Order data processing method and related device

Abstract

The embodiment of the invention provides an order data processing method, and the method comprises the steps: obtaining order data, and generating a total list based on an inventory unit contained in the order data; then determining commodity attributes corresponding to the inventory unit, and determining a plurality of target goods locations indicated by the total list in the three-dimensional storage area; a first transportation device is controlled to obtain the commodity material box from the target goods allocation, and the commodity material box is transported to a goods cache region corresponding to the commodity attribute; then, in response to input of an execution task corresponding to the order data, second transportation equipment is controlled to obtain a commodity material box indicated by the execution task from a cargo cache region, and the commodity material box is sorted and then transported to a conveying line; and the execution task is processed through the conveying line so as to execute a warehouse-out process corresponding to the order data. Therefore, the relay transportation process of various transportation devices is realized, different transportation devices can fully combine own functional characteristics to execute transportation tasks, and the processing efficiency of order data is improved.

Description

TECHNICAL FIELD

[0001] The present specification relates to the technical field of computer application, in particular, to the order data processing technology in the technical field of computer application, and more particularly to an order data processing method and related device. BACKGROUND

[0002] In the management process of automatic storage, due to the diversity of goods and the frequency of outbound operations, how to efficiently perform the task of automatic storage becomes a problem. In particular, in the vertical warehouse area, goods are placed in a three-dimensional manner, further increasing the difficulty of goods operation. Therefore, how to efficiently process the task of automatic storage becomes a problem. SUMMARY

[0003] The embodiments of the present specification provide an order data processing method and related device, which improves the task processing efficiency in automatic storage.

[0004] To achieve the above technical purpose, the embodiments of the present specification provide the following technical solutions:

[0005] In a first aspect, one embodiment of the present specification provides an order data processing method, comprising:

[0006] Obtaining order data, and generating a summary list based on the inventory unit contained in the order data;

[0007] Determining the commodity attribute corresponding to the inventory unit, so as to determine the plurality of target storage locations indicated by the summary list in the three-dimensional storage area according to the commodity attribute;

[0008] Controlling a first transportation device to obtain a commodity bin from the target storage location, and transporting the commodity bin to a commodity buffer area corresponding to the commodity attribute, the commodity buffer area being associated with the inventory unit, and the commodity bin being transported by the lifting component of the first transportation device;

[0009] In response to the input of the execution task corresponding to the order data, controlling a second transportation device to obtain a commodity bin indicated by the execution task from the commodity buffer area, and transporting the commodity bin to a conveying line after sorting, the commodity bin being transported by the backpack component of the second transportation device;

[0010] Processing the execution task through the conveying line to perform the outbound process corresponding to the order data.

[0011] In a second aspect, one embodiment of the present specification provides an order data processing device, comprising:

[0012] An acquisition unit is configured to acquire order data, and generate a summary list based on stock units contained in the order data;

[0013] A determination unit is configured to determine a commodity attribute corresponding to the stock unit, so as to determine a plurality of target storage locations indicated by the summary list in a three-dimensional storage area according to the commodity attribute;

[0014] A processing unit is configured to control a first transportation device to acquire a commodity bin from the target storage location, and transport the commodity bin to a commodity buffer area corresponding to the commodity attribute, the commodity buffer area being associated with the stock unit, and the commodity bin being transported by a lifting component of the first transportation device;

[0015] The processing unit is further configured to, in response to an input of an execution task corresponding to the order data, control a second transportation device to acquire a commodity bin indicated by the execution task from the commodity buffer area, and transport the commodity bin to a conveying line after sorting, the commodity bin being transported by a carrying component of the second transportation device;

[0016] The processing unit is further configured to process the execution task through the conveying line, so as to execute a delivery process corresponding to the order data.

[0017] Optionally, in a possible implementation, the acquisition unit is specifically configured to receive a sales delivery order imported by a resource planning system through a warehouse management system, so as to configure an order pool;

[0018] The acquisition unit is specifically configured to acquire the order data based on the order pool;

[0019] The acquisition unit is specifically configured to configure order coincidence degrees according to the stock units contained in the order data, so as to aggregate the order data to obtain the summary list.

[0020] Optionally, in a possible implementation, the acquisition unit is specifically configured to configure order coincidence degrees according to the stock units contained in the order data, so as to aggregate the order data to obtain an aggregated list;

[0021] The acquisition unit is specifically configured to acquire a commodity category and a packing requirement corresponding to each stock unit in the aggregated list;

[0022] The acquisition unit is specifically configured to aggregate the aggregated list based on the commodity category and the packing requirement to obtain the summary list.

[0023] Optionally, in one possible implementation, the processing unit is specifically configured to control the second transportation device to obtain the commodity bin indicated by the execution task from the cargo buffer area in response to the input of the execution task corresponding to the order data;

[0024] The processing unit is specifically used to sort the commodity bins according to the task performed by the robotic arm configured on the second transportation equipment, so as to obtain sorted goods.

[0025] The processing unit is specifically used to place the sorted goods into a sorting carrier;

[0026] The sorting vehicle performs object identification on the sorted goods to obtain identification information;

[0027] The processing unit is specifically used to transport the corresponding sorted goods to the conveyor line according to the identification information.

[0028] Optionally, in one possible implementation, the processing unit is specifically configured to control the second transportation device to obtain the commodity bin indicated by the execution task from the cargo buffer area in response to the input of the execution task corresponding to the order data;

[0029] The processing unit is specifically used to determine, based on the execution task, at least one sorting point corresponding to the goods in the commodity bin at the sorting station.

[0030] The processing unit is specifically used to transport the goods in the commodity bin to the corresponding sorting points through the second transport equipment to perform sorting operations and obtain sorted goods;

[0031] The processing unit is specifically used to place the sorted goods into the cross belt inlet;

[0032] The processing unit is specifically used to transport the corresponding sorted goods to the conveyor line through the cross belt inlet.

[0033] Optionally, in one possible implementation, the processing unit is specifically used to collect image information corresponding to the sorted goods;

[0034] The processing unit is specifically used to perform cargo verification based on the image information and with reference to the task being performed, so as to obtain verification information;

[0035] The processing unit is specifically used to transport the sorted goods to the conveyor line if the verification information indicates that the verification has passed.

[0036] Optionally, in one possible implementation, the processing unit is specifically used to obtain the status information corresponding to the first transportation equipment and the second transportation equipment, the inventory information corresponding to the three-dimensional storage area, and the order progress corresponding to the order data;

[0037] The processing unit is specifically used to input the status information, the inventory information and the order progress into a deep reinforcement learning model to obtain task allocation information. The deep reinforcement learning model is trained based on the objective of minimizing task execution time.

[0038] The processing unit is specifically used to configure the execution task corresponding to the first transportation device and the execution task corresponding to the second transportation device based on the task allocation information.

[0039] Optionally, in one possible implementation, the processing unit is specifically used to determine the path information corresponding to the manual channel;

[0040] The processing unit is specifically used to configure constraints based on the path information;

[0041] The processing unit is specifically used to input the constraints into the deep reinforcement learning model in order to update the task allocation information.

[0042] Thirdly, one embodiment of this specification also provides a computing device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the order data processing method described above.

[0043] Fourthly, one embodiment of this specification also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the order data processing method described above.

[0044] Fifthly, embodiments of this specification provide a computer program product or computer program, the computer program product including a computer program that can be stored in a computer-readable storage medium or in the cloud; the processor of the computer device reads the computer program, and when the processor executes the computer program, it implements the steps of the above-described order data processing method.

[0045] As can be seen from the above technical solution, the order data processing method provided in the embodiments of this specification obtains order data and generates a summary list based on the inventory units contained in the order data; then determines the product attributes corresponding to the inventory units, so as to determine multiple target storage locations indicated by the summary list in the three-dimensional storage area according to the product attributes; and controls the first transportation equipment to obtain product boxes from the target storage locations and transport the product boxes to the goods buffer area corresponding to the product attributes. The goods buffer area is associated with the inventory units, and the product boxes are transported by the lifting component of the first transportation equipment; then, in response to the input of the execution task corresponding to the order data, controls the second transportation equipment to obtain the product boxes indicated by the execution task from the goods buffer area, sorts the product boxes, and transports them to the conveyor line. The product boxes are transported by the carrying component of the second transportation equipment; and then the execution task is processed through the conveyor line to execute the outbound process corresponding to the order data. This enables relay transportation of multiple transportation devices. By using a cargo buffer area as the relay point for different transportation devices, different transportation devices can fully combine their own functional characteristics to perform transportation tasks. In the case of large-volume orders, the hierarchical sorting process based on product attributes allows similar goods to be processed in batches, improving the efficiency of order data processing. Attached Figure Description

[0046] To more clearly illustrate the technical solutions in the embodiments or prior art of this specification, the drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this specification. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0047] Figure 1 Network architecture diagram for the order data processing system;

[0048] Figure 2 A flowchart illustrating the processing architecture of order data is provided in this application embodiment;

[0049] Figure 3 A flowchart illustrating an order data processing method provided as one embodiment of this specification;

[0050] Figure 4 A schematic diagram illustrating a scenario of an order data processing method provided as one embodiment of this specification;

[0051] Figure 5 A schematic diagram of the structure of a deep reinforcement learning model provided for one embodiment of this specification;

[0052] Figure 6A schematic diagram of the functional modules of an order data processing apparatus provided in one embodiment of this specification;

[0053] Figure 7 This is a schematic diagram of the structure of a computing device provided for one embodiment of this specification. Detailed Implementation

[0054] Unless otherwise defined, the technical or scientific terms used in the embodiments of this specification shall have the ordinary meaning understood by one of ordinary skill in the art to which this specification pertains. The terms "first," "second," and similar terms used in the embodiments of this specification do not indicate any order, quantity, or importance, but are merely used to avoid confusion of constituent elements.

[0055] Unless the context otherwise requires, throughout this specification, "a plurality of" means "at least two," and "including" is interpreted as open-ended or encompassing, that is, "including, but not limited to." In the description of this specification, terms such as "one embodiment," "some embodiments," "exemplary embodiment," "example," "specific example," or "some examples" are intended to indicate that a particular feature, structure, material, or characteristic associated with that embodiment or example is included in at least one embodiment or example of this specification. The illustrative representations of the above terms do not necessarily refer to the same embodiment or example.

[0056] It should be understood that the order data processing method provided in this application can be applied to systems or programs in terminal devices that include order data processing functions, such as warehouse management applications. Specifically, the order data processing system can run on systems such as... Figure 1 In the network architecture shown, such as Figure 1 The diagram shows the network architecture of the order data processing system. As can be seen, the system can process order data from multiple sources. Specifically, it triggers the server to perform corresponding warehouse configuration processes through order collection operations on the terminal side. This can be understood as... Figure 1 The document shows various terminal devices, which can be computer devices. In real-world scenarios, more or fewer types of terminal devices may be involved in the order data processing. The specific number and types depend on the actual scenario and are not limited here. Figure 1 The example shows one server, but in real-world scenarios, multiple servers can be involved, especially in multidisciplinary output scenarios. The specific number of servers depends on the actual scenario.

[0057] In this embodiment, the server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, etc., but is not limited to these. The terminal and server can be directly or indirectly connected via wired or wireless communication, and the terminal and server can be connected to form a blockchain network; this application does not impose any restrictions.

[0058] It is understandable that the aforementioned order data processing system can run on personal mobile terminals, such as as an application for warehouse management, or it can run on servers, or it can run on third-party devices to provide order data processing to obtain the processing results of the order data from the information source. Specifically, the order data processing system can run as a program on the aforementioned devices, or it can run as a system component of the aforementioned devices, or it can run as a cloud service program. The specific operating mode depends on the actual scenario and is not limited here.

[0059] In the process of managing automated warehousing, the diversity of goods and the frequency of outbound operations make it difficult to efficiently execute automated warehousing tasks. This is especially true in vertical storage areas, where goods are placed three-dimensionally, further increasing the difficulty of handling goods. Therefore, efficiently processing automated warehousing tasks remains a challenge.

[0060] Generally, transport robots can be used for outbound transportation of goods. However, considering that the number of orders a transport robot can execute at one time is limited and it cannot process multiple orders concurrently, it is only suitable for processing small waves of orders. In scenarios with large waves of orders (such as warehouse management in the footwear and apparel industry), it cannot meet the warehouse management needs of the scenario, affecting the task processing efficiency of automated warehousing.

[0061] To address the aforementioned problems, this application proposes a method for processing order data, which is applied to... Figure 2 In the workflow framework for processing order data shown, such as Figure 2 The diagram shown is a flowchart of an order data processing process provided in an embodiment of this application. Through the operation request of the terminal, the order data imported by the resource planning system is received by the warehouse management system. The warehouse management system then controls the first and second transportation equipment to transport goods and adopts a relay method of cargo buffer to fully couple the specific transportation modes of the first and second transportation equipment.

[0062] It is understood that the order data processing method provided in this application can be a program written as processing logic in a hardware system, or it can be an order data processing device that implements the above processing logic in an integrated or external manner. As one implementation, the order data processing device acquires order data and generates a summary list based on the inventory units contained in the order data; then it determines the product attributes corresponding to the inventory units to determine multiple target storage locations indicated by the summary list in the three-dimensional storage area based on the product attributes; and controls a first transport device to retrieve product bins from the target storage locations and transport the product bins to the goods buffer area corresponding to the product attributes. The goods buffer area is associated with the inventory units, and the product bins are transported via the lifting components of the first transport device; then, in response to the input of the execution task corresponding to the order data, it controls a second transport device to retrieve the product bins indicated by the execution task from the goods buffer area, sorts the product bins, and transports them to the conveyor line. The product bins are transported via the carrying components of the second transport device; and finally, the execution task is processed through the conveyor line to execute the outbound process corresponding to the order data. This enables relay transportation of multiple transportation devices. By using a cargo buffer area as the relay point for different transportation devices, different transportation devices can fully combine their own functional characteristics to perform transportation tasks. In the case of large-volume orders, the hierarchical sorting process based on product attributes allows similar goods to be processed in batches, improving the efficiency of order data processing.

[0063] Based on the above process architecture, the following section will describe the order data processing method in this application. Please refer to [link / reference]. Figure 3 , Figure 3 A flowchart illustrating an order data processing method provided in this application embodiment, which includes at least the following steps:

[0064] 301. Obtain order data and generate a summary list based on the inventory units contained in the order data.

[0065] In this embodiment, the order data is a summary of orders for goods and products. The specific order forms may include one or more combinations such as sales outbound orders, pre-sale orders, and predicted sales orders. Considering that this embodiment is applicable to scenarios with large-scale batching of master lists, the order data can be order data under high-concurrency scenarios, such as seasonal clearance sales and major promotional activities.

[0066] The summary list, used in warehouse management for tracking the inbound and outbound movements of goods, is generated based on the inventory units contained in the order data, considering the high-concurrency scenario in this embodiment. This is done to aggregate orders. The process of generating the summary list involves first receiving sales outbound orders imported from the resource planning system through the warehouse management system to configure an order pool; then obtaining order data based on the order pool; and finally, configuring order overlap based on the inventory units contained in the order data to aggregate the order data and obtain the summary list.

[0067] Warehouse Management System (WMS) is a software system used to manage and optimize warehouse operations, covering the entire process from goods receiving, storage, picking to outbound shipment. It improves warehouse operational efficiency, accuracy, and transparency through automation and intelligent methods. Enterprise Resource Planning (ERP) is an integrated enterprise management software system designed to help companies manage their core business processes, such as production planning, procurement, sales, inventory, and finance. By integrating various enterprise resources and information, ERP systems can optimize business processes, improve operational efficiency, and enhance decision support capabilities. Furthermore, Stock Keeping Unit (SKU) is the basic unit in WMS used to uniquely identify and distinguish inventory items. Through effective SKU management and optimization, companies can achieve precise inventory control, efficient order processing, rational procurement planning, and accurate sales analysis, thereby improving warehouse operational efficiency, reducing costs, and enhancing customer satisfaction.

[0068] In conjunction with the above system, for the process of processing large-scale orders, the WMS system receives sales outbound orders imported from the ERP system. The WMS sets up a preset order pool for each wave. Under the premise of meeting the timeliness requirements, it aggregates a large number of overlapping orders (e.g., hundreds of orders) to generate a large-scale master order, forming a large-scale operation wave to be issued, thereby realizing a high-concurrency order processing process.

[0069] In addition, during the process of aggregating order data to obtain the final list, product attributes can also be considered, i.e., hierarchical aggregation based on order attributes and product attributes. First, the order overlap is configured according to the inventory units contained in the order data to aggregate the order data and obtain an aggregated list; then, the goods category and packing requirements corresponding to each inventory unit in the aggregated list are obtained; and the aggregated list is further aggregated based on the goods category and packing requirements to obtain the final list.

[0070] It is evident that, in addition to considering order overlap, order aggregation also focuses on the characteristics of the ordered goods, such as shoes, clothing, and accessories. For example, orders for shoes with similar packaging requirements are given priority in being generated into a single large batch of master orders.

[0071] Understandably, in the aforementioned high-concurrency order processing, within a single wave, multiple orders are combined into a large wave master order. Within each master order, aggregate picking is performed based on the ordered product types. Each SKU within this wave is only shipped out once and goes to a goods-to-person picking station for overall picking. SKUs within the same wave will not be picked at different stations. Furthermore, since the WMS can generate large wave master lists based on sales forecasts, it can merge orders from adjacent areas to reduce the number of handling operations on various transportation equipment.

[0072] In one possible scenario, the aforementioned high-concurrency order processing scenario is in the footwear and apparel industry. This scenario involves complex SKUs and high management difficulty. Furthermore, the footwear and apparel industry is highly seasonal, with complex combinations of styles, colors, and sizes, resulting in a massive number of SKUs (e.g., over 10,000 per season), requiring meticulous classification and management. Additionally, the product lifecycle is short: fast fashion brands launch new products weekly, requiring warehouses to respond quickly to inventory turnover and avoid unsold stock accumulation. Moreover, there are seasonal fluctuations and dynamic demand driven by promotional activities, such as significant differences between peak and off-peak periods: during major e-commerce promotions like Singles' Day and 618, orders surge, requiring warehouses to have flexible capacity (e.g., temporary warehouses, shared warehouses); while during off-peak seasons, idle resources need to be optimized. Furthermore, a balance between pre-sales and inventory preparation is required: in a pre-sale model, accurate sales forecasting is necessary, and warehouses need to dynamically adjust inventory allocation to reduce the risks of stockouts and overstocking.

[0073] Therefore, the above embodiments utilize a large-wave picking algorithm, which is applied to the footwear and apparel industry. By increasing order aggregation, reducing the number of round trips of various transportation equipment, and avoiding cross-site picking of a single SKU, each SKU will only go to one goods-to-person picking station for picking within a single wave. This is suitable for addressing pain points in the footwear and apparel industry.

[0074] 302. Determine the commodity attributes corresponding to the inventory unit, so as to determine the multiple target storage locations indicated by the master list in the automated storage area based on the commodity attributes.

[0075] In this embodiment, the goods corresponding to the order data are stored in a three-dimensional storage area. The three-dimensional storage area uses high-rise shelves and electronic tags (RFID / vision) to achieve dense storage, which is compatible with full cases (CTU / STU, flying cases and other AMR equipment) and loose parts (Kiva back rack or Kiva carrying a single material box). Therefore, it can be applied to the collaborative operation unit of large and small vehicles, that is, the collaborative operation process of the first transportation equipment and the second transportation equipment.

[0076] Specifically, the first type of transport equipment can be called a "large vehicle," which refers to Automated Mobile Robot (AMR) robots with lifting capabilities, such as CTU / STU / flying box AMR devices. These robots are responsible for retrieving full cases of goods from the storage area to the buffer area and supporting the parallel handling of multiple cases. The second type of transport equipment can be called a "small vehicle," which refers to Kiva-type AMR devices that can carry racks and single boxes. These robots are responsible for retrieving full cases from the buffer area, automatically disassembling them into individual pieces using a robotic arm, and transporting them to the picking station.

[0077] It should be noted that the product attributes corresponding to the inventory units in this embodiment include product type, such as shoes, clothing, etc.; and the style, color, and size combinations corresponding to different types. Furthermore, the storage locations in the automated storage area are configured regionally according to product type, meaning that storage locations for the same product type are located close together.

[0078] 303. Control the first transport equipment to obtain the commodity bins from the target location and transport the commodity bins to the cargo buffer area corresponding to the commodity attributes. The cargo buffer area is associated with the inventory unit, and the commodity bins are transported through the lifting components of the first transport equipment.

[0079] In this embodiment, the first transport equipment transports goods via a first path, that is, the process from the target cargo location to the cargo buffer area, specifically as follows: Figure 4 As shown, Figure 4 This is a schematic diagram of a scenario for processing order data according to one embodiment of this specification; the diagram shows a transportation scenario of a three-dimensional storage area, wherein the first path is the transportation path of the first transportation equipment, which involves the path between shelves and indicates the transportation process from the target location to the goods buffer area; the second path is the transportation path of the second transportation equipment, which involves the path outside the shelves and indicates the transportation process from the goods buffer area to the transportation line.

[0080] It is evident that by configuring the cargo buffer area, the coupling of different types of transportation equipment is achieved, making full use of the carrying capacity (lifting / carrying) of different types of transportation equipment and the adaptation to the three-dimensional storage environment; and the differentiated path configuration avoids the question of where the path starts, further improving the efficiency of cargo transportation.

[0081] It is understandable that the goods buffer area can be set at the bottom of the shelf, specifically on the outside of the shelf, to avoid path overlap; the goods buffer area is configured based on the product attributes, that is, the same goods buffer area stores the same / similar product attributes, and considering the specifics of large-scale order processing, the number of goods buffer areas corresponding to different product attributes can be one or more, so as to adapt to the high-concurrency order processing process.

[0082] Specifically, for the CTU / STU full case handling of the first transport equipment, the truck retrieves full cases of goods from high-level shelves to the buffer area according to dispatch instructions, and scans and records the SKU list inside the case. For example, the truck removes the boxes from the shelf at the designated location according to dispatch instructions, and stores the inventory boxes in the corresponding bottom buffer area of ​​the shelf according to the product attributes. For example, SKUs in orders involving the same style of shoes are stored together in the same fixed bottom buffer area of ​​the shelf. To match the characteristics of separate packaging for clothing, shoes, and accessories, clothing, shoes, and accessories are stored separately in different bottom buffer areas of the shelf. This hierarchical configuration of goods buffer areas is executed, realizing different granularities of goods buffering, and providing accurate goods support for the subsequent transportation / sorting process of the second transport equipment.

[0083] 304. In response to the input of the execution task corresponding to the order data, control the second transport equipment to obtain the commodity bins with the execution task instruction from the cargo buffer area, sort the commodity bins and transport them to the conveyor line. The commodity bins are transported by the carrying components of the second transport equipment.

[0084] In this embodiment, considering that footwear and apparel products are stored in a box containing multiple SKUs, or a box contains the same style of clothing but with multiple sizes and colors, there may be a need for matching boxes when shoes are stored and for the same style to be packed when they are shipped out. The picking process has a high error rate, such as mispicking, missed inspection, and wrong shipment, resulting in low picking efficiency. Therefore, an automation solution can be combined to assist the operation, reduce operational errors, and improve operational efficiency.

[0085] Specifically, the large cart moves goods from the shelf to the buffer area. After order allocation in the buffer area, the corresponding execution task is generated based on the order data. The small cart moves SKU inventory boxes from the buffer area to the goods-to-person picking workstation, and after manual picking, they are imported into the cross-belt entrance. This process is carried out through an intelligent scheduling system, which dynamically plans the total picking route for the large cart and the picking priority for the small cart based on order wave prediction. Within a single wave, each SKU will only go to one goods-to-person picking station for total picking, and SKUs within the same wave will not be picked at different stations.

[0086] Therefore, for the transportation process of controlling the second transport equipment to retrieve the goods bins with execution task instructions from the goods buffer area, in response to the input of the execution task corresponding to the order data, the second transport equipment can be controlled to retrieve the goods bins with execution task instructions from the goods buffer area; then, based on the execution task, at least one sorting point corresponding to the goods in the goods bins at the sorting station can be determined; and the goods in the goods bins can be transported to the corresponding sorting points by the second transport equipment to perform sorting operations and obtain sorted goods; then, the sorted goods can be placed into the cross belt inlet; and then, the corresponding sorted goods can be transported to the conveyor line through the cross belt inlet. For example, Kiva pushes the sorting carrier to the cross belt inlet, the sorting machine automatically sorts according to the destination, and after scanning and verification, the goods enter the logistics channel.

[0087] The cross-belt inlet is the cross-belt sorter, which integrates a flexible sorting channel and a weight / vision composite detection system to support rapid sorting of footwear and apparel items. Additionally, for certain popular items (identified products) with large picking volumes in a single wave, requiring multiple inventory boxes for outbound picking, the multiple inventory boxes for that SKU can be distributed across multiple goods-to-person picking workstations. This balances the workload of each workstation while reducing asynchronous waiting time between order lines during order processing. By matching the configuration process of different granularities of goods buffer zones in step 303 above, further order-level sorting can be performed on top of the goods in the bins, thereby achieving a hierarchical transportation / sorting coupling process and improving transportation efficiency.

[0088] In addition, for the sorting process, other sorting equipment such as robotic sorting can be used to replace the cross-belt sorting machine for splitting and sorting operations. That is, flexible disassembly is performed by the second transport equipment (Kiva cart). After Kiva takes the box from the buffer area, the robotic arm grabs the specified single item according to the order requirements, and after verification by the vision system, it is loaded into the sorting carrier.

[0089] Therefore, the process of controlling the second transport equipment to retrieve the commodity bins with execution task instructions from the cargo buffer area, sort the commodity bins, and transport them to the conveyor line can be implemented in response to the input of the execution task corresponding to the order data. The second transport equipment can then retrieve the commodity bins with execution task instructions from the cargo buffer area; the robotic arm configured on the second transport equipment can then sort the commodity bins according to the execution task to obtain sorted goods; the sorted goods can be placed into a sorting carrier; the sorting carrier can then perform object recognition on the sorted goods to obtain recognition information; and finally, based on the recognition information, the corresponding sorted goods can be transported to the conveyor line.

[0090] For example, Kiva, according to system instructions, moves the designated bins to the corresponding shelf bottom buffer area. Based on principles such as optimal path and balanced workload at the goods-to-person workstations, the designated bins are delivered to the designated goods-to-person picking station. When Kiva moves the bins to the picking point of the designated goods-to-person picking station, the system automatically activates the picking task for the goods in the bins. The manual picks out the required SKUs within the large wave according to the quantity required by the corresponding order line, and scans the barcode (or identifies them through RFID technology) to confirm the product information and quantity, and places them at the inlet of the cross belt.

[0091] Specifically, the sorting process of the second transport equipment is a "lifting" type sorting, meaning each robot has a liftable tray on top. When a package is placed on the tray, the robot "lifts" it and transports it. The robot's functions are as follows:

[0092] QR code navigation and autonomous decision-making: The ground is covered with a grid of QR codes. Robots scan these codes using cameras on their bottoms to pinpoint their location in real time. The central control system (the "brain") plans the optimal path for each robot based on the package's destination information.

[0093] Swarm intelligence and dynamic obstacle avoidance: Hundreds or even thousands of "Minions" operate simultaneously in the sorting area. They communicate in real time with the central control system via a wireless network, enabling the system to perform global path planning and scheduling. The robots have built-in sensors (such as LiDAR and vision sensors) that allow them to dynamically perceive their surroundings and other robots, enabling autonomous obstacle avoidance and collaborative work to prevent congestion and collisions.

[0094] Flexible sorting: The system can be deployed quickly and flexibly, without the need for complex fixed conveyor belts and sorting devices. Simply lay out QR code markers to rapidly build or adjust the sorting area layout. Sorting destinations (corresponding to different compartments) can be easily configured and modified via software.

[0095] Highly efficient and precise: The robot can work 24 / 7 and operates at speeds exceeding 3 meters per second. Its processing capacity far surpasses manual sorting; a large facility can handle tens of thousands of packages per hour with extremely high sorting accuracy (approaching 100%).

[0096] It is evident that by configuring a robotic arm in the second transportation equipment, integrated transportation and sorting can be achieved, reducing transfer steps and further improving transportation efficiency.

[0097] In another possible scenario, visual verification can be performed before transporting the sorted goods to the conveyor line. This involves first acquiring image information corresponding to the sorted goods; then verifying the goods based on the image information and executing the task to obtain verification information; if the verification information indicates that the verification passed, the sorted goods are then transported to the conveyor line. This visual verification process is applicable to the sorting scenarios described above at the sorting station / secondary transport equipment.

[0098] Visual verification is used to double-check the quantity. The conveyor line and cross-belt trolleys are connected to import goods according to order lines. The sorting machine rationally allocates sorting machine chutes according to rules such as order, same style packing, and separate packing of shoes and clothing. The corresponding order lines are transported to the corresponding chutes by the cross-belt sorting machine trolleys, so that the goods in the same packing box fall into the same chutes and the order is packed.

[0099] Specifically, through a dual verification mechanism, in the sorting station scenario, goods are picked and scanned at the pick-to-person picking station, and visual verification is performed before being imported into the cross-belt sorter; in the robotic arm scenario, AMR devices with lifting capabilities such as CTU / STU / flying boxes are used to work in relay with Kiva-like devices, and Kiva-like robotic arms are used to sort and verify the quantity twice, which improves the accuracy of goods.

[0100] 305. The task is processed through the conveyor line to execute the outbound process corresponding to the order data.

[0101] In this embodiment, the task to be executed is the task currently being executed for outbound shipment. Specifically, it can be a sub-task composed of orders in the order data. The determination of this sub-task can be based on the order of order placement or by adjusting the order according to the priority of the goods. For example, shoes occupy a large amount of warehouse space, so shoe orders are prioritized for outbound shipment. The specific form depends on the actual scenario.

[0102] In one possible scenario, the task allocation for the first and second transportation devices can be dynamically scheduled based on a scheduling system. This means the scheduling system collects real-time data on device status, inventory, and order progress, and dynamically adjusts the task allocation between the large and small vehicles using deep reinforcement learning.

[0103] Specifically, for the reinforcement learning dynamic scheduling process, the state information corresponding to the first and second transportation equipment, the inventory information corresponding to the three-dimensional storage area, and the order progress corresponding to the order data can be obtained first. Then, the state information, inventory information, and order progress are input into the deep reinforcement learning model to obtain task allocation information. The deep reinforcement learning model is trained based on the objective of minimizing task execution time. The execution tasks corresponding to the first transportation equipment and the second transportation equipment are configured based on the task allocation information.

[0104] Understandably, considering the seasonal / phased nature of footwear and apparel sales, the configuration of training objectives can optimize inventory layout based on factors such as order frequency, order quantity, and handling frequency of goods in each phase. Furthermore, by combining the picking efficiency of each picking station, the order of outbound picking for each SKU can be dynamically adjusted within large waves, ensuring that Kiva-transported inventory bins can go directly to the nearest goods-to-person station / conveyor line without turning after leaving the aisle, reducing turning waiting time and improving handling efficiency. During off-peak hours, the trolley automatically predicts the future handling frequency of SKUs based on historical orders and automatically generates sorting tasks, adjusting frequently handled goods to the aisle ends for easier outbound processing, thereby reducing the travel path of trolleys and carts during subsequent outbound operations and improving operational efficiency.

[0105] In another possible scenario, during peak sales periods, both goods-to-delivery and people-to-goods modes can coexist collaboratively, meaning that manual walking aisles are reserved during the layout. In this case, the three-dimensional storage area also includes manual aisles. Accordingly, for the task allocation and scheduling process, the path information corresponding to the manual aisles can be determined; then, constraints can be configured based on the path information; and the constraints can be input into a deep reinforcement learning model to update the task allocation information.

[0106] Through the collaboration of the above multi-mode, a high-density storage solution and a highly flexible picking operation solution can be achieved, which can take into account the needs of increased personnel for person-to-goods picking operations on peak operation days. At the same time, large-scale batch picking operations can make good use of order overlap, reduce operation steps, and improve operation efficiency.

[0107] For details on the training process of the aforementioned deep reinforcement learning model, please refer to [link / reference]. Figure 5 , Figure 5 This diagram illustrates the structure of a deep reinforcement learning model as one embodiment of this specification. The diagram shows an agent influencing the environment through actions, with the environment providing rewards, and the goal being to maximize cumulative rewards. The agent is configured based on a deep reinforcement learning model, and the actions performed are selected based on an action space, while the environment corresponds to a state space, and the reward is represented by a reward function.

[0108] Specifically, in the automated warehouse management of the embodiment, the state space can be a multi-dimensional vector: {equipment location matrix, aisle congestion index, station picking queue length, SKU heat distribution, order remaining time}; the action space can indicate the large cart task: batch transport of boxes to the buffer area (minimum batch processing = 3 boxes), the small cart task: single box direct delivery to the station (response time < 500ms), dynamic allocation: select the allocation ratio of large and small cart tasks based on Q value; and the reward function can include positive rewards: zero-turn delivery of boxes (+10), early completion of waves (+5 × remaining minutes), negative rewards: turning wait (-2 / time), path conflict (-5), order timeout (-20), and its training objective is to maximize the early completion time, that is, minimize the time to complete the order.

[0109] Through the above-described configuration, efficiency has been improved in the management of the three-dimensional storage area, specifically improving the efficiency of picking and unpacking by 40% and achieving a peak daily order volume of 200,000 orders; space utilization has been improved, warehouse density has increased by 60%, and the sales per square meter have reached an industry-leading level (≥1500 pieces / ㎡ / day); and adaptability has been enhanced: it supports rapid response to seasonal best-selling products in the footwear and apparel industry, and improves inventory turnover by 30%.

[0110] In summary, this embodiment acquires order data and generates a total order list based on the inventory units contained in the order data. Then, it determines the product attributes corresponding to the inventory units to identify multiple target storage locations indicated by the total order list in the automated storage area. A first transport device is controlled to retrieve product bins from the target storage locations and transport them to the goods buffer area corresponding to the product attributes. The goods buffer area is associated with the inventory units, and the product bins are transported via the lifting components of the first transport device. Then, in response to the input of the execution task corresponding to the order data, a second transport device is controlled to retrieve the product bins indicated by the execution task from the goods buffer area, sort the product bins, and transport them to the conveyor line. The product bins are transported via the carrying components of the second transport device. Finally, the conveyor line processes the execution task to execute the outbound process corresponding to the order data. This enables relay transportation of multiple transportation devices. By using a cargo buffer area as the relay point for different transportation devices, different transportation devices can fully combine their own functional characteristics to perform transportation tasks. In the case of large-volume orders, the hierarchical sorting process based on product attributes allows similar goods to be processed in batches, improving the efficiency of order data processing.

[0111] It should be noted that the various embodiments described in this specification emphasize the parts that differ from other embodiments, and the embodiments can be explained by comparison with each other. Any combination of the various embodiments described in this specification based on general technical knowledge is covered within the scope of this specification.

[0112] In one exemplary embodiment of this specification, an order data processing apparatus 600 is also provided, such as... Figure 6 As shown, Figure 6 A functional block diagram of an order data processing apparatus provided in one embodiment of this specification is shown. The processing apparatus 600 includes:

[0113] The acquisition unit 601 is used to acquire order data and generate a total list based on the inventory units contained in the order data;

[0114] The determining unit 602 is used to determine the commodity attributes corresponding to the inventory unit, so as to determine the multiple target storage locations indicated by the summary list in the three-dimensional storage area based on the commodity attributes;

[0115] Processing unit 603 is used to control the first transport equipment to obtain a commodity box from the target storage location and transport the commodity box to the cargo buffer area corresponding to the commodity attribute. The cargo buffer area is associated with the inventory unit. The commodity box is transported by the lifting component of the first transport equipment.

[0116] The processing unit 603 is also configured to respond to the input of the execution task corresponding to the order data, control the second transportation equipment to obtain the commodity bin indicated by the execution task from the cargo buffer area, and sort the commodity bin and transport it to the conveyor line, wherein the commodity bin is transported by the carrying component of the second transportation equipment;

[0117] The processing unit 603 is also used to process the execution task through the conveyor line to execute the outbound process corresponding to the order data.

[0118] Optionally, in one possible implementation, the acquisition unit 601 is specifically used to receive sales outbound orders imported from the resource planning system through the warehouse management system in order to configure the order pool;

[0119] The acquisition unit 601 is specifically used to acquire the order data based on the order pool;

[0120] The acquisition unit 601 is specifically used to configure the order overlap degree according to the inventory units contained in the order data, so as to aggregate the order data to obtain the total list.

[0121] Optionally, in one possible implementation, the acquisition unit 601 is specifically used to configure the order overlap degree according to the inventory units contained in the order data, so as to aggregate the order data to obtain an aggregated list;

[0122] The acquisition unit 601 is specifically used to acquire the goods category and packing requirements corresponding to each inventory unit in the aggregated list.

[0123] The acquisition unit 601 is specifically used to aggregate the aggregated list based on the goods category and the packing requirements to obtain the total list.

[0124] Optionally, in one possible implementation, the processing unit 603 is specifically configured to control the second transportation device to obtain the commodity bin indicated by the execution task from the cargo buffer area in response to the input of the execution task corresponding to the order data;

[0125] The processing unit 603 is specifically used to sort the commodity bins according to the task performed by the robotic arm configured on the second transportation equipment, so as to obtain sorted goods.

[0126] The processing unit 603 is specifically used to place the sorted goods into a sorting carrier;

[0127] The sorting vehicle performs object identification on the sorted goods to obtain identification information;

[0128] The processing unit 603 is specifically used to transport the corresponding sorted goods to the conveyor line according to the identification information.

[0129] Optionally, in one possible implementation, the processing unit 603 is specifically configured to control the second transportation device to obtain the commodity bin indicated by the execution task from the cargo buffer area in response to the input of the execution task corresponding to the order data;

[0130] The processing unit 603 is specifically used to determine at least one sorting point corresponding to the goods in the commodity bin at the sorting station based on the execution task.

[0131] The processing unit 603 is specifically used to transport the goods in the commodity bin to the corresponding sorting points through the second transport equipment to perform sorting operations and obtain sorted goods;

[0132] The processing unit 603 is specifically used to place the sorted goods into the cross belt inlet;

[0133] The processing unit 603 is specifically used to transport the corresponding sorted goods to the conveyor line through the cross belt inlet.

[0134] Optionally, in one possible implementation, the processing unit 603 is specifically used to collect image information corresponding to the sorted goods;

[0135] The processing unit 603 is specifically used to perform cargo verification based on the image information and with reference to the task being performed, so as to obtain verification information;

[0136] The processing unit 603 is specifically used to transport the sorted goods to the conveyor line if the verification information indicates that the verification has passed.

[0137] Optionally, in one possible implementation, the processing unit 603 is specifically used to obtain the status information corresponding to the first transportation equipment and the second transportation equipment, the inventory information corresponding to the three-dimensional storage area, and the order progress corresponding to the order data;

[0138] The processing unit 603 is specifically used to input the status information, the inventory information and the order progress into a deep reinforcement learning model to obtain task allocation information. The deep reinforcement learning model is trained based on the objective of minimizing task execution time.

[0139] The processing unit 603 is specifically used to configure the execution task corresponding to the first transportation device and the execution task corresponding to the second transportation device based on the task allocation information.

[0140] Optionally, in one possible implementation, the processing unit 603 is specifically used to determine the path information corresponding to the manual channel;

[0141] The processing unit 603 is specifically used to configure constraints based on the path information;

[0142] The processing unit 603 is specifically used to input the constraints into the deep reinforcement learning model in order to update the task allocation information.

[0143] Specifically, the acquisition unit, determination unit, and processing unit in this embodiment can correspond to physical components. For example, the processing unit can be a processing module such as a CPU, GPU, or FPGA. The specific physical component can be any component or combination of components with the above functions. The specific method depends on the actual scenario and is not limited here.

[0144] The aforementioned processing device acquires order data and generates a summary list based on the inventory units contained in the order data. It then determines the product attributes corresponding to the inventory units to identify multiple target storage locations indicated by the summary list in the automated storage area. The device controls a first transport device to retrieve product bins from the target storage locations and transports them to a cargo buffer area corresponding to the product attributes. The cargo buffer area is associated with the inventory units, and the product bins are transported via the lifting components of the first transport device. In response to the input of the execution task corresponding to the order data, the device controls a second transport device to retrieve the product bins indicated by the execution task from the cargo buffer area, sorts the product bins, and transports them to the conveyor line. The product bins are transported via the carrying components of the second transport device. Finally, the conveyor line processes the execution task to execute the outbound process corresponding to the order data. This enables relay transportation of multiple transportation devices. By using a cargo buffer area as the relay point for different transportation devices, different transportation devices can fully combine their own functional characteristics to perform transportation tasks. In the case of large-volume orders, the hierarchical sorting process based on product attributes allows similar goods to be processed in batches, improving the efficiency of order data processing.

[0145] Specific limitations regarding the order data processing device can be found in the above description of the order data processing method, and will not be repeated here. Each unit module in the aforementioned order data processing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0146] Another embodiment of this application also proposes a computing device, see [link to relevant documentation] Figure 7 As shown, an exemplary embodiment of this specification also provides a computing device, including: a memory and a processor, the memory storing a computer program, the processor executing the computer program to perform steps in the order data processing method according to various embodiments of this specification described above.

[0147] The internal structure of the computing device can be as follows: Figure 7As shown, the computing device includes a processor, memory, network interface, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it follows the steps of the order data processing methods according to various embodiments of this specification as described in the above embodiments.

[0148] The processor may include the main processor, as well as baseband chips, modems, etc.

[0149] The memory stores a program that executes the technical solution of this invention, and may also store an operating system and other critical business functions. Specifically, the program may include program code, which includes computer operation instructions. More specifically, the memory may include read-only memory (ROM), other types of static storage devices capable of storing static information and instructions, random access memory (RAM), other types of dynamic storage devices capable of storing information and instructions, disk storage, flash memory, etc.

[0150] The processor can be a general-purpose processor, such as a general-purpose central processing unit (CPU), a microprocessor, etc., or an application-specific integrated circuit (ASIC), or one or more integrated circuits used to control the execution of the program of the present invention. It can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0151] Input devices may include devices that receive data and information input by the user, such as keyboards, mice, cameras, scanners, light pens, voice input devices, touch screens, pedometers, or gravity sensors.

[0152] Output devices may include devices that allow information to be output to the user, such as displays, printers, speakers, etc.

[0153] The communication interface may include any transceiver-like device for communicating with other devices or communication networks, such as Ethernet, Radio Access Network (RAN), Wireless Local Area Network (WLAN), etc.

[0154] The processor executes the program stored in the memory and calls other devices, which can be used to implement the various steps of any of the order data processing methods provided in the above embodiments of this application.

[0155] The computing device may also include a display component and a voice component. The display component may be a liquid crystal display screen or an e-ink display screen. The input device of the computing device may be a touch layer covering the display component, or a button, trackball or touchpad set on the casing of the computing device, or an external keyboard, touchpad or mouse, etc.

[0156] Those skilled in the art will understand that Figure 7 The structures shown are merely block diagrams of some structures related to the solutions in this specification and do not constitute a limitation on the computing devices on which the solutions in this specification are applied. Specific computing devices may include more or fewer components than those shown in the figures, or combine certain components, or have different component arrangements.

[0157] In addition to the methods and devices described above, the order data processing methods provided in the embodiments of this specification can also be computer program products, which include computer programs that, when run by a processor, cause the processor to perform the steps in the order data processing methods according to various embodiments of this specification as described in the "Exemplary Methods" section above.

[0158] The computer program product described herein can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments described herein. These programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0159] Furthermore, embodiments of this specification also provide a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor of the steps in the order data processing methods according to various embodiments of this specification as described in the "Exemplary Methods" section above.

[0160] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this specification can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0161] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0162] The embodiments described above are merely illustrative of several implementation methods outlined in this specification. While the descriptions are specific and detailed, they should not be construed as limiting the scope of the solutions provided in this specification. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this specification, and these all fall within the scope of protection of this specification. Therefore, the scope of protection for this patent should be determined by the appended claims.

Claims

1. A method for processing order data, characterized in that, include: Obtain order data and generate a total list of orders based on the inventory units contained in the order data; Determine the product attributes corresponding to the inventory unit, and determine the multiple target storage locations indicated by the total list in the three-dimensional storage area based on the product attributes; The first transport equipment is controlled to retrieve a commodity bin from the target storage location and transport the commodity bin to the cargo buffer area corresponding to the commodity attribute. The cargo buffer area is associated with the inventory unit. The commodity bin is transported by the lifting component of the first transport equipment. In response to the input of the execution task corresponding to the order data, the second transportation equipment is controlled to obtain the commodity bin indicated by the execution task from the cargo buffer area, and the commodity bin is sorted and transported to the conveyor line. The commodity bin is transported by the carrying component of the second transportation equipment. The conveyor line processes the task to execute the outbound process corresponding to the order data.

2. The method according to claim 1, characterized in that, The step of acquiring order data and generating a total list based on the inventory units contained in the order data includes: Receive sales outbound orders imported from the resource planning system through the warehouse management system to configure the order pool; The order data is obtained based on the order pool; The order overlap is configured based on the inventory units contained in the order data to aggregate the order data and obtain the total list.

3. The method according to claim 2, characterized in that, The step of configuring order overlap based on the inventory units contained in the order data to aggregate the order data and obtain the summary list includes: The order overlap is configured based on the inventory units contained in the order data to aggregate the order data and obtain an aggregated list; Obtain the goods category and packing requirements corresponding to each inventory unit in the aggregated list; The aggregated list is obtained by aggregating the aggregated list based on the cargo category and the packing requirements.

4. The method according to claim 1, characterized in that, The step of responding to the input of the execution task corresponding to the order data, controlling the second transportation device to obtain the goods bin indicated by the execution task from the goods buffer area, and sorting the goods bin and transporting it to the conveyor line includes: In response to the input of the execution task corresponding to the order data, the second transportation device is controlled to obtain the commodity bin indicated by the execution task from the cargo buffer area; The robotic arm configured on the second transport equipment sorts the commodity bins according to the task to obtain sorted goods; Place the sorted goods into the sorting carrier; The sorting vehicle performs object identification on the sorted goods to obtain identification information; The corresponding sorted goods are transported to the conveyor line based on the identification information.

5. The method according to claim 1, characterized in that, The step of responding to the input of the execution task corresponding to the order data, controlling the second transportation device to obtain the goods bin indicated by the execution task from the goods buffer area, and sorting the goods bin and transporting it to the conveyor line includes: In response to the input of the execution task corresponding to the order data, the second transportation device is controlled to obtain the commodity bin indicated by the execution task from the cargo buffer area; Based on the task being performed, at least one sorting point corresponding to the goods in the commodity bin at the sorting station is determined; The goods in the commodity bins are transported to the corresponding sorting points by the second transport equipment to perform sorting operations and obtain sorted goods; Place the sorted goods into the cross belt inlet; The corresponding sorted goods are transported to the conveyor line through the cross belt inlet.

6. The method according to claim 4 or 5, characterized in that, The method further includes, prior to transporting the sorted goods to the conveyor line: Collect image information corresponding to the sorted goods; Based on the image information, the cargo is inspected in accordance with the task being performed to obtain inspection information; If the verification information indicates that the verification is successful, the sorted goods are transported to the conveyor line.

7. The method according to claim 1, characterized in that, The method further includes: Obtain the status information corresponding to the first and second transportation devices, the inventory information corresponding to the three-dimensional storage area, and the order progress corresponding to the order data; The status information, inventory information, and order progress are input into a deep reinforcement learning model to obtain task allocation information. The deep reinforcement learning model is trained based on the objective of minimizing task execution time. Based on the task allocation information, configure the execution tasks corresponding to the first transportation equipment and the second transportation equipment.

8. The method according to claim 7, characterized in that, The three-dimensional storage area also includes a manual passageway, and the method further includes: Determine the path information corresponding to the manual channel; Configure constraints based on the path information; The constraints are input into the deep reinforcement learning model to update the task allocation information.

9. An order data processing apparatus, characterized in that, include: An acquisition unit is used to acquire order data and generate a total list based on the inventory units contained in the order data; A determining unit is used to determine the commodity attributes corresponding to the inventory unit, so as to determine multiple target storage locations indicated by the total list in the three-dimensional storage area based on the commodity attributes; The processing unit is configured to control the first transport equipment to obtain a commodity bin from the target storage location and transport the commodity bin to the cargo buffer area corresponding to the commodity attribute. The cargo buffer area is associated with the inventory unit, and the commodity bin is transported by the lifting component of the first transport equipment. The processing unit is also configured to respond to the input of the execution task corresponding to the order data, control the second transportation equipment to obtain the commodity bin indicated by the execution task from the cargo buffer area, and sort the commodity bin and transport it to the conveyor line, wherein the commodity bin is transported by the carrying component of the second transportation equipment; The processing unit is also used to process the execution task through the conveyor line to execute the outbound process corresponding to the order data.

10. A computing device, characterized in that, The device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the order data processing method according to any one of claims 1 to 9.

Images