Seeding wall control system based on artificial intelligence

Abstract

The invention relates to the technical field of seeding walls, in particular to a seeding wall control system based on artificial intelligence, and the system comprises a first data processing center which obtains order information; order completion information is received, and notification is carried out; the first information acquisition unit is used for acquiring goods information; the second data processing center is used for receiving the classification information of the first data processing center and planning a bearing frame according to the classification information; the second information acquisition unit is used for acquiring whether the bearing frame is overflowed or not. According to the invention, the goods are divided into a compressible goods, a non-pressure-resistant goods and a non-compressible goods, the compressible goods should be placed at the bottom of the shopping bag, the non-pressure-resistant goods are placed on the compressible goods, and the non-compressible goods are placed on the non-pressure-resistant goods, so that the problem of pressure resistance of the goods is solved; and according to the orders and the classifications, the volume of each classification is calculated, the bearing frames are distributed according to the sizes, the bearing frames of the same order send out unified identifiers different from those of other orders, and the problem of excessive goods is solved.

Description

Technical Field

[0001] This invention relates to the field of seeding wall technology, and more specifically to a seeding wall control system based on artificial intelligence. Background Technology

[0002] Logistics sorting walls are core equipment in the secondary sorting of e-commerce warehouses. They use automated systems to sort goods according to orders and place them into designated slots, replacing traditional manual sorting.

[0003] With technological advancements, modern sorting walls can prevent the accumulation of goods. For example, Chinese patent application number 202510086375.2 discloses an intelligent sorting wall device, including a sorting rack and several material slots arranged in a matrix on the rack. A slide rail is fixedly connected to the inner side of each material slot, and a replacement mechanism for changing baskets is installed inside each slot. A conveying mechanism is installed on the front side of the same row of material slots. This invention uses the coordinated operation of a temporary storage component, a pushing component, an upward moving component, and a conveying mechanism to replace baskets. When a basket on the support plate is full of goods, the pushing component moves an empty basket temporarily stored on the temporary storage component forward to replace the full basket, pushing the full basket forward onto the conveying mechanism. The conveying mechanism then transports the full basket to the packaging area, eliminating the need for manual basket replacement and improving efficiency.

[0004] However, online supermarkets that offer online ordering and delivery by riders are currently very popular. These supermarkets require manual sorting, which is labor-intensive. Using AGVs in conjunction with seeding walls can significantly improve sorting efficiency.

[0005] However, the pressing issues that need to be addressed are the cargo's inability to withstand pressure and the excessive amount of cargo.

[0006] Therefore, it is necessary to provide new technical solutions to overcome the above-mentioned defects. Summary of the Invention

[0007] The purpose of this invention is to provide an artificial intelligence-based seeding wall control system that can effectively solve the above-mentioned technical problems.

[0008] To achieve the objectives of this invention, the following technical solution is adopted:

[0009] The AI-based seeding wall control system includes:

[0010] First Data Processing Center: Retrieves order information; receives order completion information and sends notifications;

[0011] First information acquisition unit: Acquires product information;

[0012] Second data processing center: Receives classification information from first data processing center and plans carrier frame based on this classification information;

[0013] Second information acquisition unit: Acquire whether the carrying frame is overflowing.

[0014] Furthermore, the second data processing center includes: an information receiving module, a data processing module, and a verification module. The information receiving module receives data from the first data processing center, the first information acquisition unit, and the second information acquisition unit. The data processing module processes the received information and generates instructions. The verification module verifies the instructions issued by the data processing module.

[0015] Furthermore, the specific process of generating instructions is as follows: the volume of goods in the order is calculated using the historical database, and a carrying frame is allocated based on this volume.

[0016] Furthermore, the specific verification process of the verification module is as follows: the first information acquisition unit scans the barcode of the goods and uses a visual camera to acquire the volume of the goods, and compares it with the historical database. If there is a discrepancy, it is corrected; the second information acquisition unit acquires whether the specific carrying frame is full and feeds it back to the second data processing center.

[0017] Furthermore: The first data processing center categorizes goods into compressible, non-compressible, and non-compressible categories, and then sends the classification information to the second data processing center.

[0018] Further steps for classifying order information are as follows: Step S1: Construct a barcode database and, when entering product information, specify whether the product is compressible, not compressible, or cannot be compressed; Step S2: The first data processing center matches the goods in the order with the barcode database and classifies the goods.

[0019] Further steps for refining the order information classification are as follows:

[0020] Step X1: Establish a comment quality scoring model to filter out invalid content;

[0021] Step X2: Fine-grained emotion recognition is performed using a hybrid model of BERT and BiLSTM;

[0022] Step X3: Perform word segmentation to break the long sentence down into several word groups.

[0023] Step X4: Use the BERT model to extract keywords;

[0024] Step X5: Adjust the product categories based on keywords.

[0025] Furthermore: if an order contains only a single category, then a single carrying box can be matched; if an order contains multiple categories, then the specific number of items in each category is analyzed, and if the number is large, then each category should match at least one carrying box.

[0026] Compared with the prior art, the present invention has the following beneficial effects:

[0027] This invention relates to an AI-based seeding wall control system that categorizes goods into three types: compressible, non-compressible, and non-compressible. Compressible goods should be placed at the bottom of the shopping bag, non-compressible goods should be placed on top of compressible goods, and non-compressible goods should be placed on top of non-compressible goods, thus solving the problem of goods' compressibility. Based on the order and category, the system calculates the volume of each category and allocates carrying frames accordingly. Carrying frames for the same order emit a unique identifier that differs from other orders, thus solving the problem of excessive goods. Attached Figure Description

[0028] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with the embodiments of the invention to explain the invention and do not constitute a limitation thereof.

[0029] Figure 1 This is a schematic diagram of the control principle of the seeding wall control system based on artificial intelligence of the present invention. Detailed Implementation

[0030] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below. Obviously, the described embodiments are some embodiments of the present invention, but not all embodiments.

[0031] It should be understood that although the steps in the control schematic diagrams of the various embodiments of the present invention are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the various embodiments may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0032] like Figure 1As shown, the present invention provides an artificial intelligence-based seeding wall control system, comprising: a first data processing center: acquiring order information and classifying goods into compressible, non-compressible, and non-compressible categories, and distributing the classification information; receiving order completion information and issuing a notification. A first information acquisition unit: scanning the goods to acquire their information. A second data processing center: receiving the classification information from the first data processing center and planning the carrying frame based on this classification information; the second information acquisition unit: determining whether the carrying frame is full.

[0033] It is important to explain in detail here that "compressible" refers to items that can withstand heavy pressure and remain stable, such as mineral water, beverages, and beer; "not pressure-resistant" refers to items that can be crushed by small objects but cannot be crushed by heavy objects, such as snacks in cardboard packaging; and "uncompressible" refers to items that cannot be crushed by either compressible or pressure-resistant materials, such as fruit.

[0034] In other words, items that can be crushed should be placed at the bottom of the shopping bag, items that are not resistant to pressure should be placed on top of items that can be crushed, and items that cannot be crushed should be placed on top of items that are not resistant to pressure.

[0035] The specific steps for classifying order information in this invention are as follows: Step S1: Construct a barcode database and, when entering product information, specify whether the product can be crushed, is not pressure-resistant, or cannot be crushed; Step S2: The first data processing center matches the goods in the order with the barcode database to classify the goods.

[0036] However, in actual use cases, the distinction between goods that are not pressure-resistant and goods that cannot be compressed is rather vague, and more often than not, it is based on the actual evaluation of the goods by consumers. Therefore, it is necessary to adjust the classification of goods according to the evaluation of consumers.

[0037] The specific steps are as follows:

[0038] Step X1: Build a comment quality scoring model to filter invalid content (such as duplicate submissions);

[0039] Step X2: Fine-grained emotion recognition is performed using a hybrid model of BERT and BiLSTM;

[0040] Step X3: Perform word segmentation, breaking the long sentence down into several word groups. The specific code is as follows:

[0041] import jieba

[0042] stopwords=set(open('stopwords.txt').read().split())def tokenize(text):

[0043] return[w for w in jieba.cut(text)if w not in stopwords]

[0044] Step X4: Use the BERT model to extract keywords.

[0045] In other words, when words such as "broken" or "crushed" appear, the goods that are not resistant to pressure should be changed to goods that cannot be crushed.

[0046] The second data processing center receives the classification information from the first data processing center and plans the carrying frames based on this classification information. This means that based on an order, the goods in that order are divided into several carrying frames.

[0047] If an order contains only a single category, then one carrying box can be matched; if an order contains multiple categories, then the specific number of items in each category is analyzed, and if the number is large, then at least one carrying box should be matched for each category.

[0048] To save space, the second data processing center can build a reserved carrying frame. That is, when there is only one item of another category, a carrying frame can be reserved first, and the decision on whether to use the reserved carrying frame is made based on the order of arrival of the goods.

[0049] For example, an order to be sorted contains a case of beer and some potato chips. In this case, the second data processing center should match two carrier boxes. In order to improve the utilization rate of the carrier boxes and save carrier boxes, the second data processing center matches one carrier box and designates the other carrier box as a reserved carrier box. When the beer enters the station first, it is already at the bottom of the carrier box, and the remaining potato chips can be directly piled on top of the beer. In this case, the second data processing center does not need to designate a reserved carrier box, thereby improving the utilization rate of the carrier boxes and saving carrier boxes.

[0050] In e-commerce, goods are generally packaged to a standard size and in small quantities, usually one piece. However, in community supermarkets, goods come in various shapes and are more numerous. Using standard shelves would take up a lot of space.

[0051] Therefore, the second data processing center includes: an information receiving module, a data processing module, and a verification module. The information receiving module receives data from the first data processing center, the first information acquisition unit, and the second information acquisition unit. The data processing module processes the received information and generates instructions. The verification module verifies the instructions issued by the data processing module.

[0052] The specific process of generating instructions is as follows: the volume of goods in the order is calculated using the historical database, and the volume is divided into multiple carrying frames based on this volume; the specific process of verification by the verification module is as follows: the first information acquisition unit scans the goods and simultaneously uses a vision camera to acquire the volume of the goods, and compares it with the historical database. If they are inconsistent, they are corrected; the second information acquisition unit acquires whether the specific carrying frame is full and feeds it back to the second data processing center.

[0053] In this application, the volume of each category is calculated based on the order and category, and the carrying frame is allocated accordingly.

[0054] Historical data was corrected using the trend deviation method, the specific method of which will not be elaborated here.

[0055] In actual use, there may be a situation where an order has multiple carrying frames. In this case, the carrying frame has at least one identification unit. In one embodiment, the identification unit is an information interaction module and a sound generation module. The information interaction module can interact with the transport vehicle and / or the second data processing center.

[0056] In other words, the first information acquisition unit scans the goods, while the second data processing center continuously monitors the process. When an order is completed, the second data processing center sends the order completion information back to the first data processing center, which then issues a notification. At this point, the second data processing center directly interacts with the carrier frame via Bluetooth or similar means. Considering communication distance and signal attenuation, the second data processing center can first transmit the data to the transport vehicle, which then transmits it to the carrier frame.

[0057] The purpose of information exchange in the second data processing center is to enable the same order's frame to emit a unified identifier that is different from other orders, making it easier to identify.

[0058] In this application, the first data processing center can also be used to plan the order in which goods enter the station, that is, the sorting order, and to jointly control the sorting order with the second data processing center. See the applicant's other patents for details; this application will not elaborate further.

[0059] This invention relates to an AI-based seeding wall control system that categorizes goods into three types: compressible, non-compressible, and non-compressible. Compressible goods should be placed at the bottom of the shopping bag, non-compressible goods on top of compressible goods, and non-compressible goods on top of non-compressible goods, thus solving the problem of goods' compressibility. Based on orders and categories, the system calculates the volume of each category and allocates carrying frames accordingly. Carrying frames from the same order emit a unique identifier different from those from other orders, addressing the issue of excessive goods.

[0060] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application 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.

[0061] 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.

[0062] It should be understood that those skilled in the art can make improvements or modifications based on the above description, and all such improvements and modifications should fall within the protection scope of the appended claims.

Claims

1. An artificial intelligence-based seeding wall control system, characterized in that: include: First Data Processing Center: Retrieves order information; Receive order completion information and send a notification; First information acquisition unit: Acquires product information; Second data processing center: Receives classification information from first data processing center and plans carrier frame based on this classification information; Second information acquisition unit: Acquire whether the carrying frame is overflowing.

2. The artificial intelligence-based seeding wall control system as described in claim 1, characterized in that: The second data processing center includes: an information receiving module, a data processing module, and a verification module. The information receiving module receives data from the first data processing center, the first information acquisition unit, and the second information acquisition unit. The data processing module processes the received information and generates instructions. The verification module verifies the instructions issued by the data processing module.

3. The artificial intelligence-based seeding wall control system as described in claim 2, characterized in that: The specific process of generating instructions is as follows: use the historical database to calculate the volume of the goods in the order, and allocate the carrying frame according to this volume.

4. The artificial intelligence-based seeding wall control system as described in claim 3, characterized in that: The specific verification process of the verification module is as follows: the first information acquisition unit scans the barcode of the goods and uses a visual camera to acquire the volume of the goods and compares it with the historical database. If they are inconsistent, they are corrected; the second information acquisition unit acquires whether the specific carrying frame is full and feeds it back to the second data processing center.

5. The artificial intelligence-based seeding wall control system as described in claim 4, characterized in that: The first data processing center categorizes goods into those that can be crushed, those that cannot withstand pressure, and those that cannot be crushed, and then sends the classification information to the second data processing center.

6. The artificial intelligence-based seeding wall control system as described in claim 5, characterized in that: The specific steps for classifying order information are as follows: Step S1: Construct a barcode database and add the product information as either compressible, not compressible, or not compressible when entering the product information; Step S2: The first data processing center matches the goods in the order with the barcode database and classifies the goods.

7. The artificial intelligence-based seeding wall control system as described in claim 6, characterized in that: The steps for correcting the order information classification are as follows: Step X1: Establish a comment quality scoring model to filter out invalid content; Step X2: Fine-grained emotion recognition is performed using a hybrid model of BERT and BiLSTM; Step X3: Perform word segmentation to break the long sentence down into several word groups. Step X4: Use the BERT model to extract keywords; Step X5: Adjust the product categories based on keywords.

8. The artificial intelligence-based seeding wall control system as described in claim 7, characterized in that: If an order contains only a single category, then one carrying box can be matched; if an order contains multiple categories, then the specific number of items in each category is analyzed, and if the number is large, then at least one carrying box should be matched for each category.

Images