Goods allocation recommendation method

Abstract

The invention provides a goods allocation recommendation method, which comprises the following steps: S1, carrying out detailed goods allocation division on a warehouse, and binding a unique electronic tag for each goods allocation, the tag comprising detailed information of the goods allocation; s2, installing an industrial camera and an electronic scale to measure the occupied area and load of the materials, and connecting the industrial camera and the electronic scale with a client terminal; s3, when a material needs to be warehoused, material information is input through the client terminal, and the system automatically calculates an optimal goods allocation and prints a two-dimensional code; s4, according to an intelligent algorithm, goods locations meeting the requirements of material types, weights and areas are selected, and the material types and placement states of adjacent goods shelves are obtained; and S5, placing the material on the specified goods, and updating the display content of the electronic tag. The goods allocation total weight, the remaining available area and the material types are comprehensively considered, space waste is avoided, the system preferentially selects the goods allocation for storing the same or similar materials on the adjacent goods shelves, the materials are more concentrated, and management, storage and taking are convenient.

Description

Technical Field

[0001] The present invention relates to the technical field of logistics and warehousing management, and in particular to a cargo location recommendation method. Background Art

[0002] In modern logistics and warehousing management, an efficient cargo location management system is crucial to improving storage space utilization and operational efficiency. The traditional cargo location management method dominated by manual experience is inefficient and error-prone, and may cause the shelves to collapse due to overloading. With the development of information technology, although rule-based cargo location recommendation systems have emerged, these systems are not flexible enough when faced with complex and changing storage needs. Especially in large-scale warehouse operations with a wide variety of materials, the limitations of preset rules affect the optimization of cargo location allocation. At the same time, the lack of advanced optimization algorithms has failed to maximize the utilization of warehouse space, and often cannot provide sufficient personalized support. Summary of the invention

[0003] In view of the shortcomings of the prior art, the present invention provides a method for recommending cargo locations. To achieve the above-mentioned purpose, the present invention adopts the following technical solutions: A method for recommending cargo space comprises the following steps: S1. Divide the warehouse into detailed cargo locations and bind a unique electronic tag to each cargo location, which contains detailed information about the cargo location; S2. Install industrial cameras and electronic scales to measure the area occupied by materials and load-bearing , and connect them with the client terminals; S3. When materials need to be put into storage, the material information is input through the customer terminal, and the system automatically calculates the optimal storage location and prints the QR code; S4. Select the cargo space that meets the material type, weight, and area requirements based on the intelligent algorithm, and obtain the material type and placement status of the adjacent shelves; S5. Place the materials on the designated goods and update the electronic tag display content; Among them, in S2, the material area and load-bearing Obtained through industrial cameras and electronic scales for measurement and used for subsequent cargo location screening.

[0004] Furthermore, the intelligent algorithm includes giving priority to the shelves to be placed closest to the warehouse entrance. Specifically, by calculating the distance between each shelf to be placed and the warehouse entrance, And select the minimum value: ;in, Indicates The distance from the shelf to be placed to the warehouse entrance.

[0005] Furthermore, the system supports users to set personalized needs for specific material storage preferences, and these preferences are given priority when recommending storage locations. Specifically, by introducing weight factors To indicate the importance of different preferences, calculate the comprehensive score : ;in, Indicates The degree to which individual preferences are satisfied. is the corresponding weight factor, is the number of personalized preferences.

[0006] Furthermore, the intelligent algorithm is based on machine learning technology and can dynamically adjust the recommendation strategy according to the actual use of the warehouse and historical data. Specifically, the system obtains the area occupied by materials through industrial cameras and electronic scales. and load-bearing Physical parameters, and input name, category and material information through the customer terminal; Filter out all cargo spaces that meet the material storage conditions, that is, the area is greater than or equal to the area occupied by the materials And the total weight of the cargo space The shelf is used as the shelf to be selected; For each shelf to be selected, the algorithm determines whether there are goods placed on it, and checks the material types and goods placement status of adjacent shelves; Among the shelves to be placed, the algorithm will select the shelf closest to the warehouse entrance as the optimal shelf, or randomly select a shelf. If the user sets personalized preferences, these preferences will be given priority in the selection; When screening for storage locations that meet the storage conditions, use the following criteria: ; ; After determining the optimal shelf, the system sends a command to the printer to print a QR code. The manager pastes the QR code onto the materials and places them at the designated location according to the system prompts. At the same time, the system automatically updates the display content of the electronic label on the goods to reflect the latest inventory status.

[0007] Furthermore, the intelligent algorithm also includes the following optimization steps: Calculate the comprehensive score of each shelf to be placed , combined with the remaining available area of ​​the cargo space , Total weight of cargo space The consistency factor of the types of materials on adjacent shelves is as follows: ; in, Indicates the consistency score of the types of materials on adjacent shelves; The shelf with the highest comprehensive score is selected as the optimal shelf.

[0008] Furthermore, the electronic tag contains detailed information about the cargo location, including location, quantity, cargo type, total weight of the cargo location, , Remaining available area of ​​cargo space , and can be updated in real time. Specifically, the remaining available area of ​​the cargo space is calculated by the following formula: ; in, is the total area of ​​cargo space, It is the first The area occupied by the materials, It is the quantity of materials stored in this cargo space.

[0009] Furthermore, each time the system completes the cargo space allocation, the algorithm will record the material information and cargo space selection result data of this operation, and add it to the historical data for subsequent optimization recommendations. Specifically, by accumulating historical data And apply the incremental learning formula to update the model parameters : ; in, is the learning rate, is the historical data at the current time point, is the historical data predicted by the model.

[0010] Compared with the prior art, the present invention has the following beneficial effects: 1. The intelligent algorithm of the present invention comprehensively considers factors such as the total weight of the cargo space, the remaining available area, and the types of materials, ensuring that each cargo space can be fully utilized to avoid wasting space. The system gives priority to cargo spaces on adjacent shelves that store the same or similar materials, making the materials more centralized and easier to manage and access; 2. Through automated equipment such as industrial cameras and electronic scales, the system can quickly obtain the physical parameters of materials and complete the selection of the optimal cargo location in a short time, greatly shortening the time for warehousing and outbound delivery, reducing dependence on manual experience, reducing the possibility of human errors, and improving the accuracy and consistency of operations; 3. Intelligent algorithms strictly check the load-bearing capacity of cargo spaces to ensure that overloaded cargo is not piled up and to avoid safety hazards such as shelf collapse. Electronic tags can update cargo space information in real time. Managers can use the system to keep abreast of the latest warehouse status and promptly identify and handle potential problems. 4. Each time after completing the allocation of cargo space, the system will record the operation data and apply the incremental learning formula to update the model parameters, continuously optimize the recommendation strategy, and improve the intelligence level of the system. Through the analysis of historical data, the system can discover common material access patterns and problems, provide valuable reference for warehouse management, and help managers make more informed decisions. Due to the high degree of automation of the system, it reduces dependence on manual labor and reduces labor costs. DETAILED DESCRIPTION

[0011] The technical solution of the present invention is further described below in conjunction with the scheme and embodiments.

[0012] The present invention provides a cargo location recommendation method, comprising the following steps: S1. Divide the warehouse into detailed cargo locations and bind a unique electronic tag to each cargo location, which contains detailed information about the cargo location; S2. Install industrial cameras and electronic scales to measure the area occupied by materials and load-bearing , and connect them with the client terminals; S3. When materials need to be put into storage, the material information is input through the customer terminal, and the system automatically calculates the optimal storage location and prints the QR code; S4. Select the cargo space that meets the material type, weight, and area requirements based on the intelligent algorithm, and obtain the material type and placement status of the adjacent shelves; S5. Place the materials on the designated goods and update the electronic tag display content; Among them, in S2, the material area and load-bearing Obtained through industrial cameras and electronic scales for measurement and used for subsequent cargo location screening.

[0013] The method first divides the warehouse into comprehensive cargo locations and equips each cargo location with a unique electronic label that contains various detailed information about the cargo location. In addition, industrial cameras and electronic scales are installed in the warehouse to accurately measure the floor space and load-bearing capacity of materials, and these devices are connected to the customer terminal. When materials need to be put into storage, managers only need to place the materials on the electronic weighing platform, then enter the material name in the customer terminal and click to print the QR code. Subsequently, the system will send photo and weighing instructions to the industrial camera and electronic scale, read the feedback value, and automatically calculate the optimal shelf according to the intelligent algorithm. The system also supports users to set storage preferences for specific materials, and considers these personalized needs when recommending cargo locations, so that goods can be placed in the most suitable cargo locations, making materials more centralized and more convenient to access. This method uses a machine learning algorithm, which can dynamically adjust the recommendation strategy based on the actual use of the warehouse and historical data, significantly improving the speed and accuracy of cargo location recommendations and improving the utilization rate of warehouse space.

[0014] In this embodiment, the intelligent algorithm includes giving priority to the shelves to be placed that are closest to the warehouse entrance. Specifically, by calculating the distance between each shelf to be placed and the warehouse entrance, And select the minimum value: ;in, Indicates The distance between the shelf to be placed and the warehouse entrance. The nearest cargo space to the warehouse entrance is selected first, which reduces the handling distance and time, further improves the operation efficiency, reduces the workload of the handling personnel, and can significantly improve the work efficiency, especially in large-scale warehouses.

[0015] In this embodiment, the system supports users to set personalized needs for specific material storage preferences, and these preferences are given priority when recommending storage locations. Specifically, by introducing weight factors To indicate the importance of different preferences, calculate the comprehensive score : ;in, Indicates The degree to which individual preferences are satisfied. is the corresponding weight factor, is the number of personalized preferences. By considering the personalized needs of users, the system can provide storage location recommendations that are more in line with user expectations, improving user experience and satisfaction. The intelligent algorithm can dynamically adjust the recommendation strategy based on the user's personalized settings and flexibly respond to complex and changing warehousing needs.

[0016] The intelligent algorithm is based on machine learning technology, combined with neural networks and Q-learning learning models, and is suitable for dynamically changing storage environments. It can dynamically adjust the recommendation strategy based on the actual usage and historical data of the warehouse. Specifically, it includes the following steps: The system obtains the area occupied by materials through industrial cameras and electronic scales and load-bearing Physical parameters, and input name, category and material information through the customer terminal; Filter out all cargo spaces that meet the material storage conditions, that is, the area is greater than or equal to the area occupied by the materials And the total weight of the cargo space The shelf is used as the shelf to be selected; For each shelf to be selected, the algorithm determines whether there are goods placed on it, and checks the material types and goods placement status of adjacent shelves; Among the shelves to be placed, the algorithm will select the shelf closest to the warehouse entrance as the optimal shelf, or randomly select a shelf. If the user sets personalized preferences, these preferences will be given priority in the selection; When screening for storage locations that meet the storage conditions, use the following criteria: ; ; After determining the optimal shelf, the system sends a command to the printer to print a QR code. The manager pastes the QR code on the material and places it in the designated location according to the system prompts. At the same time, the system automatically updates the electronic label display content on the goods to reflect the latest inventory status. Based on machine learning technology, the system can dynamically adjust the recommendation strategy according to the actual use of the warehouse and historical data, providing a more intelligent and flexible location allocation solution.

[0017] In the above embodiment, the intelligent algorithm further includes the following optimization steps: Calculate the comprehensive score of each shelf to be placed , combined with the remaining available area of ​​the cargo space , Total weight of cargo space The consistency factor of the types of materials on adjacent shelves is as follows: ; in, Indicates the consistency score of the types of materials on adjacent shelves; The shelf with the highest comprehensive score is selected as the optimal shelf. Through the comprehensive scoring formula, the system can evaluate each cargo location from multiple dimensions, such as remaining area, total weight, and consistency of adjacent shelves, to ensure that the selected cargo location is optimal. By considering the remaining available area of ​​the cargo location, the system can maximize the use of warehouse space and avoid waste.

[0018] In this embodiment, the electronic tag contains detailed information about the cargo location, including location, quantity, cargo type, total weight of the cargo location, and , Remaining available area of ​​cargo space , and can be updated in real time. Specifically, the remaining available area of ​​the cargo space is calculated by the following formula: ; in, is the total area of ​​cargo space, It is the first The area occupied by the materials, The electronic tag can update the cargo location information in real time, ensuring that the management personnel are aware of the latest inventory status at any time, improving the transparency and accuracy of management, and reducing the losses caused by inaccurate inventory by updating the cargo location information in real time, thus improving the reliability of inventory management.

[0019] In this embodiment, after the system completes the cargo space allocation each time, the algorithm will record the material information and cargo space selection result data of this operation, and add it to the historical data for subsequent optimization recommendations. Specifically, by accumulating historical data And apply the incremental learning formula to update the model parameters : ; in, is the learning rate, is the historical data at the current time point, It is the historical data predicted by the model. Through incremental learning, the system can continuously optimize the recommendation strategy and improve the accuracy and efficiency of the recommendation. By analyzing historical data, the system can discover common material access patterns and problems, provide valuable reference for warehouse management, and help managers make more informed decisions.

[0020] The present invention combines intelligent algorithms and automated equipment to not only improve the utilization rate of storage space and operating efficiency, but also enhance the safety and flexibility of warehouse management, while supporting personalized needs and achieving data-driven continuous optimization. These beneficial effects make the method have important application value in modern logistics and warehousing management, which can significantly reduce operating costs and enhance the competitiveness of enterprises.

[0021] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the purpose and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.

Claims

1. A method for recommending cargo locations, characterized in that: The following steps are involved: S1. Divide the warehouse into detailed cargo locations and bind a unique electronic tag to each cargo location, which contains detailed information about the cargo location; S2. Install industrial cameras and electronic scales to measure the area occupied by materials and load-bearing , and connect them with the client terminals; S3. When materials need to be put into storage, the material information is input through the customer terminal, and the system automatically calculates the optimal storage location and prints the QR code; S4. Select the cargo space that meets the material type, weight, and area requirements based on the intelligent algorithm, and obtain the material type and placement status of the adjacent shelves; S5. Place the materials on the designated goods and update the electronic tag display content; Among them, in S2, the material area and load-bearing Obtained through industrial cameras and electronic scales for measurement and used for subsequent cargo location screening.

2. A method for recommending cargo locations according to claim 1, characterized in that: The intelligent algorithm includes giving priority to the shelves to be placed closest to the warehouse entrance, and calculating the distance from each shelf to be placed to the warehouse entrance. And select the minimum value: ;in, Indicates The distance from the shelf to be placed to the warehouse entrance.

3. A method for recommending cargo locations according to claim 2, characterized in that: The system supports users to set their own storage preferences for specific materials. The preferences are given priority when recommending storage locations. To indicate the importance of different preferences, calculate the comprehensive score : ； in, Indicates The degree to which individual preferences are satisfied. is the corresponding weight factor, is the number of personalized preferences.

4. A method for recommending cargo locations according to any one of claims 1 to 3, characterized in that: The intelligent algorithm is based on machine learning technology and can dynamically adjust the recommendation strategy according to the actual usage and historical data of the warehouse, including the following steps: The system uses industrial cameras and electronic scales to obtain the area occupied by materials and load-bearing Physical parameters, and input name, category and material information through the customer terminal; Filter out all cargo spaces that meet the material storage conditions, that is, the area is greater than or equal to the area occupied by the materials And the total weight of the cargo space The shelf is used as the shelf to be selected; For each shelf to be selected, the algorithm determines whether there are goods placed on it, and checks the material types and goods placement status of adjacent shelves; Among the shelves to be placed, the algorithm will select the shelf closest to the warehouse entrance as the optimal shelf, or randomly select a shelf. If the user sets personalized preferences, these preferences will be given priority in the selection; When screening for storage locations that meet the storage conditions, use the following criteria: ； ； After determining the optimal shelf, the system sends a command to the printer to print a QR code. The manager pastes the QR code onto the materials and places them at the designated location according to the system prompts. At the same time, the system automatically updates the display content of the electronic label on the goods to reflect the latest inventory status.

5. A method for recommending cargo locations according to claim 4, characterized in that: The intelligent algorithm also includes the following optimization steps: Calculate the comprehensive score of each shelf to be placed , combined with the remaining available area of ​​the cargo space , Total weight of cargo space The consistency factor of the types of materials on adjacent shelves is as follows: ； in, Indicates the consistency score of the types of materials on adjacent shelves; Finally, the shelf with the highest comprehensive score is selected as the optimal shelf.

6. A method for recommending cargo locations according to claim 1, characterized in that: The electronic tag contains the location, quantity, type of goods, and total weight of the cargo space. , Remaining available area of ​​cargo space Information can be updated in real time, and the remaining available area of ​​the cargo space can be calculated using the following formula: ； in, is the total area of ​​cargo space, It is the first The area occupied by the materials, It is the quantity of materials stored in this cargo space.

7. The method for recommending cargo locations according to claim 1, characterized in that: After the system completes the cargo space allocation each time, the algorithm will record the material information and cargo space selection result data of this operation, and add it to the historical data for subsequent optimization recommendations. And apply the incremental learning formula to update the model parameters : ； in, is the learning rate, is the historical data at the current time point, is the historical data predicted by the model.

Images