Warehouse checking method, checking system, electronic equipment and intelligent warehouse system

Abstract

The invention relates to the technical field of intelligent warehousing, and particularly discloses a warehousing inventory method, an inventory system, electronic equipment and an intelligent warehouse system.The warehousing inventory method comprises the steps that an inventory rule is configured, and whether current inventory is static inventory or dynamic inventory is judged according to the inventory rule; based on different inventory types, creating corresponding inventory tasks and issuing the inventory tasks; executing an inventory transportation task, and transporting the materials by the AGV according to a path planning method; after the AGV transports the materials to the inventory work station, manual inventory is carried out; checking whether all the inventory tasks are completed or not, and if not, continuing to execute the remaining inventory tasks; and if all the checking is completed, outputting a checking report and ending the whole checking process. According to the warehouse checking method and system, warehouse checking and path planning are effectively fused, the checking efficiency of the intelligent warehouse is improved, the path planning rationality of the intelligent warehouse AGV is effectively improved by using the ABC classification method and the priority avoidance principle, and the AGV utilization rate of intelligent warehouse checking is optimized.

Description

Technical Field

[0001] The present invention relates to the field of intelligent warehousing technology, and in particular to a warehouse inventory method, a warehouse inventory system, an electronic device and an intelligent warehouse system. Background Art

[0002] The smart warehouse system is a highly integrated and automated warehouse management system, the core of which is to use advanced information technology and mechanical equipment to improve warehouse efficiency. Among them, the automated guided vehicle (AGV) plays a key role in the cargo handling process.

[0003] During warehouse inventory, materials are usually transported by AGVs. Current warehouse AGV path planning algorithms include A* algorithm, ant colony algorithm, etc. These algorithms mainly focus on a single AGV, planning a path for the AGV to successfully avoid fixed obstacles, while for dynamic obstacles, that is, other AGVs, they can only avoid them by waiting, specifying the path direction, etc., resulting in low transportation efficiency, which in turn affects the normal storage and warehousing process of the smart warehouse. Summary of the invention

[0004] The present invention aims to solve one of the technical problems in the related art to at least a certain extent. To this end, the purpose of the present invention is to provide a warehouse inventory method, inventory system, electronic equipment and intelligent warehouse system to improve the inventory efficiency of intelligent warehouse materials.

[0005] To achieve the above object, a first embodiment of the present invention provides a warehouse inventory method, the method comprising the following steps: Configure inventory counting rules and determine whether this inventory counting is static or dynamic based on the inventory counting rules; Create and issue corresponding inventory tasks based on different inventory types; Perform inventory and transportation tasks, and the AGV transports materials according to the path planning method. The path planning process varies according to the type of inventory; After the AGV transports the materials to the inventory workstation, a manual inventory is conducted. If an inventory discrepancy occurs, the cause is investigated and the inventory record is updated. If no inventory discrepancy occurs, the inventory result is entered into the system and an AGV return instruction is issued. Check whether all inventory tasks are completed. If not, continue to execute the remaining inventory tasks; if all are completed, output the inventory report and end the entire inventory process.

[0006] As an embodiment of the present invention, creating corresponding inventory tasks based on different inventory types includes: For static inventory counting, inventory counting tasks are created and issued manually; For dynamic inventory counting, manually create a dynamic inventory counting plan and set the inventory counting time point. When the set time point is reached, the system will automatically create and issue the inventory counting task.

[0007] As an embodiment of the present invention, the path planning method comprises the following steps: Draw a grid map based on the warehouse map, and build a road network model based on the grid map; In the road network model, obtain the real-time location coordinates of the AGV and the real-time location coordinates of the target material; According to the real-time location coordinates of the AGV and the target material and the storage environment status, a path planning model is designed based on the Actor-Critic algorithm; Train the path planning model, calculate the loss function, and update the network parameters; The trained path planning model is applied to the path planning of AGV in the warehouse, and the optimal path of AGV is output.

[0008] As an embodiment of the present invention, the path planning model is used to plan the action routes of all AGVs involved in the inventory task in the warehouse. The basic logic of the model includes: Use Actor-Critic algorithm to train strategy network and value network; The central controller sets the starting point and end point for each AGV based on the real-time location of the AGV and the information of the warehouse to be counted; The policy network receives the starting and ending information of the AGV and outputs the action of the AGV at the jth moment. ;

[0009] The experience replayer records the global status, rewards, and evaluation information of each AGV action; The value network receives the action information of AGV And output the action Reviews ; The central controller receives the actions of i AGVs , and output the action routes of all AGVs involved in the inventory task.

[0010] As an embodiment of the present invention, when the inventory type is dynamic inventory, the process of AGV in path planning includes: Input real-time map information, including the location of each AGV, warehouse map, and obstacle location; Implement ABC classification priority path planning, AGV first counts the important A category, and then counts the secondary BC category; According to real-time map information and inventory priority, control the AGV to move towards the direction of the maximum reward target; If an obstacle is encountered, the central controller assigns obstacle avoidance priority according to the properties of the obstacle, ensuring that the AGV for the outbound task has the highest priority, followed by the inbound AGV, and then the inventory AGV, until the AGV reaches the target.

[0011] As an embodiment of the present invention, when the inventory type is a static inventory, the process of the AGV during path planning includes: Input real-time map information, including the location of each AGV, warehouse map, and obstacle location; Control the AGV to move to the target location according to the preset path and rules; If an obstacle is encountered, the AGV will avoid it according to the new route assigned by the system until it reaches the target.

[0012] As an embodiment of the present invention, in the path planning step of the AGV performing dynamic inventory, "the reward obtained by the AGV performing the inventory task for the avoidance action taken by the AGV performing the warehousing and out-of-warehouse task" is greater than "the reward for the action taken by the AGV performing the inventory task for directly approaching the target".

[0013] To achieve the above-mentioned purpose, a second aspect of the present invention provides a warehouse inventory system, including: Inventory plan management module, used to provide transmission and reception of inventory tasks and inventory reports; Path planning management module, used to provide path planning management for inventory AGV; Inventory visualization platform, used to provide a large-screen visualization to display the current inventory information in the warehouse; Inventory task database, used to quickly read and output inventory tasks and inventory reports; AGV parameter database, used to store AGV attribute information; Warehouse map database, used to realize structured storage of shelf information, storage location dimensions, workstation information, charging station information, etc. in the warehouse; The storage location information database is used to realize structured reading and storage of storage location occupancy status within the warehouse.

[0014] To achieve the above-mentioned purpose, a third aspect of the present invention proposes an electronic device, comprising a memory, a processor and a computer program stored in the memory, wherein when the computer program is executed by the processor, the above-mentioned warehouse inventory method is implemented.

[0015] To achieve the above-mentioned purpose, the fourth aspect of the present invention proposes an intelligent warehouse system, including a hardware device, the above-mentioned electronic device and the following system: Enterprise Resource Planning System: manage raw material orders, inventory, production plans and customer orders; Warehouse management system: handles the receipt, delivery and picking of inventory materials, tracks production line demand and order shipments, and synchronizes inventory and transportation tasks; Production execution system: responsible for production line scheduling, material tracking and quality control; Warehouse inventory system: formulate inventory plans and routes, and update the visualization platform; Warehouse control system: performs in-warehouse transportation and inventory tasks, and controls hardware equipment; Order management system: handles customer order preparation and communication; Transportation management system: arrange logistics transportation to customers.

[0016] The warehouse inventory method, inventory system, electronic device and intelligent warehouse system of the embodiment of the present invention effectively integrate warehouse inventory and path planning, and effectively improve the rationality of path planning of AGV in intelligent warehouse by using ABC classification method and priority avoidance principle, and optimize the utilization rate of AGV in intelligent warehouse inventory. In addition, the intelligent warehouse system has simple principle, simple equipment layout, and real and effective scene, which is suitable for inventory work of various warehouses and improves the efficiency of intelligent warehouse inventory. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a flowchart of a warehouse inventory counting method according to an embodiment of the present invention; Figure 2 It is a schematic diagram of the process of AGV path planning during dynamic inventory in one embodiment of the present invention; Figure 3 It is a schematic diagram of the process of AGV path planning during static inventory counting according to an embodiment of the present invention; Figure 4 is an architecture diagram of a warehouse inventory counting system according to another embodiment of the present invention; Figure 5 is a schematic diagram of an inventory visualization platform according to another embodiment of the present invention; Figure 6 is a schematic diagram of a storage map according to another embodiment of the present invention; Figure 7 is an architecture diagram of a smart warehouse system according to another embodiment of the present invention; Figure 8 It is a schematic diagram of the process of the intelligent warehouse system of another embodiment of the present invention when performing warehousing in and out tasks and inventory tasks; Fig. 9 It is a schematic structural diagram of an electronic device according to another embodiment of the present invention. DETAILED DESCRIPTION

[0018] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0019] The following describes the warehouse inventory method, inventory system, electronic device and intelligent warehouse system of the embodiments of the present invention with reference to the accompanying drawings.

[0020] Figure 1 It is a flowchart of a warehouse inventory counting method according to an embodiment of the present invention.

[0021] like Figure 1 As shown, the warehouse inventory method includes the following steps: S1. Configure the inventory counting rules and determine whether this inventory counting is a static inventory counting or a dynamic inventory counting according to the inventory counting rules.

[0022] Among them, inventory rules include inventory cycle, inventory scope, inventory method, etc.

[0023] It should be noted that static inventory refers to the process of manually creating and executing inventory tasks. Since it requires human participation, its efficiency is relatively low; Dynamic inventory counting in the warehousing system refers to the process in which the system automatically triggers and executes inventory counting tasks according to a certain plan or time point. Different from static inventory counting, dynamic inventory counting is more flexible and can be automatically carried out according to actual needs and set time points, reducing real-time human involvement and improving inventory counting efficiency.

[0024] S2. Create and issue corresponding inventory tasks based on different inventory types.

[0025] S21. When this inventory count is a static inventory count, manually create inventory count tasks and assign them to corresponding inventory count workstations and AGVs.

[0026] S22. When this inventory count is a dynamic inventory count, a dynamic inventory count plan is created manually and the inventory count time point is set. When the set time point is reached, the system automatically creates an inventory count task and assigns it to the corresponding inventory workstation and AGV.

[0027] S3. Execute the inventory and transportation task. The AGV transports the materials according to the path planning method. The path planning process varies according to the different inventory types.

[0028] As an embodiment of the present invention, the path planning method includes the following steps: S31, drawing a grid map based on the warehouse map, and constructing a road network model according to the grid map; S32. In the road network model, obtain the real-time position coordinates of the AGV and the real-time position coordinates of the target material; S33, design a path planning model based on the Actor-Critic algorithm according to the real-time position coordinates of the AGV and the target material and the storage environment status; S34, train the path planning model, calculate the loss function, and update the network parameters. In this step, the loss function is used to evaluate the difference between the output of the path planning model (i.e., the result of path planning) and the desired target (i.e., the optimal path). By calculating the loss function, the network parameters can be adjusted to make the output of the path planning model closer to the desired target. This process needs to be repeated until the model converges, that is, the output result reaches the optimal or near-optimal state; S35. Apply the trained path planning model to the path planning of the AGV in the warehouse, and output the optimal path of the AGV.

[0029] S4. After the AGV transports the materials to the inventory workstation, a manual inventory is performed. If an inventory discrepancy occurs, the cause is investigated and the inventory record is updated. If no inventory discrepancy occurs, the inventory result is entered into the system and an AGV return instruction is issued. S5. Check whether all inventory tasks are completed. If not, continue to execute the remaining inventory tasks; if all are completed, output the inventory report and end the entire inventory process.

[0030] This warehouse inventory method supports both static and dynamic inventory methods, and uses a path planning model based on the Actor-Critic algorithm to perform intelligent path planning for dynamic environments (including other AGVs as dynamic obstacles), avoiding the inefficient strategy of traditional algorithms where AGVs can only wait or follow fixed paths to avoid dynamic obstacles, thereby improving transportation efficiency and the smoothness of the warehouse entry and exit process. In addition, the path planning model can obtain the real-time location coordinates of the AGV and the target material, as well as the status of the warehouse environment, in real time, and output the optimal path for the AGV. This real-time performance ensures that the AGV can efficiently perform inventory transportation tasks, reduces unnecessary waiting and delays, and improves the efficiency and accuracy of warehouse inventory.

[0031] As an embodiment of the present invention, the path planning model is used to plan the action routes of all AGVs involved in the inventory task in the warehouse. The basic logic of the model includes: Use Actor-Critic algorithm to train strategy network and value network; The central controller sets the starting point and end point for each AGV based on the real-time location of the AGV and the information of the warehouse to be counted; The policy network receives the starting and ending information of the AGV and outputs the action of the AGV at the jth moment. ; The experience replayer records the global status, rewards, and evaluation information of each AGV action; The value network receives the action information of AGV , and output the action Reviews ; The central controller receives the actions of i AGVs , and output the action routes of all AGVs involved in the inventory task.

[0032] As an embodiment of the present invention, Figure 2 As shown, when the inventory type is dynamic inventory, the process of AGV path planning includes: Input real-time map information, including the location of each AGV, warehouse map, and obstacle location; Implement ABC classification priority path planning, AGV first counts the important A category, and then counts the secondary BC category; According to real-time map information and inventory priority, control the AGV to move towards the direction of the maximum reward target; If an obstacle is encountered, the central controller assigns obstacle avoidance priority according to the properties of the obstacle, ensuring that the AGV for the outbound task has the highest priority, followed by the inbound AGV, and then the inventory AGV, until the AGV reaches the target.

[0033] To further refine the above scheme, the warehouse divides the materials into Class A, Class B, and Class C materials according to their importance. During dynamic inventory, the path planning combined with the ABC classification method is adopted to control the AGV to transport the important Class A materials to the inventory workstation for inventory. After all Class A materials are counted, the less important Class B and C materials are counted. The reward for the AGV to Class A goods is greater than that of Class B and Class C.

[0034] It is also important to note that in the path planning process of the AGV performing dynamic inventory, the "reward for the AGV performing the inventory task to avoid the AGV performing the in-and-out task and take the evasive action" is greater than the "reward for the AGV performing the inventory task to directly approach the target". That is, in the path planning process, if the AGV needs to avoid the AGV performing the in-and-out task and temporarily deviates from the target, then the "reward" obtained by this avoidance behavior is higher than the "reward" obtained by it directly approaching the target. This is actually a strategic tilt, which is intended to encourage AGVs to give priority to avoidance when encountering other AGVs to ensure the overall smoothness and safety of the storage area.

[0035] As an embodiment of the present invention, Figure 3 As shown, when the inventory type is static inventory, the process of AGV path planning includes: Input real-time map information, including the location of each AGV, warehouse map, and obstacle location; Control the AGV to move to the target location according to the preset path and rules; If an obstacle is encountered, the AGV will avoid it according to the new route assigned by the system until it reaches the target.

[0036] It should be noted that in the warehouse inventory method, the path planning method in S3 is the basis and core of the dynamic inventory path planning process and the static inventory path planning process. The path planning method provides a method for how the AGV plans the optimal path according to the real-time map information, AGV location, target material location, and warehouse environment status during the entire inventory process. The dynamic inventory path planning process and the static inventory path planning process are based on the path planning steps, and are specific applications and optimizations of path planning according to the different needs and characteristics of inventory.

[0037] Specifically, the path planning method provides basic path planning capabilities for AGVs by building a road network model, obtaining real-time location coordinates, and designing a path planning model. On this basis, the dynamic inventory path planning process dynamically adjusts and optimizes the AGV path according to the inventory priority (such as ABC classification) and real-time map information to ensure efficient execution of the inventory task. The static inventory path planning process focuses more on path planning for AGVs based on preset paths and rules to ensure the accuracy and stability of the inventory task.

[0038] Corresponding to the above embodiment, the present invention further provides an electronic device.

[0039] like Fig. 9 The figure shows a schematic diagram of the structure of an electronic device in the present invention, where the electronic device 200 includes: a processor 201 and a memory 203. The processor 201 and the memory 203 are connected, such as through a bus 202. Optionally, the electronic device 200 may further include a transceiver 204. It should be noted that in actual applications, the transceiver 204 is not limited to one, and the structure of the electronic device 200 does not constitute a limitation on the embodiments of the present invention.

[0040] The processor 201 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of the present invention. The processor 201 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0041] The bus 202 may include a path to transmit information between the above components. The bus 202 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 202 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 2 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0042] The memory 203 is used to store a computer program corresponding to the warehouse inventory counting method of the above embodiment of the present invention, and the computer program is controlled and executed by the processor 201. The processor 201 is used to execute the computer program stored in the memory 203 to implement the content shown in the above method embodiment.

[0043] The electronic device 200 includes, but is not limited to, mobile terminals such as laptop computers, PADs (tablet computers), and fixed terminals such as desktop computers. Figure 2 The electronic device 200 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0044] The electronic device 200 of the embodiment of the present invention can effectively integrate warehouse inventory and AGV path planning. By utilizing the ABC classification method and the priority avoidance principle, it effectively improves the rationality of the path planning of the AGV in the intelligent warehouse, optimizes the AGV utilization rate of the intelligent warehouse inventory, is suitable for inventory work in various warehouses, and greatly improves the inventory efficiency of the intelligent warehouse.

[0045] To achieve the above purpose, if Figure 7 , Figure 8 As shown, the present invention also proposes an intelligent warehouse system, including a hardware device, the above-mentioned electronic device and the following system: Hardware equipment includes AGV, stacker, shuttle, unpacker and roller line.

[0046] Enterprise Resource Planning System: In this embodiment, it is an ERP system. The enterprise resource planning system is used to receive raw material order information from suppliers, obtain inventory information in warehouses, track production line production plans in real time, and synchronize customer order information.

[0047] Warehouse management system: In this embodiment, it is a WMS system. The warehouse management system is used for the receipt and delivery of inventory materials, picking operations, obtaining production line material requirements, tracking order delivery status, synchronizing inventory plans, issuing delivery information, and in-warehouse transportation tasks.

[0048] Production Execution System: In this embodiment, it is an MES system, which is used for production line production scheduling, material tracking, and quality control.

[0049] Warehouse inventory system: In this embodiment, it is the WSS system. The warehouse inventory system is used to formulate inventory plans, plan inventory routes, and update the inventory visualization platform.

[0050] Warehouse control system: In this embodiment, it is the WCS system. The warehouse control system is used to accept in-warehouse transportation tasks, in-warehouse inventory tasks, and control the hardware equipment in the warehouse to perform tasks.

[0051] Order management system: In this embodiment, it is an OMS system, which is used for customer order preparation and order communication.

[0052] Transportation management system: In this embodiment, it is a TES system. The transportation management system is used to receive delivery information and arrange logistics transportation to customers.

[0053] This intelligent warehouse system has a simple principle, simple equipment layout, and real and effective scenes. It is suitable for inventory work in various warehouses and has greatly improved the inventory efficiency of intelligent warehouses.

[0054] To achieve the above purpose, if Figure 4 , Figure 5 , Figure 6 As shown, the present invention also proposes a warehouse inventory system, which is applied to the above-mentioned intelligent warehouse system, including an inventory planning management module, a path planning management module, an inventory visualization platform, an inventory task database, an AGV parameter database, a warehouse map database and a storage location information database.

[0055] The functions of the inventory plan management module include manually creating static inventory tasks based on the inventory plan issued by the WMS system, automatically generating dynamic inventory tasks, tracking and updating the real-time progress of the inventory, automatically generating inventory reports after the inventory is completed, and transmitting and receiving inventory reports.

[0056] Among them, the inventory planning management module includes: Inventory report module, which generates summary reports on inventory results; Dynamic inventory task module, which realizes the generation and status tracking of dynamic inventory tasks; The static inventory task module realizes the generation and status tracking of static inventory tasks.

[0057] The path planning management module is used to provide path planning management for inventory AGVs, including: The policy network outputs the AGV action according to the ABC classification method and priority avoidance principle; The central controller receives the actions of the AGV and outputs the action routes of all AGVs involved in the inventory; The value network outputs the evaluation of the AGV’s actions based on the AGV’s actions; The experience replayer records the global status, reward, and evaluation information of each AGV action.

[0058] like Figure 5 As shown, the functions of the inventory visualization platform include storage location information coordination, inventory task records, inventory rate records, and data interaction between the warehouse management system and the warehouse inventory system to obtain real-time storage location status information of the warehouse. These all display the current relevant inventory information of the warehouse in the form of a visual large screen.

[0059] Among them, the inventory visualization platform includes: The warehouse location information collaboration module is used to display the status of each warehouse location in the smart warehouse; The inventory task record module is used to display the currently established inventory tasks and their status; The inventory counting rate recording module displays the inventory counting completion rate of the current task according to the ABC material classification.

[0060] The inventory task database, based on the static inventory plan and dynamic inventory plan issued by the upstream WMS system, enables rapid reading and output of inventory tasks and inventory reports.

[0061] The AGV parameter database, based on the AGV attribute information uploaded by the WCS system, stores the AGV's size, real-time location, task status and other information, and converts it into a readable file for the path planning management module to call.

[0062] The warehouse map database is based on the warehouse map information to realize structured storage of shelf information, storage location dimensions, workstation information, charging station information and other data within the warehouse, and converts it into readable files for call by the path planning management module and inventory visualization platform.

[0063] The warehouse location information database, based on the warehouse location information issued by the WMS system, realizes structured reading and storage of warehouse location occupancy status in the warehouse, and converts it into readable files for the inventory planning management module to call.

[0064] Compared with existing technologies, this warehouse inventory counting system has the following advantages: Full automation: The inventory counting system can automatically generate dynamic and static inventory counting tasks, and track and update the inventory counting progress throughout the process, reducing manual intervention and improving inventory counting efficiency.

[0065] Intelligent path planning: Through the strategy network and value network, the inventory system can provide intelligent path planning for AGV to ensure the efficient execution of inventory tasks.

[0066] Real-time visualization: The inventory visualization platform can display the warehouse inventory information in real time, including storage location status, inventory tasks and their status, inventory completion rate, etc., which improves the transparency of management and the timeliness of decision-making.

[0067] Data integration and collaboration: The inventory counting system can integrate data from systems such as WMS and WCS to achieve structured storage and collaboration of information such as storage location information, AGV parameters, and warehouse maps, thereby improving the accuracy and consistency of information.

[0068] Efficient report generation: The inventory plan management module can automatically generate inventory reports after the inventory is completed, and supports the transmission and reception of reports to facilitate subsequent analysis and auditing.

[0069] In summary, the warehouse inventory counting system has the advantages of comprehensive automation, intelligent path planning, real-time visualization, data integration and collaboration, and efficient report generation, which can significantly improve the efficiency and accuracy of warehouse inventory counting.

[0070] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or otherwise processing in a suitable manner if necessary, and then stored in a computer memory.

[0071] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0072] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0073] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0074] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A warehouse inventory method, characterized in that: The method comprises the following steps: Configure inventory counting rules and determine whether this inventory counting is static or dynamic based on the inventory counting rules; Create and issue corresponding inventory tasks based on different inventory types; Perform inventory and transportation tasks, and the AGV transports materials according to the path planning method. The path planning process varies according to the type of inventory; After the AGV transports the materials to the inventory workstation, a manual inventory is conducted. If an inventory discrepancy occurs, the cause is investigated and the inventory record is updated. If no inventory discrepancy occurs, the inventory result is entered into the system and an AGV return instruction is issued. Check whether all inventory tasks are completed. If not, continue to execute the remaining inventory tasks; if all are completed, output the inventory report and end the entire inventory process.

2. The warehouse inventory method according to claim 1, characterized in that: The creation of corresponding inventory tasks based on different inventory types includes: For static inventory counting, inventory counting tasks are created and issued manually; For dynamic inventory counting, manually create a dynamic inventory counting plan and set the inventory counting time point. When the set time point is reached, the system will automatically create and issue the inventory counting task.

3. The warehouse inventory method according to claim 1, characterized in that: The path planning method comprises the following steps: Draw a grid map based on the warehouse map, and build a road network model based on the grid map; In the road network model, obtain the real-time location coordinates of the AGV and the real-time location coordinates of the target material; According to the real-time location coordinates of the AGV and the target material and the storage environment status, a path planning model is designed based on the Actor-Critic algorithm; the path planning model is trained, the loss function is calculated, and the network parameters are updated; The trained path planning model is applied to the path planning of AGV in the warehouse, and the optimal path of AGV is output.

4. The warehouse inventory method according to claim 3, characterized in that: The path planning model is used to plan the action routes of all AGVs involved in the inventory task in the warehouse. The basic logic of the model includes: Use Actor-Critic algorithm to train strategy network and value network; The central controller sets the starting point and end point for each AGV based on the real-time location of the AGV and the information of the warehouse to be counted; The policy network receives the starting and ending information of the AGV and outputs the action of the AGV at the jth moment. ; The experience replayer records the global status, rewards, and evaluation information of each AGV action; The value network receives the action information of AGV , and output the action Reviews ; The central controller receives the actions of i AGVs , and output the action routes of all AGVs involved in the inventory task.

5. The warehouse inventory method according to claim 1, characterized in that: When the inventory type is dynamic inventory, the process of AGV path planning includes: Input real-time map information, including the location of each AGV, warehouse map, and obstacle location; Implement ABC classification priority path planning, AGV first counts the important A category, and then counts the secondary BC category; According to real-time map information and inventory priority, control the AGV to move towards the direction of the maximum reward target; If an obstacle is encountered, the central controller assigns obstacle avoidance priority according to the properties of the obstacle, ensuring that the AGV for the outbound task has the highest priority, followed by the inbound AGV, and then the inventory AGV, until the AGV reaches the target.

6. The warehouse inventory method according to claim 1, characterized in that: When the inventory type is static inventory, the process of AGV path planning includes: Input real-time map information, including the location of each AGV, warehouse map, and obstacle location; Control the AGV to move to the target location according to the preset path and rules; If an obstacle is encountered, the AGV will avoid it according to the new route assigned by the system until it reaches the target.

7. The warehouse inventory method according to claim 5, characterized in that: In the path planning step of the AGV performing dynamic inventory, "the reward obtained by the AGV performing the inventory task for taking the avoidance action to avoid the AGV performing the in-and-out task" is greater than "the reward for the AGV performing the inventory task for directly approaching the target".

8. A warehouse inventory system, characterized in that: include: Inventory plan management module, used to provide transmission and reception of inventory tasks and inventory reports; Path planning management module, used to provide path planning management for inventory AGV; Inventory visualization platform, used to provide a large-screen visualization to display the current inventory information in the warehouse; Inventory task database, used to quickly read and output inventory tasks and inventory reports; AGV parameter database, used to store AGV attribute information; Warehouse map database, used to realize structured storage of shelf information, storage location dimensions, workstation information, charging station information, etc. in the warehouse; The storage location information database is used to realize structured reading and storage of storage location occupancy status within the warehouse.

9. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory, wherein when the computer program is executed by the processor, the warehouse inventory counting method as described in any one of claims 1 to 7 is implemented.

10. An intelligent warehouse system, characterized in that: The device comprises a hardware device, the electronic device according to claim 9, and the following system: Enterprise Resource Planning System: manage raw material orders, inventory, production plans and customer orders; Warehouse management system: handles the receipt, delivery and picking of inventory materials, tracks production line demand and order shipments, and synchronizes inventory and transportation tasks; Production execution system: responsible for production line scheduling, material tracking and quality control; Warehouse inventory system: formulate inventory plans and routes, and update the visualization platform; Warehouse control system: performs in-warehouse transportation and inventory tasks, and controls hardware equipment; Order management system: handles customer order preparation and communication; Transportation management system: arrange logistics transportation to customers.

Images