes with high important representation information and low cost from the selected warehouse scheduling node information, while maintaining the continuity of the trajectory and the compliance of constraints. Then, the same optimization operation is performed on the second initial warehouse scheduling trajectory information, focusing on replacing nodes with potential conflicts or cost disadvantages. Then, the cost and important representation information matching degree of the two replaced trajectories are recalculated to check whether the optimization goal of "cost reduction and important node coverage improvement" is met. If not, the above replacement and verification process is repeated. After multiple rounds of iteration, the first and second initial warehouse scheduling trajectory information with better cost and more comprehensive important node coverage are finally generated.

[0067] The warehouse scheduling method provided in this application strengthens the guiding role of high-value nodes in trajectory planning. It not only continues the core objectives of cost optimization and conflict avoidance, but also ensures that the trajectory can prioritize the coverage of nodes that are critical to warehouse operations through the updating and application of important representation information, thereby improving the fit between the trajectory and the core needs of warehousing. At the same time, relying on multiple rounds of iterative optimization, the node selection and trajectory structure are continuously adjusted so that the generated first initial warehouse scheduling trajectory information and second initial warehouse scheduling trajectory information achieve a better balance in terms of cost, conflict, and coverage of important nodes. This makes it more adaptable to the needs of multi-task collaboration and efficient resource utilization in complex warehouse environments.

[0068] Figure 4 The flowchart illustrating the implementation of the warehouse scheduling method provided in Embodiment 4 of this application is shown. The difference between this method and Embodiment 1 is that step S103 specifically includes:

[0069] Step S401: According to the preset warehouse scheduling trajectory separation spacing information, the multiple initial warehouse scheduling trajectory information is segmented to obtain multiple initial planned warehouse scheduling trajectory starting node information and multiple initial planned warehouse scheduling sub-trajectory information.

[0070] In this embodiment, the preset warehouse scheduling trajectory separation spacing information can be set manually. It can be a fixed spacing set based on the length of the warehouse channel, the speed of the transport equipment and the requirements of the operation efficiency, or it can be a spacing that is dynamically adjusted according to the total length of the initial warehouse scheduling trajectory information. First, the overall length of each initial warehouse scheduling trajectory can be calculated to determine the total path distance from the starting point to the end point. Then, according to the preset warehouse scheduling trajectory separation interval information, starting from the starting point of the initial warehouse scheduling trajectory information, the cutting points are determined sequentially. For example, if the separation interval is a fixed value, a cutting point is marked at each fixed interval. If the interval is dynamic, the separation interval is adjusted according to the channel characteristics of different segments of the trajectory. Then, the initial warehouse scheduling trajectory information is broken from the cutting points to form multiple continuous trajectory segments. Each trajectory segment is the initial planned warehouse scheduling sub-trajectory information. At the same time, the starting position of each initial planned warehouse scheduling sub-trajectory information is extracted as the starting node information of the initial planned warehouse scheduling trajectory. Then, the multiple initial planned warehouse scheduling trajectory starting node information and multiple initial planned warehouse scheduling sub-trajectory information obtained by segmentation are classified and marked to ensure that each starting node information is associated with the corresponding sub-trajectory information, thereby completing the segmentation processing of multiple initial warehouse scheduling trajectory information.

[0071] Step S402: Using the starting node information of the multiple initial planned warehouse scheduling trajectories as the center and the information of the multiple initial planned warehouse scheduling sub-trajectories as the radius, multiple warehouse scheduling range areas are generated.

[0072] In this embodiment, the specific coordinate data corresponding to the starting node information of each initial planned warehouse scheduling trajectory can be obtained first, and this coordinate data can be determined as the center position of the generated warehouse scheduling range area. Then, the actual length data of each initial planned warehouse scheduling sub-trajectory information can be extracted, and this length data can be used as the radius of the generated warehouse scheduling range area to ensure that the radius length is completely matched with the length of the sub-trajectory information. Then, with the starting node information of each initial planned warehouse scheduling trajectory as the center and the length of the corresponding initial planned warehouse scheduling sub-trajectory information as the radius, a circular area is drawn on the warehouse digital map. Each circular area is a warehouse scheduling range area. Then, the boundaries of the generated multiple warehouse scheduling range areas are marked to clarify the coverage of each area and the corresponding initial planned warehouse scheduling sub-trajectory information, so as to avoid confusion between different areas, thereby completing the generation of multiple warehouse scheduling range areas.

[0073] Step S403: Based on the preset target warehouse scheduling trajectory generation model, generate multiple target warehouse scheduling trajectory information according to the multiple warehouse scheduling range areas, multiple warehouse obstacle location information and preset transportation equipment driving direction angle range information.

[0074] In this embodiment, the preset target warehouse scheduling trajectory generation model can be manually preset, set based on a genetic algorithm, or set based on the RRT algorithm. The preset transportation equipment driving direction angle range information can be manually preset or set according to the transportation equipment's user manual. Multiple warehouse scheduling range areas, multiple warehouse obstacle location information, and the preset transportation equipment driving direction angle range information can be used as input information for the preset target warehouse scheduling trajectory generation model. Then, the target warehouse scheduling trajectory generation model analyzes each warehouse scheduling range area one by one, checking whether there are obstacles corresponding to the multiple warehouse obstacle location information within the area. If an obstacle is found in a certain warehouse scheduling range area, alternative warehouse scheduling sub-trajectory information that can bypass the obstacle is re-explored within that area. Simultaneously, combined with the preset transportation equipment driving direction angle range information, the alternative warehouse scheduling sub-trajectory information is restricted. The information includes the steering angle of the transportation equipment, ensuring that the steering angle complies with the physical limitations of the equipment. Then, a feasibility assessment is performed on the alternative warehouse scheduling sub-trajectory information within each warehouse scheduling range area. The optimal alternative warehouse scheduling sub-trajectory information that meets the requirements of no collision, compliant driving direction angle, and minimum path length increment is selected. Then, the optimal alternative warehouse scheduling sub-trajectory information within all warehouse scheduling range areas is connected sequentially according to the node order of the original initial warehouse scheduling trajectory information, replacing the problematic sub-trajectory segments in the original trajectory, and finally generating multiple target warehouse scheduling trajectory information, thus completing the generation of multiple target warehouse scheduling trajectory information.

[0075] The warehouse scheduling method provided in this application embodiment achieves precise control over the trajectory optimization range, avoiding the trajectory from deviating from the global target during the optimization process. At the same time, it fully combines the location information of obstacles in multiple warehouses with the preset range of driving direction angles of transportation equipment during the optimization process, ensuring that the generated target trajectory can both avoid obstacles and comply with the driving constraints of the equipment, effectively improving the safety and compliance of the trajectory, thereby enhancing the accuracy and efficiency of warehouse scheduling trajectory planning, and better adapting to the needs of collaborative operation of multiple transportation equipment in complex warehouse spaces.

[0076] Figure 5 The flowchart illustrating the implementation of the warehouse scheduling method provided in Embodiment 5 of this application is shown. The difference between this method and Embodiment 1 is that, after step S103, the method further includes:

[0077] Step S501: Obtain the location information of newly added obstacles in multiple warehouses.

[0078] In this embodiment, the newly added obstacle location information in the warehouse can refer to the location coordinate information of various obstacles that may affect the normal operation of transportation equipment after multiple target warehouse scheduling trajectory information are generated. This includes newly added static obstacle location information, such as temporarily added shelves and newly placed operating tables, as well as newly added dynamic obstacle location information, such as personnel temporarily entering the work area, newly scheduled transportation equipment to the warehouse space, and temporarily stacked goods. Fixed monitoring devices (such as panoramic cameras and LiDAR) deployed within the warehouse space can scan the warehouse environment in real time to capture newly added obstacles. Then, mobile sensors (such as vehicle-mounted vision sensors and millimeter-wave radar) on the transport equipment itself can perform a secondary scan of the surrounding area along the travel path to supplement the information on newly added obstacles in areas not covered by the fixed devices. The data of newly added obstacles collected by the fixed monitoring devices and the mobile sensors of the transport equipment are then transmitted to the warehouse scheduling system. The scheduling system performs coordinate calibration and validity verification on this data, eliminates misidentified interference data, and then classifies and organizes the calibrated data on the location of newly added obstacles, clarifying the type, specific coordinates, and estimated duration of each newly added obstacle. Finally, it generates location information on newly added obstacles for multiple warehouses, thereby enabling the acquisition of location information on newly added obstacles for multiple warehouses.

[0079] Step S502: Based on the preset target warehouse scheduling trajectory optimization model, the target warehouse scheduling trajectory information is optimized according to the location information of newly added obstacles in the multiple warehouses to obtain the target warehouse scheduling trajectory optimization information.

[0080] In this embodiment, the preset target warehouse scheduling trajectory optimization model can be manually preset, set based on a genetic algorithm, set based on an RRT algorithm, or set based on a reinforcement learning model related to dynamic path planning. The preset range of the transportation equipment's driving direction angle can be manually preset or set according to the transportation equipment's user manual. Multiple target warehouse scheduling trajectory information can be overlaid and analyzed with multiple new obstacle location information in warehouses. Each target warehouse scheduling trajectory information is checked one by one to see if there is spatial overlap with the new obstacle location, clarifying the target warehouse scheduling trajectory information affected by the new obstacle and the specific affected path segments. Then, for the affected target warehouse scheduling trajectory information, the starting point of the affected path segment is used as the optimization starting point, and the ending point of the corresponding path segment of the original trajectory is used as the optimization ending point to define a local optimization range, ensuring that the optimization only targets the affected area and avoids excessive adjustments to the overall trajectory structure. Then, the new obstacle location information of multiple warehouses, the starting and ending point information of the affected path segments, and the preset range of the transportation equipment's driving direction angle information are used as input to import the preset target warehouse scheduling trajectory optimization model. The model re-explores alternative path segments that can bypass newly added obstacles within the local optimization range, while limiting the turning angle of the transportation equipment in the alternative path segments to ensure that it meets the preset requirements for the driving direction angle range of the transportation equipment. Then, the feasibility of multiple alternative path segments generated by the model is evaluated, and the optimal alternative path segment with no collision, minimal path length increment, and satisfaction of the driving constraints of the transportation equipment is selected. The optimal alternative path segment replaces the affected path segments in the original target warehouse scheduling trajectory information, generating preliminary optimized trajectory information. Then, the overall coherence of the preliminary optimized trajectory information is checked to ensure that the optimized trajectory can be continuously traveled from the start point to the end point. Finally, the optimized trajectory information of multiple target warehouses is obtained, thus completing the optimization processing of multiple target warehouse scheduling trajectory information.

[0081] The warehouse scheduling method provided in this application captures dynamic changes in the warehouse environment in a timely manner, avoiding conflicts or trajectory failures of transportation equipment caused by new obstacles. It ensures the accuracy of trajectory adjustment, reduces interference with the overall warehouse scheduling process, improves the dynamic adaptability and safety of warehouse scheduling trajectories, and ensures that transportation equipment can still operate efficiently and compliantly in complex and dynamically changing warehouse spaces. It effectively solves the problem of lagging response to dynamic environmental changes in traditional warehouse scheduling and is more in line with the needs of multi-task, multi-equipment collaboration and dynamic environmental changes in actual warehouse scenarios.

[0082] Figure 6 The flowchart illustrating the implementation of the warehouse scheduling method provided in Embodiment Six of this application is shown. The difference between this method and Embodiment One described above is that, after step S103, the method further includes:

[0083] Step S601: Obtain priority information for multiple updated warehouse tasks.

[0084] In this embodiment, the updated warehousing task priority information can refer to the warehousing task level information that is redefined after multiple target warehousing scheduling trajectory information are generated, due to changes in warehousing operation requirements, such as the addition of emergency orders, the cancellation of existing tasks, and the adjustment of task deadlines. This includes information on tasks that were originally high priority being downgraded to medium or low priority, tasks that were originally medium or low priority being upgraded to high priority, and priority information corresponding to newly added tasks, such as priority information for temporarily inserted emergency allocation tasks and priority adjustment information for delayed inventory count tasks. First, the warehouse management system can monitor task status changes in real time. When the system receives a task adjustment instruction, such as when an operator manually modifies the task urgency or when the system automatically triggers a priority change based on order timeliness, the system immediately extracts the key data of the adjusted task (including task number, new urgency label, adjusted deadline, and associated warehouse scheduling node information). Then, the system verifies the validity of this data to confirm the legality and completeness of the task adjustment instruction, and removes invalid or duplicate adjustment data. Next, the verified task adjustment data is compared with the original warehouse task priority information to clarify the change type (upgrade, downgrade, addition) and specific change range of each task priority. Then, the changed task priorities are classified and organized in a unified format, each task is assigned a new priority identifier, and associated with its corresponding warehouse scheduling node information, thereby enabling the acquisition of multiple updated warehouse task priority information.

[0085] Step S602: Based on the preset target warehouse scheduling trajectory optimization model, the target warehouse scheduling trajectory information is optimized according to the updated warehouse task priority information to obtain the target warehouse scheduling trajectory optimization information.

[0086] In this embodiment, the preset target warehouse scheduling trajectory optimization model can be preset manually, set based on a genetic algorithm, set based on an RRT algorithm, or set based on a reinforcement learning model; the preset range of the driving direction angle of the transportation equipment can be preset manually or set according to the user manual of the transportation equipment. First, we can perform correlation analysis between multiple updated warehouse task priority information and multiple target warehouse scheduling trajectory information. We can then check whether the task priority corresponding to each target warehouse scheduling trajectory has changed, identifying the target warehouse scheduling trajectories affected by priority updates and their associated warehouse scheduling nodes. Then, for the affected target warehouse scheduling trajectories, we can redefine the trajectory optimization objectives: for tasks with upgraded priority, prioritize the timeliness of the trajectory and include warehouse scheduling nodes associated with high-priority tasks within the priority passage range; for tasks with downgraded priority, adjust the trajectory appropriately to avoid high-priority task trajectories and reduce resource conflicts; for trajectories corresponding to canceled tasks, replan new task trajectories or adjust them to standby status. Finally, we can integrate multiple updated warehouse task priority information, the original node information of affected trajectories, the location information of multiple warehouse obstacles, and the preset transportation equipment routes. The driving direction angle range information is used as input to import a preset target warehouse scheduling trajectory optimization model. The model recalculates the node cost based on the new priority weights (reducing the cost of nodes associated with high-priority tasks and appropriately increasing the cost of nodes associated with low-priority tasks). Under the premise of satisfying obstacle avoidance and driving direction angle constraints, the optimal path segment is re-explored. Then, the candidate path segments generated by the model are evaluated, and the optimal candidate path segment that meets the requirements of "timeliness priority for high-priority tasks and resource adaptation for low-priority tasks" and is collision-free is selected. The optimal candidate path segment replaces the path segments that need to be adjusted in the original target warehouse scheduling trajectory information, generating preliminary optimized trajectory information. Then, the overall coherence and task adaptability of the preliminary optimized trajectory information are checked to ensure that the trajectory can accurately match the updated task priority requirements. Finally, multiple target warehouse scheduling trajectory optimization information is obtained, thus completing the optimization processing of multiple target warehouse scheduling trajectory information.

[0087] The warehouse scheduling method provided in this application responds to the dynamic changes of warehouse operation tasks in real time, avoiding the disconnect between the trajectory and actual needs caused by the adjustment of task priorities. It ensures that high-priority tasks are scheduled first to meet timeliness requirements, while also achieving reasonable matching of low-priority tasks and resources, reducing resource conflicts between tasks, improving the flexibility of warehouse scheduling and the accuracy of task fulfillment, effectively solving the problem of difficulty in dynamically adapting to changes in task priorities in existing warehouse scheduling, and better meeting the actual needs of frequent adjustments to task requirements and collaborative scheduling of multiple tasks in real warehouse scenarios.

[0088] Figure 7The flowchart illustrating the implementation of the warehouse scheduling method provided in Embodiment Seven of this application is shown. The difference between this method and Embodiment One described above is that, after step S103, the method further includes:

[0089] Step S701: Obtain speed information of multiple loaded transport equipment.

[0090] In this embodiment, the speed information of the transport equipment after loading refers to the actual speed data of the transport equipment when it is loading goods in different areas of the warehouse after generating multiple target warehouse scheduling trajectory information. This includes the travel speed information of the transport equipment when carrying light-loaded goods, medium-loaded goods, and heavy-loaded goods, and the speed difference in different types of warehouse channels needs to be distinguished under each load condition. First, the weight data of the goods currently being carried is collected in real time by the load sensor on the transport equipment itself to determine the load level of the equipment. Then, the real-time travel speed data of the corresponding load condition is collected synchronously by the speed sensor of the transport equipment, and the warehouse area type corresponding to the speed data is recorded. Then, the collected load data and speed data are associated and matched to form a correspondence of "load level - warehouse area type - travel speed". Then, the validity of the associated speed data is verified, and abnormal data caused by sensor malfunction is removed. The verified speed data is corrected by referring to the load-speed reference range in the transport equipment technical parameter manual. Finally, multiple speed information of the transport equipment after loading is generated, thereby completing the acquisition of multiple speed information of the transport equipment after loading.

[0091] Step S702: Based on the preset target warehouse scheduling trajectory optimization model, the target warehouse scheduling trajectory information is optimized according to the speed information of the multiple loaded transportation equipment to obtain the target warehouse scheduling trajectory optimization information.

[0092] In this embodiment, the preset target warehouse scheduling trajectory optimization model can be preset manually, set based on a genetic algorithm, set based on an RRT algorithm, or set based on a reinforcement learning model; the preset range of the driving direction angle of the transportation equipment can be preset manually or set according to the user manual of the transportation equipment. First, the speed information of multiple loaded transport equipment can be correlated and analyzed with the scheduling trajectory information of multiple target warehouses. The load status of the transport equipment corresponding to each target warehouse scheduling trajectory can be checked one by one to determine the actual travel speed of the equipment in each segment of the trajectory under that load status. This is then compared with the speed data used in the original target trajectory planning to identify segments where speed deviations are caused by load changes. For these deviated segments, the travel time of the transport equipment in those segments is recalculated, and combined with the overall timeliness requirements of the trajectory, it is determined whether the trajectory needs to be adjusted. If the travel time of the deviated segment exceeds the original planned time by more than 10%, the segment is listed as a segment requiring optimization. A local optimization range is defined with the starting point and ending point of the deviated segment as the optimization start point and end point. Then, the speed information of multiple loaded transport equipment, the start and end point information of the segment requiring optimization, the location information of multiple warehouse obstacles, and the preset range of transport equipment travel direction angles are used as input to import the preset target warehouse scheduling trajectory. The model is optimized by replanning routes based on the actual speed after loading within a local optimization range. For road segments where speed decreases, shorter straight paths are prioritized to reduce travel time, or alternative routes with less speed impact are selected to avoid the affected road segment. Simultaneously, the turning angle of the transport equipment is limited to a preset range to avoid additional speed loss due to turning. The feasibility of multiple alternative route segments generated by the model is then assessed, and the optimal alternative route segment is selected based on "travel time closest to the original planned time, no collisions, and compliant turning." This optimal alternative route segment replaces the deviation segments in the original target warehouse scheduling trajectory information, generating preliminary optimized trajectory information. The overall coherence and timeliness of the preliminary optimized trajectory information are then verified to ensure that the total travel time of the optimized trajectory meets the task requirements and that all road segments are smoothly connected. Finally, optimized trajectory information for multiple target warehouses is obtained, thus completing the optimization process for multiple target warehouse scheduling trajectory information.

[0093] The warehouse scheduling method provided in this application accurately captures the speed differences of transportation equipment caused by changes in load, avoiding time delays or resource waste caused by discrepancies between the original trajectory and actual speed assumptions. It ensures that the trajectory is adapted to the actual driving capacity of the transportation equipment under the actual load condition, and maximizes the guarantee of task timeliness and driving safety. It effectively solves the problem of ignoring the impact of load on equipment speed in traditional warehouse scheduling, which leads to a disconnect between trajectory planning and actual operation. It improves the practicality and accuracy of warehouse scheduling trajectories, and is more in line with the actual warehouse operation scenario of dynamic speed changes after the transportation equipment is loaded with goods, helping to achieve efficient fulfillment of the entire warehouse process.

[0094] Corresponding to the method in the above embodiments, Figure 8 A structural block diagram of the warehouse scheduling device provided in the embodiments of this application is shown. For ease of explanation, only the parts related to the embodiments of this application are shown. Figure 8 The warehouse scheduling device in the example can be the execution subject of the warehouse scheduling method provided in the aforementioned embodiment 1.

[0095] Reference Figure 8 The warehouse dispatching device includes:

[0096] The information acquisition module 810 is used to acquire the location information of multiple warehouse scheduling nodes, the priority information of multiple warehouse tasks, the speed information of multiple transportation equipment, and the location information of multiple warehouse obstacles.

[0097] The initial warehouse scheduling trajectory information generation module 820 is used to generate multiple initial warehouse scheduling trajectory information based on a preset initial warehouse scheduling trajectory generation model, according to the multiple warehouse scheduling node location information, multiple warehouse task priority information, multiple transportation equipment speed information, multiple warehouse obstacle location information, and preset transportation equipment driving direction angle range information.

[0098] The target warehouse scheduling trajectory information generation module 830 is used to optimize the multiple initial warehouse scheduling trajectory information based on the preset target warehouse scheduling trajectory generation model, according to the multiple warehouse obstacle location information and the preset transportation equipment driving direction angle range information, to generate multiple target warehouse scheduling trajectory information.

[0099] The process by which each module in the warehouse scheduling device provided in this application implements its respective function can be found in the foregoing. Figure 1 The description of Embodiment 1 shown will not be repeated here.

[0100] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0101] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0102] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0103] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0104] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only for distinguishing descriptions and should not be construed as indicating or implying relative importance. It should also be understood that although the terms "first," "second," etc., are used in the text to describe various elements in some embodiments of this application, these elements should not be limited by these terms. These terms are merely used to distinguish one element from another. For example, a first table may be named a second table, and similarly, a second table may be named a first table, without departing from the scope of the various described embodiments. Both the first table and the second table are tables, but they are not the same table.

[0105] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0106] The warehouse scheduling method provided in this application can be applied to terminal devices such as mobile phones, tablets, vehicle-mounted devices, laptops, and netbooks. This application does not impose any restrictions on the specific type of terminal device.

[0107] For example, the terminal device may be a station in a WLAN, a cellular phone, a handheld device with wireless communication capabilities, a computing device or other processing device connected to a wireless modem, an in-vehicle device, a vehicle networking terminal, a computer, a laptop computer, a handheld communication device, a handheld computing device, a satellite wireless device, a wireless modem card and / or other devices for communication over a wireless system, as well as next-generation communication systems, such as mobile terminals in 5G networks or mobile terminals in future evolved public terrestrial mobile networks.

[0108] Figure 9 This is a schematic diagram of the structure of a terminal device provided in an embodiment of this application. For example... Figure 9 As shown, the terminal device 9 of this embodiment includes: at least one processor 90 ( Figure 9 (Only one is shown in the image), a memory 91, which stores a computer program 92 that can run on the processor 90. When the processor 90 executes the computer program 92, it implements the steps in the various warehouse scheduling method embodiments described above, for example... Figure 1 Steps S101 to S103 are shown. Alternatively, when the processor 90 executes the computer program 92, it implements the functions of each module / unit in the above-described device embodiments, for example... Figure 8 The functions of modules 810 to 830 are shown.

[0109] The terminal device 9 can be a desktop computer, laptop, handheld computer, or cloud server, etc. The terminal device may include, but is not limited to, a processor 90 and a memory 91. Those skilled in the art will understand that... Figure 9 This is merely an example of terminal device 9 and does not constitute a limitation on terminal device 9. It may include more or fewer components than shown, or combine certain components, or different components. For example, the terminal device may also include input transmission devices, network access devices, buses, etc.

[0110] The processor 90 may be a central processing unit, or it may be other general-purpose processors, digital signal processors, application-specific integrated circuits, off-the-shelf programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0111] In some embodiments, the memory 91 may be an internal storage unit of the terminal device 9, such as a hard disk or memory of the terminal device 9. The memory 91 may also be an external storage device of the terminal device 9, such as a plug-in hard disk or smart memory card equipped on the terminal device 9. Furthermore, the memory 91 may include both internal and external storage units of the terminal device 9. The memory 91 is used to store operating systems, applications, data, and other programs, such as the program code of the computer program. The memory 91 can also be used to temporarily store data that has been sent or will be sent.

[0112] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0113] This application also provides a terminal device, which includes at least one memory, at least one processor, and a computer program stored in the at least one memory and executable on the at least one processor. When the processor executes the computer program, it causes the terminal device to implement the steps in any of the above method embodiments.

[0114] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps described in the various method embodiments above.

[0115] This application provides a computer program product that, when run on a terminal device, enables the terminal device to implement the steps described in the various method embodiments above.

[0116] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0117] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0118] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0119] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0120] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A warehouse scheduling method, characterized in that, include: Obtain location information of multiple warehouse scheduling nodes, priority information of multiple warehouse tasks, speed information of multiple transportation equipment, and location information of multiple warehouse obstacles; Based on the preset initial warehouse scheduling trajectory generation model, multiple initial warehouse scheduling trajectory information is generated according to the multiple warehouse scheduling node location information, multiple warehouse task priority information, multiple transportation equipment speed information, multiple warehouse obstacle location information, and preset transportation equipment driving direction angle range information. Based on the preset target warehouse scheduling trajectory generation model, the multiple initial warehouse scheduling trajectory information is optimized according to the location information of the multiple warehouse obstacles and the preset range of the driving direction angle of the transportation equipment, so as to generate multiple target warehouse scheduling trajectory information.

2. The warehouse scheduling method as described in claim 1, characterized in that, The location information of the multiple warehouse scheduling nodes includes the initial node information of the warehouse scheduling trajectory, the target node information of the warehouse scheduling trajectory, and the intermediate node information of multiple warehouse scheduling trajectories; The multiple initial warehouse scheduling trajectory information includes first initial warehouse scheduling trajectory information and second initial warehouse scheduling trajectory information; The step of generating multiple initial warehouse scheduling trajectory information based on the preset initial warehouse scheduling trajectory generation model, according to the multiple warehouse scheduling node location information, multiple warehouse task priority information, multiple transportation equipment speed information, multiple warehouse obstacle location information, and preset transportation equipment travel direction angle range information, specifically includes: Based on the preset initial warehouse scheduling trajectory generation model, according to the priority information of multiple warehouse tasks, the speed information of multiple transportation equipment, the location information of multiple warehouse obstacles, and the preset range of transportation equipment driving direction angles, the intermediate node information of the multiple warehouse scheduling trajectories is selected and processed to obtain multiple warehouse scheduling node information. Based on the information of multiple warehouse scheduling nodes, the location information of multiple warehouse obstacles, the speed information of multiple transportation equipment, the preset range of transportation equipment driving direction angles, and the preset calibration speed information of transportation equipment, the cost information of the first warehouse scheduling node is calculated. Based on the initial node information of the warehouse scheduling trajectory, the target node information of the warehouse scheduling trajectory, the cost information of the first warehouse scheduling node, and the information of multiple warehouse scheduling nodes, the first initial warehouse scheduling trajectory information is generated; Based on the first initial warehouse scheduling trajectory information, generate warehouse scheduling trajectory conflict information; Based on the preset initial warehouse scheduling trajectory generation model, the cost information of the second warehouse scheduling node is calculated according to the information of multiple warehouse scheduling nodes, multiple warehouse task priority information, multiple transportation equipment speed information, multiple warehouse obstacle location information, warehouse scheduling trajectory conflict information, preset transportation equipment driving direction angle range information and preset transportation equipment calibration speed information. Based on the initial node information of the warehouse scheduling trajectory, the target node information of the warehouse scheduling trajectory, the cost information of the second warehouse scheduling node, and the information of multiple warehouse scheduling nodes, the second initial warehouse scheduling trajectory information is generated; Based on the preset initial warehouse scheduling trajectory generation model, the first initial warehouse scheduling trajectory information and the second initial warehouse scheduling trajectory information are iteratively optimized according to the cost information of the first warehouse scheduling node and the cost information of the second warehouse scheduling node to generate the first initial warehouse scheduling trajectory information and the second initial warehouse scheduling trajectory information.

3. The warehouse scheduling method as described in claim 2, characterized in that, The step of generating the first and second initial warehouse scheduling trajectory information based on the preset initial warehouse scheduling trajectory generation model, by iteratively optimizing the first and second initial warehouse scheduling trajectory information according to the cost information of the first and second warehouse scheduling nodes, specifically includes: Key characterization information for obtaining information from multiple warehouse scheduling nodes; Extract the warehouse scheduling node information corresponding to the first initial warehouse scheduling trajectory information and the warehouse scheduling node information corresponding to the second initial warehouse scheduling trajectory information to obtain multiple warehouse scheduling node information to be selected; Based on the cost information of the first and second warehouse scheduling nodes, the multiple warehouse scheduling node information to be selected is processed to obtain multiple selected warehouse scheduling node information. Based on the important characterization information of the multiple warehouse scheduling nodes and the preset important characterization enhancement rules, the important characterization information of the multiple selected warehouse scheduling nodes is updated to obtain multiple updated important characterization information; the updated important characterization information corresponds one-to-one with the selected warehouse scheduling node information. Based on the preset initial warehouse scheduling trajectory generation model, the first initial warehouse scheduling trajectory information and the second initial warehouse scheduling trajectory information are iteratively optimized according to the cost information of the first warehouse scheduling node, the cost information of the second warehouse scheduling node, the important characterization information of multiple warehouse scheduling nodes, and multiple updated important characterization information, so as to generate the first initial warehouse scheduling trajectory information and the second initial warehouse scheduling trajectory information.

4. The warehouse scheduling method as described in claim 1, characterized in that, The step of generating multiple target warehouse scheduling trajectories based on the preset target warehouse scheduling trajectory generation model, which optimizes the multiple initial warehouse scheduling trajectory information according to the multiple warehouse obstacle location information and the preset transportation equipment driving direction angle range information, specifically includes: Based on the preset warehouse scheduling trajectory separation spacing information, the multiple initial warehouse scheduling trajectory information is segmented to obtain multiple initial planned warehouse scheduling trajectory starting node information and multiple initial planned warehouse scheduling sub-trajectory information. Using the starting node information of the multiple initial planned warehouse scheduling trajectories as the center and the information of the multiple initial planned warehouse scheduling sub-trajectories as the radius, multiple warehouse scheduling range areas are generated. Based on the preset target warehouse scheduling trajectory generation model, multiple target warehouse scheduling trajectory information is generated according to the multiple warehouse scheduling range areas, multiple warehouse obstacle location information, and preset transportation equipment driving direction angle range information.

5. The warehouse scheduling method as described in claim 1, characterized in that, After the step of optimizing the multiple initial warehouse scheduling trajectory information based on the multiple warehouse obstacle location information and the preset transportation equipment driving direction angle range information to generate multiple target warehouse scheduling trajectory information according to the preset target warehouse scheduling trajectory generation model, the method further includes: Obtain the location information of newly added obstacles in multiple warehouses; Based on the preset target warehouse scheduling trajectory optimization model, the target warehouse scheduling trajectory information is optimized according to the location information of newly added obstacles in the multiple warehouses to obtain the target warehouse scheduling trajectory optimization information.

6. The warehouse scheduling method as described in claim 1, characterized in that, After the step of optimizing the multiple initial warehouse scheduling trajectory information based on the multiple warehouse obstacle location information and the preset transportation equipment driving direction angle range information to generate multiple target warehouse scheduling trajectory information according to the preset target warehouse scheduling trajectory generation model, the method further includes: Retrieve priority information for multiple updated warehouse tasks; Based on the preset target warehouse scheduling trajectory optimization model, the target warehouse scheduling trajectory information is optimized according to the updated warehouse task priority information to obtain the target warehouse scheduling trajectory optimization information.

7. The warehouse scheduling method as described in claim 1, characterized in that, After the step of optimizing the multiple initial warehouse scheduling trajectory information based on the multiple warehouse obstacle location information and the preset transportation equipment driving direction angle range information to generate multiple target warehouse scheduling trajectory information according to the preset target warehouse scheduling trajectory generation model, the method further includes: Obtain speed information for multiple loaded transport devices; Based on the preset target warehouse scheduling trajectory optimization model, the target warehouse scheduling trajectory information is optimized according to the speed information of the multiple loaded transportation equipment to obtain the target warehouse scheduling trajectory optimization information.

8. A warehouse scheduling device, characterized in that, include: The information acquisition module is used to acquire location information of multiple warehouse scheduling nodes, priority information of multiple warehouse tasks, speed information of multiple transportation equipment, and location information of multiple warehouse obstacles. The initial warehouse scheduling trajectory information generation module is used to generate multiple initial warehouse scheduling trajectory information based on a preset initial warehouse scheduling trajectory generation model, according to the multiple warehouse scheduling node location information, multiple warehouse task priority information, multiple transportation equipment speed information, multiple warehouse obstacle location information, and preset transportation equipment driving direction angle range information. The target warehouse scheduling trajectory information generation module is used to optimize the multiple initial warehouse scheduling trajectory information based on the preset target warehouse scheduling trajectory generation model, the multiple warehouse obstacle location information and the preset transportation equipment driving direction angle range information, and generate multiple target warehouse scheduling trajectory information.

9. A terminal device, characterized in that, The terminal device includes a memory and a processor. The memory stores a computer program that can run on the processor. When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 7.

Images