Method and device of controlling stacker, three-dimensional warehouse automation system, electronic device, storage medium, and program

Abstract

To provide a method and a device for controlling a stacker, a three-dimensional warehouse automation system, an electronic device, a storage medium, and a program, which are related to the field of an intelligence technique for chemical fiber production.SOLUTION: The method includes: acquiring an intermediate table in response to receiving a task allocation request sent from a stacker; recognizing a plurality of images in a first aisle of a three-dimensional warehouse through an image recognition model to obtain storage state information of a plurality of locations in the first aisle; determining a temporary work task of the stacker based on the intermediate table; determining, based on the storage state information of the plurality of locations in the first aisle, a position of a target location corresponding to the temporary work task; and sending the temporary work task and the position of the target location to the stacker, so that the stacker executes the temporary work task based on the position of the target location.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present disclosure relates to the field of intelligent technologies for chemical fiber production, and particularly to a control method and apparatus for a stacker and an automated three-dimensional warehouse system.

Background Art

[0002] In the field of chemical fiber production, three-dimensional warehouses have advantages such as high space utilization rate and high degree of automation, so three-dimensional warehouses are widely applied in factories for winding package packaging and the like.

Summary of the Invention

Problems to be Solved by the Invention

[0003] As an important piece of equipment in a three-dimensional warehouse, the working state of the stacker affects the efficiency of inbound and outbound operations. Therefore, how to improve the task execution efficiency and safety of the stacker has become a technical problem that needs to be solved urgently.

Means for Solving the Problems

[0004] The present disclosure provides a control method and apparatus for a stacker, an automated three-dimensional warehouse system, an electronic device, a storage medium, and a program.

[0005] According to a first aspect of the present disclosure, there is provided a control method for a stacker applied to an image recognition system, the method including: in response to receiving a task assignment request sent from the stacker, obtaining an intermediate table, where at least unfinished work tasks of a warehouse management system are recorded in the intermediate table, and the task assignment request is sent by the stacker when communication with the warehouse management system is interrupted; recognizing a plurality of images in a first aisle of the three-dimensional warehouse by an image recognition model to obtain storage status information of a plurality of locations in the first aisle; determining a temporary work task of the stacker based on the intermediate table; Based on the storage status information of multiple locations in the first aisle, determining the location of the target location corresponding to the temporary work task, Including transmitting the temporary work task and the location of the target location to the stacker in order to execute the temporary work task based on the location of the target location by the stacker.

[0006] According to a second aspect of the present disclosure, a three-dimensional warehouse automation system is provided, and the system includes A warehouse management system for transmitting a normal work task to the stacker and transmitting an intermediate table to the computing power center when communicating with the stacker, A computing power center for storing the intermediate table, where at least the unfinished work tasks of the warehouse management system are recorded in the intermediate table, A stacker for executing a normal work task when receiving the normal work task transmitted from the warehouse management system. When the communication with the warehouse management system is interrupted, in order to transmit a task assignment request to the image recognition system, receiving the temporary work task and the location of the target location returned by the image recognition system, and executing the temporary work task based on the location of the target location, An image recognition system for obtaining the intermediate table from the computing power center in response to receiving the task assignment request transmitted from the stacker, recognizing multiple images in the first aisle of the three-dimensional warehouse by the image recognition model, obtaining the storage status information of multiple locations in the first aisle, determining the temporary work task of the stacker based on the intermediate table, determining the location of the target location corresponding to the temporary work task based on the storage status information of multiple locations in the first aisle, and transmitting the temporary work task and the location of the target location to the stacker.

[0007] According to a third aspect of the present disclosure, a control device for a stacker applied to an image recognition system is provided, and the control device includes A first acquisition module for acquiring an intermediate table in response to receiving a task assignment request sent from a stacker, wherein at least unfinished work tasks of a warehouse management system are recorded in the intermediate table, and the task assignment request is sent by the stacker when communication with the warehouse management system is interrupted, the first acquisition module; A recognition module for recognizing a plurality of images in a first aisle of a three-dimensional warehouse by an image recognition model to obtain storage status information of a plurality of locations in the first aisle; A first determination module for determining a temporary work task of the stacker based on the intermediate table; A second determination module for determining the position of a target location corresponding to the temporary work task based on the storage status information of a plurality of locations in the first aisle; A first transmission module for transmitting the temporary work task and the position of the target location to the stacker so that the stacker executes the temporary work task based on the position of the target location.

[0008] According to a fourth aspect of the present disclosure, an electronic device is provided, and the device includes: At least one processor; A memory communicatively connected to the at least one processor, wherein instructions executable by the at least one processor are stored in the memory, and when the instructions are executed by the at least one processor, any one of the methods in the embodiments of the present disclosure is executed.

[0009] According to a fifth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute any one of the methods in the embodiments of the present disclosure is provided.

[0010] According to a sixth aspect of the present disclosure, a program is provided, and when the program is executed by a processor, any one of the methods in the embodiments of the present disclosure is realized.

[0011] According to the technology of the present disclosure, when the stacker interrupts communication with the warehouse management system, the stacker can execute a temporary work task based on the storage status information of the location, which helps to improve the task execution efficiency and safety of the stacker.

[0012] It should be understood that the content described herein is not intended to describe the key points or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. For other features of the present disclosure, understanding is promoted through the following description.

Brief Description of the Drawings

[0013] The above and other features, advantages, and aspects of the embodiments of the present disclosure will become more apparent by referring to the following detailed description in connection with the drawings. In the drawings, the same or similar reference numerals represent the same or similar elements.

[0014]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Modes for Carrying Out the Invention

[0015] Hereinafter, exemplary embodiments of the present disclosure will be described with reference to the drawings. Here, various details of the embodiments of the present disclosure are included for ease of understanding, and they should be considered merely exemplary. Therefore, those skilled in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, in the following description, descriptions of known functions and structures are omitted for clarity and simplicity.

[0016] In the embodiments of the specification of the present disclosure, the claims, and the above-mentioned drawings, terms such as "first", "second", and "third" are not necessarily used to describe a specific order or priority, but are for distinguishing similar objects. Furthermore, the terms "comprising" and "having" and their variants are intended for non-exclusive inclusion, for example, including a series of steps or units. A method, system, product, or device need not be limited to the explicitly listed steps or units, and may include other steps or units not explicitly listed or inherent to these processes, methods, products, or devices.

[0017] Before describing the technical aspects of the embodiments of the present disclosure, first, technical terms that may be used in the present disclosure will be described.

[0018] A stereoscopic warehouse, also called a high-rise warehouse or a high-bay warehouse, is a warehouse that stores unit goods in racks with a height ranging from several floors to dozens of floors, and performs the inbound and outbound operations of goods using corresponding material handling equipment. The warehouse body is composed of racks, aisle stacker cranes, inbound (outbound) workbenches, automatic loading (unloading), and operation control systems.

[0019] A Warehouse Management System (WMS) is a system specialized for warehouse management. With efficient task execution and process planning strategies as the core, it collaborates with location management, barcode / QR code (registered trademark) management, and warehouse automation equipment to significantly improve work efficiency and resource utilization rate.

[0020] In the related art, in a chemical industrial production plant for winding package packaging, after the packaging process of the winding package is completed, the stacked winding packages are stored in a three-dimensional warehouse by a stacker. The three-dimensional warehouse includes a plurality of aisles, and at least one stacker in each aisle is responsible for the incoming and / or outgoing of products. The three-dimensional warehouse is also called a high-rise warehouse or a high-bay warehouse, which refers to a warehouse that uses racks with a height of several floors, a dozen floors, or even dozens of floors to store unit goods and performs the incoming and outgoing operations of goods with corresponding material conveying equipment.

[0021] In the related art, the stacker is the main equipment for storing winding packages, and a plurality of stackers move within the aisle. To ensure the safe operation of the stacker within the aisle of the three-dimensional warehouse, it mainly relies on regular patrol inspections based on work tasks or monitoring and control by a warehouse management system. However, the efficiency of manual patrol inspections is low. When monitoring through the warehouse management system, the warehouse management system may collapse, affecting the task execution efficiency and safety of the stacker. In addition, there may be workers or animals straying into the three-dimensional warehouse, so it is necessary to monitor and control the three-dimensional warehouse in real time to ensure the safety of operations.

[0022] The present disclosure proposes a control method, system, and device for a stacker to at least partially solve one or more of the above problems and other potential problems. By recognizing the image of the aisle in the three-dimensional warehouse, storage state information is obtained, and based on the storage state information of the location, the stacker is assisted in executing temporary work tasks, which helps to improve the task execution efficiency and safety of the stacker.

[0023] Embodiments of the present disclosure provide a method for controlling a stacker applied to an image recognition system. FIG. 1 is a flowchart of the method for controlling a stacker according to an embodiment of the present disclosure. This method for controlling a stacker can be applied to a stacker control device. The stacker control device is installed on an electronic device in an image recognition system. The image recognition system is one of the components of a three-dimensional warehouse automation system. In some possible implementations, the method for controlling a stacker can also be implemented by a processor calling computer-readable instructions stored in a memory. As shown in FIG. 1, the method for controlling a stacker includes the following.

[0024] In S101, in response to receiving a task assignment request sent from the stacker, an intermediate table is obtained. The intermediate table records at least unfinished work tasks of the warehouse management system. The task assignment request is sent by the stacker when the communication with the warehouse management system is interrupted.

[0025] In S102, a plurality of images in the first aisle of the three-dimensional warehouse are recognized by an image recognition model to obtain storage status information of a plurality of locations in the first aisle.

[0026] In S103, a temporary work task of the stacker is determined based on the intermediate table.

[0027] In S104, based on the storage status information of a plurality of locations in the first aisle, the position of the target location corresponding to the temporary work task is determined.

[0028] In S105, in order for the stacker to execute the temporary work task based on the position of the target location, the temporary work task and the position of the target location are sent to the stacker.

[0029] In an embodiment of the present disclosure, the image recognition system can obtain an intermediate table from the computing power center. The computing power center can be used for the operation of important software in a chemical industrial production plant and has good stability. The image recognition system can communicate with the computing power center, and the warehouse management system can also communicate with the computing power center. The image recognition system can communicate with the stacker. The warehouse management system can communicate with the stacker. The warehouse management system reports the execution status of tasks at regular intervals, and the computing power center can generate an intermediate table based on the execution status of the tasks. Alternatively, the warehouse management system uploads the intermediate table to the computing power center at regular intervals.

[0030] In an embodiment of the present disclosure, the stacker is an important conveying facility in a three-dimensional warehouse. The stacker can automatically, quickly and accurately load and unload goods in the three-dimensional warehouse, and can improve the utilization rate of the warehouse and the working efficiency. The main components of the stacker can include a fork for picking up, transporting and stacking goods in the warehouse or the working site, a platform for placing goods, a lifting mechanism for realizing the lifting operation of goods, a traveling mechanism for realizing the movement of the stacker in the warehouse, and a control system for controlling various operations and movements of the stacker. Here, the fork can adopt an electric or hydraulic drive mode and can be extended, retracted and rotated as required. The stage can adopt a steel structure or an aluminum alloy structure with sufficient supporting capacity and stability. The lifting mechanism can adopt an electric or hydraulic drive mode and has the characteristics of high precision, good stability and reliability. The traveling mechanism can adopt a wheel or crawler structure and has the characteristics of fast moving speed and stable operation. The control system can adopt control devices such as PLC or single-chip microcomputer and has the characteristics of high degree of automation and simple operation.

[0031] In an embodiment of the present disclosure, the task assignment request is a request sent from a stacker to an image recognition system when the warehouse management system crashes. The task assignment request may be a task assignment request generated by the stacker based on a target scenario. The task assignment request may also be a task assignment request generated based on a manually input command. The above is only an exemplary description and does not limit all possible acquisition methods included in the task assignment request, which will not be enumerated here.

[0032] FIG. 2 is a schematic diagram showing the content of the intermediate table. As shown in FIG. 2, the intermediate table can record the completed work tasks and uncompleted work tasks of the warehouse system, and at least the work tasks not assigned by the warehouse management system are recorded in the intermediate table. Specifically, the content of the completed work tasks recorded in the intermediate table can include the number of completed works, the completion time of the completed work tasks, and the types of completed work tasks such as inbound tasks and outbound tasks. The content of the uncompleted work tasks recorded in the intermediate table can include the deadline of the uncompleted work tasks, the types of the uncompleted work tasks, and the like.

[0033] In an embodiment of the present disclosure, the warehouse management system can provide functions such as inbound management, outbound management, transfer management, inventory adjustment, barcode printing, etc., and can support lot management of products, expiration date management, multiple packaging specifications, multiple packaging barcodes, etc., to realize complete warehouse logistics information management.

[0034] In an embodiment of the present disclosure, the warehouse management system can communicate with the computing power center and the stacker. When the communication between the stacker and the warehouse management system is interrupted, it can include the crash of the warehouse management system and the failure of the stacker. Here, when the warehouse management system crashes, it can include cases where there are defects in the software of the warehouse management system itself, such as being attacked by a virus and causing problems in the software, resulting in a system crash, or problems occurring in the hardware of the warehouse management system, such as servers, network devices, storage devices, power modules, etc., resulting in a system crash, or problems occurring in power fluctuations such as unstable power supply and voltage fluctuations of the warehouse management system, resulting in a system crash.

[0035] In an embodiment of the present disclosure, the image recognition model is used to recognize multiple images in the aisle of the stereoscopic warehouse to obtain storage status information. The training method of the image recognition model includes obtaining the historical storage status information and historical images of multiple sample locations in the stereoscopic warehouse, inputting the historical storage status information and historical images of the multiple sample locations into a preset model to obtain the predicted storage status values of the multiple sample locations, constructing a loss function based on the true storage status values and the predicted storage status values of the multiple sample locations, and training the preset model based on the loss function to obtain the image recognition model. Here, the image recognition model is a pre-trained model.

[0036] In some embodiments, the first aisle is a passage for connecting between the warehouse rack and the stacker. The first aisle is usually located parallel to the stacker rails between the racks. The width and height of the aisle can be determined by the scale and layout of the warehouse. In a stereoscopic warehouse, the aisle is mainly used for the movement of the stacker and the loading and unloading of goods.

[0037] In some embodiments, the plurality of images are images of the first aisle of the automated storage and retrieval system. The plurality of images can be collected by cameras on the control frames arranged in the aisle, or can also be collected by cameras arranged around the stacker. The images can also be collected by a drone. The camera can be attached to the support frame where the stacker is located, or can also be attached to the overhead above the aisle. The plurality of images can be images directly taken by the camera, or can also be several images cut from the video taken by the camera. The plurality of images in the first aisle can be images taken by different cameras in the same time period, or can also be a plurality of images collected by the same camera during the process that the stacker moves several rounds in the first aisle.

[0038] In some embodiments, the storage state information can include the winding packages stored in the location, the winding packages not yet stored in the location, the lot numbers of the winding packages stored in the location, the number of the winding packages stored in the location, the types of the winding packages stored in the location, etc. The main types of filaments according to the embodiments of the present disclosure can include one or more of Partially Oriented Yarns (POY), Fully Drawn Yarns (FDY), Draw Textured Yarns (DTY) (or low-elastic filaments), etc. For example, specific types of filaments can include Polyester Partially Oriented Yarns, Polyester Fully Drawn Yarns, Polyester Drawn Yarns, Polyester Draw Textured Yarns, Polyester Staple Fiber, etc.

[0039] In some embodiments, the ad-hoc task is a task that the stacker should execute when the communication between the stacker and the warehouse management system is interrupted. Here, the ad-hoc task may be a task such as an ad-hoc warehousing task, an ad-hoc outbound task, an ad-hoc location transfer task, etc.

[0040] In some embodiments, the position of the target location is the position of the ad-hoc task. Exemplarily, an inbound task is executed for the DTY wound package with lot number A001, and the DTY wound package with lot number A001 is warehoused in the third warehouse on the tenth floor on the left side of aisle 20.

[0041] In some embodiments, when the ad-hoc task is a product warehousing task, the stacker executing the ad-hoc task based on the position of the target location includes storing the product to be warehoused at the target location.

[0042] When the ad-hoc task is a product outbound task, the stacker executing the ad-hoc task based on the position of the target location includes taking out the product to be outbound from the target location. The communication interruption between the stacker and the warehouse management system includes not receiving a preset signal sent from the warehouse management system within the preset time of the stacker.

[0043] Here, the preset signal may be a Heartbeat Signal, and the warehouse management system can periodically send a heartbeat signal to the stacker to notify the stacker whether the current warehouse management system is in a normal state. The stacker can also determine whether the warehouse management system is in a normal state based on whether it has received the heartbeat signal within the preset time. If the heartbeat signal sent from the warehouse management system is not received within the preset time, it is determined whether an abnormality has occurred in the warehouse management system, and a task assignment request is sent to the image recognition system so as not to affect the inbound and outbound efficiency. The images within the first aisle can be collected by a camera or a drone.

[0044] In response to receiving a task assignment request sent from a stacker, the solution of the embodiment of the present disclosure obtains an intermediate table, recognizes a plurality of images in the first aisle of the stereoscopic warehouse by an image recognition model, obtains the storage status information of a plurality of locations in the first aisle, determines the temporary work task of the stacker based on the intermediate table, determines the position of the target location corresponding to the temporary work task based on the storage status information of the plurality of locations in the first aisle, and sends the temporary work task and the position of the target location to the stacker for the stacker to execute the temporary work task based on the position of the target location. In this way, when the communication between the stacker and the warehouse management system is interrupted, the stacker can execute the temporary work task based on the storage status information of the location, which helps to improve the task execution efficiency and safety of the stacker.

[0045] In some embodiments, the control method of the stacker includes receiving the execution status of a temporary work task sent from the stacker and updating the intermediate table based on the execution status of the temporary work task.

[0046] In some embodiments, the execution status of the temporary work may include the progress status of the temporary task, the start time of the temporary task, the end time of the temporary task, the number of completed temporary tasks, etc. Here, the progress status of the temporary task may include that the temporary task is not completed, the temporary task is completed, the temporary task is in progress, etc.

[0047] In some embodiments, updating the intermediate table based on the execution status of the temporary work task means that when it is detected that the temporary work task is not completed, the temporary work task is determined to be in an incomplete state in the intermediate table; when it is detected that the temporary work task is completed, the temporary work task is determined to be in a completed state in the intermediate table; and when it is detected that the temporary work task is in progress, the temporary work task can be determined to be in progress in the intermediate table.

[0048] In this way, the image recognition system can perform timely statistics and updates on the intermediate table, and can quickly understand the working status of the stacker during its crash period after the recovery operation of the warehouse management system, so that the warehouse management system can quickly assign new work tasks to the stacker, improve the working efficiency of the stacker, and further improve the efficiency of incoming and outgoing storage.

[0049] In some embodiments, the control method of the stacker further includes, in response to receiving a task end request sent from the stacker, sending an updated intermediate table to the warehouse management system, and the warehouse management system performs aggregation processing based on the updated intermediate table and the intermediate table stored by the warehouse management system itself, and determines normal work tasks based on the aggregated intermediate table. The task end request is sent after the communication between the stacker and the warehouse management system is restored.

[0050] In some embodiments, the task end request is a request sent from the stacker to the image recognition system when the warehouse management system is successfully recovered. When the image recognition system receives the task end request sent from the stacker, it stops generating temporary work tasks.

[0051] In some embodiments, after the warehouse storage system resumes communication with the stacker, the image recognition system can send an updated intermediate table to the warehouse storage system. The warehouse storage system compares the updated intermediate table with the intermediate table stored by the warehouse management system itself, and then aggregates them to obtain an aggregated intermediate table, and determines the normal work tasks of the stacker based on the aggregated intermediate table.

[0052] Here, the image recognition system can also send the updated intermediate table to the warehouse management system via the computing power center.

[0053] In some embodiments, when the image recognition system can establish communication with the warehouse management system, the updated intermediate table can also be directly sent to the warehouse management system.

[0054] In some embodiments, the normal operation task is a task issued by the warehouse storage system. At this time, communication between the warehouse storage system and the stacker is normal.

[0055] In some embodiments, when stacker A detects that communication with the warehouse storage system has been successfully restored, it sends a task completion request to the image recognition system. The image recognition system then sends the updated intermediate table to the warehouse storage. The warehouse management system performs an aggregation process based on the updated intermediate table and the intermediate table stored in the warehouse management system itself, determines the normal operation tasks based on the aggregated intermediate table. The content of the updated intermediate table is that for the DTY wound package with lot number A001, "Inbound task execution - Completed"; for the FDY wound package with lot number B005, "Inbound task execution - Not completed"; for the POY wound package with lot number F011, "Outbound task execution - Completed". The content of the intermediate table stored in the warehouse management system itself is that for the DTY wound package with lot number A001, "Inbound task execution - Not completed"; for the FDY wound package with lot number B005, "Inbound task execution - Not completed"; for the POY wound package with lot number F011, "Outbound task execution - Not completed". Based on the aggregated intermediate table in this case, it is determined that the normal operation task is the inbound task for the FDY wound package with lot number B005.

[0056] In this way, after the warehouse storage system is successfully restored, based on the intermediate table sent by the image recognition system, the normal operation tasks can be re-determined, which helps the warehouse storage system quickly enter the normal operation state, improves the work efficiency and accuracy of the stacker, and thereby can improve the efficiency of the incoming / outgoing of the winding packages.

[0057] In some embodiments, after receiving the task assignment request, the control method of the stacker includes: the image recognition system sending an image shooting instruction for instructing the locations to be imaged and the imaging angles, which are some of the locations in all the locations included in the first file, to the stacker, and the stacker taking images of the locations to be imaged at the imaging angles based on the image shooting instruction; and receiving the images of the locations to be imaged in the first file sent from the stacker, where the multiple images include the images of the locations to be imaged.

[0058] Here, the imaging instruction may be an imaging instruction for a specific location specified by the image recognition system.

[0059] In some embodiments, the image shooting instruction can be used to instruct the number of stackers to turn on the power, the shooting angles of the cameras of the stackers, and the locations to be imaged by the cameras of the stackers. Here, the image shooting instruction can also be realized based on the lifting mechanism and the traveling mechanism of the stacker. Exemplarily, the image shooting instruction may be such that the right camera of the stacker is turned on to take three images at an elevation angle of 60 degrees, or may be such that all the cameras of the stacker are turned on to take one image each at elevation angles of 30 degrees, 60 degrees, and 90 degrees respectively.

[0060] In some embodiments, the shooting location can only shoot one location, can also continuously shoot multiple locations, or can also specify the shooting of a specific location. The shooting angle can only shoot one angle, can also continuously shoot multiple angles, or can also specify the shooting of a specific location.

[0061] In some embodiments, the image recognition system can continuously receive images captured by a camera located on the overhead of the first aisle, and based on the images captured by the camera located on the overhead of the first aisle, can analyze the storage status information of at least some locations. When receiving a task assignment request sent from a stacker, in combination with the storage status information of at least some locations, it can determine the locations to be shot from all locations within the first aisle, and further instruct the stacker to shoot images of the locations to be shot.

[0062] As an example, the image recognition system sends image shooting commands to Stacker A, Stacker B, and Stacker C. The image shooting command for Stacker A is an image shooting command to turn on the left and right cameras simultaneously and shoot the 14th location on the 10th floor at a depression angle of 30 degrees. The image shooting command for Stacker B is an image shooting command to turn on all the arranged cameras and shoot three images of the 11th location on the 20th floor at an elevation angle of 75 degrees and a depression angle of 30 degrees respectively. The image shooting command for Stacker C is an image shooting command to turn on the left and right cameras and shoot the 7th, 8th, 9th, and 10th locations on the 27th floor at a depression angle of 80 degrees respectively. Stacker A, Stacker B, and Stacker C each send the captured images to the image recognition system.

[0063] In this way, the stacker captures an image based on an image capture command sent from the image recognition system, and sends the captured image to the image recognition system. This helps the image recognition system to check the storage status information of multiple locations of the first aisle, helps to accurately generate temporary work tasks, and helps to improve the execution accuracy of the work tasks of the stacker.

[0064] In an embodiment of the present disclosure, the control method of the stacker includes: the image recognition system determines the storage status information of at least some locations of the first aisle during a preset period starting from the generation time of the intermediate table and having a preset threshold time length based on the intermediate table; comparing the storage status information obtained by the image recognition model with the storage status information determined based on the intermediate table; and recording the first type of locations where the storage status information obtained by the image recognition model does not match the storage status information determined based on the intermediate table, and the first type of locations are the locations whose storage status should be checked.

[0065] Here, the preset period can be set and adjusted according to the user's needs and task requirements. The preset period starts from the generation time of the intermediate table, and the end point of the preset period can be adjusted according to the user's needs and task requirements.

[0066] In some embodiments, the first type of location is a location for which the storage status should be verified. As an example, the storage status information obtained based on the image recognition model is "the third location on the 10th floor on the left side of aisle 20 - received - FDY wound package with lot number B005, the 17th location on the 21st floor on the right side of aisle 70 - received - DTY wound package with lot number A011, the 21st location on the 16th floor on the right side of aisle 60 - received, the second location on the 32nd floor on the left side of aisle 90 - not received", and the storage status information obtained from the intermediate table is "the third location on the 10th floor on the left side of aisle 20 - received - FDY wound package with lot number B005, the 17th location on the 21st floor on the right side of aisle 70 - received - DTY wound package with lot number A011, the 21st location on the 16th floor on the right side of aisle 60 - not received, the second location on the 32nd floor on the left side of aisle 90 - not received". Compare the storage status information obtained by the image recognition model with the storage status information determined based on the intermediate table, and record the first type of location where the storage status information obtained by the image recognition model does not match the storage status information determined based on the intermediate table, that is, the 21st location on the 16th floor on the right side of aisle 60. The 21st location on the 16th floor on the right side of aisle 60 is the first type of location for which the storage status should be verified.

[0067] In this way, by comparing the storage status information obtained by the image recognition model with the storage status information determined based on the intermediate table, it is possible to obtain the first type of location where the storage status information does not match, and it is possible to timely verify the storage status information of the first type of location, avoid duplication of work, and help improve the task execution efficiency and safety of the stacker.

[0068] In an embodiment of the present disclosure, determining the position of a target location corresponding to a temporary work task based on the storage state information of a plurality of locations of the first aisle includes, when the temporary work task is a temporary warehouse task, selecting a target location for the temporary warehouse task from at least one second-type location where the storage state information obtained by an image recognition model matches the storage state information determined based on an intermediate table, and determining the position of the target location, where the second-type location is a location where no goods are stored.

[0069] In some embodiments, the second-type location is a location where no goods are stored. As an example, when the temporary work task is a temporary warehousing task, the storage state information obtained based on the image recognition model is "the 7th location on the second floor on the left side of aisle 14 - warehoused - FDY wound package with lot number B011, the 14th location on the 36th floor on the right side of aisle 21 - not warehoused, the 19th location on the 22nd floor on the right side of aisle 44 - not warehoused, the 12th location on the 25th floor on the left side of aisle 16 - not warehoused", and the storage state information obtained from the intermediate table is "the 7th location on the second floor on the left side of aisle 14 - warehoused - FDY wound package with lot number B011, the 14th location on the 36th floor on the right side of aisle 21 - warehoused, the 19th location on the 22nd floor on the right side of aisle 44 - not warehoused, the 12th location on the 25th floor on the left side of aisle 16 - not warehoused". From at least one second-type location where the storage state information obtained by the image recognition model matches the storage state information determined based on the intermediate table, target locations for the temporary warehousing task, that is, the 19th location on the 22nd floor on the right side of aisle 44 and the 12th location on the 25th floor on the left side of aisle 16, are selected. The second-type location is a location where no goods are stored.

[0070] In this way, from among at least one second type of location where the storage status information obtained by the image recognition model matches the storage status information determined based on the intermediate table, a target location can be selected for the temporary storage task, which helps improve the efficiency and accuracy of the temporary storage task.

[0071] In an embodiment of the present disclosure, based on the storage status information of a plurality of locations of the first aisle, determining the position of the target location corresponding to the temporary work task means that when the temporary work task is a temporary outbound task, from among at least one third type of location where the storage status information obtained by the image recognition model matches the storage status information determined based on the intermediate table, in combination with the cargo lot number targeted by the temporary outbound task, a target location is selected for the temporary outbound task and the position of the target location is determined. Here, the third type of location is the location where the goods are stored.

[0072] In some embodiments, the third type of location is the location where the goods are stored. As an example, when the temporary work task is a temporary outbound task, the storage status information obtained based on the image recognition model is "the 20th location on the left side of aisle 4, 14th floor - received - FDY winding package with lot number B011, the 6th location on the right side of aisle 41, 20th floor - FDY winding package with lot number B011, the 9th location on the right side of aisle 31, 12th floor - DTY winding package of A011, the 12th location on the left side of aisle 16, 25th floor - not received", and the storage status information obtained from the intermediate table is "the 20th location on the left side of aisle 4, 14th floor - not received, the 6th location on the right side of aisle 41, 20th floor - FDY winding package with lot number B011, the 9th location on the right side of aisle 31, 12th floor - DTY winding package of A011, the 12th location on the left side of aisle 16, 25th floor - not received". Among at least one third type of location where the storage status information obtained by the image recognition model and the storage status information determined based on the intermediate table match, that is, the 6th location on the right side of aisle 41, 20th floor - FDY winding package with lot number B011, the 9th location on the right side of aisle 31, 12th floor - DTY winding package of A011. If the goods lot number targeted by the temporary outbound task is the DTY winding package of A011, then the target location for the temporary outbound task, that is, the 9th location on the right side of aisle 31, 12th floor, is selected. This location is already a location where goods are stored.

[0073] In this way, from among at least one third type of location where the storage status information obtained by the image recognition model and the storage status information determined based on the intermediate table match, in combination with the goods lot number targeted by the temporary outbound task, the target location for the temporary outbound task can be selected, which helps to improve the efficiency and accuracy of the temporary outbound task.

[0074] In an embodiment of the present disclosure, for the image recognition model to recognize a plurality of images in the first aisle of the stereoscopic warehouse and obtain the storage status information of a plurality of locations in the first aisle, the image recognition system inputs the plurality of images and the historical storage status information of the stereoscopic warehouse into the image recognition model, and obtains the storage status information of the plurality of locations output by the image recognition model. Here, the image recognition model is used to identify whether there is cargo stored at a location and the label of the cargo stored at the location.

[0075] In some embodiments, the historical storage status information can refer to the historical records of past cargo in-warehouse and out-warehouse stored in the warehouse management system. The historical storage status information can include the location of the cargo in the stereoscopic warehouse, the inventory quantity, the in-warehouse date, the out-warehouse date, the winding package lot number, etc.

[0076] In some embodiments, the identification of the cargo may be the cargo number, label, two-dimensional code, etc.

[0077] In this way, since the storage status information recognized by the image recognition model refers to the historical storage status information of the stereoscopic warehouse, the accuracy of the image recognition model can be improved.

[0078] FIG. 3 is a schematic diagram showing the training of the image recognition model according to an embodiment of the present disclosure. As shown in FIG. 3, the image recognition model acquires the historical storage status information and historical images of a plurality of sample locations in the stereoscopic warehouse, inputs the historical storage status information and historical images of the plurality of sample locations into a preset model to obtain the predicted storage status values of the plurality of sample locations, constructs a loss function based on the true storage status values and predicted storage status values of the plurality of sample locations, and trains the preset model based on the loss function to obtain the image recognition model, and is obtained by training in this way.

[0079] In some embodiments, the sample locations can be set and adjusted individually according to needs.

[0080] In some embodiments, the historical image is an image corresponding to the historical storage status information of the sample location. The historical image can be obtained by a camera arranged on a stacker, can also be obtained by a camera arranged on the overhead of the aisle, or can also be obtained by a drone. The above is only an exemplary description, and does not limit all possible acquisition methods included in the historical image, which are not enumerated here.

[0081] In this way, the storage status information of the location can be predicted by a pre-trained image recognition model, and the position of the target location corresponding to the temporary work task can be determined based on the storage status information of the location, which helps to improve the working efficiency of the stacker and thus realize the intelligent management of the warehousing / outbound of the winding package.

[0082] Embodiments of the present disclosure also propose an automated stereoscopic warehouse system capable of executing the above-described stacker control method. FIG. 4 is a schematic block diagram of an automated stereoscopic warehouse system 400 according to an embodiment of the present disclosure. As shown in FIG. 4, the automated stereoscopic warehouse system 400 includes a warehouse management system 410 for transmitting normal work tasks to the stacker when communicating with the stacker, and the warehouse management system 410 is further used for transmitting an intermediate table to the computing power center; a computing power center 420 for storing an intermediate table in which at least uncompleted work tasks of the warehouse management system are recorded; a stacker 430 for executing a normal work task when receiving the normal work task transmitted from the warehouse management system, and when the communication with the warehouse management system is interrupted, the stacker 430 transmits a task assignment request to the image recognition system, receives the temporary work task and the position of the target location returned by the image recognition system, and is further used for executing the temporary work task based on the position of the target location; and an image recognition system 440 for, in response to receiving the task assignment request transmitted from the stacker, obtaining the intermediate table from the computing power center, recognizing a plurality of images in the first aisle of the stereoscopic warehouse by using an image recognition model to obtain the storage state information of a plurality of locations in the first aisle, determining the temporary work task of the stacker based on the intermediate table, determining the position of the target location corresponding to the temporary work task based on the storage state information of the plurality of locations in the first aisle, and transmitting the temporary work task and the position of the target location to the stacker.

[0083] Note that the present disclosure does not limit the number of stackers in the automated stereoscopic warehouse system.

[0084] In this way, through the mutual cooperation of the warehouse management system, the computing power center, the stacker, and the image recognition system of the automated stereoscopic warehouse system, when the communication between the stacker and the warehouse management system is interrupted, the stacker can execute the temporary work task based on the storage state information of the location, which helps to improve the task execution efficiency and safety of the stacker.

[0085] The schematic diagrams shown in FIGS. 2 and 3 are merely schematic and not restrictive, and the content in the figures can be appropriately adjusted or changed according to the working needs, and it should be understood that it will not be repeated here. Those skilled in the art can make various obvious changes and / or substitutions based on the examples in FIGS. 2 and 3, and the obtained solutions still belong to the disclosure scope of the embodiments of the present disclosure.

[0086] In an embodiment of the present disclosure, a control device for a stacker is provided. As shown in FIG. 5, the control device for the stacker a first acquisition module 510 for acquiring an intermediate table in response to receiving a task assignment request sent from the stacker, where at least unfinished work tasks of the warehouse management system are recorded in the intermediate table, and the task assignment request is sent by the stacker when the communication with the warehouse management system is interrupted, the first acquisition module 510; a recognition module 520 for recognizing a plurality of images in the first aisle of the three-dimensional warehouse by an image recognition model to obtain storage status information of a plurality of locations in the first aisle; a first determination module 530 for determining a temporary work task of the stacker based on the intermediate table; a second determination module 540 for determining the position of a target location corresponding to the temporary work task based on the storage status information of a plurality of locations in the first aisle; and a first transmission module 550 for transmitting the temporary work task and the position of the target location to the stacker so that the stacker executes the temporary work task based on the position of the target location.

[0087] In some embodiments, the control device for the stacker further includes a first reception module (not shown in FIG. 5) for receiving the execution status of the temporary work task sent from the stacker, and an update module (not shown in FIG. 5) for updating the intermediate table based on the execution status of the temporary work task.

[0088] In some embodiments, in response to receiving a task completion request sent from the stacker, the control device of the stacker sends an updated intermediate table to the warehouse management system, and the warehouse management system performs an aggregation process based on the updated intermediate table and the intermediate table stored by the warehouse management system itself, and further includes a second transmission module (not shown in FIG. 5) for determining a normal operation task based on the aggregated intermediate table. The task completion request is sent after the communication between the stacker and the warehouse management system is restored.

[0089] In some embodiments, after receiving a task assignment request, the control device of the stacker sends an image capture command for instructing the location to be photographed and the photographing angle to the stacker, and is a third transmission module for the stacker to capture an image of the location to be photographed at the photographing angle based on the image capture command. The location to be photographed is a part of the locations in all the locations included in the first aisle. The third transmission module (not shown in FIG. 5) and a second reception module (not shown in FIG. 5) for receiving an image of the location to be photographed in the first aisle sent from the stacker are further provided, and the plurality of images include images of the locations to be photographed.

[0090] In some embodiments, the control device of the stacker is a third determination module (not shown in FIG. 5) for determining the storage state of at least a part of the locations of the first aisle during a preset period based on the intermediate table. The preset period starts from the generation time of the intermediate table and has a preset threshold time length. The third determination module, a comparison module (not shown in FIG. 5) for comparing the storage state information obtained by the image recognition model with the storage state information determined based on the intermediate table, and a recording module (not shown in FIG. 5) for recording the first type of locations where the storage state information obtained by the image recognition model and the storage state information determined based on the intermediate table do not match. The first type of locations are the locations for which the storage state should be confirmed. The recording module is further provided.

[0091] In some embodiments, when the temporary work task is a temporary storage task, the second decision module 540 selects a target location for the temporary storage task from at least one second type of location where the storage status information obtained by the image recognition model matches the storage status information determined based on the intermediate table, and is a first decision sub-module for determining the location of the target location. The second type of location is a location where no goods are stored, and includes the first decision sub-module.

[0092] In some embodiments, when the temporary work task is a temporary outbound task, the second decision module 540 selects a target location for the temporary outbound task in combination with the lot number of the goods targeted by the temporary outbound task from at least one third type of location where the storage status information obtained by the image recognition model matches the storage status information determined based on the intermediate table, and is a second decision sub-module for determining the location of the target location. The third type of location is a location where goods are stored, and includes the second decision sub-module.

[0093] In some embodiments, the recognition module 520 is an input sub-module for inputting a plurality of images and the historical storage status information of the three-dimensional warehouse into the image recognition model to obtain the storage status information of a plurality of locations output by the image recognition model. The image recognition model is used to identify whether goods are stored in a location and the label of the goods stored in the location, and includes the input sub-module.

[0094] In some embodiments, the image recognition model obtains the historical storage state information and historical images of a plurality of sample locations in the three-dimensional warehouse, inputs the historical storage state information and historical images of the plurality of sample locations into a preset model to obtain predicted values of the storage states of the plurality of sample locations, constructs a loss function based on the true values and predicted values of the storage states of the plurality of sample locations, and trains the preset model based on the loss function to obtain an image recognition model, thereby obtaining the trained model through training.

[0095] The functions of each processing module in the stacker control device according to the embodiments of the present disclosure can be understood by referring to the description of the foregoing stacker state prediction method. Each processing module in the stacker control device according to the embodiments of the present disclosure can be implemented by an analog circuit that realizes the functions according to the embodiments of the present disclosure, and it should be understood by those skilled in the art that it can also be implemented by the operation of software on an electronic device that executes the functions according to the embodiments of the present disclosure.

[0096] When the stacker in the stacker control device according to the embodiment of the present disclosure interrupts communication with the warehouse management system, the stacker can execute a temporary work task based on the storage state information of the location, which helps to improve the task execution efficiency and safety of the stacker.

[0097] According to the embodiments of the present disclosure, the present disclosure further provides an electronic device and a non-transitory computer-readable storage medium.

[0098] FIG. 6 is a structural block diagram of an electronic device according to an embodiment of the present disclosure. As shown in FIG. 6, the electronic device includes a memory 610 and a processor 620, and a computer program executable by the processor 620 is stored in the memory 610. The number of the memory 610 and the processor 620 can be one or more. The memory 610 can store one or more computer programs, and when the one or more computer programs are executed by the electronic device, the electronic device is caused to execute the method provided by the above-described method embodiment. The electronic device can further include the following. A communication interface 630 is used for communicating with an external device and performing data interaction and transmission.

[0099] When the memory 610, the processor 620, and the communication interface 630 are independently implemented, the memory 610, the processor 620, and the communication interface 630 are connected to each other via a bus and can communicate with each other. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The bus can be classified into an address bus, a data bus, a control bus, and the like. For ease of explanation, only a single thick line is shown in FIG. 6, but it does not indicate only a single bus or a single type of bus.

[0100] Optionally, in a specific implementation form, when the memory 610, the processor 620, and the communication interface 630 are integrated on one chip, the memory 610, the processor 620, and the communication interface 630 can communicate with each other via an internal interface.

[0101] The above-mentioned processor may be a Central Processing Unit (CPU), and it should be understood that it may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware assemblies, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc. Note that the processor can be a processor that supports the Advanced RISC Machines (ARM) architecture.

[0102] Furthermore, optionally, the memory may include a read-only memory and a random access memory, and may further include a non-volatile random access memory. The memory can be either a volatile memory or a non-volatile memory, or can include both a volatile memory and a non-volatile memory. Here, the non-volatile memory can include ROM (Read-Only Memory), PROM (Programmable ROM), EPROM (Erasable PROM), EEPROM (Electrically EPROM), or flash memory. The volatile memory can include a random access memory (Random Access Memory, RAM) that functions as an external cache. By way of example and not limitation, many forms of RAM are available. For example, Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDR SDRAM), Enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), and Direct RAMBUS RAM (DR RAM).

[0103] In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, all or part of it may be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, the process or function according to the embodiments of the present disclosure is generated in whole or in part. The computer may be a general-purpose computer, a dedicated computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wire (such as coaxial cable, optical fiber, Digital Subscriber Line (DSL)) or wireless (such as infrared, Bluetooth®, microwave, etc.). The computer-readable storage medium may be any available medium accessible by a computer or a data storage device including a server, data center, etc. integrated with one or more available media. The available medium may be a magnetic medium (such as a floppy (registered trademark) disk, hard disk, magnetic tape), an optical medium (such as a Digital Versatile Disc (DVD)), or a semiconductor medium (such as a Solid State Disk (SSD)). It should be noted that the computer-readable storage medium referred to in the present disclosure may be a non-volatile storage medium, in other words, a non-transitory storage medium.

[0104] Those skilled in the art can understand that all or some of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by instructing related hardware through a program. The program may be stored in a computer-readable storage medium, and the above storage medium may be a read-only memory, a magnetic disk, an optical disk, or the like.

[0105] In the description of the embodiments of the present disclosure, the description of reference terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials, or features described in relation to the embodiment or example are included in at least one embodiment or example of the present disclosure. Moreover, the specific features, structures, materials, or features described can be combined in any one or more embodiments or examples in an appropriate manner. Furthermore, those skilled in the art may combine different embodiments or examples described in the present disclosure and the features of different embodiments or examples without conflict.

[0106] In the description of the embodiments of the present disclosure, " / " represents the meaning of "or" unless otherwise specified. For example, A / B may represent either A or B. The "and / or" in the present disclosure only explains the relationship of related objects and indicates that there may be three types of relationships. For example, A and / or B can represent the following. There are three situations where A exists alone, A and B exist simultaneously, and B exists alone.

[0107] In the description of the embodiments of the present disclosure, the terms "first" and "second" are used only for the purpose of description and should not be construed as indicating or implying relative importance, nor should they be construed as implying the number of the technical features shown. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the embodiments of the present disclosure, "a plurality" means two or more unless otherwise specified.

[0108] The above are only exemplary embodiments of the present disclosure and do not limit the present disclosure. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle scope of the present disclosure should all be included within the protection scope of the present disclosure.

[0109] In the description of this specification, terms such as "center", "longitudinal direction", "lateral direction", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial direction", "radial direction", "circumferential direction", etc. indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings. It is only intended to facilitate the description of the present disclosure and simplify the description, and does not indicate or suggest that the mentioned device or element must have a specific orientation, be configured and operate in a specific orientation. Therefore, it should not be construed as a limitation of the present disclosure.

Claims

1. A stacker control method applied to an image recognition system, comprising: obtaining an intermediate table in response to receiving a task allocation request sent from the stacker, the intermediate table recording at least an incomplete work task of the warehouse management system, the task allocation request being sent by the stacker when communication with the warehouse management system is interrupted; Recognizing a plurality of images in a first aisle of a multi-level warehouse using an image recognition model to obtain storage state information of a plurality of locations in the first aisle; determining a temporary work task for the stacker based on the intermediate table; determining a location of a target location corresponding to the temporary work task based on the storage state information of the plurality of locations in the first aisle; transmitting the temporary work task and the location of the target location to the stacker for executing the temporary work task based on the location of the target location by the stacker. How to control the stacker.

2. A method for controlling the stacker, comprising the steps of: receiving an execution status of the temporary work task transmitted from the stacker; and updating the intermediate table based on the execution status of the temporary work task. A method for controlling a stacker according to claim 1.

3. The stacker control method includes: The method further includes transmitting the updated intermediate table to the warehouse management system in response to receiving a task end request transmitted from the stacker, the warehouse management system performing an aggregation process based on the updated intermediate table and an intermediate table stored in the warehouse management system itself, and determining a normal work task based on the aggregated intermediate table, wherein the task end request is transmitted after communication between the stacker and the warehouse management system is restored. A method for controlling a stacker according to claim 2.

4. After receiving the task allocation request, the stacker control method includes: An image capture command is sent to the stacker to indicate a location and an angle at which the image should be captured, and the stacker captures an image of the location at the angle based on the image capture command, the location being a part of all locations included in the first aisle; and receiving an image of the location to be photographed in the first aisle transmitted from the stacker, wherein the plurality of images includes an image of the location to be photographed. A method for controlling a stacker according to claim 1.

5. The stacker control method includes: Determining a storage state of at least a part of the locations of the first aisle for a preset period based on the intermediate table, the preset period starting from a generation time of the intermediate table and having a time length of a preset threshold value; comparing storage state information obtained by the image recognition model with storage state information determined based on the intermediate table; and recording a first type of location where the storage state information obtained by the image recognition model does not match the storage state information determined based on the intermediate table, the first type of location being a location where the storage state should be confirmed. A method for controlling a stacker according to claim 1.

6. determining a location of a target location corresponding to the temporary work task based on the storage state information of the plurality of locations of the first aisle, and when the temporary work task is a temporary warehousing task, selecting the target location for the temporary warehousing task from among at least one second type location whose storage state information obtained by the image recognition model matches storage state information determined based on an intermediate table, and determining a position of the target location, wherein the second type location is a location where no cargo is stored. A method for controlling a stacker according to claim 5.

7. determining a location of a target location corresponding to the temporary work task based on the storage state information of the plurality of locations of the first aisle, When the temporary work task is a temporary retrieval task, selecting the target location for the temporary retrieval task from among at least one third type location whose storage state information obtained by the image recognition model matches the storage state information determined based on the intermediate table, in combination with a cargo lot number targeted by the temporary retrieval task, and determining a position of the target location, wherein the third type location is a location where cargo is stored. A method for controlling a stacker according to claim 5.

8. Recognizing a plurality of images in a first aisle of a multi-level warehouse using the image recognition model to obtain storage state information of a plurality of locations in the first aisle, inputting the plurality of images and historical storage status information of the multi-story warehouse into the image recognition model, and obtaining storage status information of the plurality of locations output by the image recognition model, wherein the image recognition model is used to identify whether or not cargo is stored at a location and an identification of the cargo stored at the location. A method for controlling a stacker according to claim 1.

9. The image recognition model is Acquire historical storage state information and historical images of a plurality of sample locations in the multi-level warehouse; inputting the historical storage condition information and the historical images of the plurality of sample locations into a preset model to obtain a storage condition prediction for the plurality of sample locations; constructing a loss function based on the true storage condition values ​​and the predicted storage condition values ​​of the plurality of sample locations; The preset model is trained based on the loss function to obtain the image recognition model, A method for controlling a stacker according to claim 1.

10. A multi-level warehouse automation system, comprising: a warehouse management system for transmitting a normal work task to the stacker and transmitting an intermediate table to the computing center when communicating with the stacker; A computing center for storing the intermediate table, the intermediate table recording at least the uncompleted work tasks of the warehouse management system; a stacker for executing the normal work task when the normal work task transmitted from the warehouse management system is received, and when communication with the warehouse management system is interrupted, the stacker receives a temporary work task and a target location position returned by the image recognition system in order to send a task allocation request to the image recognition system, and executes the temporary work task based on the target location position; an image recognition system for acquiring an intermediate table from the computing center in response to receiving a task allocation request transmitted from a stacker, the image recognition system recognizing a plurality of images in a first aisle of a multi-level warehouse using an image recognition model to obtain storage state information of a plurality of locations in the first aisle, determining a temporary work task for the stacker based on the intermediate table, determining a position of a target location corresponding to the temporary work task based on the storage state information of the plurality of locations in the first aisle, and transmitting the temporary work task and the position of the target location to the stacker. Multi-level warehouse automation system.

11. A stacker control device applied to an image recognition system, comprising: a first acquisition module for acquiring an intermediate table in response to receiving a task allocation request sent from a stacker, the intermediate table recording at least uncompleted work tasks of a warehouse management system, the task allocation request being sent by the stacker when communication with the warehouse management system is interrupted; a recognition module for recognizing a plurality of images in a first aisle of a multi-level warehouse using an image recognition model to obtain storage state information of a plurality of locations in the first aisle; a first determination module for determining a temporary work task of the stacker based on the intermediate table; a second determination module for determining a position of a target location corresponding to the temporary work task based on the storage state information of the plurality of locations in the first aisle; a first transmission module for transmitting the temporary work task and a position of the target location to the stacker so that the stacker executes the temporary work task based on the position of the target location. Stacker control device.

12. At least one processor; a memory in communication with the at least one processor; The memory stores instructions executable by the at least one processor, the instructions, when executed by the at least one processor, causing the at least one processor to perform a method according to any one of claims 1 to 9. Electronic devices.

13. A non-transitory computer readable storage medium for storing instructions that cause a computer to perform the method of any one of claims 1 to 9.

14. A program for implementing the method according to any one of claims 1 to 9 when executed by a processor in a computer.

Images