Intelligent inventory management system for household appliance spare and accessory parts

Abstract

The invention, which relates to the technical field of intelligent inventory management, discloses an intelligent inventory management system for household appliance spare and accessory parts, comprising a problem diagnosis module used for generating an inventory management first-level problem label and an inventory management second-level problem label; the intelligent demand prediction module is used for carrying out classification demand prediction according to the problem label generated by the problem diagnosis module and carrying out dynamic parameter adjustment on a prediction value; the dynamic classification management module is used for carrying out intelligent warehouse division, supplier collaborative optimization and digital agreement on the household appliance spare and accessory parts; and the intelligent storage module is used for upgrading hardware and carrying out software integration operation. According to the invention, historical data, market trend and seasonal fluctuation are utilized to accurately predict the requirements of spare and accessory parts. Classification is performed according to the value and demand fluctuation of the spare and accessory parts, and fine management is implemented. Through a VMI + JMI mixed mode, a supply chain is optimized to be cooperatively combined with an RFID technology and automatic storage equipment, so that the warehouse management efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent inventory management, and in particular to an intelligent inventory management system for household appliance parts. Background Art

[0002] In the modern home appliance industry, companies face complex inventory management challenges driven by evolving consumer demands, technological advancements, and intensifying market competition. Traditional inventory management methods often rely on manual record-keeping and empirical judgment, lacking flexibility and real-time performance, and can easily lead to inventory overstocks, stockouts, and inefficient supply chain operations. Especially for products like home appliance parts, which have a wide variety and fluctuating demand, achieving accurate inventory forecasts, effective resource allocation, and rapid response to market demand have become critical challenges facing companies.

[0003] Currently, Chinese invention patent application number CN202510494671.6 discloses a warehouse information management method and system based on the Internet of Things. The method includes obtaining storage data for a region on different dates, using the storage data to determine high-load areas in the region, determining the frequency of change coefficients of different types of goods and frequently changing goods based on the changes in the storage data of different types of goods in the high-load area on different dates, obtaining storage data for different frequently changing goods in the region, and combining the frequency of change coefficients of different frequently changing goods to determine the warehouse information management strategy based on Internet of Things devices in the region, thereby improving the accuracy of the warehouse storage data. However, existing technologies cannot accurately predict spare parts demand based on historical data, market trends, and seasonal fluctuations, cannot classify spare parts based on their value and demand fluctuations, and cannot implement refined management, resulting in low warehouse management efficiency. Summary of the Invention

[0004] The technical problem solved by the present invention is that the existing technology cannot accurately predict the demand for spare parts based on historical data, market trends and seasonal fluctuations, cannot classify spare parts according to their value and demand fluctuations, implement refined management, and has low warehouse management efficiency.

[0005] To solve the above technical problems, the present invention provides the following technical solutions: an intelligent inventory management system for household appliance parts, comprising a problem diagnosis module, an intelligent demand forecasting module, a dynamic classification management module, and an intelligent warehousing module: The problem diagnosis module is used to generate inventory management first-level problem tags and inventory management second-level problem tags; The intelligent demand forecasting module is used to perform classified demand forecasting based on the problem labels generated by the problem diagnosis module, and to dynamically adjust the parameters of the forecast values; The dynamic classification management module is used to perform intelligent warehouse division, supplier collaborative optimization and digital agreement for household appliance parts; The intelligent storage module is used to upgrade hardware and perform software integration operations.

[0006] Preferably, the problem diagnosis module includes: Using big data to diagnose inventory management needs for household appliance parts, we obtain first-level inventory management problem labels, which include inaccurate demand forecasts, unbalanced inventory structures, insufficient supply chain collaboration, and inefficient warehouse management. Using the k-means algorithm, we further categorize these first-level inventory management problem labels into second-level inventory management problem labels, which include: Demand forecast inaccuracies include seasonal fluctuations, fragmented historical sales data, lack of linkage effects between upstream and downstream supply chains, and order fluctuations; Inventory structure imbalance includes mixed management of high-value core components and low-value consumable parts and rigid safety stock settings; Inadequate supply chain collaboration includes long supplier response cycles, lack of linkage with OEM demand planning, and high order execution deviation rates; Inefficient warehouse management includes low warehouse digital coverage, low execution rate and low storage space utilization.

[0007] Preferably, the intelligent demand forecasting module includes: Collect historical sales data, and use an arithmetic mean method or a long-short-term memory model to predict future demand based on the historical sales data; When it is necessary to predict the demand for common parts with stable demand, the arithmetic mean is used to calculate the future demand. The forecast includes: inputting the discrete sales data of the past n months and outputting the future demand forecast value; When predicting seasonal spare parts based on long-term dependencies in a time series, a long short-term memory model is used to predict future sales. The prediction includes: inputting the standardized feature values ​​of the first-level inventory management problem labels and outputting the rolling forecast values ​​for the next n months.

[0008] Preferably, dynamically adjusting the parameters of the predicted value includes: Combined with seasonal fluctuations, the forecast value is adjusted by the adjustment coefficient. The mathematical expression of the seasonal adjustment coefficient is: ; in, is the seasonal adjustment coefficient, which is used to adjust the demand forecast value. To regulate the intensity, it indicates the amplitude of seasonal fluctuations. is the current month; Multiply the future demand forecast using the arithmetic mean method or the long short-term memory model by S to adjust for seasonal fluctuations.

[0009] Preferably, the dynamic classification management module includes an intelligent warehouse division unit, a supplier collaborative optimization unit and a digital agreement unit. The intelligent warehouse division unit includes: Set up smart warehouse allocation rules, which include: Classify spare parts into the first, second and third categories based on their annual cost proportion and demand volatility; The first category includes spare parts with the first value or the first demand fluctuation. The first category of spare parts is managed by combining JIT and safety stock strategies; The second category includes spare parts with the second value or the second demand fluctuation, and the economic batch ordering strategy is adopted to manage the second category of spare parts; The third category includes spare parts with third value or third demand fluctuations, such as screws and nuts. The second category of spare parts is managed using an automatic replenishment strategy.

[0010] Preferably, the household appliance parts are intelligently sorted according to the intelligent sorting rules, and the intelligent sorting includes: For the first category of spare parts, deploy RFID smart cabinets. Scan the code when receiving them to trigger inventory deductions, and set inventory warning thresholds; The third category of spare parts are centrally stored in the central warehouse, and are counted quarterly, using the ABC classification method to optimize storage locations.

[0011] Preferably, the supplier collaborative optimization unit includes: The VMI+JMI hybrid model is used for collaboration between warehouses and suppliers. The collaboration logic includes: The core components and spare parts are managed by the supplier, and the inventory threshold = average daily usage × 7 days; Common parts and spare parts share the OEM production plan on a quarterly basis, and are replenished in batches according to the minimum order quantity.

[0012] Preferably, the digital protocol unit includes: Connect with supplier systems through API to automatically trigger order generation; The order triggering logic includes: If the component is a critical component, the order quantity is the larger of the current demand and the safety stock, and the delivery time is s times the standard delivery time, where s is the preset delivery time threshold; If it is a common part, the order quantity is the current demand and the delivery time is executed according to the normal order process.

[0013] When there is a problem of delayed delivery by a supplier, the system will automatically switch to an alternative supplier. When the product quality is unqualified, the return process will be triggered and the current employee's monthly score will be deducted.

[0014] Preferably, the intelligent storage module includes: Upgrade the hardware, including: Deploy RFID access control system to automatically count in and out of the warehouse; Automated guided vehicles are used for storage and handling, and ant colony algorithms are used to optimize the handling path; Perform software integration operations, including: Connect the warehouse management system with the production execution system to automatically synchronize material requirements of production work orders; An inventory health dashboard is provided, which includes a visual display of key indicators of spare parts, including inventory turnover rate, percentage of obsolete inventory, and supplier on-time delivery rate. When a key indicator deviates from a preset threshold corresponding to the key indicator, an SMS notification alert is triggered.

[0015] Preferably, continuous optimization of the intelligent inventory management system for household appliance spare parts includes: Update demand forecast model parameters every quarter; Optimize warehouse layout based on IoT data and place hot-selling parts closer to the production line.

[0016] The invention's beneficial effects include leveraging historical data, market trends, and seasonal fluctuations to accurately forecast spare parts demand, categorizing parts based on their value and demand fluctuations, and implementing refined management. A hybrid VMI+JMI model optimizes supply chain collaboration, combining RFID technology and automated warehousing equipment to improve warehouse management efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A schematic diagram of the basic process of an intelligent inventory management system for household appliance parts provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, but not all of the embodiments.

[0019] Reference Figure 1 , which is an embodiment of the present invention, provides an intelligent inventory management system for household appliance parts, including a problem diagnosis module, an intelligent demand forecasting module, a dynamic classification management module, and an intelligent warehousing module: The problem diagnosis module is used to generate inventory management first-level problem tags and inventory management second-level problem tags; The intelligent demand forecasting module is used to perform classified demand forecasting based on the problem labels generated by the problem diagnosis module, and to dynamically adjust the parameters of the forecast values; The dynamic classification management module is used for intelligent warehouse division, supplier collaboration optimization and digital agreement of household appliance parts; The intelligent warehousing module is used to upgrade hardware and perform software integration operations.

[0020] Through the implementation of the above-mentioned intelligent inventory management system, the supply chain responsiveness of household appliance parts can be effectively improved, inventory costs can be reduced, warehousing and logistics processes can be optimized, and the rapid changes in market demand can be met, thereby improving overall operational efficiency.

[0021] The problem diagnosis module includes: Using big data to diagnose inventory management needs for household appliance parts, we obtained first-level inventory management problem labels, which include inaccurate demand forecasts, unbalanced inventory structures, insufficient supply chain collaboration, and inefficient warehouse management. Using the k-means algorithm, we further categorized these first-level inventory management problem labels into second-level inventory management problem labels, which include: Demand forecast inaccuracies include seasonal fluctuations, fragmented historical sales data, lack of linkage effects between upstream and downstream supply chains, and order fluctuations; Inventory structure imbalance includes mixed management of high-value core components and low-value consumable parts and rigid safety stock settings; Inadequate supply chain collaboration includes long supplier response cycles, lack of linkage with OEM demand planning, and high order execution deviation rates; Inefficient warehouse management includes low warehouse digital coverage, low execution rate and low storage space utilization.

[0022] The intelligent demand forecasting module includes: Collect historical sales data and use the arithmetic mean method or long-short-term memory model to predict future demand based on the historical sales data; When forecasting common parts with stable demand, such as screws and nuts, the arithmetic mean is used to calculate future demand. The forecast involves inputting discrete sales data from the past n months and outputting future demand forecasts. The average demand is calculated based on historical data to eliminate short-term fluctuations. When predicting seasonal spare parts based on long-term dependencies in a time series, a long short-term memory model is used to predict future sales. The prediction includes: inputting the standardized feature values ​​of the first-level inventory management problem labels and outputting the rolling forecast values ​​for the next n months.

[0023] Dynamic parameter adjustment of the predicted value includes: Combined with seasonal fluctuations, the forecast value is adjusted by the adjustment coefficient. The mathematical expression of the seasonal adjustment coefficient is: ; in, is the seasonal adjustment coefficient, which is used to adjust the demand forecast value. To regulate the intensity, it indicates the amplitude of seasonal fluctuations. is the current month; Multiply the future demand forecast using the arithmetic mean method or the long short-term memory model by S to adjust for seasonal fluctuations.

[0024] The dynamic classification management module includes an intelligent warehouse division unit, a supplier collaborative optimization unit, and a digital agreement unit. The intelligent warehouse division unit includes: Set up smart warehouse allocation rules, which include: Classify spare parts into the first, second and third categories based on their annual cost proportion and demand volatility; The first category includes spare parts with the highest value or the highest demand fluctuation, such as variable frequency controllers. The first category of spare parts is managed by combining JIT and safety stock strategies. The second category includes spare parts with secondary value or secondary demand fluctuations, such as power cords. The economic batch ordering strategy is used to manage the second category of spare parts; The third category includes spare parts with third value or third demand fluctuations, such as screws and nuts. The second category of spare parts is managed using an automatic replenishment strategy.

[0025] Smart warehouse sorting is performed on household appliance parts according to smart warehouse sorting rules. Smart warehouse sorting includes: For the first category of spare parts, deploy RFID smart cabinets. Scan the code when receiving them to trigger inventory deductions, and set inventory warning thresholds; The third category of spare parts are centrally stored in the central warehouse, and are counted quarterly. The ABC classification method is used to optimize the storage location, for example, Category A is close to the delivery port.

[0026] The supplier collaborative optimization unit includes: The VMI+JMI hybrid model is used for collaboration between warehouses and suppliers. The collaboration logic includes: The core components and spare parts are managed by the supplier, and the inventory threshold = average daily usage × 7 days; Common parts and spare parts share the OEM production plan on a quarterly basis, and are replenished in batches according to the minimum order quantity.

[0027] The digital protocol unit includes: Connect with supplier systems through API to automatically trigger order generation; The order triggering logic includes: If the component is a critical component, the order quantity is the larger of the current demand and the safety stock, and the delivery time is s times the standard delivery time, where s is the preset delivery time threshold; If it is a common part, the order quantity is the current demand and the delivery time is executed according to the normal order process.

[0028] When there is a problem of delayed delivery by a supplier, the system will automatically switch to an alternative supplier. When the product quality is unqualified, the return process will be triggered and the current employee's monthly score will be deducted.

[0029] Smart warehousing modules include: Upgrade the hardware, including: Deploy RFID access control system, automatically count in and out of warehouse, and ensure the accuracy of inventory data; Utilize automated guided vehicles for storage and handling, and employ ant colony algorithms to optimize handling routes, reduce manual intervention, and improve storage efficiency; Perform software integration operations, including: Connect the warehouse management system with the production execution system to automatically synchronize material requirements of production work orders; An inventory health dashboard is provided, which includes a visual display of key indicators of spare parts, including inventory turnover rate, percentage of obsolete inventory, and supplier on-time delivery rate. When a key indicator deviates from a preset threshold corresponding to the key indicator, an SMS notification alert is triggered.

[0030] Continuous optimization of the intelligent inventory management system for household appliance spare parts includes: Update demand forecast model parameters every quarter to maintain forecast accuracy; Optimize warehouse layout based on IoT data, place hot-selling parts closer to the production line, and improve delivery efficiency.

[0031] In one embodiment, an inventory control strategy is optimized, and the optimization includes: The (R, S) model is used to optimize the inventory control strategy. The calculation formula of the strategy optimization solution is: R = average daily usage × delivery time + safety stock; S=R+maximum buffer stock; For example, when the average daily demand for air conditioner motherboards (first-category spare parts) is 50 pieces, the delivery time is 14 days, and the safety stock is 300 pieces, the strategy optimization solution yields R = 50 × 14 + 300 = 1000 pieces, and S = 1500 pieces. When the average daily demand for remote control batteries (category 3 spare parts) is 200 pieces and the delivery time is 7 days, the strategy optimization solution yields R = 200 × 7 = 1400 pieces and S = 2000 pieces. Supplemental differentiation strategies include: Real-time monitoring of inventory levels for Category 1 spare parts. Supplier direct supply channels are prioritized when replenishment is triggered. The reorder point (R) is reduced by 10%, and safety stock is increased by 20% to cope with demand fluctuations. For bulk orders of Category III spare parts, the order point R is raised to monthly usage × 1.5, and the inventory limit S is allowed to fluctuate by ±15%.

[0032] The (R, S) model is a continuous inventory monitoring strategy widely used in inventory management across manufacturing and service industries. Its core concept is to balance inventory costs with service levels by tracking inventory levels in real time and dynamically adjusting replenishment timing and quantity.

[0033] The principles include: R represents the reorder point. When the inventory level drops to the preset threshold R, a replenishment request is triggered. R = average daily usage × delivery time + safety stock. Average daily usage is the historical average daily consumption; lead time is the time (in days) from order placement to goods arrival; and safety stock is the buffer stock set aside to cope with demand fluctuations or supply uncertainties. The upper limit of inventory after replenishment is set to R + safety stock or adjusted according to business needs, S = R + maximum buffer stock; The replenishment logic is: when the inventory level ≤ R, the system automatically triggers replenishment; Replenishment quantity = S-current inventory; Ensure that inventory returns to S after replenishment.

[0034] It is suitable for seasonal goods with large demand fluctuations (home appliances, clothing), spare parts inventory (automobiles, industrial equipment), long supply cycles, imported or customized components, components with long delivery times (such as chips, special steels), and core components with high out-of-stock costs (such as medical equipment parts, aircraft engine components).

[0035] In one embodiment, the solution optimization process is: Take material code 529459 (Wikus saw blade) as an example: The original parameters include order point R=30, maximum inventory S=90, and delivery time of 28 days; Questions include: The historical average monthly consumption is only 20 units, resulting in inventory backlog (sluggish inventory risk); The optimized parameters include: R = (20 / 30 days) × 28 days + 300 = 10.67 × 28 + 300 ≈ 600 units; S=600+300=900 units; The results include: reducing capital tie-up by extending replenishment cycles, reducing safety stocks (obsolete inventory was reduced by 70%).

[0036] This invention leverages historical data, market trends, and seasonal fluctuations to accurately forecast spare parts demand. It categorizes parts based on their value and demand fluctuations, enabling refined management. This hybrid VMI+JMI model optimizes supply chain collaboration and improves warehouse management efficiency by integrating RFID technology and automated warehousing equipment.

[0037] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code. The storage medium may be implemented by any type of volatile or non-volatile storage device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0038] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. 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 solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An intelligent inventory management system for household appliance parts, characterized in that: Including problem diagnosis module, intelligent demand forecast module, dynamic classification management module and intelligent warehousing module: The problem diagnosis module is used to generate inventory management first-level problem tags and inventory management second-level problem tags; The intelligent demand forecasting module is used to perform classified demand forecasting based on the problem labels generated by the problem diagnosis module, and to dynamically adjust the parameters of the forecast values; The dynamic classification management module is used to perform intelligent warehouse division, supplier collaborative optimization and digital agreement for household appliance parts; The intelligent storage module is used to upgrade hardware and perform software integration operations.

2. The intelligent inventory management system for household appliance parts according to claim 1, characterized in that: The problem diagnosis module includes: Using big data to diagnose inventory management needs for household appliance parts, we obtain first-level inventory management problem labels, which include inaccurate demand forecasts, unbalanced inventory structures, insufficient supply chain collaboration, and inefficient warehouse management. Using the k-means algorithm, we further categorize these first-level inventory management problem labels into second-level inventory management problem labels, which include: Demand forecast inaccuracies include seasonal fluctuations, fragmented historical sales data, lack of linkage effects between upstream and downstream supply chains, and order fluctuations; Inventory structure imbalance includes mixed management of high-value core components and low-value consumable parts and rigid safety stock settings; Inadequate supply chain collaboration includes long supplier response cycles, lack of linkage with OEM demand planning, and high order execution deviation rates; Inefficient warehouse management includes low warehouse digital coverage, low execution rate and low storage space utilization.

3. The intelligent inventory management system for household appliance parts according to claim 2, characterized in that: The intelligent demand forecasting module includes: Collect historical sales data, and use an arithmetic mean method or a long-short-term memory model to predict future demand based on the historical sales data; When it is necessary to predict the demand for common parts with stable demand, the arithmetic mean is used to calculate the future demand. The forecast includes: inputting the discrete sales data of the past n months and outputting the future demand forecast value; When predicting seasonal spare parts based on long-term dependencies in a time series, a long short-term memory model is used to predict future sales. The prediction includes: inputting the standardized feature values ​​of the first-level inventory management problem labels and outputting the rolling forecast values ​​for the next n months.

4. The intelligent inventory management system for household appliance parts according to claim 3, characterized in that: Dynamic parameter adjustment of the predicted value includes: Combined with seasonal fluctuations, the forecast value is adjusted by the adjustment coefficient. The mathematical expression of the seasonal adjustment coefficient is: ； in, is the seasonal adjustment coefficient, which is used to adjust the demand forecast value. is the adjustment intensity, which indicates the amplitude of seasonal fluctuations. is the current month; Multiply the future demand forecast using the arithmetic mean method or the long short-term memory model by S to adjust for seasonal fluctuations.

5. The intelligent inventory management system for household appliance parts according to claim 4, characterized in that: The dynamic classification management module includes an intelligent warehouse division unit, a supplier collaborative optimization unit and a digital protocol unit. The intelligent warehouse division unit includes: Set up smart warehouse allocation rules, which include: Classify spare parts into the first, second and third categories based on their annual cost proportion and demand volatility; The first category includes spare parts with the first value or the first demand fluctuation. The first category of spare parts is managed by combining JIT and safety stock strategies; The second category includes spare parts with the second value or the second demand fluctuation, and the economic batch ordering strategy is adopted to manage the second category of spare parts; The third category includes spare parts with third value or third demand fluctuations, such as screws and nuts. The second category of spare parts is managed using an automatic replenishment strategy.

6. The intelligent inventory management system for household appliance parts according to claim 5, characterized in that: Smart warehouse sorting is performed on household appliance parts according to smart warehouse sorting rules. Smart warehouse sorting includes: For the first category of spare parts, deploy RFID smart cabinets. Scan the code when receiving them to trigger inventory deductions, and set inventory warning thresholds; The third category of spare parts are centrally stored in the central warehouse, and are counted quarterly, using the ABC classification method to optimize storage locations.

7. The intelligent inventory management system for household appliance parts according to claim 6, characterized in that: The supplier collaborative optimization unit includes: The VMI+JMI hybrid model is used for collaboration between warehouses and suppliers. The collaboration logic includes: The core components and spare parts are managed by the supplier, and the inventory threshold = average daily usage × 7 days; Common parts and spare parts share the OEM production plan on a quarterly basis, and are replenished in batches according to the minimum order quantity.

8. The intelligent inventory management system for household appliance parts according to claim 7, characterized in that: The digital protocol unit includes: Connect with supplier systems through API to automatically trigger order generation; The order triggering logic includes: If the component is a critical component, the order quantity is the larger of the current demand and the safety stock, and the delivery time is s times the standard delivery time, where s is the preset delivery time threshold; If it is a common part, the order quantity is the current demand and the delivery time is based on the regular order process; When there is a problem of delayed delivery by a supplier, the system will automatically switch to an alternative supplier. When the product quality is unqualified, the return process will be triggered and the current employee's monthly score will be deducted.

9. The intelligent inventory management system for household appliance parts according to claim 8, characterized in that: The intelligent storage module includes: Upgrade the hardware, including: Deploy RFID access control system to automatically count in and out of the warehouse; Automated guided vehicles are used for storage and handling, and ant colony algorithms are used to optimize the handling path; Perform software integration operations, including: Connect the warehouse management system with the production execution system to automatically synchronize material requirements of production work orders; An inventory health dashboard is provided, which includes a visual display of key indicators of spare parts, including inventory turnover rate, percentage of obsolete inventory, and supplier on-time delivery rate. When a key indicator deviates from a preset threshold corresponding to the key indicator, an SMS notification alert is triggered.

10. The intelligent inventory management system for household appliance parts according to claim 9, characterized in that: Continuous optimization of the intelligent inventory management system for household appliance spare parts includes: Update demand forecast model parameters every quarter; Optimize warehouse layout based on IoT data and place hot-selling parts closer to the production line.

Images