Carrier guiding method and device for emergency task allocation

Abstract

The invention discloses a carrier guiding method and device for emergency task allocation, and a server side method comprises the steps: receiving an emergency carrying request sent by a client side, the emergency carrying request being used for requesting the server side to search for a carrier which can preferentially process an emergency carrying task; the carrying request carries the emergency task information and the task emergency degree of the emergency carrying task; under the condition that the task emergency degree is larger than a preset threshold value, the real-time state of each carrier currently operating in the warehouse is obtained; inputting the carrying vehicle real-time state and the emergency task information of each carrying vehicle into a preset carrying vehicle search plug-in, and outputting a target carrying vehicle corresponding to the emergency carrying task; and distributing the emergency task information and a preset priority processing identifier to the target carrying vehicle, wherein the preset priority processing identifier is used for guiding the target carrying vehicle to carry out priority processing on the emergency carrying task. Therefore, by adopting the embodiment of the invention, the optimal carrier can be found in a short time, and the operation efficiency of a storage center is improved.

Description

Technical Field

[0001] This application relates to the technical field of vehicle control, and particularly to a guiding method and device for a handling vehicle for emergency task allocation. Background Art

[0002] During the process of goods handling in a large e-commerce warehouse, goods need to be transported from the storage area to the sorting area and then from the sorting area to the shipping area. The entire process involves multiple links and a large number of handling vehicles. Currently, automated handling systems have been adopted in warehousing centers to achieve automatic handling of goods by handling vehicles. However, when e-commerce warehouses process peak-hour orders, there may be a need to prioritize the processing of certain emergency orders, or in manufacturing, certain production lines may require an emergency replenishment of raw materials. In such cases, the handling vehicles need to be able to respond quickly and prioritize emergency tasks.

[0003] In the related art, under normal circumstances, handling vehicles can efficiently complete the goods handling tasks according to the established task plan. However, during the actual operation, an emergency handling task may suddenly occur in the warehousing center. At this time, the management personnel need to find a suitable handling vehicle from a large number of running handling vehicles to allocate the emergency task.

[0004] However, this process not only takes a long time but also depends on the experience of the management personnel, making it difficult to find the optimal handling vehicle in a short time and affecting the operation efficiency of the warehousing center. Summary of the Invention

[0005] Embodiments of this application provide a guiding method and device for a handling vehicle for emergency task allocation. To provide a basic understanding of some aspects of the disclosed embodiments, a simple summary is given below. This summary part is not a general review, nor is it intended to identify key / important constituent elements or delineate the protection scope of these embodiments. Its sole purpose is to present some concepts in a simple form as a prelude to the detailed description that follows.

[0006] In a first aspect, embodiments of this application provide a guiding method for a handling vehicle for emergency task allocation, which is applied to a server. The method includes: Receiving an emergency handling request sent by a client. The emergency handling request is used to request the server to search for a handling vehicle that can prioritize the processing of an emergency handling task. The handling request carries the emergency task information and the task urgency of the emergency handling task; When the task urgency is greater than a preset threshold, obtaining the real-time status of each handling vehicle currently running in the warehouse; Input the real-time status of each transporter and the emergency task information into a preset transporter search plug-in, and output the target transporter corresponding to the emergency transportation task; the preset transporter search plug-in is used to search for the optimal transporter that can give priority to handling the emergency transportation task from each transporter currently running in the warehouse; Allocate the emergency task information and a preset priority handling flag to the target transporter, and the preset priority handling flag is used to guide the target transporter to give priority to handling the emergency transportation task.

[0007] In a second aspect, an embodiment of the present application provides a transporter guiding device for emergency task allocation. The device includes: A receiving module, configured to receive an emergency transportation request sent by a client. The emergency transportation request is used to request the server to search for a transporter that can give priority to handling the emergency transportation task. The transportation request carries the emergency task information and the task urgency of the emergency transportation task; An obtaining module, configured to obtain the real-time status of each transporter currently running in the warehouse when the task urgency is greater than a preset threshold; An output module, configured to input the real-time status of each transporter and the emergency task information into a preset transporter search plug-in, and output the target transporter corresponding to the emergency transportation task; the preset transporter search plug-in is used to search for the optimal transporter that can give priority to handling the emergency transportation task from each transporter currently running in the warehouse; An allocation module, configured to allocate the emergency task information and a preset priority handling flag to the target transporter, and the preset priority handling flag is used to guide the target transporter to give priority to handling the emergency transportation task.

[0008] The technical solution provided by the embodiment of the present application may include the following beneficial effects: In the embodiment of the present application, on the one hand, when the task urgency exceeds the preset threshold, the system interrupts the regular scheduling cycle, actively obtains the real-time status of all warehouse transporters and combines it with the preset transporter search plug-in for searching. The preset transporter search plug-in can search for the optimal transporter that can give priority to handling the emergency transportation task, and can accurately locate the optimal transporter automatically in a short time, realizing an overall improvement in warehouse operation efficiency. On the other hand, the real-time status of the transporter can reflect the transporter position, power, and task progress data in real time, ensuring that the preset transporter search plug-in makes decisions based on the latest status, thereby avoiding misjudgment caused by information lag.

[0009] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. Description of the Drawings

[0010] The accompanying drawings here are incorporated into the specification and form a part of this specification, showing embodiments consistent with this application, and are used together with the specification to explain the principles of this application.

[0011] Figure 1 It is a schematic flowchart of a method for guiding a transport vehicle for emergency task allocation provided by an embodiment of this application; Figure 2 It is a plugin structure diagram of a preset transport vehicle search plugin provided by an embodiment of this application; Figure 3 It is a schematic structural diagram of a transport vehicle provided by an embodiment of this application; Figure 4 It is a schematic diagram of an application scenario provided by an embodiment of this application; Figure 5 It is a schematic flowchart of a model training method for a maximum allowable delay time prediction model provided by an embodiment of this application; Figure 6 It is a schematic structural diagram of a guiding device for a transport vehicle for emergency task allocation provided by an embodiment of this application; Figure 7 It is a schematic structural diagram of an electronic device provided by an embodiment of this application. Detailed implementation manners

[0012] The following description and drawings fully illustrate the specific implementation manners of this application, enabling those skilled in the art to practice them.

[0013] It should be clear that the described embodiments are only a part of the embodiments of this application, rather than all of them. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in this application without creative efforts fall within the scope of protection of this application.

[0014] When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with this application. On the contrary, they are merely examples of devices and methods consistent with some aspects of this application as detailed in the appended claims.

[0015] In the description of the present application, it should be understood that terms such as "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances. In addition, in the description of the present application, unless otherwise specified, "a plurality" means two or more. "And / or" describes the association relationship of associated objects and indicates that three relationships can exist. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally represents an "or" relationship between the associated objects before and after.

[0016] Currently, under normal circumstances, the forklift can efficiently complete the task of transporting goods according to the established task plan. However, during the actual operation process, an emergency transportation task may suddenly occur in the warehousing center. At this time, the management personnel need to find a suitable forklift from a large number of running forklifts to assign the emergency task.

[0017] The inventor realized that this process not only takes a long time, but also depends on the experience of the management personnel, making it difficult to find the optimal forklift in a short time and affecting the operation efficiency of the warehousing center.

[0018] To solve the above problems, the present application provides a forklift guiding method and device for emergency task allocation to solve the problems existing in the above related technical problems. In the embodiments of the present application, on the one hand, when the task urgency exceeds the preset threshold, the system interrupts the regular scheduling cycle, actively obtains the real-time status of all forklifts in the warehouse and combines it with a preset forklift search plugin for searching. The preset forklift search plugin can search out the optimal forklift for preferentially handling emergency transportation tasks, and can accurately locate the optimal forklift automatically in a short time, realizing an overall improvement in the warehousing operation efficiency. On the other hand, the real-time status of the forklift can reflect the forklift position, power, and task progress data in real time, ensuring that the preset forklift search plugin makes decisions based on the latest status, thereby avoiding misjudgment caused by information lag. The following will be described in detail using exemplary embodiments.

[0019] The following will be combined with the attached Figure 1 - attached Figure 5 to introduce in detail the forklift guiding method for emergency task allocation provided by the embodiments of the present application. This method can be implemented depending on a computer program and can run on a forklift guiding device for emergency task allocation based on the von Neumann architecture. This computer program can be integrated into an application or run as an independent tool-type application.

[0020] Please refer to Figure 1 , which is a schematic flowchart of a forklift guiding method for emergency task allocation provided by the embodiments of the present application and is applied to the server. As Figure 1As shown, the method of the embodiment of the present application includes the following steps: S101, receiving an emergency transport request sent by a client, the emergency transport request is used to request the server to search for a transport vehicle that can handle the emergency transport task with priority, and the transport request carries emergency task information and task urgency of the emergency transport task; The client is the terminal interface where users initiate requests (such as the operation interface of the warehouse management system, mobile device apps, etc.). Urgent handling requests are instructions for handling tasks initiated by users that need to be processed immediately, usually including urgent task information and task urgency. The server is the core processing module of the warehouse scheduling system, responsible for receiving requests, coordinating transport vehicle resources, and issuing task instructions. Urgent task information is metadata that describes handling requirements. Task urgency is a level parameter that identifies the urgency of the task.

[0021] In some embodiments of the present application, a user triggers an urgent handling task request through an operation interface (such as a web terminal or mobile app of a warehouse management system). The input parameters included in the request include urgent task information and task urgency. Urgent task information includes cargo attributes (type, volume, weight), start / end point coordinates. The task urgency is manually selected by the user or automatically determined by the system. The request is encapsulated in JSON or Protobuf protocol and sent to the server via HTTP / REST or MQTT. The server receives the urgent handling request sent by the client, parses the data in the urgent handling request, and obtains the urgent task information and task urgency of the urgent handling task.

[0022] S102, when the task urgency is greater than a preset threshold, obtaining the real-time status of each transporter currently operating in the warehouse; Among them, the preset threshold is the critical value of urgency preset by the system. If it exceeds this value, it is determined to be an urgent task that requires immediate response. The preset threshold is used to filter non-urgent requests to prevent resources from being occupied by low-priority tasks. The real-time status of the transporter is the dynamic operation data of the transporter at the current moment, including the current position, remaining power, cargo capacity, and task progress of the current transport task. The current position is the coordinates of the transporter in the warehouse map. The remaining power is the remaining battery capacity of the transporter (such as 85% or 42kWh). The cargo capacity is the current volume / weight that the transporter can carry. The task progress is the completion percentage of the currently executed task (such as 70%).

[0023] In some embodiments of the present application, when the task urgency is greater than a preset threshold, for example, task urgency = 4 > preset threshold = 3, in this case, the current position, remaining power, cargo capacity and task progress of each truck currently operating in the warehouse are obtained, and the real-time status of each truck is shown in Table 1.

[0024] Table 1

[0025] In some other embodiments of the present application, when the task urgency is less than or equal to a preset threshold, for example, the task urgency = 2 < the preset threshold = 3, in this case, it indicates that someone deliberately cuts in line. At this time, a task assignment rejection message is generated and fed back to the client, and the current states of the handling vehicles are maintained.

[0026] S103. Input the real-time state of each handling vehicle and the emergency task information into a preset handling vehicle search plug-in, and output the target handling vehicle corresponding to the emergency handling task; the preset handling vehicle search plug-in is used to search for the optimal handling vehicle that preferentially processes the emergency handling task from each handling vehicle currently operating in the warehouse.

[0027] Among them, the emergency task information includes the task start point , the task end point and the attributes of the goods to be carried ; the real-time state of each handling vehicle includes the current position , the remaining power , the load capacity and the task progress of the current task being carried .

[0028] For example Figure 2 As shown, the preset handling vehicle search plug-in includes a filtering module, a calculation module, an analysis module, a weighted summation module, a determination module, and an output module.

[0029] In some embodiments of the present application, the specific process of inputting the real-time state of each handling vehicle and the emergency task information into the preset handling vehicle search plug-in and outputting the target handling vehicle for the emergency handling task includes: the filtering module compares the remaining power, load capacity of each handling vehicle with the goods attributes to filter out the handling vehicles that do not meet the preset physical constraints; according to the current position, task start point, and task end point of each handling vehicle, filter out the handling vehicles with conflicts with the emergency handling task path to obtain multiple candidate handling vehicles; the calculation module calculates the total duration for each candidate handling vehicle to complete the emergency handling task starting from the current moment based on the task progress of the current task being carried by each candidate handling vehicle, and obtains the total completion duration of each candidate handling vehicle; the analysis module analyzes the maximum allowable delay time for the current task being carried after inserting the emergency handling task for each candidate handling vehicle as the influence result of each candidate handling vehicle; the weighted summation module performs a weighted summation of the total completion duration of each candidate handling vehicle and the influence result of each candidate handling vehicle to obtain the comprehensive priority score of each candidate handling vehicle; the determination module determines the target handling vehicle for the emergency handling task according to the comprehensive priority score of each candidate handling vehicle; the output module outputs the target handling vehicle for the emergency handling task.

[0030] In some embodiments of the present application, the specific process of comparing the remaining power, load capacity of each transporter with the cargo attributes to filter out transporters that do not meet the preset physical constraints includes: determining the cargo capacity and the required handling time according to the cargo attributes; calculating the minimum power threshold required to perform the emergency handling task through the required handling time; taking the cargo capacity and the minimum power threshold as the preset physical constraints; comparing the load capacity with the cargo capacity and comparing the remaining power with the minimum power threshold to filter out transporters with a load capacity less than the cargo capacity or a remaining power less than the minimum power threshold.

[0031] For example, compare the remaining power (which needs to support the entire emergency task), load capacity of the transporter with the cargo attributes, and eliminate transporters that do not meet the physical constraints. Filter out transporters that do not meet the physical constraints (such as or ).

[0032] Among them, the time window method or the conflict search algorithm (CBS) can be used to detect conflicts, so as to filter out transporters whose paths conflict with the emergency handling task path according to the current positions, task start points, and task end points of each transporter. For example, the task end point of the task that the transporter is currently performing is in the opposite direction and cannot be bypassed.

[0033] In some embodiments of the present application, the specific process of calculating the total time required for each candidate transporter to complete the emergency handling task starting from the current moment according to the task progress of the task currently being carried by each candidate transporter includes: determining whether the task currently being carried by each candidate transporter is an empty return; if so, determining that the task currently being carried by each candidate transporter can be interrupted; if not, determining that the task currently being carried by each candidate transporter cannot be interrupted; in the case where the task currently being carried by each candidate transporter cannot be interrupted, calculating the remaining time of the task currently being carried by each candidate transporter according to the task progress of the task currently being carried by each candidate transporter; using the dynamic path planning algorithm to determine the shortest time for each candidate transporter to move from the current position to the task start point to obtain the movement time of each candidate transporter; calculating the handling time of each candidate transporter from the task start point to the task end point; summing up the remaining time, movement time, and handling time of the task currently being carried by each candidate transporter to obtain the total time required for each candidate transporter to complete the emergency handling task starting from the current moment.

[0034] In some embodiments, in the case where the task currently being carried by each candidate transporter can be interrupted, the remaining time of the task currently being carried by each candidate transporter is directly assigned 0.

[0035] For example, if the current task of the vehicle can be interrupted (such as an empty return), then ; If it is not interruptible, calculate the remaining time of the current task being carried by each candidate carrier vehicle. The calculation formula is:

[0036] Where, is the remaining time of the current task being carried by the candidate carrier vehicle, is the carrier vehicle the completed progress of the current task, is the carrier vehicle standard operation speed, is the carrier vehicle from the current position to the end point of the current task dynamic path time.

[0037] Where, use the dynamic path planning algorithm (such as A* algorithm) to calculate the shortest time from the current position to the task start point :

[0038] Where, the handling time of each candidate carrier vehicle from the task start point to the task end point, that is, from to handling time The calculation formula is:

[0039] Where, is the cargo loading / unloading time, is the original handling time of the candidate carrier vehicle from the task start point to the task end point, Where, the total duration for each candidate carrier vehicle to complete the urgent handling task starting from the current moment .

[0040] In some embodiments of the present application, the specific process of analyzing the maximum allowable delay time of the current task being carried after inserting an urgent handling task for each candidate carrier vehicle includes: constructing the basic features and dynamic environment features of each candidate carrier vehicle; converting the basic features and dynamic environment features into numerical vectors that can be processed by the model, and splicing the conversion results to obtain the final feature vector of each candidate carrier vehicle; inputting the final feature vector of each candidate carrier vehicle into a pre-trained maximum allowable delay time prediction model; where, the pre-trained maximum allowable delay time prediction model is a neural network for predicting the maximum allowable delay time of the current task being carried; outputting the maximum allowable delay time of the current task being carried after inserting an urgent handling task for each candidate carrier vehicle.

[0041] Specifically, the specific process of constructing the basic features of each candidate transporter includes: calculating the distance from each candidate transporter to the task start point and the length of the emergency task path according to the task start point, task end point, and current position; constructing a first vector between the current position and the task end point, and constructing a second vector between the task start point and the task end point; calculating the included angle between the current path direction of each candidate transporter and the direction of the emergency transportation task path according to the first vector and the second vector; taking the distance from each candidate transporter to the task start point, the length of the emergency task path, and the included angle as the geometric features of each candidate transporter; obtaining the latest completion time of the task currently carried by each candidate transporter to obtain the time estimation feature; constructing the resource status feature of each candidate transporter according to the remaining power and load capacity; taking the geometric feature, time estimation feature, and resource status feature as the basic features of each candidate transporter.

[0042] Specifically, the specific process of constructing the dynamic environment features of each candidate transporter includes: using a dynamic path planning algorithm to determine the time for each candidate transporter to move from the current position to the task start point and the time to move from the task start point to the task end point; determining the grid overlap ratio between the task path of the task currently carried by each candidate transporter and the task path of the emergency transportation task; determining the number of active transporters within the preset range of each candidate transporter; taking the determined time, grid overlap ratio, and the number of active transporters within the preset range of each candidate transporter as the dynamic environment features of each candidate transporter.

[0043] In some other embodiments of the present application, the specific process of analyzing the maximum allowable delay time of the current task carried by each candidate transporter after inserting an emergency transportation task includes: obtaining the current system time; adding the current system time to the total completion duration of each candidate transporter to obtain an accumulation result; obtaining the latest completion time of the task currently carried by each candidate transporter; subtracting the accumulation result from the latest completion time to obtain the maximum allowable delay time of the current task carried by each candidate transporter after inserting an emergency transportation task.

[0044] For example, the maximum allowable delay time The calculation formula is: ; is the latest completion time of the task currently carried by each candidate transporter, is the current system time.

[0045] If , it is marked as an unacceptable impact, and the candidate transporter is excluded.

[0046] If , it is marked as an acceptable impact.

[0047] In some embodiments of the present application, the total completion time of each candidate carrier vehicle is weighted and summed with the impact result of each candidate carrier vehicle to obtain the comprehensive priority score of each candidate carrier vehicle. The calculation formula is:

[0048] where is a configurable weight.

[0049] In some embodiments of the present application, after obtaining the comprehensive priority score of each candidate carrier vehicle , sort the candidate carrier vehicles in descending order, and select the candidate carrier vehicle with the highest score as . .

[0050] S104. Allocate the emergency task information and the preset priority processing flag to the target carrier vehicle. The preset priority processing flag is used to guide the target carrier vehicle to preferentially process the emergency handling task.

[0051] where the target carrier vehicle is the optimal carrier vehicle selected through multi-module screening (such as filtering, weighted scoring). The appearance of this carrier vehicle is, for example Figure 3 as shown, and there is an acceleration sensor 4, a battery 1, a load sensor 2 and a weight sensor 3 on this carrier vehicle.

[0052] In an embodiment of the present application, after determining the target carrier vehicle, the emergency task information and the preset priority processing flag are sent to the target carrier vehicle.

[0053] Further, the current carrier vehicle receives the emergency task information and the preset priority processing flag, and the current carrier vehicle processes the emergency handling task according to the emergency task information and the preset priority processing flag.

[0054] For example Figure 4 as shown, the client generates an emergency handling request and sends it to the server. The server receives the emergency handling request sent by the client. The emergency handling request is used to request the server to search for a carrier vehicle that can preferentially process the emergency handling task. The handling request carries the emergency task information and the task urgency of the emergency handling task; when the task urgency is greater than the preset threshold, the server obtains the real-time status of each carrier vehicle currently running in the warehouse; the server inputs the real-time status of each carrier vehicle and the emergency task information into a preset carrier vehicle search plug-in, and outputs the target carrier vehicle corresponding to the emergency handling task; the preset carrier vehicle search plug-in is used to search for the optimal carrier vehicle that preferentially processes the emergency handling task from each carrier vehicle currently running in the warehouse; the server allocates the emergency task information and the preset priority processing flag to the target carrier vehicle, and the preset priority processing flag is used to guide the target carrier vehicle to preferentially process the emergency handling task.

[0055] In an embodiment of the present application, on the one hand, when the task urgency exceeds a preset threshold, the system interrupts the regular scheduling cycle and actively obtains the real-time status of the full-warehouse forklift truck and performs a search in combination with a preset forklift truck search plug-in. The preset forklift truck search plug-in can search for the optimal forklift truck for preferentially processing urgent handling tasks, and can accurately locate the optimal forklift truck automatically in a short time, realizing an overall improvement in warehouse operation efficiency. On the other hand, the real-time status of the forklift truck can reflect the position, power, and task progress data of the forklift truck in real time, ensuring that the preset forklift truck search plug-in makes decisions based on the latest status, thereby avoiding misjudgment caused by information lag.

[0056] Please refer to Figure 5 , which is a schematic flowchart of a model training method for a gravity distribution uniformity recognition model provided by an embodiment of the present application. As Figure 5 shown, the method of the embodiment of the present application may include the following steps: S201, collect historical task logs of historical handling tasks, where the historical task logs include forklift truck status, task attributes, environmental parameters, and actual delay time; Among them, historical handling tasks refer to the set of handling tasks actually executed by the forklift truck within a certain period in the past, recording the operation conditions of the forklift truck in different scenarios. Historical task logs are detailed records of historical handling tasks, containing various information during the task execution process. They are the key data sources for constructing the prediction model and are used to train the model to identify the patterns and rules of task delays. Forklift truck status refers to various status information of the forklift truck when performing historical tasks. Task attributes are the characteristics of the handling task itself, such as task start point, task end point, cargo attributes, latest completion time, latest completion time. Environmental parameters describe the characteristics of the environment where the forklift truck performs the task, such as path planning, grid overlap ratio, and number of active forklift trucks. Actual delay time refers to the actual delay time that occurs during the task execution process of the forklift truck.

[0057] In some embodiments of the present application, the collection of the forklift truck status data includes: through sensors on the forklift truck (such as a power sensor, a load sensor, a GPS positioning module, etc.), real-time collection of information such as the remaining power, the load capacity, and the current location of the forklift truck. The collection of the task attribute data includes: storing these data in the database of the server and recording the status at each time point. When allocating tasks, information such as the starting point, the ending point, the cargo attributes, and the latest completion time of the task are recorded. These data are usually generated by the task management system and associated with the task records of the forklift truck. The collection of the environmental parameter data includes using path planning algorithms (such as the A* algorithm, the Dijkstra algorithm, etc.) to calculate the path information of the forklift truck, including the path length, the grid overlap ratio, etc. Information such as the number of active forklift trucks in the current warehouse is obtained through the Warehouse Management System (WMS). After the task is completed, the difference between the actual completion time and the latest completion time of the task is calculated to obtain the actual delay time. The delay time is recorded in the task log. The collected data such as the forklift truck status, the task attributes, the environmental parameters, and the actual delay time are stored in a structured database.

[0058] S202, simulate scenarios of inserting multiple emergency tasks through reinforcement learning to perform data simulation on the historical task logs, and obtain the simulation data and the simulation maximum allowable delay time of each historical forklift truck; Among them, reinforcement learning is a machine learning method that learns the optimal policy through the interaction between the agent and the environment to maximize the cumulative reward. Data simulation refers to using computer technology to simulate and imitate various phenomena, processes, and systems in the real world to generate virtual data. In reinforcement learning, data simulation is used to simulate the interaction process between the agent and the environment and generate data for training and validating the model.

[0059] In some embodiments of the present application, the agent is a forklift truck, and its status includes the remaining power, the load capacity, the current location, etc. The environment is a warehouse, and its status includes the task starting point, the ending point, the cargo attributes, the number of active forklift trucks, etc. The reward can be defined as the timeliness of task completion, the resource utilization efficiency, etc. For example, if the forklift truck completes the task within the specified time, a positive reward is obtained; if there is a delay, a negative reward is obtained. Use reinforcement learning algorithms (such as Q-learning, DQN, etc.) to train the agent. The goal of the model is to learn the optimal policy for inserting emergency tasks in different states to maximize the cumulative reward.

[0060] Among them, parameters such as the starting point, ending point, and cargo attributes of the task are randomly generated through historical task logs to simulate different scenarios of inserting emergency tasks. The agent selects actions (such as inserting an emergency task) according to the current policy, and the environment feedbacks new states and rewards based on the actions. Information such as the state, action, and reward of each interaction is recorded to generate a simulation data set. A prediction model (such as a neural network) is trained using the simulation data, with the input including the state of the forklift, task attributes, environment parameters, etc., and the output being the maximum allowable delay time.

[0061] S203. Based on the simulation data of each historical forklift, construct the historical basic features and historical dynamic environment features of each candidate forklift; It should be noted that constructing the historical basic features and historical dynamic environment features of each candidate forklift based on the simulation data of each historical forklift has the same logic as constructing the basic features and dynamic environment features of each candidate forklift in step S102, which will not be elaborated here.

[0062] S204. Correlate the historical basic features and historical dynamic environment features of each candidate forklift with the simulation maximum allowable delay time to obtain model training samples; S205. Use a neural network to create a maximum allowable delay time prediction model; S206. Input the model training samples into the maximum allowable delay time prediction model to output the model loss value; S207. When the model loss value reaches the minimum, obtain the pre-trained maximum allowable delay time prediction model.

[0063] In the embodiment of the present application, the pre-trained maximum allowable delay time prediction model is a neural network used to predict the maximum allowable delay time of the currently carried task. Through this model, the system can accurately predict the maximum allowable delay time of each candidate forklift for the current task after inserting an emergency task, so as to more precisely select the most suitable forklift to execute the emergency task, avoiding delays or conflicts caused by unreasonable task allocation and ensuring that the emergency task can be completed in a timely manner.

[0064] In the embodiment of the present application, this model is constructed based on a neural network and trained through reinforcement learning and historical data simulation, and can adapt to different task scenarios and environmental changes. This enables the system to quickly make optimal decisions when facing complex emergency tasks and improves the overall flexibility of the system.

[0065] The following is an embodiment of the device of the present application, which can be used to execute the method embodiment of the present application. For the details not disclosed in the embodiment of the device of the present application, please refer to the method embodiment of the present application.

[0066] Please refer to Figure 6, which shows a schematic structural diagram of a forklift guiding device for emergency task allocation provided by an exemplary embodiment of the present application. The forklift guiding device for emergency task allocation can be implemented as all or part of an electronic device through software, hardware, or a combination of both. The device 1 includes a receiving module 10, an obtaining module 20, an output module 30, and an allocation module 40.

[0067] The receiving module 10 is configured to receive an emergency handling request sent by a client. The emergency handling request is used to request the server to search for a forklift that can preferentially handle the emergency handling task. The handling request carries the emergency task information and task urgency of the emergency handling task. The obtaining module 20 is configured to obtain the real-time forklift status of each forklift currently operating in the warehouse when the task urgency is greater than a preset threshold. The output module 30 is configured to input the real-time forklift status of each forklift and the emergency task information into a preset forklift search plug-in, and output the target forklift corresponding to the emergency handling task. The preset forklift search plug-in is used to search for the optimal forklift that preferentially handles the emergency handling task from each forklift currently operating in the warehouse. The allocation module 40 is configured to allocate the emergency task information and a preset preferential handling flag to the target forklift. The preset preferential handling flag is used to guide the target forklift to preferentially handle the emergency handling task.

[0068] It should be noted that when the forklift guiding device for emergency task allocation provided in the above embodiment executes the forklift guiding method for emergency task allocation, only the above-mentioned division of each functional module is used for illustration. In practical applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the forklift guiding device for emergency task allocation provided in the above embodiment and the embodiment of the forklift guiding method for emergency task allocation belong to the same concept. The implementation process is detailed in the method embodiment and will not be repeated here.

[0069] The serial numbers of the above embodiments of the present application are only for description and do not represent the advantages and disadvantages of the embodiments.

[0070] In an embodiment of the present application, on the one hand, when the task urgency exceeds a preset threshold, the system interrupts the regular scheduling cycle, actively obtains the real-time status of the full-warehouse forklift and performs a search in combination with a preset forklift search plug-in. The preset forklift search plug-in can search for the optimal forklift for preferentially handling urgent handling tasks, and can accurately locate the optimal forklift automatically in a short time, realizing an overall improvement in the efficiency of warehousing operations. On the other hand, the real-time status of the forklift can reflect the forklift position, power, and task progress data in real time, ensuring that the preset forklift search plug-in makes decisions based on the latest status, thereby avoiding misjudgments caused by information lag.

[0071] The present application also provides a computer-readable medium, on which program instructions are stored. When the program instructions are executed by a processor, the forklift guidance method for emergency task allocation provided by each of the above method embodiments is implemented.

[0072] The present application also provides a computer program product containing instructions. When it runs on a computer, it causes the computer to execute the forklift guidance method for emergency task allocation of each of the above method embodiments.

[0073] Please refer to Figure 7 , which is a schematic structural diagram of an electronic device provided by an embodiment of the present application. As Figure 7 shown, the electronic device 1000 may include: at least one processor 1001, at least one network interface 1004, a user interface 1003, a memory 1005, and at least one communication bus 1002.

[0074] Among them, the communication bus 1002 is used to realize the connection and communication between these components.

[0075] Among them, the user interface 1003 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 1003 may further include a standard wired interface and a wireless interface.

[0076] Among them, the network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0077] Among them, the processor 1001 may include one or more processing cores. The processor 1001 connects various parts within the entire electronic device 1000 through various interfaces and lines, and executes various functions of the electronic device 1000 and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 1005, and by calling the data stored in the memory 1005. Optionally, the processor 1001 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor 1001 may integrate one or a combination of several of a central processing unit (CPU), a graphics processing unit (GPU), and a modem, etc. Among them, the CPU mainly processes the operating system, user interface, application programs, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 1001 and may be implemented separately by a single chip.

[0078] Among them, the memory 1005 may include random access memory (RAM) and may also include read-only memory. Optionally, the memory 1005 includes a non-transitory computer-readable storage medium. The memory 1005 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 1005 may include a program storage area and a data storage area. Among them, the program storage area may store instructions for implementing the operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store the data involved in the above-mentioned various method embodiments. Optionally, the memory 1005 may also be at least one storage system located far from the aforementioned processor 1001. As Figure 7 shown, the memory 1005, as a computer storage medium, may include an operating system, a network communication module, a user interface module, and a forklift guidance application program for emergency task allocation.

[0079] In Figure 7In the electronic device 1000 shown, the user interface 1003 is mainly used to provide an interface for the user to input and obtain the data input by the user; while the processor 1001 can be used to call the forklift guiding application program stored in the memory 1005 for emergency task allocation, and specifically perform the following operations: Receive an emergency handling request sent by the client. The emergency handling request is used to request the server to search for a forklift that can give priority to handling the emergency handling task. The handling request carries the emergency task information and task urgency of the emergency handling task; When the task urgency is greater than the preset threshold, obtain the real-time forklift status of each forklift currently running in the warehouse; Input the real-time forklift status of each forklift and the emergency task information into a preset forklift search plug-in, and output the target forklift corresponding to the emergency handling task; the preset forklift search plug-in is used to search for the optimal forklift that gives priority to handling the emergency handling task from each forklift currently running in the warehouse; Allocate the emergency task information and a preset priority handling flag to the target forklift. The preset priority handling flag is used to guide the target forklift to give priority to handling the emergency handling task.

[0080] In one embodiment, when the processor 1001 executes the operation of inputting the real-time forklift status of each forklift and the emergency task information into a preset forklift search plug-in and outputting the target forklift of the emergency handling task, it specifically performs the following operations: The filtering module compares the remaining power, load capacity and cargo attributes of each forklift to filter out the forklifts that do not meet the preset physical constraints; according to the current position, task start point and task end point of each forklift, filter out the forklifts with conflicts with the emergency handling task path, and obtain multiple candidate forklifts; The calculation module calculates the total duration for each candidate forklift to complete the emergency handling task starting from the current moment according to the task progress of the task currently being carried by each candidate forklift, and obtains the total completion duration of each candidate forklift; The analysis module analyzes the maximum allowable delay time of the current task being carried by each candidate forklift after inserting the emergency handling task as the influence result of each candidate forklift; The weighted summation module performs weighted summation on the total completion duration of each candidate forklift and the influence result of each candidate forklift to obtain the comprehensive priority score of each candidate forklift; The determination module determines the target forklift of the emergency handling task according to the comprehensive priority score of each candidate forklift; The output module outputs the target forklift of the emergency handling task.

[0081] In one embodiment, when the processor 1001 executes the operation of comparing the remaining power, load capacity of each transporter with the cargo attributes to filter out transporters that do not meet the preset physical constraints, it specifically performs the following operations: Determine the cargo capacity and the required handling duration according to the cargo attributes; Calculate the minimum power threshold required to execute the emergency handling task based on the required handling duration; Take the cargo capacity and the minimum power threshold as the preset physical constraints; Compare the load capacity with the cargo capacity, and compare the remaining power with the minimum power threshold to filter out transporters with a load capacity less than the cargo capacity or a remaining power less than the minimum power threshold.

[0082] In one embodiment, when the processor 1001 executes the operation of calculating the total duration for each candidate transporter to complete the emergency handling task starting from the current moment according to the task progress of the currently handled task of each candidate transporter, it specifically performs the following operations: Determine whether the currently handled task of each candidate transporter is an empty return; If so, determine that the currently handled task of each candidate transporter is interruptible; if not, determine that the currently handled task of each candidate transporter is not interruptible; In the case where the currently handled task of each candidate transporter is not interruptible, calculate the remaining time of the currently handled task of each candidate transporter according to the task progress of the currently handled task of each candidate transporter; Use the dynamic path planning algorithm to determine the shortest time for each candidate transporter to move from the current position to the task starting point, and obtain the moving time of each candidate transporter; Calculate the handling time for each candidate transporter from the task starting point to the task ending point; Sum up the remaining time, moving time, and handling time of the currently handled task of each candidate transporter to obtain the total duration for each candidate transporter to complete the emergency handling task starting from the current moment.

[0083] In one embodiment, when the processor 1001 executes the operation of analyzing the maximum allowable delay time of the currently handled task after inserting the emergency handling task for each candidate transporter, it specifically performs the following operations: Construct the basic features and dynamic environment features of each candidate transporter; Convert the basic features and dynamic environment features into numerical vectors that can be processed by the model, and splice the conversion results to obtain the final feature vector of each candidate transporter; Input the final feature vector of each candidate transporter into a pre-trained maximum allowable delay time prediction model; wherein, the pre-trained maximum allowable delay time prediction model is a neural network used to predict the maximum allowable delay time of the current transportation task. Output the maximum allowable delay time of the current transportation task after each candidate transporter inserts an emergency transportation task.

[0084] In one embodiment, when the processor 1001 executes to construct the basic features of each candidate transporter, the following operations are specifically performed: Calculate the distance from each candidate transporter to the task start point and the length of the emergency task path according to the task start point, task end point, and current position. Construct a first vector between the current position and the task end point, and construct a second vector between the task start point and the task end point. Calculate the included angle between the current path direction of each candidate transporter and the direction of the emergency transportation task path according to the first vector and the second vector. Take the distance from each candidate transporter to the task start point, the length of the emergency task path, and the included angle as the geometric features of each candidate transporter. Obtain the latest completion time of the current transportation task of each candidate transporter to obtain the time estimation feature. Construct the resource status feature of each candidate transporter according to the remaining battery power and load capacity. Take the geometric feature, time estimation feature, and resource status feature as the basic features of each candidate transporter.

[0085] In one embodiment, when the processor 1001 executes to construct the dynamic environment features of each candidate transporter, the following operations are specifically performed: Use a dynamic path planning algorithm to determine the time for each candidate transporter to move from the current position to the task start point and the time to move from the task start point to the task end point. Determine the grid overlap ratio between the task path of the current transportation task of each candidate transporter and the task path of the emergency transportation task. Determine the number of active transporters within the preset range of each candidate transporter. Take the determined time, grid overlap ratio, and the number of active transporters within the preset range of each candidate transporter as the dynamic environment features of each candidate transporter.

[0086] In one embodiment, when the processor 1001 executes the process of generating a pre-trained maximum allowable delay time prediction model, the following operations are specifically performed: Collect the historical task logs of historical transportation tasks, where the historical task logs include transporter status, task attributes, environmental parameters, and actual delay time. Simulate scenarios of inserting multiple emergency tasks through reinforcement learning to perform data simulation on historical task logs, and obtain simulation data of each historical transporter and the maximum allowable delay time of the simulation; According to the simulation data of each historical transporter, construct the historical basic features and historical dynamic environment features of each candidate transporter; Associate the historical basic features and historical dynamic environment features of each candidate transporter with the maximum allowable delay time of the simulation to obtain model training samples; Use a neural network to create a maximum allowable delay time prediction model; Input the model training samples into the maximum allowable delay time prediction model and output the model loss value; When the model loss value reaches the minimum, obtain the pre-trained maximum allowable delay time prediction model.

[0087] In one embodiment, when the processor 1001 executes the analysis of the maximum allowable delay time of the currently carried task after inserting an emergency handling task for each candidate transporter, it specifically performs the following operations: Obtain the current system time; Accumulate the current system time with the total completion duration of each candidate transporter to obtain an accumulation result; Obtain the latest completion time of the currently carried task of each candidate transporter; Subtract the accumulation result from the latest completion time to obtain the maximum allowable delay time of the currently carried task after inserting an emergency handling task for each candidate transporter.

[0088] In the embodiment of the present application, on the one hand, when the task urgency exceeds the preset threshold, the system interrupts the regular scheduling cycle, actively obtains the real-time status of all warehouse transporters and performs a search in combination with a preset transporter search plug-in. The preset transporter search plug-in can search for the optimal transporter that preferentially processes emergency handling tasks, and can accurately locate the optimal transporter automatically in a short time, realizing an overall improvement in warehouse operation efficiency. On the other hand, the real-time status of the transporter can reflect the position, power, and task progress data of the transporter in real time, ensuring that the preset transporter search plug-in makes decisions based on the latest status, thereby avoiding misjudgment caused by information lag.

[0089] Those of ordinary skill in the art can understand that all or part of the processes of implementing the above embodiment methods can be completed by instructing relevant hardware through a computer program. The program for guiding the transporter for emergency task allocation can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above method embodiments. Among them, the storage medium of the program for guiding the transporter for emergency task allocation can be a magnetic disk, an optical disk, a read-only memory, or a random access memory, etc.

[0090] The above disclosure is only for the preferred embodiments of the present application. Of course, the scope of rights of the present application cannot be limited thereby. Therefore, equivalent changes made according to the claims of the present application still fall within the scope covered by the present application.

Claims

1. A method for guiding a transport vehicle for emergency task allocation, characterized in that: Applied to the server, the method includes: Receiving an emergency transport request sent by a client, wherein the emergency transport request is used to request the server to search for a transport vehicle that can handle the emergency transport task with priority, and the transport request carries emergency task information and task urgency of the emergency transport task; When the task urgency is greater than a preset threshold, obtaining the real-time status of each transporter currently operating in the warehouse; Input the real-time status of each transporter and the emergency task information into a preset transporter search plug-in, and output the target transporter corresponding to the emergency transport task; the preset transporter search plug-in is used to search for the optimal transporter that preferentially handles the emergency transport task from the transporters currently running in the warehouse; The emergency task information and a preset priority processing mark are allocated to the target transport vehicle, and the preset priority processing mark is used to guide the target transport vehicle to give priority to the emergency transport task.

2. The method according to claim 1, characterized in that The emergency task information includes the task start point, task end point and the properties of the goods to be transported; the real-time status of each transporter includes the current position, remaining power, cargo capacity and the task progress of the current transport task; the preset transporter search plug-in includes a filtering module, a calculation module, an analysis module, a weighted summation module, a determination module and an output module; The step of inputting the real-time status of each transporter and the emergency task information into a preset transporter search plug-in and outputting a target transporter for the emergency transport task comprises: The filtering module compares the remaining power and cargo capacity of each transport vehicle with the cargo attributes to filter out the transport vehicles that do not meet the preset physical constraints; according to the current position, task starting point, and task end point of each transport vehicle, the transport vehicles that conflict with the emergency transport task path are filtered out to obtain multiple candidate transport vehicles; The calculation module calculates the total time for each candidate transport vehicle to complete the emergency transport task from the current moment according to the task progress of the current transport task of each candidate transport vehicle, so as to obtain the total completion time of each candidate transport vehicle; The analysis module analyzes the maximum allowable delay time of each candidate transport vehicle on the current transport task after the candidate transport vehicle is inserted into the emergency transport task as the impact result of each candidate transport vehicle; The weighted sum module performs a weighted summation of the total completion time of each candidate transport vehicle and the impact result of each candidate transport vehicle to obtain a comprehensive priority score of each candidate transport vehicle; The determination module determines the target transport vehicle for the emergency transport task according to the comprehensive priority score of each candidate transport vehicle; The output module outputs the target transport vehicle of the emergency transport task.

3. The method according to claim 2, characterized in that The comparing the remaining power and cargo capacity of each transport vehicle with the cargo attribute to filter out the transport vehicles that do not meet the preset physical constraints includes: Determine the cargo capacity and the time required for transportation according to the cargo properties; Calculate the minimum power threshold required to perform the emergency transport task based on the time required for the transport; Using the cargo capacity and the minimum power threshold as preset physical constraints; The cargo capacity is compared with the cargo capacity, and the remaining power is compared with the minimum power threshold, so as to filter out the trucks whose cargo capacity is less than the cargo capacity or whose remaining power is less than the minimum power threshold.

4. The method according to claim 2, characterized in that: The calculating, based on the task progress of the current transport task of each candidate transport vehicle, the total time for each candidate transport vehicle to complete the emergency transport task from the current moment includes: Determine whether the current transport task of each candidate transport vehicle is to return empty-load; If yes, determine that the current task being carried by each candidate transport vehicle can be interrupted; if no, determine that the current task being carried by each candidate transport vehicle cannot be interrupted; In the case that the current transport task of each candidate transport vehicle cannot be interrupted, the remaining time of the current transport task of each candidate transport vehicle is calculated according to the task progress of the current transport task of each candidate transport vehicle; Using a dynamic path planning algorithm to determine the shortest time for each candidate transport vehicle to move from the current position to the starting point of the task, and obtain the moving time of each candidate transport vehicle; Calculating the transport time of each candidate transport vehicle from the task starting point to the task end point; The remaining time of the current transport task of each candidate transport vehicle, the moving time, and the transport time are summed to obtain the total time for each candidate transport vehicle to complete the transport of the emergency transport task from the current moment.

5. The method according to claim 2, characterized in that: Analyzing the maximum allowable delay time of each candidate transport vehicle for the current transport task after inserting the emergency transport task, including: Constructing basic features and dynamic environment features of each candidate transport vehicle; Convert the basic features and dynamic environment features into numerical vectors that can be processed by the model, and concatenate the conversion results to obtain the final feature vector of each candidate transport vehicle; Inputting the final feature vector of each candidate transport vehicle into a pre-trained maximum allowable delay time prediction model; wherein the pre-trained maximum allowable delay time prediction model is a neural network used to predict the maximum allowable delay time of the current transport task; Outputting the maximum allowable delay time of each candidate transport vehicle for the current transport task after being inserted into the urgent transport task.

6. The method according to claim 5, characterized in that The basic features of each candidate transport vehicle are constructed, including: Calculate the distance from each candidate transport vehicle to the task starting point and the length of the emergency task path according to the task starting point, the task end point and the current position; Constructing a first vector between the current position and the task end point, and constructing a second vector between the task start point and the task end point; Calculate the angle between the current path direction of each candidate transport and the direction of the emergency transport task path according to the first vector and the second vector; The distance from each candidate transport vehicle to the task starting point, the length of the emergency task path, and the direction angle are used as the geometric features of each candidate transport vehicle; Obtaining the latest completion time of the current transport task of each candidate transport vehicle to obtain a time estimation feature; Constructing resource status characteristics of each candidate transport vehicle according to the remaining power and cargo capacity; The geometric features, the time estimation features and the resource status features are used as basic features of each candidate transport vehicle.

7. The method according to claim 5, characterized in that The step of constructing the dynamic environment features of each candidate transport vehicle comprises: Using a dynamic path planning algorithm to determine the time for each candidate transport vehicle to move from a current position to the task starting point and the time for each candidate transport vehicle to move from the task starting point to the task end point; Determine a grid overlap ratio between a task path of a task currently being carried by each candidate transport vehicle and a task path of the urgent transport task; Determining the number of active transport vehicles within a preset range of each candidate transport vehicle; The determined time, the grid overlap ratio, and the number of active transport vehicles within a preset range of each candidate transport vehicle are used as dynamic environment features of each candidate transport vehicle.

8. The method according to claim 5, characterized in that The following steps are used to generate a pre-trained maximum allowable delay prediction model, including: Collect historical task logs of historical handling tasks, wherein the historical task logs include the status of the handling vehicle, task attributes, environmental parameters, and actual delay time; By simulating the scenario of inserting multiple urgent tasks through reinforcement learning, data simulation is performed on the historical task log to obtain simulation data of each historical transport vehicle and the maximum allowable delay time of the simulation; Constructing historical basic features and historical dynamic environment features of each candidate transport vehicle according to the simulation data of each historical transport vehicle; Associating the historical basic characteristics and historical dynamic environment characteristics of each candidate transport vehicle with the maximum allowable delay time of the simulation to obtain a model training sample; A neural network was used to create a maximum allowable delay time prediction model; Inputting the model training sample into the maximum allowable delay time prediction model, and outputting the model loss value; When the model loss value reaches the minimum, a pre-trained maximum allowable delay time prediction model is obtained.

9. The method according to claim 2, characterized in that: Analyzing the maximum allowable delay time of each candidate transport vehicle for the current transport task after inserting the emergency transport task, including: Get the current system time; The current time of the system is added to the total completion time of each candidate transport vehicle to obtain an accumulation result; Obtaining the latest completion time of the current transport task of each candidate transport vehicle; The latest completion time is subtracted from the accumulated result to obtain the maximum allowable delay time for each candidate transport vehicle for the current transport task after the candidate transport vehicle is inserted into the urgent transport task.

10. A transport vehicle guiding device for emergency task allocation, characterized in that: The device comprises: A receiving module, used to receive an emergency transport request sent by a client, wherein the emergency transport request is used to request the server to search for a transport vehicle that can handle the emergency transport task with priority, and the transport request carries the emergency task information and task urgency of the emergency transport task; An acquisition module, used for acquiring the real-time status of each transporter currently operating in the warehouse when the urgency of the task is greater than a preset threshold; An output module, used to input the real-time status of each transporter and the emergency task information into a preset transporter search plug-in, and output a target transporter corresponding to the emergency transport task; the preset transporter search plug-in is used to search for the optimal transporter that preferentially handles the emergency transport task from each transporter currently running in the warehouse; The allocation module is used to allocate the emergency task information and a preset priority processing mark to the target transport vehicle, and the preset priority processing mark is used to guide the target transport vehicle to give priority to the emergency transport task.

Images